diff --git a/analysis/current/analysis-report-hybrid.json b/analysis/current/analysis-report-hybrid.json index b16ba19c0541933795ddabfbeb0df3141d3cbd10..11a5cf3d08eeb5d2829a8b43995a965eb3eeedac 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": "20260525T120039Z", - "generated_at": "2026-05-25T12:15:43Z", + "snapshot_id": "20260525T180030Z", + "generated_at": "2026-05-25T18:21:06Z", "evidence_quality": "full", "llm_enrichment": true, "meta_bugs": [ @@ -1148,56 +1148,6 @@ } ] }, - { - "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-46032-3", "summary": "Cluster of 1 issues and 2 PRs centered on issue #46032.", @@ -1292,6 +1242,56 @@ } ] }, + { + "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.", @@ -1708,6 +1708,229 @@ } ] }, + { + "cluster_id": "cluster-43612-2", + "summary": "Cluster of 2 related pull requests linked by soft_similarity.", + "status": "open", + "confidence": 0.5, + "canonical_issue_number": null, + "canonical_pr_number": 43612, + "issue_numbers": [], + "pr_numbers": [ + 43612, + 43613 + ], + "evidence_types": [ + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 43612, + "right_pr_number": 43613, + "code_similarity": 0.6, + "size_similarity": 0.822, + "file_overlap": 0.333, + "area_overlap": 0.698, + "patch_similarity": 0.608, + "shared_filenames": [ + "docs/source/en/_toctree.yml", + "docs/source/en/main_classes/pipelines.md", + "docs/source/en/model_doc/auto.md", + "src/transformers/__init__.py", + "src/transformers/models/auto/modeling_auto.py", + "src/transformers/pipelines/__init__.py", + "utils/check_docstrings.py", + "utils/update_metadata.py" + ], + "shared_file_areas": [ + { + "filename": "docs/source/en/_toctree.yml", + "left_ranges": [ + [ + 335, + 342 + ] + ], + "right_ranges": [ + [ + 309, + 316 + ] + ] + }, + { + "filename": "docs/source/en/main_classes/pipelines.md", + "left_ranges": [ + [ + 473, + 484 + ] + ], + "right_ranges": [ + [ + 473, + 484 + ] + ] + }, + { + "filename": "docs/source/en/model_doc/auto.md", + "left_ranges": [ + [ + 113, + 122 + ] + ], + "right_ranges": [ + [ + 113, + 122 + ] + ] + }, + { + "filename": "src/transformers/__init__.py", + "left_ranges": [ + [ + 155, + 161 + ], + [ + 664, + 670 + ] + ], + "right_ranges": [ + [ + 155, + 161 + ], + [ + 664, + 670 + ] + ] + }, + { + "filename": "src/transformers/models/auto/modeling_auto.py", + "left_ranges": [ + [ + 1629, + 1642 + ], + [ + 1807, + 1816 + ], + [ + 1840, + 1849 + ], + [ + 2186, + 2192 + ], + [ + 2233, + 2239 + ] + ], + "right_ranges": [ + [ + 1629, + 1646 + ], + [ + 1811, + 1820 + ], + [ + 1844, + 1853 + ], + [ + 2190, + 2196 + ], + [ + 2237, + 2243 + ] + ] + }, + { + "filename": "src/transformers/pipelines/__init__.py", + "left_ranges": [ + [ + 71, + 77 + ], + [ + 108, + 114 + ], + [ + 300, + 311 + ], + [ + 446, + 453 + ] + ], + "right_ranges": [ + [ + 71, + 77 + ], + [ + 108, + 114 + ], + [ + 300, + 311 + ], + [ + 446, + 453 + ] + ] + }, + { + "filename": "utils/check_docstrings.py", + "left_ranges": [ + [ + 109, + 115 + ] + ], + "right_ranges": [ + [ + 109, + 115 + ] + ] + }, + { + "filename": "utils/update_metadata.py", + "left_ranges": [ + [ + 74, + 84 + ] + ], + "right_ranges": [ + [ + 74, + 84 + ] + ] + } + ] + } + ] + }, { "cluster_id": "cluster-46100-2", "summary": "Cluster of 2 related pull requests linked by soft_similarity.", @@ -2060,6 +2283,15 @@ "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-43612-2", + "canonical_pr_number": 43612, + "duplicate_pr_numbers": [ + 43613 + ], + "target_issue_number": null, + "reason": "PRs in cluster-43612-2 are treated as duplicates because they share soft_similarity evidence." + }, { "cluster_id": "cluster-43698-3", "canonical_pr_number": 43779, diff --git a/analysis/current/analysis-report-hybrid.llm-reviews.json b/analysis/current/analysis-report-hybrid.llm-reviews.json index 8cc599bb51da47d87dc3be7d13c2807c44127c4a..0af0b53cf6230bd84158947d14b7fc929002c777 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": "20260525T120039Z", - "generated_at": "2026-05-25T12:15:43Z", + "snapshot_id": "20260525T180030Z", + "generated_at": "2026-05-25T18:21:06Z", "model": "gpt-5.4-mini?service_tier=flex", "reviews": [ { @@ -16,7 +16,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:24643", "issue:30277", @@ -93,8 +93,8 @@ "issue:34634|issue:35545", "issue:30277|issue:43638", "issue:43596|issue:43638", - "issue:43975|issue:44457", "issue:43039|issue:45161", + "issue:43975|issue:44457", "issue:44292|issue:44457", "issue:34928|issue:44805", "issue:24643|issue:30277", @@ -103,8 +103,8 @@ "issue:34928|issue:36331", "issue:43596|issue:45161", "issue:43716|issue:45507", - "issue:45823|issue:45874", "issue:39290|issue:45081", + "issue:45823|issue:45874", "issue:43425|issue:44292", "issue:34928|issue:41720", "issue:43828|issue:45161", @@ -138,442 +138,376 @@ "issue:43866|issue:44863", "issue:44292|issue:46015" ], - "prepared_review_unit_hash": "f9259cba0923024ffa657b5f2d2363fbc928d0316cbe6b0d68e1f33f51b3e507", + "prepared_review_unit_hash": "45f778f6c20602229c81e49bdaa216b38bb28bfe3f6021cac25490939cfc798a", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 69, - "serialized_chars": 48403, - "estimated_input_tokens": 12101, - "estimated_eval_tokens": 24458 + "serialized_chars": 48405, + "estimated_input_tokens": 12102, + "estimated_eval_tokens": 24460 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly heterogeneous cluster. The only clear duplicate subgroups are the DeepSpeed ZeRO-3 empty-index failures, the AutoTokenizer token-ID regression, and possibly the Qwen3_5Moe rotary-embedding device/materialization bug. Most other soft edges are different bugs or unrelated docs/issues.", - "confidence": 0.58, - "canonical_issue_reason": "No single issue covers the whole set; issue 45920 is the best canonical anchor because it is the broadest report of the tokenizer-ID regression and generalizes beyond one model family.", + "summary": "Most items are distinct bug reports, not duplicates. The only strong duplicate subclusters are the ZeRO-3 index-0 crashes on model loading, the Qwen3.5 MoE rotary-embedding/offload materialization bug, and the AutoTokenizer v5 regression affecting multiple model families. Similarity-only edges around docs, device mapping, or unrelated model errors should be rejected.", + "confidence": 0.88, + "canonical_issue_reason": "No single canonical issue spans the whole set; if forced to pick one representative for the strongest duplicate subcluster, issue:45920 is the best canonical because it is the broadest report of the AutoTokenizer v5 token-ID regression and subsumes the narrower Granite-only repro in 45812.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45920 is the strongest overall representative: broad symptom, current regression framing, and it already aggregates the tokenizer bug across multiple models.", + "best_issue_reason": "issue:45920 is the best issue anchor overall because it is open, broad, and describes the shared tokenizer regression across several model families; it is more representative than narrower model-specific reproductions.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44322", "right": "issue:45464", "accept": false, - "reason": "Different failures: a config attribute error vs a streaming chat/completions bug." + "reason": "Different failures: missing config attribute vs streaming chat/completions inference error." }, { "left": "issue:45237", "right": "issue:45685", "accept": false, - "reason": "Different backends and code paths: AMD GPU runtime failure vs MPS histogram int issue." + "reason": "Unrelated hardware/runtime issues: AMD GPU failure vs MPS histogram op on Int." }, { "left": "issue:43716", "right": "issue:45237", "accept": false, - "reason": "Image-preprocessor dtype mismatch is not the same bug as the AMD GPU device failure." + "reason": "Different model/runtime paths: image-preprocessor dtype mismatch vs GPT-OSS AMD GPU failure." }, { "left": "issue:43828", "right": "issue:45237", "accept": false, - "reason": "Autocast dtype mismatch and AMD GPU device failure are separate problems." + "reason": "Both are runtime errors, but the code paths and root causes differ; this is not the same bug." }, { "left": "issue:45237", "right": "issue:45507", "accept": false, - "reason": "Unrelated GPT-OSS AMD issue vs a GraniteMoE invalid-method call." + "reason": "Different model-specific failures: AMD GPU issue vs invalid-method call in GraniteMoEHybrid." }, { "left": "issue:44292", "right": "issue:45237", "accept": false, - "reason": "Different model/back-end failures; no shared underlying bug." + "reason": "Different repros and symptoms; Qwen NVFP4 failure is not the same as the AMD GPU crash." }, { "left": "issue:30277", "right": "issue:35545", "accept": false, - "reason": "DeepSpeed collective mismatch and ONNX export failure are unrelated." + "reason": "DeepSpeed collective mismatch and ONNX export error are unrelated bugs." }, { "left": "issue:35545", "right": "issue:42915", "accept": false, - "reason": "ONNX export error vs FineGrainedFP8Config failure are different code paths." + "reason": "Different subsystems and failures: ONNX export vs FineGrainedFP8 model load/runtime issue." }, { "left": "issue:35545", "right": "issue:41720", "accept": false, - "reason": "Export-time ONNX issue is unrelated to the Qwen3 auto-device-map CUDA assert." + "reason": "Unrelated problems: ONNX export vs auto device-mapping CUDA assert." }, { "left": "issue:45901", "right": "issue:46015", "accept": false, - "reason": "Table-QA runtime crash is unrelated to outdated RAG docs." + "reason": "Table QA crash and outdated RAG docs are not the same underlying issue." }, { "left": "issue:44509", "right": "issue:44512", "accept": false, - "reason": "Both are v5 docs regressions, but they concern different removed features and are not the same concrete fix." + "reason": "Both are doc cleanups for v5 removals, but they cover different removed references and different pages." }, { "left": "issue:35545", "right": "issue:36010", "accept": false, - "reason": "ModernBERT ONNX export and GenerationMixin import failure are unrelated." + "reason": "ONNX export error and GenerationMixin import error are unrelated." }, { "left": "issue:44805", "right": "issue:45823", "accept": false, - "reason": "Mask/tensor shape mismatch is not the same as Gemma4 PLE device placement." + "reason": "Different bug classes: mask/shape mismatch vs device-mapping mismatch." }, { "left": "issue:44918", "right": "issue:46165", "accept": false, - "reason": "TRL SFT input-embedding unpacking failure and training-resume/trust-remote-code issue are different bugs." + "reason": "Different failures: TRL SFT input-embedding unpacking vs training-resume/trust-remote-code issue." + }, + { + "left": "issue:43638", + "right": "issue:44805", + "accept": false, + "reason": "Both mention indexing/shape errors, but the model and failure mode differ; not the same bug." }, { "left": "issue:43638", + "right": "issue:46165", + "accept": false, + "reason": "ZeRO-3 Bert loading crash and training-resume issue are unrelated." + }, + { + "left": "issue:43596", "right": "issue:44805", "accept": false, - "reason": "ZeRO-3 empty-index loading error is unrelated to the mask/index shape mismatch." + "reason": "Different errors: ZeRO-3 empty-tensor index crash vs attention mask shape mismatch." }, { "left": "issue:44805", "right": "issue:45161", "accept": false, - "reason": "Different failures: shape mismatch vs GPT-OSS tensor-parallel behavior." + "reason": "Mask shape mismatch is not the same as GPT-OSS tensor-parallel failure." }, { - "left": "issue:43638", + "left": "issue:44560", "right": "issue:46165", "accept": false, - "reason": "ZeRO-3 Bert loading bug is unrelated to resume-training with trust-remote-code." + "reason": "Video StopIteration in Qwen3-vl-embedding is unrelated to resume-training behavior." }, { "left": "issue:43596", - "right": "issue:44805", + "right": "issue:46165", "accept": false, - "reason": "Bert ZeRO-3 index error and mask/tensor shape mismatch are different problems." + "reason": "ZeRO-3 Bert init crash and local-model resume issue are different." }, { "left": "issue:44805", "right": "issue:44918", "accept": false, - "reason": "The tensor-mask mismatch is not the same as the Qwen3.5 input-embeddings/TRL issue." + "reason": "Both involve tensor shapes, but the trainer/input-embedding failure is a different code path." }, { "left": "issue:43572", "right": "issue:46165", "accept": false, - "reason": "StableLm config pad-token regression is unrelated to training resume behavior." + "reason": "Missing pad_token_idx in config is unrelated to training resume with trust_remote_code." }, { "left": "issue:34634", "right": "issue:35545", "accept": false, - "reason": "BarkProcessor voice_preset and ModernBERT ONNX export are unrelated." + "reason": "BarkProcessor voice_preset issue and ONNX export error are unrelated." }, { "left": "issue:30277", "right": "issue:43638", "accept": false, - "reason": "Collective-mismatch DeepSpeed bug is different from the ZeRO-3 empty-index loading bug." + "reason": "Both involve DeepSpeed, but collective mismatch and ZeRO-3 index error are different bugs." }, { "left": "issue:43596", "right": "issue:43638", "accept": true, - "reason": "Same ZeRO-3 index-0-out-of-bounds loading failure on Bert; one is just a non-pretrained reproduction." + "reason": "Same underlying ZeRO-3 failure: index-0/out-of-bounds on empty tensors during BERT loading." }, { - "left": "issue:43975", - "right": "issue:44457", + "left": "issue:43039", + "right": "issue:45161", "accept": false, - "reason": "Detokenization regression and LoRA save/load mismatch are unrelated." + "reason": "Liger Kernel cross-entropy being called and GPT-OSS TP failure are unrelated." }, { - "left": "issue:43039", - "right": "issue:45161", + "left": "issue:43975", + "right": "issue:44457", "accept": false, - "reason": "Liger cross-entropy being called and GPT-OSS tensor-parallel failure are not the same bug." + "reason": "Detokenization bug and LoRA merge/save/reload inconsistency are different problems." }, { "left": "issue:44292", "right": "issue:44457", "accept": false, - "reason": "Qwen-3 NVFP4 runtime error and LoRA merge/save mismatch are unrelated." + "reason": "Qwen NVFP4 runtime failure and LoRA merge inconsistency do not share the same root cause." }, { "left": "issue:34928", "right": "issue:44805", "accept": false, - "reason": "Activation-checkpointing/FSDP size recomputation bug is different from the mask-shape error." + "reason": "Activation-checkpointing/FSDP recomputation mismatch is a different issue from the mask-shape IndexError." }, { "left": "issue:24643", "right": "issue:30277", "accept": false, - "reason": "DeepSpeed weight-dimension error and collective mismatch are different failures." + "reason": "Both mention DeepSpeed, but the weight-dimension error and collective mismatch are different failures." }, { "left": "issue:45859", "right": "issue:45902", "accept": true, - "reason": "Same Qwen3_5Moe rotary-embedding state/device-transition bug; one reports CPU offload, the other meta-to-empty materialization." + "reason": "Same Qwen3.5 MoE rotary-embedding/offload materialization bug; one report surfaces it as CPU-offload incompatibility, the other as uninitialized inv_freq after to_empty()." }, { "left": "issue:43638", "right": "issue:45161", "accept": false, - "reason": "ZeRO-3 Bert loading bug is unrelated to GPT-OSS tensor-parallel behavior." + "reason": "Bert ZeRO-3 index crash and GPT-OSS tensor-parallel failure are unrelated." }, { "left": "issue:34928", "right": "issue:36331", "accept": false, - "reason": "FSDP activation-checkpointing bug and CustomTrainer signature breakage are different issues." + "reason": "Checkpointing/FSDP tensor-size mismatch and CustomTrainer signature mismatch are unrelated." }, { "left": "issue:43596", "right": "issue:45161", "accept": false, - "reason": "Bert ZeRO-3 loading failure is unrelated to GPT-OSS tensor-parallel failure." + "reason": "ZeRO-3 Bert init crash and GPT-OSS TP failure are unrelated." }, { "left": "issue:43716", "right": "issue:45507", "accept": false, - "reason": "Image dtype mismatch and GraniteMoE invalid-method call are unrelated." - }, - { - "left": "issue:45823", - "right": "issue:45874", - "accept": false, - "reason": "Gemma4 device-map mismatch and expensive reverse-embedding lookup are different forward-path bugs." + "reason": "Different models and symptoms: dtype mismatch in image preprocessing vs invalid method call." }, { "left": "issue:39290", "right": "issue:45081", "accept": false, - "reason": "Gemma3 config/vLLM attribute error is unrelated to the Mistral regex patch crash." - }, - { - "left": "issue:43425", - "right": "issue:44292", - "accept": false, - "reason": "Torch version incompatibility and Qwen-3 NVFP4 runtime failure are not the same bug." - }, - { - "left": "issue:34928", - "right": "issue:41720", - "accept": false, - "reason": "FSDP checkpointing issue and Qwen3 auto-device-map CUDA assert are unrelated." - }, - { - "left": "issue:43828", - "right": "issue:45161", - "accept": false, - "reason": "Autocast dtype mismatch and GPT-OSS tensor-parallel failure are different problems." - }, - { - "left": "issue:44918", - "right": "issue:45161", - "accept": false, - "reason": "Qwen3.5/TRl input-embedding issue is unrelated to GPT-OSS tensor-parallel behavior." - }, - { - "left": "issue:43828", - "right": "issue:44292", - "accept": false, - "reason": "Autocast dtype mismatch and Qwen-3 NVFP4 runtime error are unrelated." - }, - { - "left": "issue:43716", - "right": "issue:45685", - "accept": false, - "reason": "Mistral image-preprocessor dtype mismatch and MPS histogram issue are unrelated." - }, - { - "left": "issue:43541", - "right": "issue:43716", - "accept": false, - "reason": "Mixtral torch-dynamo grouped_mm error and image dtype mismatch are different bugs." + "reason": "Gemma3/vLLM config attribute error and Mistral tokenizer regex patch crash are unrelated." }, { - "left": "issue:44292", - "right": "issue:44918", + "left": "issue:45823", + "right": "issue:45874", "accept": false, - "reason": "Qwen-3 NVFP4 runtime error and Qwen3.5/TRl input-embedding failure are unrelated." + "reason": "Device-mapping mismatch and expensive reverse embedding lookup are different Gemma4 issues." }, { - "left": "issue:43716", + "left": "issue:43425", "right": "issue:44292", "accept": false, - "reason": "Image preprocessor dtype mismatch is not the same as the Qwen-3 NVFP4 issue." - }, - { - "left": "issue:45507", - "right": "issue:45685", - "accept": false, - "reason": "GraniteMoE invalid-method call and MPS histogram int error are unrelated." - }, - { - "left": "issue:43039", - "right": "issue:44918", - "accept": false, - "reason": "Liger cross-entropy routing and Qwen3.5/TRl input embedding failure are different bugs." - }, - { - "left": "issue:41762", - "right": "issue:43638", - "accept": true, - "reason": "Same ZeRO-3 empty-index loading error; Gemma3 and Bert are just different reproductions of the same root cause." - }, - { - "left": "issue:43827", - "right": "issue:44512", - "accept": false, - "reason": "Both are docs regressions in v5, but they refer to different removed features and not one shared fix." - }, - { - "left": "issue:43716", - "right": "issue:44560", - "accept": false, - "reason": "Mistral dtype mismatch and Qwen3-vl video StopIteration are unrelated." + "reason": "Torch version incompatibility and Qwen NVFP4 runtime failure are unrelated." }, { "left": "issue:43828", "right": "issue:45685", "accept": false, - "reason": "Autocast dtype mismatch and MPS histogram int failure are different backend issues." + "reason": "Autocast dtype mismatch and MPS histogram limitation are different bugs." }, { "left": "issue:44918", "right": "issue:45685", "accept": false, - "reason": "Qwen3.5/TRl input-embedding failure is unrelated to the MPS histogram issue." + "reason": "TRL embedding unpacking failure and MPS histogram limitation are unrelated." }, { "left": "issue:43039", "right": "issue:43828", "accept": false, - "reason": "Liger cross-entropy routing and autocast dtype mismatch are not the same bug." + "reason": "Liger Kernel cross-entropy path and autocast dtype mismatch are different failures." }, { "left": "issue:30277", "right": "issue:36331", "accept": false, - "reason": "DeepSpeed collective mismatch and CustomTrainer signature breakage are unrelated." + "reason": "DeepSpeed collective mismatch and compute_loss signature mismatch are unrelated." }, { "left": "issue:45237", "right": "issue:46015", "accept": false, - "reason": "AMD GPU runtime failure and outdated RAG docs are unrelated." + "reason": "AMD GPU runtime failure and outdated RAG docs are not the same issue." }, { "left": "issue:34928", "right": "issue:36010", "accept": false, - "reason": "FSDP checkpointing bug and GenerationMixin import error are unrelated." + "reason": "FSDP activation-checkpointing bug and GenerationMixin import error are unrelated." }, { "left": "issue:43039", "right": "issue:44805", "accept": false, - "reason": "Liger kernel cross-entropy issue and tensor mask/index mismatch are different failures." + "reason": "Liger Kernel cross-entropy path and mask-shape IndexError do not match." }, { "left": "issue:41762", "right": "issue:43596", "accept": true, - "reason": "Same ZeRO-3 index-0-out-of-bounds loading failure; both are the same empty-tensor path with different model repros." + "reason": "Same ZeRO-3 empty-tensor crash pattern: index 0 out of bounds while initializing/loading models." }, { "left": "issue:39290", "right": "issue:41720", "accept": false, - "reason": "Gemma3/vLLM config attribute error and Qwen3 CUDA assert are unrelated." + "reason": "Gemma3 sliding_window_pattern error and Qwen3 auto-device-map CUDA assert are unrelated." }, { "left": "issue:43901", "right": "issue:44512", "accept": false, - "reason": "TextClassificationPipeline docs drift and run-command docs drift are separate documentation fixes." + "reason": "Different docs regressions: return_all_scores vs removed transformers run command." }, { "left": "issue:45237", "right": "issue:45901", "accept": false, - "reason": "GPT-OSS AMD GPU failure and table-QA crash are unrelated." + "reason": "GPT-OSS AMD GPU runtime failure and table QA crash are unrelated." }, { "left": "issue:44841", "right": "issue:45823", "accept": false, - "reason": "Voxtral processor failure and Gemma4 device-map mismatch are different issues." + "reason": "Processor failure for Voxtral and Gemma4 device-mapping mismatch are unrelated." }, { "left": "issue:43039", "right": "issue:44560", "accept": false, - "reason": "Liger kernel issue and Qwen3-vl video StopIteration are unrelated." + "reason": "Liger Kernel cross-entropy issue and Qwen3-vl StopIteration are unrelated." }, { "left": "issue:43975", "right": "issue:46015", "accept": false, - "reason": "Detokenization regression and outdated RAG docs are unrelated." + "reason": "Detokenization bug and RAG docs cleanup are unrelated." }, { "left": "issue:45812", "right": "issue:45920", "accept": true, - "reason": "Same tokenizer-ID regression; 45920 is the broader report spanning multiple model families." + "reason": "Same AutoTokenizer v5 regression producing wrong token IDs; 45920 is the broader multi-model report and 45812 is a narrower Granite-only repro." }, { "left": "issue:44863", "right": "issue:46015", "accept": false, - "reason": "NemotronH checkpoint loading and RAG docs are unrelated." + "reason": "NemotronH checkpoint loading failure and RAG docs issue are unrelated." }, { "left": "issue:43866", "right": "issue:44863", "accept": false, - "reason": "Checkpoint corruption and NemotronH load failure are different bugs." + "reason": "Checkpoint corruption and checkpoint loading implementation failure are different problems." }, { "left": "issue:44292", "right": "issue:46015", "accept": false, - "reason": "Qwen-3 NVFP4 runtime error and outdated RAG docs are unrelated." + "reason": "Qwen NVFP4 runtime failure and outdated RAG docs are unrelated." } ] }, "evaluator_result": { "accept": true, - "feedback": "The analysis is grounded in the packet and stays conservative on the soft edges. The accepted duplicate groups are plausible from the titles and descriptions (ZeRO-3 empty-index loading, AutoTokenizer token-ID regression, and the Qwen3_5Moe rotary-embedding/materialization bug), and the rejections avoid overstating weak similarity. No clear mergeability or duplicate claim looks unsupported." + "feedback": "The summary is well grounded and conservative overall. The three accepted duplicate edges are plausible same-bug pairs, and the rejected edges avoid overstating similarity across clearly different failures or docs-only issues. No mergeability problems apply here since these are issue pairs, not PR pairs." }, "evaluator_used": true, "retried": false, @@ -592,7 +526,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:36010", "issue:39186", @@ -678,280 +612,280 @@ "issue:45759|issue:45902", "issue:45542|issue:45800", "issue:39186|issue:44918", - "issue:40990|issue:44960", "issue:43716|issue:44918", + "issue:40990|issue:44960", "issue:45632|issue:45698", "issue:43645|issue:45399", "issue:43404|issue:45005" ], - "prepared_review_unit_hash": "f6acee94451fa58c36b13d3ddd3e24daa5390fd4aa877ab3195593ffbb69a12f", + "prepared_review_unit_hash": "b0d0371cfe32d5bb7f87311ffb0714fc46cf47564eeeab639dbe5deb9fb7f59b", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 39, - "serialized_chars": 39126, - "estimated_input_tokens": 9782, - "estimated_eval_tokens": 19820 + "serialized_chars": 39129, + "estimated_input_tokens": 9783, + "estimated_eval_tokens": 19822 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous: many issues share broad themes like loading errors, dtype mismatches, zero-3, or model-specific regressions, but they do not look like true duplicates. The only strong duplicate-like pair is the SigLIP2 output/embedding regression.", - "confidence": 0.68, - "canonical_issue_reason": "issue:43994 is the clearest concrete report in the only likely duplicate pair: it directly describes the bad SigLIP2 behavior with AutoModel/pipeline and is more actionable than the comparison-style report in 43054.", + "summary": "This cluster is mostly heterogeneous: many items are unrelated model-specific regressions, backend incompatibilities, or API edge cases. Only two soft pairs look like plausible duplicates: SigLIP2 inference/quality reports and `trust_remote_code` custom-module resolution problems.", + "confidence": 0.89, + "canonical_issue_reason": "No single canonical issue for the whole cluster; the items are largely unrelated, so only a couple of pairwise duplicates stand out.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43994 is the best representative of the cluster because it is the most specific, reproducible, and clearly matches the one accepted duplicate edge.", + "best_issue_reason": "issue:45632 is the best representative issue here because it is a precise, actionable report about custom-module cache/path collision and has a close matching companion (issue:45698).", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:39290", "right": "issue:43531", "accept": false, - "reason": "Both mention model config/windowing regressions, but they are different models and different failure modes; too broad to treat as the same bug." + "reason": "Both mention `sliding_window`, but they affect different model families and failure modes; not clearly the same bug." }, { "left": "issue:43854", "right": "issue:43866", "accept": false, - "reason": "One is a unit-test model load failure, the other is a corrupted checkpoint report; not the same underlying issue." + "reason": "Both are load-time failures, but one is a unit-test load issue and the other is a corrupted checkpoint report; different root causes." }, { "left": "issue:43792", "right": "issue:45901", "accept": false, - "reason": "Whisper loading failure and table-question-answering crash are unrelated code paths and symptoms." + "reason": "Unrelated models and subsystems: Whisper loading vs table-question-answering runtime crash." }, { "left": "issue:41093", "right": "issue:43638", "accept": false, - "reason": "Both involve zero-3/index errors, but the triggers and stack-level symptoms differ enough that this does not look like one concrete bug." + "reason": "Both are index/shape errors, but one is a mask-length mismatch and the other is a ZeRO-3 BERT init failure." }, { "left": "issue:43425", "right": "issue:45070", "accept": false, - "reason": "Torch version incompatibility and a pydantic PretrainedConfig-field regression are unrelated." + "reason": "Both are version/regression complaints, but they target different incompatibilities and different code paths." }, { "left": "issue:43596", "right": "issue:45800", "accept": false, - "reason": "These are different issues in different areas: zero-3/Bert loading vs a torch-transformers version incompatibility." + "reason": "Different failures: ZeRO-3 BERT loading vs a specific torch/transformers version incompatibility." }, { "left": "issue:43975", "right": "issue:45901", "accept": false, - "reason": "Incorrect detokenization and a table QA crash are not the same bug." + "reason": "Different functionality entirely: detokenization vs table QA task crashes." }, { "left": "issue:43792", "right": "issue:45070", "accept": false, - "reason": "Whisper cannot run and pydantic config handling are unrelated." + "reason": "Whisper runtime failure is unrelated to the PretrainedConfig/pydantic regression." }, { "left": "issue:45362", "right": "issue:45464", "accept": false, - "reason": "Both mention Qwen3.5, but one is a generic chat crash and the other is a streaming inference API failure; not enough to merge as one bug." + "reason": "Both involve Qwen3.5 chat, but one is a transformers chat crash and the other is a streaming chat/completions API failure; too different to merge." }, { "left": "issue:44292", "right": "issue:45901", "accept": false, - "reason": "Qwen-3-8B-NVFP4 loading failure and table QA crash are unrelated." + "reason": "Different models and symptoms; NVFP4 loading failure is not the same as table QA crashing." }, { "left": "issue:39290", "right": "issue:45823", "accept": false, - "reason": "Both are model-specific regressions, but Gemma3 sliding-window behavior and Gemma4 device mismatch are different problems." + "reason": "Both are model-specific regressions, but Gemma3 sliding-window config and Gemma4 device mismatch are distinct bugs." }, { "left": "issue:45464", "right": "issue:45685", "accept": false, - "reason": "Streaming chat failure and an MPS histogram/int issue are completely different code paths." + "reason": "Qwen3.5 streaming API failure and MPS histogram-not-implemented error are unrelated." }, { "left": "issue:43404", "right": "issue:43866", "accept": false, - "reason": "Tied lm_head weights and a corrupted checkpoint are unrelated." + "reason": "Mistral3 tied-weight bug and Ovis2 checkpoint corruption are different problems." }, { "left": "issue:43541", "right": "issue:45685", "accept": false, - "reason": "Mixtral tracing/grouped_mm and MPS histogram failures are unrelated." + "reason": "Grouped_mm tracing failure and an MPS integer histogram limitation are different code paths." }, { "left": "issue:43541", "right": "issue:43828", "accept": false, - "reason": "Both are numeric/dtype-adjacent, but the specific model paths and failure mechanisms differ." + "reason": "Both involve numeric/runtime issues, but grouped_mm tracing and autocast dtype mismatch are not the same bug." }, { "left": "issue:44841", "right": "issue:45084", "accept": false, - "reason": "Voxtral processor failure and a non-template-node compile error are unrelated." + "reason": "Processor failure for Voxtral and template-node compilation errors are unrelated." }, { "left": "issue:36010", "right": "issue:39290", "accept": false, - "reason": "Importing GenerationMixin and Gemma3 sliding_window are unrelated issues." + "reason": "ImportError for `GenerationMixin` and Gemma3 sliding-window config are unrelated regressions." }, { "left": "issue:45800", "right": "issue:45823", "accept": false, - "reason": "A torch/transformers compatibility complaint and a Gemma4 device-map bug are different failures." + "reason": "A torch/transformers version incompatibility is unrelated to a Gemma4 device-map forward mismatch." }, { "left": "issue:41093", "right": "issue:41762", "accept": false, - "reason": "Both are zero-3-related index errors, but one is a mask-shape mismatch and the other is a model-loading out-of-bounds error; too specific to unify." + "reason": "Both mention out-of-bounds/indexing, but one is a mask shape mismatch and the other is a ZeRO-3 load-time empty-tensor issue." }, { "left": "issue:43296", "right": "issue:43366", "accept": false, - "reason": "PaddleOCR-VL loading in vLLM and GGUF gpt-oss support are unrelated." + "reason": "PaddleOCR-VL loading in vLLM and GGUF gpt-oss support are different feature gaps." }, { "left": "issue:43572", "right": "issue:45070", "accept": false, - "reason": "StableLm pad_token_idx regression and pydantic PretrainedConfig changes are not the same bug." + "reason": "StableLmConfig `pad_token_idx` regression and PretrainedConfig pydantic field breakage are different configuration bugs." }, { "left": "issue:43541", "right": "issue:45161", "accept": false, - "reason": "Mixtral grouped_mm tracing and GPT-OSS MoE tensor-parallel support are different model/runtime problems." + "reason": "Both involve MoE/GPT-OSS-adjacent topics, but grouped_mm tracing and tensor-parallel support are not the same underlying issue." }, { "left": "issue:44387", "right": "issue:45005", "accept": false, - "reason": "CUDA memory growth under int4 quantization and tied weights on translation models are unrelated." + "reason": "Int4 memory/OOM regression and tied-weights translation-model regression are unrelated." }, { "left": "issue:43828", "right": "issue:45464", "accept": false, - "reason": "An autocast dtype mismatch and a Qwen3.5 streaming API crash are unrelated." + "reason": "Autocast dtype mismatch in Phi-tiny-MoE is unrelated to Qwen3.5 streaming API failure." }, { "left": "issue:44291", "right": "issue:45070", "accept": false, - "reason": "init_empty_weights argument handling and a pydantic config-field regression do not match." + "reason": "Both are v5 regressions, but one is `init_empty_weights` argument handling and the other is a pydantic field breakage." }, { "left": "issue:43366", "right": "issue:45464", "accept": false, - "reason": "GPT-OSS GGUF support and Qwen3.5 streaming chat failures are unrelated." + "reason": "GGUF gpt-oss architecture support and Qwen3.5 streaming inference are unrelated." }, { "left": "issue:45020", "right": "issue:45800", "accept": false, - "reason": "Remote-code model breakage and a torch/transformers version incompatibility are too broad and not the same concrete bug." + "reason": "Remote-code model breakage and torch/transformers version incompatibility are different root causes." }, { "left": "issue:43531", "right": "issue:45070", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior and pydantic config handling are unrelated." + "reason": "Sliding-window behavior on Qwen3-MoE is unrelated to the PretrainedConfig pydantic regression." }, { "left": "issue:43541", "right": "issue:44589", "accept": false, - "reason": "Mixtral tracing errors and Float8 storage lookup failures are different runtime issues." + "reason": "Grouped_mm tracing failure and missing Float8 storage support are distinct runtime issues." }, { "left": "issue:41093", "right": "issue:43596", "accept": false, - "reason": "Both mention zero-3 IndexErrors, but the exact failure surfaces and models differ enough to reject as duplicates." + "reason": "Both are index-related, but they arise from different workflows and failure points." }, { "left": "issue:43054", "right": "issue:43994", "accept": true, - "reason": "Same SigLIP2 regression: both reports describe bad/nonsensical SigLIP2 text embeddings or outputs compared with expected behavior." + "reason": "Both report SigLIP2 behaving incorrectly at inference/loading time; they likely stem from the same model implementation bug." }, { "left": "issue:45759", "right": "issue:45902", "accept": false, - "reason": "Composite Qwen config unwrapping and uninitialized rotary embedding memory are different bugs." + "reason": "Multimodal config unwrapping and rotary-embedding uninitialized-memory issues are different bugs." }, { "left": "issue:45542", "right": "issue:45800", "accept": false, - "reason": "TensorBoard/TensorFlow backend handling and torch/transformers version incompatibility are unrelated." + "reason": "TensorBoard-without-TensorFlow backend error is unrelated to torch/transformers version incompatibility." }, { "left": "issue:39186", "right": "issue:44918", "accept": false, - "reason": "FSDP 2-D weight error and Qwen3.5 SFT embedding unpacking are different problems." + "reason": "FSDP weight-shape failure and Qwen3.5 embedding unpacking in TRL are different problems." }, { - "left": "issue:40990", - "right": "issue:44960", + "left": "issue:43716", + "right": "issue:44918", "accept": false, - "reason": "High perplexity on GPT-OSS and a GLM5 issue are unrelated." + "reason": "Mistral3 image-preprocessor dtype mismatch and Qwen3.5 SFT embedding unpacking are unrelated." }, { - "left": "issue:43716", - "right": "issue:44918", + "left": "issue:40990", + "right": "issue:44960", "accept": false, - "reason": "Mistral-3 image-preprocessor dtype mismatch and Qwen3.5 SFT embedding unpacking are unrelated." + "reason": "High perplexity on gpt-oss-20b and a GLM5 issue are not the same bug." }, { "left": "issue:45632", "right": "issue:45698", - "accept": false, - "reason": "Both involve custom model loading, but one is a cache-path collision and the other is wrong module selection after save/load; not clearly the same concrete bug." + "accept": true, + "reason": "Both describe `trust_remote_code`/custom-module resolution loading the wrong local module; same cache/path-selection bug." }, { "left": "issue:43645", "right": "issue:45399", "accept": false, - "reason": "Notebook custom-model initialization and flash-attn2 fallback gating are unrelated." + "reason": "Custom-model Jupyter init breakage and flash-attn2 fallback gating are unrelated." }, { "left": "issue:43404", "right": "issue:45005", "accept": false, - "reason": "Both discuss tied weights, but they affect different model families and likely different code paths; too broad to merge." + "reason": "Both concern tied weights, but they affect different model classes and likely different implementations." } ] }, "evaluator_result": { "accept": true, - "feedback": "The writeup is grounded in the packet and stays conservative on the rejects. The one accepted soft pair, issue:43054 and issue:43994, is reasonably supported by the titles alone as the same SigLIP2 output-quality regression. No mergeability problems apply here." + "feedback": "The summary is grounded in the packet: the cluster is mostly heterogeneous, and the two accepted soft pairs are the only ones that look plausibly duplicate based on the issue titles. The rejected pairs are phrased conservatively and do not overclaim identity. No mergeability problems apply here." }, "evaluator_used": true, "retried": false, @@ -970,7 +904,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:36331", "issue:38175", @@ -1057,244 +991,244 @@ "issue:43881|issue:43883", "issue:43782|issue:44960" ], - "prepared_review_unit_hash": "28ff74252fd5eb7c48632c059f5dc1887acb1b7e8491ed2c4e1aba2bd7c987fc", + "prepared_review_unit_hash": "fe6e7d225e607b85d1d877238cfb3a1ee69fc17f49b91c645b66b1c7df3cbdde", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 34, - "serialized_chars": 37510, - "estimated_input_tokens": 9378, - "estimated_eval_tokens": 19012 + "serialized_chars": 37508, + "estimated_input_tokens": 9377, + "estimated_eval_tokens": 19010 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous, with one clear duplicate subgroup around the Transformers 5.x non-persistent-buffer corruption regression. The rest of the pairs are only broadly similar by subsystem or model family, not the same concrete bug.", - "confidence": 0.9, - "canonical_issue_reason": "issue:43644 is the earliest and broadest statement of the shared regression (\u201cfills non-persistent buffers with junk\u201d), making it the best anchor for the duplicate set; later reports like issue:43950 and issue:44534 look like narrower manifestations of the same loading bug.", + "summary": "This cluster is mostly heterogeneous, but there is a clear duplicate pocket around the Transformers 5.x non-persistent buffer regression. Most other pairs are different model-specific or API-specific bugs and should stay separate.", + "confidence": 0.84, + "canonical_issue_reason": "issue:43950 is the clearest, broadest statement of the shared regression: non-persistent buffers are corrupted during `from_pretrained()` in Transformers 5.x. It also naturally subsumes the later specific symptom in issue:45902 and the near-duplicate wording in issue:44534.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43950 is the most actionable standalone report because it names the failure mode precisely (`from_pretrained()` corrupting `register_buffer(persistent=False)` state) and aligns cleanly with the duplicate reports.", + "best_issue_reason": "issue:43950 best represents the duplicate set because it names the root regression directly and generalizes across the specific downstream symptoms reported later.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:42915", "right": "issue:45399", "accept": false, - "reason": "Different problems: Qwen3Moe FP8 failure vs a flash-attn2 fallback gating issue." + "reason": "Different failures: Qwen3Moe FP8 loading vs FlashAttention fallback gating." }, { "left": "issue:44530", "right": "issue:45005", "accept": false, - "reason": "Different bugs: Qwen3.5 PagedAttention cache crash vs tied-weights handling in translation models." + "reason": "Qwen3.5 packed-sequence/cache crash is not the same bug as the tied-weights v5 regression." }, { "left": "issue:43873", "right": "issue:45005", "accept": false, - "reason": "Quantization/offloading behavior is unrelated to tied-weights regressions." + "reason": "Quantization/offloading behavior is unrelated to tied-weights handling." }, { "left": "issue:44863", "right": "issue:45005", "accept": false, - "reason": "NemotronH checkpoint loading is a separate model-compatibility issue, not tied-weights handling." + "reason": "NemotronH checkpoint loading failure is a different code path from tied-weights issues." }, { "left": "issue:44360", "right": "issue:44512", "accept": false, - "reason": "DSA indexer architecture discussion is unrelated to docs mentioning a removed CLI command." + "reason": "DSA indexer/ReLU discussion is unrelated to a docs typo about the run command." }, { "left": "issue:44918", "right": "issue:45507", "accept": false, - "reason": "TRl SFT embedding unpacking and GraniteMoE invalid-method calls are different model/path failures." + "reason": "TRL embedding unpacking and GraniteMoE invalid-method calls are different model/trainer bugs." }, { "left": "issue:44492", "right": "issue:44512", "accept": false, - "reason": "A typo in cache strategy docs is not the same as stale docs about the removed run command." + "reason": "Cache-strategy typo is not the same as removed-run-command documentation drift." }, { "left": "issue:43975", "right": "issue:44292", "accept": false, - "reason": "Different model/output issues: detokenization regression vs NVFP4 runtime failure." + "reason": "DeepSeek detokenization regression and Qwen3 NVFP4 load failure are different bugs." }, { "left": "issue:44292", "right": "issue:45507", "accept": false, - "reason": "Qwen NVFP4 runtime failure is unrelated to GraniteMoE calling an invalid method." + "reason": "Qwen3 NVFP4 load failure is unrelated to GraniteMoEHybrid's invalid method call." }, { "left": "issue:43950", "right": "issue:44534", "accept": true, - "reason": "Both report the same Transformers 5.x regression where non-persistent buffers are materialized with junk values." + "reason": "Same underlying non-persistent-buffer corruption regression in Transformers 5.x, phrased with different surface symptoms." }, { "left": "issue:43644", "right": "issue:43950", - "accept": true, - "reason": "Same underlying bug: Transformers 5.x corrupts non-persistent buffers during loading/materialization." + "accept": false, + "reason": "`trust_remote_code` missing fields is a different regression than buffer corruption during load." }, { "left": "issue:39692", "right": "issue:43054", "accept": false, - "reason": "Both involve SigLIP2, but one is a docs/example mismatch and quantization failure while the other is degraded text embeddings." + "reason": "Broken docs example and poor SigLIP2 text embeddings are different problems." }, { "left": "issue:43828", "right": "issue:44928", "accept": false, - "reason": "Both mention Qwen/positioning problems, but the concrete failures differ: dtype mismatch under autocast vs RLHF gradient explosion." + "reason": "Autocast dtype mismatch is a different failure from Qwen3.5 position-id/SDPA instability." }, { "left": "issue:36331", "right": "issue:41762", "accept": false, - "reason": "CustomTrainer signature mismatch and Gemma3 ZeRO-3 loading error are unrelated runtime failures." + "reason": "Trainer API kwarg breakage is unrelated to Gemma3 ZeRO-3 loading." }, { "left": "issue:41628", "right": "issue:45800", "accept": false, - "reason": "AutoImageProcessor import/export breakage is not the same as a torch-version compatibility issue." + "reason": "Importing `AutoImageProcessor` and a torch/transformers version incompatibility are not the same concrete bug." }, { "left": "issue:43950", "right": "issue:45902", - "accept": false, - "reason": "Related buffer/materialization theme, but 45902 is a specific Qwen3.5 rotary-embedding uninitialized-memory bug, not the same generic from_pretrained corruption report." + "accept": true, + "reason": "Issue:45902 is a concrete symptom of the same non-persistent-buffer/materialization corruption regression described in issue:43950." }, { "left": "issue:43872", "right": "issue:44589", "accept": false, - "reason": "bitsandbytes parameter-construction incompatibility is distinct from missing Float8 storage support." + "reason": "Bitsandbytes constructor mismatch and missing Float8 storage are separate quantization issues." }, { "left": "issue:43866", "right": "issue:44403", "accept": false, - "reason": "Checkpoint corruption and noisy loading are different failures." + "reason": "A corrupted checkpoint and generic loading noise are not the same underlying bug." }, { "left": "issue:43054", "right": "issue:45701", "accept": false, - "reason": "Both mention tokenization/model output quality, but one is SigLIP2 text embedding degradation and the other is a general tokenization change regression." + "reason": "SigLIP2 embedding quality and version-dependent tokenization changes are different concerns." }, { "left": "issue:41553", "right": "issue:43883", "accept": false, - "reason": "Bad AutoTokenizer error handling for Voxtral is unrelated to Molmo missing `all_tied_weights_keys`." + "reason": "Bad AutoTokenizer error handling for Voxtral is unrelated to Molmo's missing tied-weights attribute." }, { "left": "issue:38175", "right": "issue:43054", "accept": false, - "reason": "Zero probabilities in siglip2-base and worse SigLIP2 text embeddings are different symptoms with different likely causes." + "reason": "Both involve SigLIP2, but zero probabilities and lower text-embedding quality are not clearly the same concrete bug." }, { "left": "issue:44910", "right": "issue:45859", "accept": false, - "reason": "Qwen3.5 flash-attention crash from 3D position_ids is not the same as CPU-offload incompatibility in rotary embedding." + "reason": "FlashAttention packed-sequence crash on Qwen3.5 is distinct from CPU-offload incompatibility in rotary embedding." }, { "left": "issue:45663", "right": "issue:45902", "accept": false, - "reason": "Gemma4 FSDP2 shared_kv_states bug is unrelated to Qwen3.5 rotary-embedding uninitialized memory." + "reason": "Gemma4 FSDP2 KeyError and Qwen3.5 buffer materialization corruption are unrelated." }, { "left": "issue:41553", "right": "issue:43881", "accept": false, - "reason": "Bad AutoTokenizer error messaging for Voxtral and glm-4v-9b loading failure are separate model-loading issues." + "reason": "Voxtral tokenizer error messaging and glm-4v-9b load failure are different bugs." }, { "left": "issue:42947", "right": "issue:44387", "accept": false, - "reason": "LoRA gradient-checkpointing ineffectiveness and int4 CUDA memory growth are different training/runtime regressions." + "reason": "LoRA checkpointing ineffectiveness is not the same as int4 quantization memory growth/OOM." }, { "left": "issue:43054", "right": "issue:43493", - "accept": false, - "reason": "Both are SigLIP2-related, but one is text embedding quality while the other is HF-vs-JAX implementation discrepancy." + "accept": true, + "reason": "Both point at the same SigLIP2 HF-vs-JAX implementation discrepancy that degrades text-side behavior." }, { "left": "issue:44403", "right": "issue:44451", "accept": false, - "reason": "General loading noise and inability to load a specific model are not the same bug." + "reason": "Generic loading noise and inability to load a specific model are not the same defect." }, { "left": "issue:43975", "right": "issue:45237", "accept": false, - "reason": "Detokenization regression and AMD GPU runtime incompatibility are unrelated." + "reason": "Detokenization regression and AMD GPU execution failure are unrelated." }, { "left": "issue:43643", "right": "issue:45020", "accept": false, - "reason": "Missing fields from AutoConfig with trust_remote_code is a different issue than models broadly breaking under recent transformers versions." + "reason": "Missing fields from `AutoConfig` with `trust_remote_code` is only one possible symptom inside a broader remote-code complaint, not a clearly identical bug." }, { "left": "issue:44403", "right": "issue:44488", "accept": false, - "reason": "Both are loading-related, but they target different models and failure modes." + "reason": "These are different model-loading reports, not the same bug." }, { "left": "issue:42947", "right": "issue:43856", "accept": false, - "reason": "LoRA checkpointing behavior and Qwen3 MoE memory usage are different optimization/training issues." + "reason": "PEFT gradient-checkpointing behavior and Qwen3 MoE memory usage are different training issues." }, { "left": "issue:41762", "right": "issue:42915", "accept": false, - "reason": "Gemma3 ZeRO-3 loading failure and Qwen3Moe FP8 failure are unrelated model-loading bugs." + "reason": "Gemma3 ZeRO-3 load failure and Qwen3Moe FP8 failure are unrelated." }, { "left": "issue:43881", "right": "issue:43883", "accept": false, - "reason": "Different model load failures: glm-4v-9b loading vs Molmo tied-weights attribute error." + "reason": "Different models and different failure modes: glm-4v-9b load error vs Molmo tied-weights attribute error." }, { "left": "issue:43782", "right": "issue:44960", "accept": false, - "reason": "Qwen3VL weight-only loading error and GLM5 are separate model-specific failures." + "reason": "Qwen3VL weight_only load failure and GLM5 are unrelated model-specific issues." } ] }, "evaluator_result": { "accept": true, - "feedback": "The analysis is grounded in the packet and stays conservative overall. The canonical cluster anchor around issue:43644 / issue:43950 / issue:44534 is well-supported by the titles, timestamps, and the shared non-persistent-buffer corruption wording. The remaining soft-edge rejections are cautious and consistent with the available evidence, and the accepted pairings are the strongest clear duplicate links in the set." + "feedback": "The summary is grounded in the packet and stays conservative overall. The only accepted duplicate pockets are the clearly related SigLIP2 pair and the Transformers v5 non-persistent-buffer regression cluster, which are both supported by the issue titles. The rest of the soft-edge rejections are appropriately cautious for a heterogeneous cluster." }, "evaluator_used": true, "retried": false, @@ -1313,7 +1247,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:24643", "issue:30064", @@ -1366,22 +1300,22 @@ ], "soft_pairs": [ "issue:45685|issue:45823", - "issue:42491|issue:44368", - "issue:44991|issue:45399", "issue:43824|issue:43872", + "issue:44991|issue:45399", + "issue:42491|issue:44368", "issue:45020|issue:45823", "issue:44661|issue:45020", "issue:43828|issue:45823", "issue:45081|issue:45399", "issue:45020|issue:45356", "issue:43742|issue:45399", - "issue:43827|issue:44509", "issue:43404|issue:43950", + "issue:43827|issue:44509", "issue:43638|issue:45823", "issue:42915|issue:45020", - "issue:43792|issue:44220", "issue:43257|issue:43866", "issue:43872|issue:44291", + "issue:43792|issue:44220", "issue:42915|issue:43872", "issue:41553|issue:44991", "issue:36331|issue:41093", @@ -1399,20 +1333,20 @@ "issue:45325|issue:45902", "issue:43366|issue:43828" ], - "prepared_review_unit_hash": "faabc12376afaeba77f54a8cd36a21250ffeb99d184495018aa61abf6f726e8a", + "prepared_review_unit_hash": "be43def021e578871f06c3fb7c8ac526b41bbc41750e98122562524d7c10ef52", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 33, - "serialized_chars": 38072, + "serialized_chars": 38069, "estimated_input_tokens": 9518, "estimated_eval_tokens": 19292 }, @@ -1421,216 +1355,216 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly a heterogeneous cluster of unrelated bugs. I only see a few true duplicate-style matches: two docs issues about stale v5 pipeline references, two mask-shape mismatch reports, and one `_is_hf_initialized` initialization regression. The rest are similar-at-a-glance but not the same underlying problem.", - "confidence": 0.74, - "canonical_issue_reason": "There is no single canonical issue for the whole cluster; 44509 is the cleanest anchor only for the docs/pipeline-removal duplicate pair because it is the broader, more explicit report.", + "summary": "Mostly unrelated issues; only a few soft pairs look like true duplicates, mainly exact-regression matches in tokenizer/docs/loading paths. No PRs are present.", + "confidence": 0.67, + "canonical_issue_reason": "issue:44291 is the clearest, most explicit reproduction of the shared `_is_hf_initialized` loading regression, and it lines up directly with the bitsandbytes-related duplicate.", "canonical_pr_reason": null, - "best_issue_reason": "44509 is the strongest overall issue candidate among the confirmed duplicates: it clearly states the v5 docs regression and subsumes 43827.", + "best_issue_reason": "issue:44291 is the strongest issue anchor in this set because it describes a concrete, version-scoped code-path failure with a clear fix surface.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45685", "right": "issue:45823", "accept": false, - "reason": "Different models and failures: MPS/int histogram error vs Gemma4 PLE device mismatch." + "reason": "Different failures: MPS integer histogram support vs device placement mismatch in Gemma4 PLE." }, { - "left": "issue:42491", - "right": "issue:44368", + "left": "issue:43824", + "right": "issue:43872", "accept": false, - "reason": "Both involve Qwen3 LoRA/configuration, but one is a cross-version compatibility break and the other is a tie_word_embeddings warning; not the same bug." + "reason": "Both are import/load failures, but they point to different model families and different failure modes." }, { "left": "issue:44991", "right": "issue:45399", "accept": false, - "reason": "Tokenizer loading regression vs flash-attn fallback gating; different code paths and symptoms." + "reason": "Tokenizer loading regression vs flash-attention fallback gating; unrelated code paths." }, { - "left": "issue:43824", - "right": "issue:43872", + "left": "issue:42491", + "right": "issue:44368", "accept": false, - "reason": "Import error for a model class vs bitsandbytes `_is_hf_initialized` incompatibility; unrelated failures." + "reason": "Both mention Qwen/LoRA warnings, but one is a hard loading incompatibility and the other is a config warning." }, { "left": "issue:45020", "right": "issue:45823", "accept": false, - "reason": "Broad remote_code breakage vs a specific device-map forward mismatch; not the same underlying issue." + "reason": "Remote-code regression and device-map mismatch are different bugs." }, { "left": "issue:44661", "right": "issue:45020", "accept": false, - "reason": "A tooling failure in add-new-model-like vs a runtime remote_code regression; different problems." + "reason": "Different issues: tokenizer mapping helper failure vs broad remote_code breakage." }, { "left": "issue:43828", "right": "issue:45823", "accept": false, - "reason": "Autocast dtype mismatch on Phi-tiny-MoE is separate from Gemma4 device placement." + "reason": "Autocast dtype mismatch is not the same as a device-map forward mismatch." }, { "left": "issue:45081", "right": "issue:45399", "accept": false, - "reason": "Mistral tokenizer regex patch crash is unrelated to flash-attn fallback logic." + "reason": "Tokenizer regex crash vs flash-attn availability checks; not the same bug." }, { "left": "issue:45020", "right": "issue:45356", "accept": false, - "reason": "Different tokenizer regressions with different failure modes; not one concrete bug." + "reason": "Broad remote_code breakage and Kimi tokenizer regression are distinct." }, { "left": "issue:43742", "right": "issue:45399", "accept": false, - "reason": "Generic model load failure vs flash-attn fallback checks; no shared code-path evidence." - }, - { - "left": "issue:43827", - "right": "issue:44509", - "accept": true, - "reason": "Same underlying docs regression: both report stale references to pipeline tasks removed in v5; 44509 is the broader formulation." + "reason": "MobileLLM loading/key error and flash-attn fallback gating are unrelated." }, { "left": "issue:43404", "right": "issue:43950", "accept": false, - "reason": "lm_head tying bug vs non-persistent buffer corruption; different state-handling issues." + "reason": "Weight tying bug and non-persistent buffer corruption are different loading regressions." + }, + { + "left": "issue:43827", + "right": "issue:44509", + "accept": true, + "reason": "Both are the same docs cleanup: stale v5 pipeline-task references that were removed." }, { "left": "issue:43638", "right": "issue:45823", "accept": false, - "reason": "DeepSpeed ZeRO-3 index error on a Bert model vs Gemma4 device mismatch; unrelated." + "reason": "Zero-3 index error with a non-pretrained Bert model is unrelated to Gemma4 device placement." }, { "left": "issue:42915", "right": "issue:45020", "accept": false, - "reason": "Qwen3 MoE + FineGrainedFP8Config vs broad remote_code breakage; too different." - }, - { - "left": "issue:43792", - "right": "issue:44220", - "accept": false, - "reason": "Whisper failing to run and a fbank helper issue may be related, but the evidence is too thin to treat them as the same bug." + "reason": "Qwen3 MoE weight conversion under deepspeed is not the same as general remote_code breakage." }, { "left": "issue:43257", "right": "issue:43866", "accept": false, - "reason": "Qwen3 MoE weight-conversion/loading bug vs corrupted Ovis2 checkpoint; different root causes." + "reason": "Weight loading under accelerate/deepspeed and a corrupted checkpoint are different problems." }, { "left": "issue:43872", "right": "issue:44291", "accept": true, - "reason": "Same `_is_hf_initialized` initialization regression showing up in bitsandbytes/Int8Params and init_empty_weights loading paths." + "reason": "Same underlying `_is_hf_initialized`/tensor-construction TypeError during model loading; these can be fixed together." + }, + { + "left": "issue:43792", + "right": "issue:44220", + "accept": true, + "reason": "Both point to the Whisper feature-extraction path failing in the same audio preprocessing code." }, { "left": "issue:42915", "right": "issue:43872", "accept": false, - "reason": "Different Qwen3/MoE loading and FP8-related problems; no shared concrete failure." + "reason": "Qwen3 MoE weight conversion and bitsandbytes constructor incompatibility are unrelated." }, { "left": "issue:41553", "right": "issue:44991", "accept": false, - "reason": "Bad error message for Voxtral tokenizer loading vs est-roberta tokenizer load failure; different issues." + "reason": "Both are tokenizer-loading complaints, but they affect different models and likely different causes." }, { "left": "issue:36331", "right": "issue:41093", "accept": false, - "reason": "Trainer API signature break vs tensor/mask shape mismatch; unrelated." + "reason": "Trainer API kwarg mismatch and tensor mask shape mismatch are unrelated." }, { "left": "issue:43257", "right": "issue:45305", "accept": false, - "reason": "Qwen3 MoE weight loading under accelerate+deepspeed vs gradient averaging with GAS; different training bugs." + "reason": "DeepSpeed weight-loading failure and GAS gradient averaging regression are different code paths." }, { "left": "issue:42947", "right": "issue:45923", "accept": false, - "reason": "General ineffective gradient checkpointing under PEFT LoRA vs a specific missing supports_gradient_checkpointing flag; not enough evidence they are the same bug." + "reason": "Gradient checkpointing issue in PEFT LoRA is not the same as a missing supports_gradient_checkpointing flag on a remote-code model." }, { "left": "issue:43940", "right": "issue:45313", "accept": false, - "reason": "Both are ZeRO-3 weight-loading failures on Qwen variants, but the affected model paths and symptoms differ enough that I would not merge them." + "reason": "Both involve Qwen + ZeRO-3 loading, but the model targets and failure descriptions are not concrete duplicates." }, { "left": "issue:43854", "right": "issue:44863", "accept": false, - "reason": "Different model-loading failures for different architectures; no concrete match." + "reason": "Different model-loading failures with no clear shared code path." }, { "left": "issue:44928", "right": "issue:45588", "accept": false, - "reason": "RLHF NaN/SDPA fallback problem vs flash_attention `s_aux=None` crash; separate issues." + "reason": "RLHF NaN/SDPA fallback issue is unrelated to a flash_attention.py crash on sink-less models." }, { "left": "issue:43872", "right": "issue:45538", "accept": false, - "reason": "Bitsandbytes `_is_hf_initialized` incompatibility vs CLIPTokenizer max length bug; unrelated." + "reason": "bitsandbytes constructor compatibility and CLIPTokenizer max-length behavior are unrelated." }, { "left": "issue:41093", "right": "issue:44805", "accept": true, - "reason": "Same mask/tensor shape mismatch class with essentially the same IndexError, just reported with different concrete sizes." + "reason": "Same mask/index shape mismatch error; the titles describe the same underlying IndexError." }, { "left": "issue:41553", "right": "issue:44488", "accept": false, - "reason": "Bad Voxtral error message vs failure to load a different model; no shared bug." + "reason": "Different tokenizer-loading failures for different models; not the same bug." }, { "left": "issue:44479", "right": "issue:44560", "accept": false, - "reason": "Separate video-input regressions affecting different model families and error paths." + "reason": "Both are video-related Qwen regressions, but the concrete failures are different enough to keep separate." }, { "left": "issue:44530", "right": "issue:44863", "accept": false, - "reason": "PagedAttentionCache/linear_attention crash vs checkpoint-loading failure; unrelated." + "reason": "PagedAttentionCache linear_attention crash and NemotronH checkpoint loading failure are unrelated." }, { "left": "issue:24643", "right": "issue:30064", "accept": false, - "reason": "DeepSpeed weight shape error vs void segmentation-map processing; completely different subsystems." + "reason": "Training with DeepSpeed and void segmentation map processing are unrelated issues." }, { "left": "issue:45325", "right": "issue:45902", "accept": false, - "reason": "Qwen2.5-VL rope scaling bug vs Qwen3.5 MoE rotary embedding memory/materialization bug; different code paths." + "reason": "RoPE position-id scaling bug and uninitialized-memory materialization bug are different." }, { "left": "issue:43366", "right": "issue:43828", "accept": false, - "reason": "GGUF gpt-oss support request vs Phi-tiny-MoE autocast dtype mismatch; not the same bug." + "reason": "GGUF architecture support and dtype mismatch under autocast are unrelated." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays appropriately conservative. The three accepted duplicate-style pairs are well supported by the issue titles/bodies, and the rest are cautiously rejected without overclaiming shared root cause. No mergeability concerns apply here since these are issue pairs, not PR pairs." + "feedback": "The assessment is grounded in the packet: the cited issue titles support the main anchors, the summary stays appropriately cautious, and the soft-edge rejections are conservative. The accepted pairs are all at least plausibly same-bug duplicates from the text, and there are no PR pairs to evaluate." }, "evaluator_used": true, "retried": false, @@ -1649,7 +1583,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:36010", "issue:38175", @@ -1689,6 +1623,7 @@ "issue:44918", "issue:44960", "issue:44977", + "issue:44991", "issue:45030", "issue:45276", "issue:45313", @@ -1710,8 +1645,8 @@ "issue:43645|issue:43646", "issue:42915|issue:43957", "issue:43366|issue:44589", - "issue:44560|issue:44918", "issue:42617|issue:43366", + "issue:44560|issue:44918", "issue:36010|issue:42915", "issue:44661|issue:45823", "issue:44560|issue:44805", @@ -1731,234 +1666,241 @@ "issue:45313|issue:45357", "issue:42915|issue:44756", "issue:42491|issue:45276", - "issue:43708|issue:44075" + "issue:43708|issue:44075", + "issue:44488|issue:44991" ], - "prepared_review_unit_hash": "944e43036bcbde4e806bcc5895c616fc0b7dd3e2319d6e9543a46d4dfc552d99", + "prepared_review_unit_hash": "2174bc32ae48c0c2a60dadbfb229a7393e36f267246c8e6f95e3e6d53c916ec0", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 32, - "serialized_chars": 36619, - "estimated_input_tokens": 9155, - "estimated_eval_tokens": 18566 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37489, + "estimated_input_tokens": 9373, + "estimated_eval_tokens": 19002 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a mix of unrelated transformer bugs; only a few soft pairs look like true duplicates of the same concrete regression. The clearest duplicate subcluster is the Transformers v5 non-persistent-buffer corruption report.", - "confidence": 0.78, - "canonical_issue_reason": "No single canonical issue fits the whole cluster because most items describe different bugs. If one representative is needed, issue 43644 is the best anchor for the clear duplicate pair with 44534 about non-persistent buffers being filled with junk in Transformers v5.", + "summary": "This is a mixed cluster with several small duplicate islands rather than one unified bug. The clearest duplicates are around Transformers v5 regressions (non-persistent buffers, custom model init, ZeRO-3/BERT failures) and a SigLIP2 output issue; most other pairs are unrelated model-specific bugs.", + "confidence": 0.67, + "canonical_issue_reason": "No single cluster-wide canonical issue fits all items because the set splits into multiple unrelated bugs. If a representative anchor is needed, 43644 is the cleanest duplicate pair anchor for the non-persistent-buffer regression.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43644 is the strongest representative because it predates 44534 and describes the core regression most directly: Transformers v5 corrupting non-persistent buffers during load.", + "best_issue_reason": "43644 is the best single issue anchor: it is a crisp, well-scoped Transformers v5 regression and is duplicated almost verbatim by 44534.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45663", "right": "issue:45823", "accept": false, - "reason": "Different Gemma4 failures: FSDP2 shared_kv_states KeyError vs device_map='auto' PLE device mismatch." + "reason": "Both are Gemma4 issues, but one is an FSDP2 shared_kv_states bug and the other is a device_map=\"auto\" device mismatch; different code paths." }, { "left": "issue:44155", "right": "issue:45584", "accept": false, - "reason": "Different models and failure modes: AudioFlamingo3 batched leakage vs Whisper empty-transcription generation." + "reason": "AudioFlamingo3 batched inference leak and Whisper empty-transcription handling are unrelated bugs." }, { "left": "issue:43366", "right": "issue:43531", "accept": false, - "reason": "Unrelated Qwen3-MoE sliding_window bug vs GGUF gpt-oss architecture support request." + "reason": "GGUF gpt-oss support and Qwen3-MoE sliding_window behavior are different features/problems." }, { "left": "issue:43950", "right": "issue:45834", "accept": false, - "reason": "Non-persistent buffer regression vs Kosmos2.5 long-ocr index error are different bugs." + "reason": "Non-persistent buffer corruption and Kosmos2.5 long-ocr index errors are unrelated." }, { "left": "issue:43824", "right": "issue:43957", "accept": false, - "reason": "Different loading problems: missing Qwen2_5_VL export vs meta-device loading issues across models." + "reason": "One is a missing Qwen2_5_VL export/import, the other is meta-device loading breakage; not the same bug." }, { "left": "issue:44560", "right": "issue:45685", "accept": false, - "reason": "Different subsystems and errors: Qwen3-vl StopIteration on video vs MPS histogram not implemented for Int." + "reason": "Qwen3-VL video StopIteration and MPS histogram support for Int are unrelated." }, { "left": "issue:43550", "right": "issue:44910", "accept": false, - "reason": "Different code paths: Bamba torch.compile/SDPA failure vs Qwen3.5 Flash Attention crash from 3D position_ids." + "reason": "Different attention-backend failures on different models; too broad to be the same concrete bug." }, { "left": "issue:43645", "right": "issue:43646", "accept": true, - "reason": "Same underlying Transformers v5 custom-model initialization regression; one is a notebook manifestation of the same breakage." + "reason": "Same Transformers v5 custom model initialization regression; the notebook mention is just an environment-specific manifestation." }, { "left": "issue:42915", "right": "issue:43957", "accept": false, - "reason": "Qwen3-MoE FineGrainedFP8 failure is unrelated to meta-device loading regressions." + "reason": "Qwen3-MoE FP8 failure and meta-device loading problems are distinct issues." }, { "left": "issue:43366", "right": "issue:44589", "accept": false, - "reason": "GGUF gpt-oss support is unrelated to Float8 storage lookup failures." + "reason": "GGUF model support and Float8 storage import errors are unrelated." }, { - "left": "issue:44560", - "right": "issue:44918", + "left": "issue:42617", + "right": "issue:43366", "accept": false, - "reason": "Different Qwen3-vl problems: video StopIteration vs embedding unpacking with TRL SFT trainer." + "reason": "3d_parallel.py failure and GGUF gpt-oss support are different areas." }, { - "left": "issue:42617", - "right": "issue:43366", + "left": "issue:44560", + "right": "issue:44918", "accept": false, - "reason": "3d_parallel.py execution failure is not the same bug as GGUF gpt-oss support." + "reason": "Qwen3-VL video StopIteration and Qwen3.5 embedding unpacking with TRL are unrelated." }, { "left": "issue:36010", "right": "issue:42915", "accept": false, - "reason": "ImportError for GenerationMixin is unrelated to Qwen3Moe FineGrainedFP8 failure." + "reason": "GenerationMixin import failure and Qwen3-MoE FP8 failure are unrelated." }, { "left": "issue:44661", "right": "issue:45823", "accept": false, - "reason": "TOKENIZER_MAPPING_NAMES add-new-model-like bug is unrelated to Gemma4 PLE device mismatch." + "reason": "Tokenizer-mapping model registration bug and Gemma4 PLE device mismatch are unrelated." }, { "left": "issue:44560", "right": "issue:44805", "accept": false, - "reason": "Different runtime errors in different Qwen3-vl contexts: video StopIteration vs mask/tensor shape mismatch." + "reason": "Different indexing/sequence bugs in different model paths." }, { "left": "issue:43632", "right": "issue:45834", "accept": false, - "reason": "_is_hf_initialized flag regression is unrelated to Kosmos2.5 OCR index errors." + "reason": "_is_hf_initialized regression and Kosmos2.5 OCR index error are unrelated." }, { "left": "issue:38175", "right": "issue:43994", "accept": true, - "reason": "Both report the same SigLIP2 bad-output regression on google/siglip2-base-patch16-224, just with different symptoms." + "reason": "Both report the same SigLIP2 bad-output regression on google/siglip2-base-patch16-224; 43994 is a later re-report of the same model/processor problem." }, { "left": "issue:43638", "right": "issue:44661", "accept": false, - "reason": "Zero-3 BertModel indexing error and add-new-model-like TOKENIZER_MAPPING_NAMES issue are distinct." + "reason": "ZeRO-3 BertModel index error and add-new-model-like tokenizer mapping failure are different bugs." }, { "left": "issue:43596", "right": "issue:44661", "accept": false, - "reason": "DeepSpeed ZeRO-3 BertModel index error is unrelated to TOKENIZER_MAPPING_NAMES handling." + "reason": "ZeRO-3 BertModel index error and tokenizer-mapping registration are unrelated." }, { "left": "issue:44661", "right": "issue:44805", "accept": false, - "reason": "TOKENIZER_MAPPING_NAMES bug and mask/tensor shape mismatch are unrelated." + "reason": "Different model-registration vs tensor-mask shape error." }, { "left": "issue:44877", "right": "issue:45030", "accept": false, - "reason": "Strict config loading for granite_speech is not the same as glm4v config validation failure." + "reason": "Both involve config validation, but they affect different model families and appear to be separate breakages." }, { "left": "issue:43317", "right": "issue:44756", "accept": false, - "reason": "device_map/offload loading failure is unrelated to the Strix Halo mmap OOM workaround request." + "reason": "device_map/offload load failure and Strix Halo mmap OOM are not the same concrete bug." }, { "left": "issue:43644", "right": "issue:44534", "accept": true, - "reason": "Same regression: Transformers v5 fills non-persistent buffers with junk; 44534 is a later duplicate phrasing of the same bug." + "reason": "Verbatim duplicate regression: Transformers v5 fills non-persistent buffers with junk." }, { "left": "issue:38175", "right": "issue:39692", "accept": false, - "reason": "SigLIP2 wrong outputs are not the same as the documentation example's model/processor mismatch and quantization errors." + "reason": "The docs-example issue also includes quantization/doc errors, so it is not clearly the same concrete bug as the runtime SigLIP2 zero-probability report." }, { "left": "issue:42491", "right": "issue:43720", "accept": false, - "reason": "Qwen3 MoE LoRA hf4.x/hf5.x incompatibility is unrelated to BitNet packed-weight loading in accelerate." + "reason": "Qwen3_MoE LoRA compatibility on hf5.x and BitNet packed-weight loading are unrelated." }, { "left": "issue:41720", "right": "issue:42915", "accept": false, - "reason": "Qwen3 auto device-mapping cudaErrorAssert and Qwen3Moe FineGrainedFP8 are different failures." + "reason": "Auto device mapping cudaErrorAssert and Qwen3-MoE FP8 failure are different issues." }, { "left": "issue:44960", "right": "issue:44977", "accept": false, - "reason": "GLM5 and Qwen3.5 flash-attention generation failures are unrelated bugs." + "reason": "GLM5 and Qwen3.5 flash-attention failures are unrelated." }, { "left": "issue:44451", "right": "issue:44488", - "accept": false, - "reason": "Both are model-loading failures, but they concern different checkpoints and do not clearly share the same concrete bug." + "accept": true, + "reason": "Both are current-version load failures for closely related BERT checkpoints; this looks like the same loader regression." }, { "left": "issue:45313", "right": "issue:45357", "accept": false, - "reason": "Qwen3.5 ZeRO-3 weight loading and save_pretrained visual-encoder key saving are different regressions." + "reason": "DeepSpeed ZeRO-3 load failure and incorrect save_pretrained visual encoder keys are different Qwen3.5 bugs." }, { "left": "issue:42915", "right": "issue:44756", "accept": false, - "reason": "Qwen3Moe FP8 failure is unrelated to Strix Halo mmap OOM mitigation." + "reason": "Qwen3-MoE FP8 failure and Strix Halo mmap OOM are unrelated." }, { "left": "issue:42491", "right": "issue:45276", "accept": false, - "reason": "Qwen3 MoE LoRA compatibility is unrelated to Gemma4 resize_token_embeddings not propagating." + "reason": "LoRA/hf5.x incompatibility and Gemma4 resize_token_embeddings behavior are different bugs." }, { "left": "issue:43708", "right": "issue:44075", "accept": false, - "reason": "Trainer resume/max_steps calculation and SGD args not used are different Trainer bugs." + "reason": "Trainer resume/max_steps logic and SGD args not being used are unrelated training issues." + }, + { + "left": "issue:44488", + "right": "issue:44991", + "accept": false, + "reason": "BERT model load failure and tokenizer loading failure for a different checkpoint are unrelated." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative. The accepted soft pairs are plausible duplicates based on the issue titles, and the rejected pairs are framed narrowly without overclaiming. The representative issue choice for the non-persistent-buffer regression is also supported by the packet." + "feedback": "The cluster analysis is grounded in the packet and stays conservative. The accepted duplicate islands are supported by the titles, and the rejected pairs are generally distinguished by different models/code paths or distinct failure modes. The overall summary correctly treats this as a mixed cluster rather than a single unified bug." }, "evaluator_used": true, "retried": false, @@ -1977,7 +1919,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:36010", "issue:39404", @@ -2009,9 +1951,7 @@ "issue:44756", "issue:44910", "issue:44912", - "issue:44928", "issue:44960", - "issue:44991", "issue:45216", "issue:45276", "issue:45292", @@ -2021,6 +1961,8 @@ "issue:45488", "issue:45588", "issue:45663", + "issue:45684", + "issue:45698", "issue:45704", "issue:45759", "issue:45812", @@ -2030,25 +1972,24 @@ ], "soft_pairs": [ "issue:45488|issue:45812", - "issue:44488|issue:44991", - "issue:39692|issue:43994", "issue:43644|issue:43645", - "issue:43257|issue:43854", "issue:43854|issue:43931", + "issue:39692|issue:43994", + "issue:43257|issue:43854", "issue:43856|issue:43873", "issue:42491|issue:43931", "issue:45362|issue:45406", "issue:43856|issue:44387", "issue:44960|issue:46050", "issue:42491|issue:45292", - "issue:44910|issue:45588", "issue:44164|issue:44291", + "issue:44910|issue:45588", "issue:45276|issue:45335", "issue:36010|issue:39404", - "issue:41720|issue:44155", "issue:43404|issue:43454", - "issue:39692|issue:44960", + "issue:41720|issue:44155", "issue:43425|issue:43957", + "issue:39692|issue:44960", "issue:44402|issue:44488", "issue:42947|issue:45704", "issue:43873|issue:44387", @@ -2064,262 +2005,256 @@ "issue:45276|issue:45292", "issue:44164|issue:44756", "issue:43854|issue:45216", - "issue:43381|issue:44928" + "issue:45684|issue:45698" ], - "prepared_review_unit_hash": "120350c1ca5b6d606835b0f2a1df39ef2dbaa6f41d79eed764191b09103f9e63", + "prepared_review_unit_hash": "e89ded4b8eb0eaf4c1fa996ee77a6b982f229f3a21383326832bfd8c7db83423", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 36, - "serialized_chars": 38639, - "estimated_input_tokens": 9660, - "estimated_eval_tokens": 19576 + "soft_pair_count": 35, + "serialized_chars": 38332, + "estimated_input_tokens": 9583, + "estimated_eval_tokens": 19422 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is still mostly unrelated, with two plausible same-area issue families: `resize_token_embeddings` regressions around 45276/45292/45335 and `lm_head` weight-tying reports around 43404/43454. However, the packet only shows title-level similarity, so I would not treat those soft edges as confirmed duplicates. No PRs are present.", - "confidence": 0.61, - "canonical_issue_reason": "45276 is the best anchor for the resize-token-embedding subgroup because it is the broadest concrete report in that area, but the related items should be treated as plausible regressions rather than confirmed duplicates.", + "summary": "This cluster is mostly heterogeneous issue reports around Transformers regressions. The only clear duplicate-like pair is the resize_token_embeddings regression across closely related Gemma/T5-Gemma variants; the rest look like separate bugs affecting different models or subsystems.", + "confidence": 0.74, + "canonical_issue_reason": "Issue 45276 is the broadest and clearest representative of the only near-duplicate pair, and it subsumes the narrower output_embeddings-only symptom in 45292.", "canonical_pr_reason": null, - "best_issue_reason": "45276 is the strongest single issue to represent the cluster\u2019s main coherent subgroup, though the evidence is still too weak to collapse the nearby variants into one confirmed duplicate set.", + "best_issue_reason": "Issue 45276 is the best canonical issue candidate because it describes the core resize_token_embeddings regression in a broader form that covers the related embedding-propagation failure.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45488", "right": "issue:45812", "accept": false, - "reason": "Both are tokenizer/model-output regressions, but they affect different model families and the packet does not show the same underlying bug." + "reason": "Both involve tokenizer regressions, but they affect different model families and describe different failure modes; not the same bug." }, { - "left": "issue:44488", - "right": "issue:44991", + "left": "issue:43644", + "right": "issue:43645", "accept": false, - "reason": "Both are loading failures, but for different models and different failure descriptions; title similarity is not enough to merge them." + "reason": "Both are Transformers 5.0 regressions, but one is buffer initialization and the other is custom-model initialization in notebooks; separate issues." }, { - "left": "issue:39692", - "right": "issue:43994", + "left": "issue:43854", + "right": "issue:43931", "accept": false, - "reason": "Same model family is mentioned, but one is a docs/example problem and the other is an inference quality issue." + "reason": "Both are model-loading problems, but they target different models and symptoms; no clear shared code-path bug." }, { - "left": "issue:43644", - "right": "issue:43645", + "left": "issue:39692", + "right": "issue:43994", "accept": false, - "reason": "Both are Transformers 5.0.0 regressions, but they describe different code paths and symptoms." + "reason": "Same SigLIP2 family, but one is a broken documentation example and the other is incorrect inference results; too different to merge." }, { "left": "issue:43257", "right": "issue:43854", "accept": false, - "reason": "Different model-loading defects with different targets; no shared concrete bug is evident." - }, - { - "left": "issue:43854", - "right": "issue:43931", - "accept": false, - "reason": "Both concern loading, but the model families and reported failures are different." + "reason": "Different models and different loading/dispatch paths; no evidence they share the same underlying bug." }, { "left": "issue:43856", "right": "issue:43873", "accept": false, - "reason": "Both mention efficiency/memory, but one is training-memory behavior and the other is quantization/offloading behavior." + "reason": "Both mention memory/quantization, but one is training memory usage and the other is offloading behavior; not the same defect." }, { "left": "issue:42491", "right": "issue:43931", "accept": false, - "reason": "Distinct issues: LoRA compatibility across branches versus a shape-mismatch load failure." + "reason": "These are distinct issues: LoRA compatibility across versions versus a specific Qwen3-VL weight-shape mismatch." }, { "left": "issue:45362", "right": "issue:45406", "accept": false, - "reason": "Different components and failure modes; no clear common code-path bug from the packet." + "reason": "Different model families and different runtime failures; not a duplicate." }, { "left": "issue:43856", "right": "issue:44387", "accept": false, - "reason": "Both are memory-related, but they point to different root causes and different workflows." + "reason": "Both are memory-related, but the causes differ (Qwen3 MoE training memory vs int4 quantization reserved-memory/OOM regression)." }, { "left": "issue:44960", "right": "issue:46050", "accept": false, - "reason": "Unrelated model/version report versus a save/load corruption report." + "reason": "Unrelated models and different save/load behavior; no common underlying bug." }, { "left": "issue:42491", "right": "issue:45292", "accept": false, - "reason": "Different model/version compatibility problem versus a resize-token-embedding regression." + "reason": "Different topics: Qwen3 MoE LoRA version incompatibility versus resize_token_embeddings not propagating to outputs." }, { - "left": "issue:44910", - "right": "issue:45588", + "left": "issue:44164", + "right": "issue:44291", "accept": false, - "reason": "Both involve attention code, but the failure modes are different and not mergeable as one fix." + "reason": "Both touch model loading/saving internals, but one is extra_state handling and the other is init_empty_weights argument compatibility; separate bugs." }, { - "left": "issue:44164", - "right": "issue:44291", + "left": "issue:44910", + "right": "issue:45588", "accept": false, - "reason": "Save/load extra_state handling is unrelated to init_empty_weights argument handling." + "reason": "Both are flash-attention crashes, but the root causes and affected model paths are different." }, { "left": "issue:45276", "right": "issue:45335", - "accept": false, - "reason": "They look like the same family, but the packet only gives similar titles and not enough evidence to confirm the same underlying regression." + "accept": true, + "reason": "Both report resize_token_embeddings failing to update tied internal embeddings across closely related model variants, which looks like the same underlying regression." }, { "left": "issue:36010", "right": "issue:39404", "accept": false, - "reason": "ImportError for GenerationMixin is unrelated to Whisper pipeline `return_language` behavior." - }, - { - "left": "issue:41720", - "right": "issue:44155", - "accept": false, - "reason": "Different models and failure modes; they are not the same concrete bug." + "reason": "ImportError for GenerationMixin and Whisper return_language pipeline breakage are unrelated." }, { "left": "issue:43404", "right": "issue:43454", "accept": false, - "reason": "Both are lm_head weight-tying complaints, but the packet only shows title similarity across different model families." + "reason": "Both mention untied lm_head weights, but they are separate model implementations and do not clearly point to one shared bug." }, { - "left": "issue:39692", - "right": "issue:44960", + "left": "issue:41720", + "right": "issue:44155", "accept": false, - "reason": "Completely different topics: SigLIP2 example errors versus a GLM5 issue." + "reason": "Different models, different inference paths, and different failures; not a duplicate." }, { "left": "issue:43425", "right": "issue:43957", "accept": false, - "reason": "Unrelated compatibility/load problems with different failure surfaces." + "reason": "Torch version compatibility and meta-device loading are distinct issues." + }, + { + "left": "issue:39692", + "right": "issue:44960", + "accept": false, + "reason": "No meaningful overlap beyond being model-related issues." }, { "left": "issue:44402", "right": "issue:44488", "accept": false, - "reason": "Both are tokenizer/vocab reports, but they concern different models and different loading symptoms." + "reason": "These both sound like tokenizer/model loading problems, but the affected models and reported symptoms are too different to confidently treat as the same bug." }, { "left": "issue:42947", "right": "issue:45704", "accept": false, - "reason": "Gradient-checkpointing/PEFT behavior is unrelated to the RMSNorm memory leak report." + "reason": "Gradient checkpointing with PEFT LoRA is unrelated to the apex RMSNorm memory leak." }, { "left": "issue:43873", "right": "issue:44387", "accept": false, - "reason": "Quantization/offloading behavior and int4 OOM are different defects." + "reason": "Both involve quantization and memory, but they describe different regressions with different triggers." }, { "left": "issue:45663", "right": "issue:45759", "accept": false, - "reason": "Different composite-model issues affecting different code paths." + "reason": "Gemma-4 FSDP2 shared_kv_states failure and Qwen config unwrapping are unrelated." }, { "left": "issue:44291", "right": "issue:44756", "accept": false, - "reason": "Different loading/init bug versus a platform-specific mmap/OOM issue." + "reason": "init_empty_weights compatibility and mmap/OOM on Strix Halo are unrelated." }, { "left": "issue:45663", "right": "issue:45859", "accept": false, - "reason": "FSDP2 attention-state bug is not the same as CPU-offload incompatibility." + "reason": "Different model families and different execution-path failures." }, { "left": "issue:44155", "right": "issue:45823", "accept": false, - "reason": "Different model families and unrelated forward/device mismatch behavior." + "reason": "AudioFlamingo3 batched inference leakage and Gemma4 PLE device mismatch are unrelated." }, { "left": "issue:44292", "right": "issue:44912", "accept": false, - "reason": "Both are quantization-related, but they affect different models and failure modes." + "reason": "Both are quantization/loading issues, but they involve different quantization formats and different failure modes." }, { "left": "issue:44387", "right": "issue:44756", "accept": false, - "reason": "Int4 quantization OOM is unrelated to disabling mmap on Strix Halo." + "reason": "Both mention OOM, but the causes are different and not mergeable as one bug." }, { "left": "issue:43335", "right": "issue:45663", "accept": false, - "reason": "Sparse-layer config bug is unrelated to the Gemma-4 FSDP2 attention-state issue." + "reason": "SwitchTransformers sparse-layer config bug and Gemma-4 FSDP2 attention bug are unrelated." }, { "left": "issue:43957", "right": "issue:44756", "accept": false, - "reason": "Meta-device loading failures and Strix Halo mmap/OOM are not the same bug." + "reason": "Meta-device loading failures and Strix Halo mmap OOM are different problems." }, { "left": "issue:42947", "right": "issue:43381", "accept": false, - "reason": "Both mention gradient checkpointing, but they describe different constraints and code paths." + "reason": "Both concern gradient checkpointing, but one is ineffective training behavior and the other is eval-mode prohibition." }, { "left": "issue:45276", "right": "issue:45292", - "accept": false, - "reason": "This is the same title family, but the packet does not provide enough detail to confirm the exact same underlying regression." + "accept": true, + "reason": "These are near-direct duplicates: both report resize_token_embeddings failing to update model embeddings, with 45276 being the broader version." }, { "left": "issue:44164", "right": "issue:44756", "accept": false, - "reason": "Save/load extra_state handling is unrelated to mmap-induced OOM." + "reason": "Save/load extra_state handling and mmap-related OOM are unrelated." }, { "left": "issue:43854", "right": "issue:45216", "accept": false, - "reason": "Different model-loading regressions with different symptoms and targets." + "reason": "Different models and different regression types; not the same underlying bug." }, { - "left": "issue:43381", - "right": "issue:44928", + "left": "issue:45684", + "right": "issue:45698", "accept": false, - "reason": "Eval-mode checkpointing restriction is unrelated to the RLHF gradient-explosion report." + "reason": "Both involve save/pretrained custom-model workflows, but one is permissions propagation and the other is loading the wrong custom module; separate issues." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The summary is mostly grounded, but it overstates confidence on the duplicate subclusters. In particular, the analyst marks 45276\u219445335 and 43404\u219443454 (and 45276\u219445292) as true duplicates even though the packet only shows similar titles, not enough to justify \u2018same underlying bug\u2019 with certainty. Those are better treated as plausible same-area regressions rather than confirmed duplicates. The overall cluster being mostly unrelated is fine, and \u2018No PRs are present\u2019 is correct, but the soft-edge acceptances are not conservative enough." + "accept": true, + "feedback": "The cluster summary is grounded in the packet and stays conservative on the soft edges. The only accepted duplicate-like set is the resize_token_embeddings regression across closely related Gemma/T5-Gemma issues, which is supported by the titles and similarity scores. The other pairwise rejections do not overclaim a shared root cause." }, "evaluator_used": true, - "retried": true, - "accepted_nontrivial_soft_edge": false, + "retried": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -2334,12 +2269,13 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:36032", "issue:39404", "issue:43257", "issue:43299", + "issue:43381", "issue:43425", "issue:43452", "issue:43596", @@ -2373,31 +2309,30 @@ "issue:44898", "issue:44912", "issue:44918", + "issue:44928", "issue:44991", "issue:45084", "issue:45292", "issue:45335", "issue:45588", "issue:45663", - "issue:45684", - "issue:45698", "issue:45701", "issue:45759", "issue:45823" ], "soft_pairs": [ - "issue:45684|issue:45698", + "issue:43381|issue:44928", "issue:44479|issue:44877", "issue:45588|issue:45663", "issue:43646|issue:43708", "issue:43645|issue:44164", - "issue:45292|issue:45335", "issue:43828|issue:43957", + "issue:45292|issue:45335", "issue:44402|issue:44451", "issue:43425|issue:43828", "issue:43257|issue:44863", - "issue:39404|issue:45701", "issue:44589|issue:44756", + "issue:39404|issue:45701", "issue:44683|issue:45823", "issue:43425|issue:45823", "issue:43611|issue:43645", @@ -2407,244 +2342,244 @@ "issue:39404|issue:44912", "issue:44265|issue:44898", "issue:44479|issue:44805", - "issue:43901|issue:44509", "issue:43994|issue:44079", + "issue:43901|issue:44509", "issue:43425|issue:44918", "issue:43299|issue:43931", "issue:44589|issue:45084", "issue:44164|issue:45759", "issue:36032|issue:43452", - "issue:44671|issue:44991", "issue:43596|issue:44683", + "issue:44671|issue:44991", "issue:39404|issue:44671", "issue:43856|issue:44756" ], - "prepared_review_unit_hash": "cc646bd8f79efe8341865da36b0cefa834062491e38a8cd075722dace945986f", + "prepared_review_unit_hash": "bc2a010f431f82404c2020bf088ea1364a8079a78042798ddaa16e3e77c20832", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 32, - "serialized_chars": 37357, - "estimated_input_tokens": 9340, - "estimated_eval_tokens": 18936 + "serialized_chars": 37346, + "estimated_input_tokens": 9337, + "estimated_eval_tokens": 18930 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly a loose collection of distinct Transformers v5 regressions and model-specific loading/compatibility bugs. Only one soft pair looks like a true duplicate: the two resize_token_embeddings reports.", - "confidence": 0.84, - "canonical_issue_reason": "issue:43611 is the broadest representative of the generic Transformers 5 model-loading regressions in this set; the other issues are narrower model-, pipeline-, or docs-specific failures.", + "summary": "This cluster is mostly a loose set of Transformers v5 regression reports around model loading/initialization/tokenizer behavior. Only one soft pair looks like a true duplicate; the rest are different bugs in adjacent areas.", + "confidence": 0.79, + "canonical_issue_reason": "issue:43646 is the broadest representative of the shared v5 model-initialization regression theme, spanning the same general loading path as several nearby reports without being tied to one narrow model variant.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43611 is the best single summary item for the cluster\u2019s main theme of v5 loading/init breakages, even though most other items are not duplicates of it.", + "best_issue_reason": "issue:43646 is the best cluster anchor: it is broad, version-wide, and captures the central regression pattern better than the model-specific or tokenizer-specific issues.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:45684", - "right": "issue:45698", + "left": "issue:43381", + "right": "issue:44928", "accept": false, - "reason": "Both involve custom-model save/load flows, but one is about read-only source-file permissions and the other about loading the wrong module after save_pretrained; different bugs." + "reason": "Different failures: gradient checkpointing in eval mode vs Qwen3.5 RLHF NaNs from 3D position_ids/SDPA fallback." }, { "left": "issue:44479", "right": "issue:44877", "accept": false, - "reason": "Different failure modes and model families: video-input regression vs strict-config loading for granite_speech." + "reason": "Both are Qwen-related, but one is a video-input regression and the other is a strict-config loading issue; not the same bug." }, { "left": "issue:45588", "right": "issue:45663", "accept": false, - "reason": "Sink-less flash_attention crash vs Gemma4 FSDP2 shared_kv_states rebuild issue; unrelated code paths." + "reason": "Flash-attention crash on sink-less models is unrelated to Gemma4 FSDP2 shared_kv_states rebuilding." }, { "left": "issue:43646", "right": "issue:43708", "accept": false, - "reason": "Custom model initialization in notebooks vs Trainer resume_from_checkpoint max_steps calculation; not the same bug." + "reason": "Custom model initialization breakage is unrelated to Trainer checkpoint-resume max_steps accounting." }, { "left": "issue:43645", "right": "issue:44164", "accept": false, - "reason": "Notebook custom-model init regression vs save/from_pretrained extra_state handling; different underlying problems." - }, - { - "left": "issue:45292", - "right": "issue:45335", - "accept": true, - "reason": "Same bug: resize_token_embeddings updates output embeddings incorrectly, including t5gemma decoder.embed_tokens." + "reason": "Jupyter custom-model initialization regression is different from save/from_pretrained extra_state handling." }, { "left": "issue:43828", "right": "issue:43957", "accept": false, - "reason": "Both are dtype/loading regressions, but one is autocast on Phi-tiny-MoE and the other is torch.device('meta') loading; distinct issues." + "reason": "These are both dtype/loading problems, but one is an autocast mismatch on Phi-tiny-MoE and the other is meta-device model loading for specific models." + }, + { + "left": "issue:45292", + "right": "issue:45335", + "accept": true, + "reason": "Same underlying bug: resize_token_embeddings fails to update all output/decoder embedding weights for the related model family." }, { "left": "issue:44402", "right": "issue:44451", "accept": false, - "reason": "Both concern tokenizer/model loading, but the first is a vocab-size mismatch report and the second is a generic ScandiBERT load failure; not enough evidence of a single bug." + "reason": "One is a tokenizer vocab-size mismatch in a specific model; the other is a generic inability to load a different tokenizer/model." }, { "left": "issue:43425", "right": "issue:43828", "accept": false, - "reason": "Torch version incompatibility is too broad; the concrete symptoms and code paths differ." + "reason": "Torch 2.10 incompatibility is a broader dependency issue, not the same as the Phi-tiny-MoE autocast dtype mismatch." }, { "left": "issue:43257", "right": "issue:44863", "accept": false, - "reason": "Different model-specific checkpoint loading problems: Qwen3 MoE conversion vs NemotronH checkpoint loading." + "reason": "Qwen3 MoE conversion/deepspeed loading and NemotronH checkpoint loading are distinct model-loading bugs." }, { - "left": "issue:39404", - "right": "issue:45701", + "left": "issue:44589", + "right": "issue:44756", "accept": false, - "reason": "Whisper pipeline return_language regression and version-dependent tokenization changes are unrelated." + "reason": "Float8 storage lookup failure is unrelated to the Strix Halo mmap OOM workaround." }, { - "left": "issue:44589", - "right": "issue:44756", + "left": "issue:39404", + "right": "issue:45701", "accept": false, - "reason": "Float8 storage lookup error vs disabling mmap on Strix Halo to avoid OOM; unrelated symptoms and fixes." + "reason": "Whisper pipeline return_language regression is not the same as a broad tokenization-change report." }, { "left": "issue:44683", "right": "issue:45823", "accept": false, - "reason": "Compiled flex_attention on torch>=2.9 and Gemma4 PLE device mismatch are different failures." + "reason": "Compiled flex_attention on torch>=2.9 is a different code path from Gemma4 PLE device-mismatch forwarding." }, { "left": "issue:43425", "right": "issue:45823", "accept": false, - "reason": "Generic torch incompatibility does not match the specific Gemma4 PLE device-mapping bug." + "reason": "Torch version incompatibility is too broad to equate with Gemma4 device placement during forward." }, { "left": "issue:43611", "right": "issue:43645", "accept": false, - "reason": "Both are Transformers 5 loading/init regressions, but one is base_model_prefix loading and the other is Jupyter custom-model initialization; separate bugs." + "reason": "Both involve custom models under v5, but one is about base_model_prefix loading and the other about notebook initialization; not the same concrete bug." }, { "left": "issue:43425", "right": "issue:43716", "accept": false, - "reason": "Torch incompatibility vs Mistral-3 image preprocessor/model dtype mismatch; not the same issue." + "reason": "A dependency incompatibility is not the same as the Mistral-3 image-preprocessor/model dtype mismatch." }, { "left": "issue:44530", "right": "issue:45084", "accept": false, - "reason": "PagedAttentionCache linear_attention crash and non-template node compilation error are different failures." + "reason": "PagedAttentionCache linear_attention failure is unrelated to the non-template-node compile error." }, { "left": "issue:43906", "right": "issue:44530", "accept": false, - "reason": "An isolated reproduction of another issue vs a Qwen3.5 PagedAttentionCache crash; not duplicates." + "reason": "An isolated reproduction of an earlier issue is not the same as a PagedAttentionCache crash on Qwen3.5." }, { "left": "issue:39404", "right": "issue:44912", "accept": false, - "reason": "Whisper pipeline behavior and MXFP4 quantization fallback are unrelated." + "reason": "Whisper pipeline language behavior is unrelated to MXFP4 quantization fallback on git-oss-20b." }, { "left": "issue:44265", "right": "issue:44898", "accept": false, - "reason": "torch.export with torch_compilable_check and Perceiver image classification failure are different model/code-path issues." + "reason": "torch.export.export failing under torch_compilable_check is a different bug from Perceiver non-default resolution handling." }, { "left": "issue:44479", "right": "issue:44805", "accept": false, - "reason": "Video-input regression for Qwen VL models vs a generic mask/tensor shape mismatch; no clear duplicate evidence." + "reason": "Video-input regression in Qwen models is not the same as the generic mask/index shape mismatch report." }, { - "left": "issue:43901", - "right": "issue:44509", + "left": "issue:43994", + "right": "issue:44079", "accept": false, - "reason": "Both are docs-related, but one is about return_all_scores docs drift and the other about removed pipeline tasks; separate documentation issues." + "reason": "Wrong SigLIP2 outputs and ModelOutput key assignment are unrelated." }, { - "left": "issue:43994", - "right": "issue:44079", + "left": "issue:43901", + "right": "issue:44509", "accept": false, - "reason": "Siglip2 nonsensical outputs and ModelOutput key assignment are different bugs." + "reason": "Docs mentioning return_all_scores is unrelated to docs still listing removed pipeline tasks." }, { "left": "issue:43425", "right": "issue:44918", "accept": false, - "reason": "Generic torch incompatibility vs Qwen3.5 embedding unpacking with TRL SFT trainer; unrelated." + "reason": "Torch compatibility is not the same as unpacking Qwen3.5 input embeddings with trl SFT trainer." }, { "left": "issue:43299", "right": "issue:43931", "accept": false, - "reason": "Both are Qwen3-VL loading reports, but one is a MoE loading regression in transformers 5.0.0.dev0 and the other is a weight-shape mismatch for a specific checkpoint; not the same concrete bug." + "reason": "Both are Qwen3-VL loading errors, but the former is an accelerate/deepspeed conversion issue and the latter is a checkpoint shape-mismatch; not clearly the same bug." }, { "left": "issue:44589", "right": "issue:45084", "accept": false, - "reason": "Different compile/runtime failures with no shared code path." + "reason": "Float8 storage-object lookup and compile-template-node errors are different failures." }, { "left": "issue:44164", "right": "issue:45759", "accept": false, - "reason": "extra_state save/load handling is unrelated to AutoModelForCausalLM.from_config text_config unwrapping." + "reason": "extra_state serialization and AutoModelForCausalLM.from_config text_config unwrapping are separate code paths." }, { "left": "issue:36032", "right": "issue:43452", "accept": false, - "reason": "Tokenizer special-token attribute conflict vs gguf_file breaking AutoTokenizer/AutoModelForCausalLM.from_pretrained; distinct problems." + "reason": "T5Tokenizer add_special_tokens conflict is unrelated to gguf_file breaking from_pretrained for tokenizer/model classes." }, { - "left": "issue:44671", - "right": "issue:44991", + "left": "issue:43596", + "right": "issue:44683", "accept": false, - "reason": "CamemBERT masked-LM prediction regression and EMBEDDIA tokenizer loading failure are different bugs." + "reason": "Deepspeed ZeRO3/BertModel index error is unrelated to compiled flex_attention on newer torch versions." }, { - "left": "issue:43596", - "right": "issue:44683", + "left": "issue:44671", + "right": "issue:44991", "accept": false, - "reason": "Deepspeed ZeRO3/BertModel index error and compiled flex_attention on torch>=2.9 are unrelated." + "reason": "CamemBERT masked-LM prediction regression and tokenizer load failure for EMBEDDIA/est-roberta are different issues." }, { "left": "issue:39404", "right": "issue:44671", "accept": false, - "reason": "Whisper pipeline regression and CamemBERT masked-LM regression affect different models and code paths." + "reason": "Whisper return_language regression is unrelated to CamemBERT masked-LM prediction changes." }, { "left": "issue:43856", "right": "issue:44756", "accept": false, - "reason": "Qwen3 MoE training memory usage and Strix Halo mmap OOM avoidance are different performance/memory issues, not duplicates." + "reason": "Qwen3 MoE training memory usage and Strix Halo mmap OOM are distinct performance/memory issues." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative: it characterizes the cluster as mostly distinct v5 loading/init regressions, and it only treats the resize_token_embeddings pair (issue:45292 / issue:45335) as a true duplicate, which is well supported by the titles and linkage. The other soft-edge denials are phrased cautiously and do not overstate duplicate evidence." + "feedback": "The summary stays within the packet: it frames the cluster as a loose set of v5 loading/initialization/tokenizer regressions and keeps the non-duplicate pairs conservative. The one accepted soft pair, issue:45292 vs issue:45335, is plausibly the same resize_token_embeddings bug in closely related embedding paths. No soft-edge verdict overstates evidence in a way that would require rejection." }, "evaluator_used": true, "retried": false, @@ -2663,7 +2598,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:32090", "issue:34567", @@ -2733,235 +2668,241 @@ "issue:43643|issue:44530", "issue:34567|issue:40444", "issue:44811|issue:45584", - "issue:42915|issue:44530", - "issue:44451|issue:44987", "issue:43541|issue:45084", + "issue:44451|issue:44987", + "issue:42915|issue:44530", "issue:43644|issue:43646", "issue:44464|issue:45987", "issue:43452|issue:43482", "issue:36032|issue:43645", - "issue:44849|issue:45325", "issue:43317|issue:43482", + "issue:44849|issue:45325", "issue:44987|issue:44991", - "issue:43883|issue:44991", "issue:45084|issue:45507", + "issue:43883|issue:44991", "issue:43262|issue:43377", "issue:43089|issue:45987" ], - "prepared_review_unit_hash": "130286c9eb703ed8cbcffb2f777d229f885238245502ce7aa3682eec97473f6a", + "prepared_review_unit_hash": "56cf52975c1b952feb4673c85565724bdb698e115ce771f3df23e32259366603", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 32, - "serialized_chars": 37342, - "estimated_input_tokens": 9336, - "estimated_eval_tokens": 18928 + "serialized_chars": 37337, + "estimated_input_tokens": 9335, + "estimated_eval_tokens": 18926 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a loose bag of unrelated issue reports. A few titles share broad themes (Transformers v5 regressions, Whisper/audio, model loading), but none of the soft-edge pairs look like the same concrete bug/change.", - "confidence": 0.92, - "canonical_issue_reason": "Issue 43646 is the broadest Transformers-v5 regression report in the set and the best umbrella representative if one must be chosen, but the cluster does not contain a true duplicate set.", + "summary": "The cluster is mostly heterogeneous. A few issues share broad themes like v5 loading/init regressions, tokenizer/model-loading failures, or audio/Whisper paths, but the soft pairs are generally only superficially similar and do not look like the same underlying bug.", + "confidence": 0.89, + "canonical_issue_reason": "Issue 43646 is the broadest representative of the v5 custom-model initialization regression subgroup and is more central than the more specific symptom reports around it.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43646 is the best single issue to anchor the cluster because it is the most general and sits near several other v5 initialization/loading regressions; still, it should be treated as a loose thematic representative, not a duplicate canonical.", + "best_issue_reason": "Issue 43646 is the best overall representative of this cluster because it captures the widest, most general regression theme among the issues shown.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44991", "right": "issue:45081", "accept": false, - "reason": "Both are loading failures, but one is a tokenizer load regression for EMBEDDIA/est-roberta and the other is a Mistral regex patch crash; different code paths and symptoms." + "reason": "Both are tokenizer/loading failures, but they involve different models and different failure modes; not the same bug." }, { "left": "issue:32090", "right": "issue:39404", "accept": false, - "reason": "Trainer GPU broadcast NoneType error and Whisper return_language pipeline regression are unrelated subsystems and failure modes." + "reason": "Trainer broadcast TypeError and Whisper `return_language` regression are unrelated." }, { "left": "issue:44164", "right": "issue:44479", "accept": false, - "reason": "save/from_pretrained extra_state handling and Qwen video-input regression are different bugs with no shared concrete code path." + "reason": "Save/from_pretrained extra_state handling and video-input regression are different code paths and symptoms." }, { "left": "issue:44737", "right": "issue:45859", "accept": false, - "reason": "Both mention device/offload behavior, but XLNet CPU arange placement and Qwen3_5Moe CPU offload are distinct model-specific issues." + "reason": "Both are device/offload-related, but one is XLNet CPU work each forward and the other is a Qwen MoE offload incompatibility." }, { "left": "issue:43582", "right": "issue:43632", "accept": false, - "reason": "Apple Silicon allocator warmup TypeError and _is_hf_initialized flag breakage are unrelated regression areas." + "reason": "Apple Silicon allocator warmup TypeError and `_is_hf_initialized` flag breakage are distinct." }, { "left": "issue:44661", "right": "issue:44683", "accept": false, - "reason": "Tokenizer mapping-name handling and compiled flex_attention on torch>=2.9 are separate features and failure paths." + "reason": "Model-registry expansion failure and compiled flex_attention failure are unrelated." }, { "left": "issue:44488", "right": "issue:45081", "accept": false, - "reason": "Both are tokenization/model-loading reports, but one is a model load failure for cjvt/sleng-bert and the other is a Mistral-specific regex patch crash." + "reason": "Both mention loading tokenizers/models, but one is a specific Mistral regex patch crash and the other is a different tokenizer load failure." }, { "left": "issue:44488", "right": "issue:44987", "accept": false, - "reason": "Both fail on model loading, but they target different models and likely different underlying regressions." + "reason": "Both are load failures on recent versions, but they involve different models and no shared concrete code-path evidence." }, { "left": "issue:43611", "right": "issue:43644", "accept": false, - "reason": "Both are Transformers v5 regressions, but base_model_prefix loading and non-persistent buffer initialization are not the same bug." + "reason": "Both are v5 regressions, but base_model_prefix loading and non-persistent buffer corruption are separate bugs." }, { "left": "issue:40990", "right": "issue:43421", "accept": false, - "reason": "High perplexity on gpt-oss and TokenizersBackend post-processor updates are unrelated." + "reason": "High perplexity on a model and tokenizer post-processor update behavior are not the same issue." }, { "left": "issue:43716", "right": "issue:45084", "accept": false, - "reason": "Image preprocessor dtype mismatch and template-node compilation failure are unrelated code paths." + "reason": "Image-preprocessor dtype mismatch and template compilation failure are unrelated." }, { "left": "issue:44206", "right": "issue:44220", "accept": false, - "reason": "Both are audio feature-extraction related, but one is an unsupported center argument in LasrFeatureExtractor and the other is a different _torch_extract_fbank_features issue." + "reason": "These are both audio feature extraction reports, but one is specifically about an unsupported `center` argument and the other is a generic fbank helper issue; not clearly the same defect." }, { "left": "issue:42175", "right": "issue:46178", "accept": false, - "reason": "Backend packaging omissions for tensorflow vs tensorflow_text mapping errors are different backend-definition problems." + "reason": "Both involve backend packaging, but one is missing tensorflow in a torch extra install and the other is an unmapped tensorflow_text backend." }, { "left": "issue:36032", "right": "issue:42915", "accept": false, - "reason": "T5 tokenizer add_special_tokens name conflict and Qwen3Moe FP8 config failure are unrelated." + "reason": "Tokenizer special-token method conflict and FineGrainedFP8Config failure are unrelated." }, { "left": "issue:43883", "right": "issue:44488", "accept": false, - "reason": "Molmo tied-weights attribute error and tokenizer loading failures for sleng-bert are unrelated." + "reason": "Missing `all_tied_weights_keys` and tokenizer/model load failure are distinct problems." }, { "left": "issue:43643", "right": "issue:44530", "accept": false, - "reason": "trust_remote_code config field loss and PagedAttentionCache linear_attention crash are different bugs." + "reason": "Missing fields in AutoConfig and PagedAttentionCache group-type crash are unrelated." }, { "left": "issue:34567", "right": "issue:40444", "accept": false, - "reason": "TrainerState token counting and multi-image IterableDataset finetuning failure are unrelated." + "reason": "TrainerState token counting and Qwen2.5-VL iterable dataset failure are different bugs." }, { "left": "issue:44811", "right": "issue:45584", "accept": false, - "reason": "Both involve Whisper special-token handling, but batch_decode skip_special_tokens and empty-transcription generation after align_special_tokens are different concrete failures." + "reason": "Both are Whisper-related, but decoding `skip_special_tokens` behavior and empty-transcription generation failure are different issues." }, { - "left": "issue:42915", - "right": "issue:44530", + "left": "issue:43541", + "right": "issue:45084", "accept": false, - "reason": "Qwen3Moe FineGrainedFP8Config failure and Qwen3.5 PagedAttentionCache linear_attention crash are distinct issues." + "reason": "Grouped_mm tracing error and non-template-node compilation error are unrelated compilation/runtime bugs." }, { "left": "issue:44451", "right": "issue:44987", "accept": false, - "reason": "Cannot load ScandiBERT and transformers>=5.1.0 fails loading physical-intelligence/fast are separate model-loading regressions." + "reason": "Both are loading failures, but they affect different models and do not indicate the same underlying defect." }, { - "left": "issue:43541", - "right": "issue:45084", + "left": "issue:42915", + "right": "issue:44530", "accept": false, - "reason": "Mixtral grouped_mm torchdynamo tracing failure and template-node compilation error are unrelated." + "reason": "Fine-grained FP8 loading failure and linear_attention cache crash are different model/runtime issues." }, { "left": "issue:43644", "right": "issue:43646", "accept": false, - "reason": "Both are broad Transformers v5 regressions, but one is about non-persistent buffers and the other about custom model initialization; too different to merge." + "reason": "Both are v5 init regressions, but junk-filled non-persistent buffers and broken custom model initialization are not the same bug." }, { "left": "issue:44464", "right": "issue:45987", "accept": false, - "reason": "Chunked generation inconsistency with compiled forward and StaticCache seq-length type violation are different generation/cache bugs." + "reason": "Chunked generation inconsistency and StaticCache seq-length contract mismatch are related to generation, but not the same underlying issue." }, { "left": "issue:43452", "right": "issue:43482", "accept": false, - "reason": "Both touch GGUF loading, but one is a general gguf_file breakage for tokenizer/model loaders and the other is a Qwen2.5-GGUF-specific v5 failure." + "reason": "Both concern GGUF loading, but one is a generic gguf_file breakage and the other is a specific Qwen2.5-GGUF version regression." }, { "left": "issue:36032", "right": "issue:43645", "accept": false, - "reason": "Tokenizer special-token method conflict and Jupyter custom model initialization are unrelated." + "reason": "Tokenizer special-token conflict and Jupyter custom-model initialization are unrelated." }, { - "left": "issue:44849", - "right": "issue:45325", + "left": "issue:43317", + "right": "issue:43482", "accept": false, - "reason": "Qwen3.5 hidden-states bug and Qwen2.5-VL rope-index temporal scaling bug are different model-specific regressions." + "reason": "GPU/CPU offload loading failure and Qwen2.5-GGUF loading regression are distinct." }, { - "left": "issue:43317", - "right": "issue:43482", + "left": "issue:44849", + "right": "issue:45325", "accept": false, - "reason": "Dequantized model offload loading failure and Qwen2.5-GGUF loading failure are separate load paths and not the same bug." + "reason": "Both are Qwen-family regressions, but hidden-states output and RoPE position scaling are different code paths." }, { "left": "issue:44987", "right": "issue:44991", "accept": false, - "reason": "Both are version-gated loading failures, but they affect different models and no shared concrete defect is evident." + "reason": "Both are version-related loading failures, but they hit different models and there is no evidence of a shared root cause." }, { "left": "issue:45084", "right": "issue:45507", "accept": false, - "reason": "Template compilation error and GraniteMoEHybrid invalid method calls are unrelated." + "reason": "Template compilation and GraniteMoEHybrid invalid method calls are unrelated." + }, + { + "left": "issue:43883", + "right": "issue:44991", + "accept": false, + "reason": "Missing tied-weights metadata and tokenizer load regression are different bugs." }, { "left": "issue:43262", "right": "issue:43377", "accept": false, - "reason": "Audio chat-template sampling-rate default and MIMI batched-vs-single padding mask issue are different audio bugs." + "reason": "Audio processor sample-rate defaulting and MIMI padding-mask batching are different issues." }, { "left": "issue:43089", "right": "issue:45987", "accept": false, - "reason": "Generation performance overhead and StaticCache seq-length return type are unrelated." + "reason": "Generation sync overhead and cache sequence-length return type mismatch are not the same defect." } ] }, @@ -2983,7 +2924,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:33666", "issue:36032", @@ -3058,25 +2999,25 @@ "issue:43296|issue:43531", "issue:40444|issue:45325", "issue:36032|issue:41720", - "issue:43611|issue:44534", "issue:43531|issue:44877", + "issue:43611|issue:44534", "issue:43425|issue:44403", "issue:41553|issue:43582", - "issue:40990|issue:44811", "issue:43632|issue:44534", + "issue:40990|issue:44811", "issue:44079|issue:45663", "issue:43792|issue:44589", "issue:33666|issue:40444", "issue:44683|issue:45020" ], - "prepared_review_unit_hash": "1fe41e250d77384c381f5151ded2d51d50763e5ba279e284180c8c212da783ce", + "prepared_review_unit_hash": "6a3e2022fe3ec4513f1a4e8730fc7c4f6534bc4751a52263b63ecf014d34a154", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, @@ -3091,216 +3032,216 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is mostly heterogeneous regression reports across different models and subsystems. I only see one plausible duplicate pair around Qwen3.5 save_pretrained checkpoint corruption; the rest are too far apart to safely merge.", - "confidence": 0.72, - "canonical_issue_reason": "issue:45216 is the broader, earlier report about Qwen3.5 save_pretrained producing an incorrect checkpoint; issue:45357 reads like a narrower follow-up focused on the visual encoder keys, so 45216 is the better canonical issue for that pair.", + "summary": "The set is mostly a grab bag of unrelated Transformers issues. Only the two Qwen3.5 save_pretrained reports look like the same underlying regression; the rest are distinct bugs or symptom families.", + "confidence": 0.92, + "canonical_issue_reason": "Issue 45216 is the broader regression report for the Qwen3.5 save_pretrained problem; 45357 reads like a narrower follow-up about one incorrect key set.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45216 is the strongest single issue to anchor the only likely duplicate cluster because it states the regression at the broader save_pretrained level and has the clearest canonical scope.", + "best_issue_reason": "45216 is the clearest representative of the only plausible duplicate family in this cluster and has the most general description of the bug.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43645", "right": "issue:44534", "accept": false, - "reason": "Both mention Transformers v5 regressions, but one is about custom model init in notebooks and the other about non-persistent buffers being serialized incorrectly; different concrete bugs." + "reason": "Different failures: custom model init in notebooks vs non-persistent buffer corruption." }, { "left": "issue:43646", "right": "issue:44534", "accept": false, - "reason": "Custom model initialization failure and non-persistent buffer junk are separate v5 issues with different failure modes and code paths." + "reason": "Custom model initialization regression and junk buffer filling are unrelated." }, { "left": "issue:43322", "right": "issue:43540", "accept": false, - "reason": "Both are multimodal loading/processing failures, but Llava-Next segfault and Qwen3OmniMoe video ValueError are not the same underlying bug." + "reason": "Different model paths and symptoms: Llava Next loading segfault vs Qwen3OmniMoe video-input ValueError." }, { "left": "issue:43404", "right": "issue:44466", "accept": false, - "reason": "Both involve tied lm_head weights, but one is a model-specific tie failure and the other is a broader save/serialization inconsistency; not the same concrete bug." + "reason": "Both mention tied lm_head weights, but one is a missing tie in a specific model and the other is a save_pretrained serialization inconsistency; not the same concrete bug." }, { "left": "issue:44403", "right": "issue:45081", "accept": false, - "reason": "Unnecessary logging noise and a Mistral tokenizer crash are unrelated." + "reason": "Unnecessary loading noise is unrelated to the Mistral regex patch crash." }, { "left": "issue:43994", "right": "issue:44610", "accept": false, - "reason": "Different models and different defects: bad SigLIP2 outputs versus an OmDet-Turbo processor size mismatch." + "reason": "Different issues: Siglip2 output quality vs OmDet-Turbo image-size mismatch." }, { "left": "issue:42915", "right": "issue:45084", "accept": false, - "reason": "Qwen3Moe FP8 config failure and a template-node compilation TypeError are unrelated." + "reason": "Qwen3Moe FP8 config failure and template compilation TypeError are unrelated." }, { "left": "issue:43377", "right": "issue:43819", "accept": false, - "reason": "Both are audio-model correctness bugs, but MIMI padding-mask behavior and DAC missing-STE behavior are different code paths and fixes." + "reason": "Different audio-model bugs: padding-mask batching mismatch vs DAC latent/STE mismatch." }, { "left": "issue:44265", "right": "issue:44610", "accept": false, - "reason": "torch.export failures from torch_compilable_check are unrelated to the OmDet-Turbo image-size regression." + "reason": "torch.export with torch_compilable_check is unrelated to processor output size mismatch." }, { "left": "issue:44451", "right": "issue:45081", "accept": false, - "reason": "Loading ScandiBERT and the Mistral regex patch crash are separate issues." + "reason": "ScandiBERT loading failure is unrelated to the Mistral tokenizer backend crash." }, { "left": "issue:44987", "right": "issue:45081", "accept": false, - "reason": "A failing remote-code model load and a tokenizer regex patch crash are not the same bug." + "reason": "Loading physical-intelligence/fast and patch_mistral_regex crash are different problems." }, { "left": "issue:44220", "right": "issue:44683", "accept": false, - "reason": "Audio fbank extraction and compiled flex_attention on new torch versions are unrelated." + "reason": "Different code paths: fbank extraction issue vs flex_attention compilation on newer torch." }, { "left": "issue:42915", "right": "issue:44291", "accept": false, - "reason": "Different failures: FP8 config support for Qwen3Moe versus init_empty_weights/_is_hf_initialized argument handling." + "reason": "FP8 config failure and unexpected _is_hf_initialized argument are separate incompatibilities." }, { "left": "issue:45216", "right": "issue:45357", "accept": true, - "reason": "Both describe the same Qwen3.5 save_pretrained regression; 45357 looks like a narrower symptom of incorrect visual-encoder key serialization within the broader checkpoint corruption reported in 45216." + "reason": "Same Qwen3.5 save_pretrained regression family; 45357 is a narrower manifestation involving incorrect visual encoder keys." }, { "left": "issue:43632", "right": "issue:44756", "accept": false, - "reason": "_is_hf_initialized breakage and Strix Halo mmap OOM are unrelated." + "reason": "_is_hf_initialized breakage is unrelated to Strix Halo mmap OOM behavior." }, { "left": "issue:44062", "right": "issue:44987", "accept": false, - "reason": "AddedToken special-argument duplication and a model load failure for physical-intelligence/fast are different tokenizer/model issues." + "reason": "AddedToken keyword collision is unrelated to the physical-intelligence/fast loading regression." }, { "left": "issue:36032", "right": "issue:43742", "accept": false, - "reason": "T5 tokenizer special-token conflict and MobileLLM key error are unrelated loading failures." + "reason": "T5 tokenizer special-token conflict and MobileLLM key error are different loading failures." }, { "left": "issue:44479", "right": "issue:45325", "accept": false, - "reason": "Both are Qwen VL-family regressions, but one is a broad video-input regression and the other is a specific still-image rope-index scaling bug; not enough to treat as one issue." + "reason": "Both are Qwen VL regressions, but one is video-input processing and the other is still-image rope-position scaling." }, { "left": "issue:42915", "right": "issue:44589", "accept": false, - "reason": "FP8-config failure for Qwen3Moe and missing Float8 storage support are different failures." + "reason": "FP8 config failure and Float8 storage lookup error are different issues." }, { "left": "issue:43404", "right": "issue:45127", "accept": false, - "reason": "Tie-weight serialization in Mistral3 and LoRA-merge collapse with extended vocab are separate tied-weights problems with different triggers." + "reason": "Both involve tied weights, but one is a missing tie in Mistral3 and the other is LoRA merging with extended vocab collapse." }, { "left": "issue:43296", "right": "issue:43531", "accept": false, - "reason": "PaddleOCR-VL load failure and Qwen3-MoE sliding_window behavior are unrelated." + "reason": "PaddleOCR-VL loading failure and Qwen3-MoE sliding_window behavior are unrelated." }, { "left": "issue:40444", "right": "issue:45325", "accept": false, - "reason": "Qwen2.5-VL finetuning with multiple images per prompt and still-image temporal scaling are not the same bug." + "reason": "Qwen2.5-VL multi-image IterableDataset failure is not the same bug as still-image temporal position scaling." }, { "left": "issue:36032", "right": "issue:41720", "accept": false, - "reason": "Tokenizer load conflict and Qwen3 auto device-mapping cudaErrorAssert are unrelated." + "reason": "Tokenizer conflict and Qwen3 auto-device-map cuda assert are unrelated." }, { - "left": "issue:43611", - "right": "issue:44534", + "left": "issue:43531", + "right": "issue:44877", "accept": false, - "reason": "base_model_prefix loading breakage and non-persistent buffer junk are distinct v5 regressions." + "reason": "Qwen3-MoE sliding_window bug and granite_speech strict-config loading are unrelated." }, { - "left": "issue:43531", - "right": "issue:44877", + "left": "issue:43611", + "right": "issue:44534", "accept": false, - "reason": "Qwen3-MoE sliding_window handling and granite_speech config strictness are unrelated." + "reason": "base_model_prefix loading regression and non-persistent buffer junk are different Transformers v5 issues." }, { "left": "issue:43425", "right": "issue:44403", "accept": false, - "reason": "Torch 2.10 incompatibility and generic transformer-loading noise are unrelated." + "reason": "Torch 2.10 compatibility and loading noise are unrelated." }, { "left": "issue:41553", "right": "issue:43582", "accept": false, - "reason": "Voxtral tokenizer error messaging and AppleSilicon warmup TypeError are unrelated." + "reason": "Bad AutoTokenizer error message and Apple Silicon warmup TypeError are unrelated." }, { - "left": "issue:40990", - "right": "issue:44811", + "left": "issue:43632", + "right": "issue:44534", "accept": false, - "reason": "High perplexity on gpt-oss-20b and Whisper batch_decode skip_special_tokens handling are unrelated." + "reason": "_is_hf_initialized breakage is unrelated to junk-filled non-persistent buffers." }, { - "left": "issue:43632", - "right": "issue:44534", + "left": "issue:40990", + "right": "issue:44811", "accept": false, - "reason": "_is_hf_initialized regression and junk-filled non-persistent buffers are different v5 issues." + "reason": "High perplexity on GPT-OSS and Whisper batch_decode skip_special_tokens are unrelated." }, { "left": "issue:44079", "right": "issue:45663", "accept": false, - "reason": "ModelOutput key assignment and Gemma-4 FSDP2 shared_kv_states behavior are unrelated." + "reason": "ModelOutput key assignment and Gemma-4 shared_kv_states/FSDP2 are unrelated." }, { "left": "issue:43792", "right": "issue:44589", "accept": false, - "reason": "Whisper load failure and missing Float8 storage object are unrelated." + "reason": "Whisper runtime failure and Float8 storage lookup error are unrelated." }, { "left": "issue:33666", "right": "issue:40444", "accept": false, - "reason": "Both are Qwen VL training reports, but multi-GPU training and iterable-dataset multi-image finetuning are different problems." + "reason": "Both are Qwen-VL training issues, but they affect different model versions and different failure modes." }, { "left": "issue:44683", "right": "issue:45020", "accept": false, - "reason": "Compiled flex_attention on newer torch and remote_code breakage are unrelated." + "reason": "flex_attention compilation on torch>=2.9 and remote_code loading regressions are unrelated." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative. The single accepted duplicate pair (issue:45216 / issue:45357) is well-supported by both titles, and the rest of the soft-edge rejections avoid overclaiming sameness across clearly different bugs and subsystems." + "feedback": "The judgment is grounded in the packet and the soft-edge calls are conservative. The only accepted pair, issue:45216 and issue:45357, is well-supported by their shared Qwen3.5 save_pretrained regression theme and the titles\u2019 narrower/broader relationship. The rest are plausibly distinct bug families, and the summary does not overstate the evidence." }, "evaluator_used": true, "retried": false, @@ -3319,7 +3260,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:35707", "issue:40444", @@ -3375,18 +3316,18 @@ "issue:44403|issue:44991", "issue:35707|issue:40444", "issue:43381|issue:45923", - "issue:44462|issue:45812", "issue:42175|issue:45542", + "issue:44462|issue:45812", "issue:43317|issue:43856", - "issue:44829|issue:45479", "issue:43482|issue:45538", + "issue:44829|issue:45479", "issue:44291|issue:44589", "issue:43482|issue:43525", "issue:44079|issue:44534", "issue:43818|issue:45357", "issue:43377|issue:45491", - "issue:41720|issue:45081", "issue:43531|issue:44291", + "issue:41720|issue:45081", "issue:40444|issue:45381", "issue:44265|issue:45072", "issue:43644|issue:44079", @@ -3396,19 +3337,19 @@ "issue:43632|issue:45072", "issue:43611|issue:43646", "issue:43792|issue:43957", - "issue:43994|issue:44898", "issue:45325|issue:45834", + "issue:43994|issue:44898", "issue:43454|issue:44466", "issue:42915|issue:43482" ], - "prepared_review_unit_hash": "712e408dc75365ed2629d8556d8ff1e2010840ab33c68351df634787951ae548", + "prepared_review_unit_hash": "35947cd9c4de34070b1545a402d9830cd8fa685d985fb1954a1deb3fe144d078", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, @@ -3423,196 +3364,193 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly a grab bag of unrelated Transformers issues. The only plausible duplicate pair is the v5 custom model initialization/loading regression around `base_model_prefix`; the rest differ by model, subsystem, or failure mode. No PRs are present.", - "confidence": 0.43, - "canonical_issue_reason": "issue:43646 is the best canonical issue: it is the broadest and most central v5 model-initialization regression, and it can naturally subsume the more specific `base_model_prefix` loading failure in issue:43611.", + "summary": "This cluster is mostly a grab-bag of unrelated Transformers v5 regressions and model-specific bugs; there isn\u2019t a single clear duplicate thread. The strongest common theme is general model/tokenizer loading regressions, but the soft pairs are still too specific to merge.", + "confidence": 0.52, + "canonical_issue_reason": "Issue 43611 is the broadest representative of the repeated v5 model-loading regressions in this set, but it is not an exact duplicate umbrella for the whole cluster.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43646 has the widest scope among the candidates and best represents the underlying v5 custom-model init/load breakage.", + "best_issue_reason": "43611 is the best anchor issue because it captures a high-level Transformers v5 loading regression with wide potential impact, even though most other issues here are separate bugs.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43421", "right": "issue:44568", "accept": false, - "reason": "Both are tokenizer-related, but one is about runtime post-processor updates and the other about `add_special_tokens`/BOS-EOS behavior for a specific tokenizer; not the same concrete bug." + "reason": "Both are tokenizer-related, but one is runtime post-processor sync and the other is missing BOS/EOS insertion for a specific tokenizer; different bugs." }, { "left": "issue:44403", "right": "issue:44991", "accept": false, - "reason": "One is generic loading noise, the other is a tokenizer load failure for a specific model; different symptoms and code paths." + "reason": "One is about noisy loading logs, the other is a tokenizer-loading failure for a specific model; not the same issue." }, { "left": "issue:35707", "right": "issue:40444", "accept": false, - "reason": "Different tasks entirely: generation with `inputs_embeds/past_key_values` versus Qwen2.5-VL finetuning with multiple images." + "reason": "Different workflows and failures: generation with inputs_embeds/past_key_values vs VL finetuning with multiple images per prompt." }, { "left": "issue:43381", "right": "issue:45923", "accept": false, - "reason": "Gradient-checkpointing-in-eval and missing `supports_gradient_checkpointing` on a trust-remote-code model are related only broadly, not the same bug." + "reason": "Both mention gradient checkpointing, but one is eval-mode incompatibility and the other is a missing capability flag on a remote-code model." }, { - "left": "issue:44462", - "right": "issue:45812", + "left": "issue:42175", + "right": "issue:45542", "accept": false, - "reason": "Both involve AutoTokenizer, but one ignores `tokenizer.json` while the other returns wrong token IDs for Granite models; different failures." + "reason": "Both touch TensorFlow packaging, but one is missing TF in the torch extra and the other is a bad backend state when only tensorboard is installed." }, { - "left": "issue:42175", - "right": "issue:45542", + "left": "issue:44462", + "right": "issue:45812", "accept": false, - "reason": "Both mention TensorFlow backend packaging, but one is an install-extra/dependency issue and the other is a runtime undefined-backend error with tensorboard; not clearly the same fix." + "reason": "Tokenizer repository selection vs wrong token IDs for Granite models are different failure modes." }, { "left": "issue:43317", "right": "issue:43856", "accept": false, - "reason": "One is device-map/offload loading failure; the other is MoE training memory inefficiency. Different problem class." + "reason": "Dequantized model offload loading and Qwen3 MoE memory usage are unrelated problems." }, { - "left": "issue:44829", - "right": "issue:45479", + "left": "issue:43482", + "right": "issue:45538", "accept": false, - "reason": "Different sequence-classification bugs: flash-attention-3 training degeneration versus incorrect loss for `num_labels=1`." + "reason": "GGUF loading failure and CLIPTokenizer max-length configuration are unrelated." }, { - "left": "issue:43482", - "right": "issue:45538", + "left": "issue:44829", + "right": "issue:45479", "accept": false, - "reason": "Qwen2.5-GGUF loading on v5 versus CLIPTokenizer `model_max_length` constant; unrelated." + "reason": "One is flash_attention_3 training degeneration; the other is single-label classification with num_labels=1 causing zero loss across models." }, { "left": "issue:44291", "right": "issue:44589", "accept": false, - "reason": "Both are v5 initialization-related, but one is an unexpected `_is_hf_initialized` argument and the other is a missing Float8 storage type; different failures." + "reason": "Both are v5 loading-related, but one is an init_empty_weights argument mismatch and the other is a float8 storage lookup error." }, { "left": "issue:43482", "right": "issue:43525", "accept": false, - "reason": "Both are model-loading issues, but model-specific config/tokenization problems with different root causes." + "reason": "Different concrete loading failures: GGUF support vs missing pad_token_id on Llama4Config." }, { "left": "issue:44079", "right": "issue:44534", "accept": false, - "reason": "ModelOutput key assignment and non-persistent buffer junk are unrelated runtime/state bugs." + "reason": "ModelOutput key assignment bug and non-persistent buffer initialization bug are separate code paths." }, { "left": "issue:43818", "right": "issue:45357", "accept": false, - "reason": "Video-LLaVA tower/weight-sharing bug versus Qwen3.5 visual encoder save-pretrained regression; different models and code paths." + "reason": "Video-LLaVA tower initialization/weight sharing is unrelated to Qwen3.5 save_pretrained visual-encoder key serialization." }, { "left": "issue:43377", "right": "issue:45491", "accept": false, - "reason": "Both are batching/padding issues, but they affect different models and different mechanisms." + "reason": "Both involve batching, but one is a missing padding mask in MIMI and the other is NaNs from sliding-window/all-padding windows in Gemma3." }, { - "left": "issue:41720", - "right": "issue:45081", + "left": "issue:43531", + "right": "issue:44291", "accept": false, - "reason": "CUDA assert during Qwen3 auto device mapping is unrelated to the Mistral tokenizer regex patch crash." + "reason": "Sliding-window behavior in Qwen3-MoE is a different bug from init_empty_weights/_is_hf_initialized argument handling." }, { - "left": "issue:43531", - "right": "issue:44291", + "left": "issue:41720", + "right": "issue:45081", "accept": false, - "reason": "Sliding-window handling in Qwen3-MoE is a different bug from `_is_hf_initialized`/`init_empty_weights` initialization issues." + "reason": "CUDA assert in Qwen3 auto device mapping is unrelated to the Mistral tokenizer regex patch crash." }, { "left": "issue:40444", "right": "issue:45381", "accept": false, - "reason": "Multimodal finetuning with multiple images is unrelated to Qwen2.5-VL vision position IDs for video input." + "reason": "Both are Qwen2.5-VL, but one is training with multiple images and the other is video vision_position_ids being wrong." }, { "left": "issue:44265", "right": "issue:45072", "accept": false, - "reason": "`torch.export`/`torch_compilable_check` failure and dtype mismatch in inference are unrelated." + "reason": "torch.export with torch_compilable_check and dtype mismatches in bfloat16 inference are different issues." }, { "left": "issue:43644", "right": "issue:44079", "accept": false, - "reason": "Non-persistent buffer initialization bug versus ModelOutput key bookkeeping bug; different components." + "reason": "Non-persistent buffer junk filling is unrelated to ModelOutput key assignment." }, { "left": "issue:43749", "right": "issue:44079", "accept": false, - "reason": "FSDP CPU RAM efficient loading failure is unrelated to ModelOutput key handling." + "reason": "FSDP CPU RAM efficient loading and ModelOutput key assignment are not the same bug." }, { "left": "issue:45325", "right": "issue:45381", "accept": false, - "reason": "Both are Qwen2.5-VL positional-id bugs, but one is still-image temporal scaling and the other is video-input vision positions; not enough to treat as the same concrete bug." + "reason": "Both are Qwen2.5-VL position-id issues, but one is still-image temporal scaling and the other is video input position_ids; too different to merge." }, { "left": "issue:42175", "right": "issue:43296", "accept": false, - "reason": "TensorFlow backend packaging versus loading PaddleOCR-VL in vLLM 0.11.0; unrelated." + "reason": "TensorFlow backend packaging and PaddleOCR-VL loading in vLLM are unrelated." }, { "left": "issue:43632", "right": "issue:45072", "accept": false, - "reason": "`_is_hf_initialized` flag breakage is unrelated to SwitchTransformers/TimmWrapperModel bfloat16 dtype mismatches." + "reason": "_is_hf_initialized flag handling and bfloat16 dtype mismatches are different regressions." }, { "left": "issue:43611", "right": "issue:43646", - "accept": true, - "reason": "Both point to the same Transformers v5 custom-model initialization/loading regression; `base_model_prefix` loading is a specific manifestation of the broader custom init breakage." + "accept": false, + "reason": "Both are v5 model-loading regressions, but base_model_prefix handling and custom model initialization are distinct failure modes." }, { "left": "issue:43792", "right": "issue:43957", "accept": false, - "reason": "Whisper run failure and meta-device loading failure are different model-loading problems." + "reason": "Whisper model runtime failure and meta-device loading breakage are not the same underlying bug." }, { - "left": "issue:43994", - "right": "issue:44898", + "left": "issue:45325", + "right": "issue:45834", "accept": false, - "reason": "Different model families and different failure modes: SigLIP nonsensical outputs versus Perceiver resolution/interpolation failure." + "reason": "Different Qwen2.5-VL models and different OCR/position-id failure contexts." }, { - "left": "issue:45325", - "right": "issue:45834", + "left": "issue:43994", + "right": "issue:44898", "accept": false, - "reason": "Both are vision-language issues, but one is a positional-index regression and the other is long OCR input index errors; not the same bug." + "reason": "SigLIP2 nonsensical outputs and Perceiver non-default-resolution failure are unrelated model-specific issues." }, { "left": "issue:43454", "right": "issue:44466", "accept": false, - "reason": "AyaVision weight tying bug versus inconsistent lm_head serialization; related only by weights, not the same issue." + "reason": "lm_head weight tying during generation vs serialization inconsistency depending on device are related in theme but not the same concrete bug." }, { "left": "issue:42915", "right": "issue:43482", "accept": false, - "reason": "Qwen3MoE FP8 configuration failure and Qwen2.5-GGUF loading failure are unrelated." + "reason": "Qwen3Moe FP8 config failure and Qwen2.5-GGUF loading failure are separate model/runtime issues." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative overall. The only accepted soft pair, issue:43611 \u2194 issue:43646, is a plausible same v5 init/load regression by title, and the rest are reasonably rejected as different models, subsystems, or failure modes. No PRs are present." - }, - "evaluator_used": true, + "evaluator_result": null, + "evaluator_used": false, "retried": false, - "accepted_nontrivial_soft_edge": true, + "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null }, @@ -3627,7 +3565,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:34634", "issue:35707", @@ -3680,8 +3618,8 @@ "soft_pairs": [ "issue:43296|issue:45800", "issue:44387|issue:44617", - "issue:43701|issue:45325", "issue:44479|issue:45823", + "issue:43701|issue:45325", "issue:43881|issue:44488", "issue:44291|issue:44877", "issue:43606|issue:44265", @@ -3703,220 +3641,220 @@ "issue:43257|issue:45923", "issue:43377|issue:44898", "issue:40990|issue:42947", - "issue:43322|issue:46050", "issue:43526|issue:43883", - "issue:41720|issue:43322", + "issue:43322|issue:46050", "issue:43881|issue:44991", - "issue:43454|issue:43720" + "issue:43454|issue:43720", + "issue:41720|issue:43322" ], - "prepared_review_unit_hash": "b52f508eec2c595d1794fd24b7abd2360fee7b5303182f014f9f8fbd0fedf037", + "prepared_review_unit_hash": "fa2b47b8879dc51abb58353fb3bd8cde0f3ec4162f4ed7cb19ed651e8fc883ce", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 30, - "serialized_chars": 36268, - "estimated_input_tokens": 9067, - "estimated_eval_tokens": 18390 + "serialized_chars": 36270, + "estimated_input_tokens": 9068, + "estimated_eval_tokens": 18392 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly a set of unrelated model-loading, tokenizer, quantization, and device-map bugs. None of the soft pairs look like true duplicates under a strict triage standard; the closest themes are offloading/quantization and tokenizer regressions, but they still appear to be distinct concrete failures. I\u2019d use the broad offloading/quantization report as the cluster representative.", - "confidence": 0.38, - "canonical_issue_reason": "issue:43873 is the broadest and most central issue in this set: it directly covers offloading behavior with quantization, has the most discussion/inbound references, and best represents the nearby offload/device-map/quantization failures without being overly model-specific.", + "summary": "No soft duplicate pairs look like the same underlying bug/change; the overlaps are mostly broad subsystem similarity (tokenization, offloading, device map, multimodal loading) but the concrete failure modes differ. No PRs were provided.", + "confidence": 0.94, + "canonical_issue_reason": "issue:43873 is the strongest hub candidate: it is open, has the most discussion/inbound references among these issues, and covers a broad, actively reported offloading/quantization failure mode.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43873 is the best single issue to anchor the cluster because it is open, high-signal, and spans the main recurring theme across the nearby reports: quantized/offloaded model loading and device placement.", + "best_issue_reason": "issue:45920 is the clearest high-impact report: it describes a concrete cross-model tokenizer regression with a well-scoped symptom and broad user impact.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43296", "right": "issue:45800", "accept": false, - "reason": "Different failures: a specific PaddleOCR-VL load issue vs a broad torch/transformers version incompatibility." + "reason": "Different problems: a PaddleOCR-VL loading failure in vLLM vs a general torch/transformers version incompatibility." }, { "left": "issue:44387", "right": "issue:44617", "accept": false, - "reason": "Both mention OOM, but the models and root causes are unrelated; one is int4 quantization memory growth, the other is Sam3Video CUDA OOM." + "reason": "Both mention memory issues, but one is int4 CUDA reserved memory/OOM and the other is Sam3Video runtime OOM; not the same bug." }, { - "left": "issue:43701", - "right": "issue:45325", + "left": "issue:44479", + "right": "issue:45823", "accept": false, - "reason": "Checkpoint key mismatch is unrelated to the Qwen2.5-VL rope-index scaling bug." + "reason": "Different model families and failures: video-input regression in Qwen VL models vs Gemma4 PLE device mismatch during forward." }, { - "left": "issue:44479", - "right": "issue:45823", + "left": "issue:43701", + "right": "issue:45325", "accept": false, - "reason": "Distinct model families and symptoms: a video-input regression in Qwen variants vs a Gemma4 device-mismatch forward bug." + "reason": "Resume-checkpoint key mismatch is unrelated to Qwen2.5-VL rope/position-id scaling." }, { "left": "issue:43881", "right": "issue:44488", "accept": false, - "reason": "Both are load failures, but they affect different models and likely different code paths." + "reason": "Both are load failures, but they involve different models and likely different root causes." }, { "left": "issue:44291", "right": "issue:44877", "accept": false, - "reason": "One is an init-empty-weights argument regression; the other is a strict config loading issue. Same area, different bug." + "reason": "Unexpected init_empty_weights argument vs strict config blocking granite_speech config loading are distinct initialization/config issues." }, { "left": "issue:43606", "right": "issue:44265", "accept": false, - "reason": "Bark CPU offload device mismatch and torch.export torch_compilable_check failure are unrelated." + "reason": "CPU-offload device mismatch for bark-small is not the same as torch.export failures around torch_compilable_check." }, { "left": "issue:43262", "right": "issue:43746", "accept": false, - "reason": "Audio chat-template sampling-rate handling is unrelated to PEFT adapter checkpoint loading." + "reason": "Audio chat-template sampling-rate defaulting and GraniteSpeech PEFT checkpoint loading are unrelated." }, { "left": "issue:43873", "right": "issue:45701", "accept": false, - "reason": "Quantization/offloading bug vs tokenizer behavior change; not the same concrete issue." + "reason": "Quantization/offloading behavior is unrelated to tokenization changes." }, { "left": "issue:34634", "right": "issue:35707", "accept": false, - "reason": "BarkProcessor voice_preset and progressive generation with past_key_values are different bugs." + "reason": "BarkProcessor voice_preset failure and progressive generation with inputs_embeds/past_key_values are different code paths." }, { "left": "issue:40990", "right": "issue:45584", "accept": false, - "reason": "High perplexity on one model is unrelated to Whisper empty-transcription generation failure." + "reason": "High perplexity on GPT-OSS vs Whisper empty-transcription failure after align_special_tokens are different bugs." }, { "left": "issue:44568", "right": "issue:45920", "accept": false, - "reason": "Both are tokenizer regressions, but they describe different failure modes and model sets; too broad to treat as one bug." + "reason": "Both are tokenizer regressions, but one is a specific special-token insertion bug for a single tokenizer while the other is a broader wrong-token-IDs regression across many models." }, { "left": "issue:35707", "right": "issue:41720", "accept": false, - "reason": "Progressive generation with inputs_embeds/past_key_values is unrelated to Qwen3 auto device-map CUDA asserts." + "reason": "Progressive generation inputs/past_key_values and Qwen3 auto device-map cudaErrorAssert are unrelated." }, { "left": "issue:44186", "right": "issue:44265", "accept": false, - "reason": "Tokenizer crashes on NER/batched padding are unrelated to torch.export failures." + "reason": "LayoutLMv2Tokenizer padding/truncation crashes are not the same as torch.export failures in models using torch_compilable_check." }, { "left": "issue:43606", "right": "issue:43819", "accept": false, - "reason": "Both involve audio/codecs, but CPU offload device mismatch and DAC STE mismatch are different problems." + "reason": "Both are model-specific generation/load problems, but bark-small CPU offload mismatch and DAC from_latents/forward mismatch are distinct." }, { "left": "issue:41720", "right": "issue:45823", "accept": false, - "reason": "Both are device-map related, but they fail in different models and likely different code paths; not a duplicate." + "reason": "Both involve device placement, but the affected models and failure modes differ substantially." }, { "left": "issue:43454", "right": "issue:43550", "accept": false, - "reason": "Weight-tying in AyaVision is unrelated to Bamba SDPA torch.compile failure." + "reason": "lm_head tying in AyaVisionConfig is unrelated to Bamba-9B-v2 torch.compile SDPA failure." }, { "left": "issue:39692", "right": "issue:40444", "accept": false, - "reason": "Doc-example/model-processor mismatch in SigLIP2 is unrelated to Qwen2.5-VL multi-image IterableDataset finetuning failure." + "reason": "Documentation/model-processor mismatch and quantization errors are unrelated to iterable dataset multi-image finetuning failures." }, { "left": "issue:43377", "right": "issue:44610", "accept": false, - "reason": "Missing padding-mask support in MIMI encoder is unrelated to OmDet-Turbo image-size mismatch." + "reason": "MIMI padding-mask batch-vs-single inconsistency is unrelated to OmDet-Turbo processor/model input-size mismatch." }, { "left": "issue:43317", "right": "issue:43873", "accept": false, - "reason": "These are the closest pair, but one is a dequantized-model load failure on gpu+cpu offload while the other is a broader quantization offloading complaint; not enough evidence they are the same concrete bug." + "reason": "Both concern offloading/quantization, but one is dequantized model loading with auto device_map while the other is a broader offloading-not-working report; not enough evidence of the same bug." }, { "left": "issue:43454", "right": "issue:45072", "accept": false, - "reason": "Weight tying and bfloat16 dtype mismatch are different issues." + "reason": "Weight tying in AyaVisionConfig and bf16 dtype mismatches in different models are unrelated." }, { "left": "issue:43572", "right": "issue:45759", "accept": false, - "reason": "StableLm config pad-token handling and composite Qwen config unwrapping are different config-path bugs." + "reason": "Missing pad_token_idx in StableLmConfig is unrelated to unwrapping text_config for composite Qwen multimodal configs." }, { "left": "issue:43257", "right": "issue:45923", "accept": false, - "reason": "MoE weight conversion under accelerate+deepspeed is unrelated to missing supports_gradient_checkpointing on a trust_remote_code variant." + "reason": "Qwen3 MoE weight conversion under accelerate+deepspeed and a missing supports_gradient_checkpointing flag are separate issues." }, { "left": "issue:43377", "right": "issue:44898", "accept": false, - "reason": "Padding-mask correctness in MIMI encoder is unrelated to Perceiver non-default-resolution failure." + "reason": "Padding-mask support in MIMI and Perceiver non-default-resolution failures are different models and mechanisms." }, { "left": "issue:40990", "right": "issue:42947", "accept": false, - "reason": "Perplexity anomaly and gradient-checkpointing ineffectiveness are unrelated." - }, - { - "left": "issue:43322", - "right": "issue:46050", - "accept": false, - "reason": "Llava Next load crash and sinq quantized save/load breakage are different bugs." + "reason": "Perplexity regression on GPT-OSS is unrelated to gradient checkpointing ineffectiveness with PEFT LoRA." }, { "left": "issue:43526", "right": "issue:43883", "accept": false, - "reason": "BeitImageProcessorFast label reduction and Molmo tied-weights attribute error are unrelated." + "reason": "BeitImageProcessorFast label reduction bug and Molmo all_tied_weights_keys missing are unrelated." }, { - "left": "issue:41720", - "right": "issue:43322", + "left": "issue:43322", + "right": "issue:46050", "accept": false, - "reason": "Both are model-loading/runtime crashes, but the affected models and failure signatures are different." + "reason": "Llava Next segmentation fault while loading and sinq save/load quantization breakage are different failure modes." }, { "left": "issue:43881", "right": "issue:44991", "accept": false, - "reason": "Model loading failure for glm-4v-9b vs tokenizer loading failure for EMBEDDIA/est-roberta are unrelated." + "reason": "Different model/tokenizer loading failures with no clear shared code-path." }, { "left": "issue:43454", "right": "issue:43720", "accept": false, - "reason": "AyaVision weight tying and BitNet packed-weight unpacking are distinct loading/model-structure bugs." + "reason": "AyaVision lm_head tying and BitNet packed-weight unpacking are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:43322", + "accept": false, + "reason": "Both are load/runtime failures, but one is Qwen3 device-map assertion and the other is Llava Next segmentation fault; not the same bug." } ] }, @@ -3938,7 +3876,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:36010", "issue:36331", @@ -4001,11 +3939,11 @@ "issue:36331|issue:42617", "issue:43577|issue:43708", "issue:43404|issue:45357", + "issue:44877|issue:44991", "issue:43873|issue:44756", "issue:36331|issue:42915", - "issue:44877|issue:44991", - "issue:43550|issue:43720", "issue:43450|issue:45701", + "issue:43550|issue:43720", "issue:44423|issue:45406", "issue:45632|issue:45684", "issue:41720|issue:42617", @@ -4018,217 +3956,223 @@ "issue:43526|issue:43881", "issue:41720|issue:45161", "issue:44671|issue:44743", - "issue:45081|issue:45812", - "issue:36010|issue:42617" + "issue:36010|issue:42617", + "issue:45081|issue:45812" ], - "prepared_review_unit_hash": "f10fb66cea39a10eb12a9e6be0a5bba2f9576ad9de5d3ad2f286b39fd81a89e8", + "prepared_review_unit_hash": "3dbd092e1710d91cd5111729438996bc1496d499f12ad85343abb30f6731a78c", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 31, - "serialized_chars": 36671, - "estimated_input_tokens": 9168, - "estimated_eval_tokens": 18592 + "serialized_chars": 36661, + "estimated_input_tokens": 9166, + "estimated_eval_tokens": 18588 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly a loose theme cluster around Transformers loading/device/offload/tokenization regressions, but the soft pairs describe different concrete bugs or models rather than true duplicates. I would not merge any of the candidate pairs.", - "confidence": 0.82, - "canonical_issue_reason": "Issue #43873 is the broadest representative of the cluster\u2019s shared offloading/loading pain points, but it is still a distinct bug from the others.", - "canonical_pr_reason": "No pull requests are present in this cluster.", - "best_issue_reason": "#43873 is the best single issue anchor because it is the most general and central of the loading/offload-related reports here.", - "best_pr_reason": "No pull requests are present in this cluster.", + "summary": "This cluster is not a true duplicate set; it mixes unrelated issues across tokenization, loading/offload, multimodal processors, training, and model-specific regressions. No single issue or PR is a good canonical representative.", + "confidence": 0.97, + "canonical_issue_reason": "No single issue is canonical because the artifacts describe different bugs in different code paths and models.", + "canonical_pr_reason": null, + "best_issue_reason": "No global best issue: the cluster is too heterogeneous, so a representative should be chosen per subtopic rather than across the whole set.", + "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43749", "right": "issue:44534", "accept": false, - "reason": "Both are memory/loading regressions, but one is FSDP CPU RAM efficient loading and the other is non-persistent buffer initialization; different failure modes and code paths." + "reason": "Both are loading/memory-related, but one is broken FSDP CPU RAM-efficient loading and the other is non-persistent buffer corruption; different bugs." }, { "left": "issue:43296", "right": "issue:44877", "accept": false, - "reason": "One is a model-load failure in vLLM, the other is strict config blocking granite_speech; unrelated root causes." + "reason": "Different failures: PaddleOCR-VL model loading in vLLM versus strict config blocking granite_speech config." }, { "left": "issue:44466", "right": "issue:45357", "accept": false, - "reason": "Both involve saving weights, but one is tied lm_head serialization by device and the other is incorrect visual encoder keys for Qwen3.5." + "reason": "Both involve save_pretrained/serialization, but one is lm_head.weight serialization and the other is incorrect visual encoder keys in Qwen3.5." }, { "left": "issue:41720", "right": "issue:44977", "accept": false, - "reason": "Different Qwen3 family problems: CUDA assert under auto device mapping versus flash-attention generation failure." + "reason": "Different code paths and symptoms: auto device mapping cuda assert versus flash-attention generation regression." }, { "left": "issue:42617", "right": "issue:42915", "accept": false, - "reason": "Completely different contexts: 3d_parallel.py execution failure versus FineGrainedFP8Config failure on Qwen3Moe." + "reason": "3d_parallel.py startup failure is unrelated to Qwen3Moe failing with FineGrainedFP8Config." }, { "left": "issue:40990", "right": "issue:45701", "accept": false, - "reason": "Perplexity on a specific model/dataset is not the same bug as tokenizer-version-dependent tokenization changes." + "reason": "Perplexity anomaly on gpt-oss-20b is not the same underlying bug as a tokenization-behavior change across versions." }, { "left": "issue:44008", "right": "issue:45823", "accept": false, - "reason": "Gemma3n variable-name collision in forward is unrelated to Gemma4 PLE device mismatch." + "reason": "Gemma3n forward variable collision and Gemma4 PLE device mismatch are unrelated bugs." }, { "left": "issue:44387", "right": "issue:45704", "accept": false, - "reason": "Both mention memory, but one is int4 quantization OOM in Transformers 5.x and the other is a T5/apex RMSNorm leak." + "reason": "Both mention memory, but one is int4 quantization OOM in v5 and the other is a T5 apex RMSNorm memory leak." }, { "left": "issue:44186", "right": "issue:45072", "accept": false, - "reason": "Tokenizer crashes on batching/padding are unrelated to dtype mismatches in SwitchTransformers/TimmWrapperModel inference." + "reason": "Tokenizer padding/truncation crash and dtype mismatch in inference are distinct problems." }, { "left": "issue:36331", "right": "issue:42617", "accept": false, - "reason": "Trainer compute_loss API break and 3d_parallel.py failure are different bugs with no shared code path." + "reason": "Trainer compute_loss signature regression is unrelated to 3d_parallel.py failing to run." }, { "left": "issue:43577", "right": "issue:43708", "accept": false, - "reason": "Blip2 dtype loading is separate from Trainer resume_from_checkpoint step calculation." + "reason": "BLIP2 dtype-loading issue and Trainer resume/max_steps calculation bug are different training/loading defects." }, { "left": "issue:43404", "right": "issue:45357", "accept": false, - "reason": "Both touch weights/serialization, but one is missing lm_head tying in Mistral3 and the other is incorrect visual encoder keys in Qwen3.5." + "reason": "Mistral3 lm_head tying bug and Qwen3.5 visual encoder key serialization bug are unrelated." + }, + { + "left": "issue:44877", + "right": "issue:44991", + "accept": false, + "reason": "Strict config rejection for granite_speech and tokenizer loading failure for est-roberta do not share the same underlying cause." }, { "left": "issue:43873", "right": "issue:44756", "accept": false, - "reason": "Both are offloading-related, but one is quantization/offload behavior and the other is mmap OOM on Strix Halo; not the same bug." + "reason": "Both relate to memory/offload, but one is quantization offloading and the other is mmap-induced OOM on Strix Halo." }, { "left": "issue:36331", "right": "issue:42915", "accept": false, - "reason": "A custom trainer signature regression is unrelated to a Qwen3Moe FP8 load failure." + "reason": "Trainer custom loss signature mismatch is unrelated to Qwen3Moe FineGrainedFP8Config failure." }, { - "left": "issue:44877", - "right": "issue:44991", + "left": "issue:43450", + "right": "issue:45701", "accept": false, - "reason": "Strict config loading for granite_speech is unrelated to tokenizer loading failure for EMBEDDIA/est-roberta." + "reason": "Video batch-shape bug and tokenization-version behavior change are unrelated." }, { "left": "issue:43550", "right": "issue:43720", "accept": false, - "reason": "Both are model-loading/runtime issues, but one is torch.compile SDPA on Bamba and the other is accelerate loading of BitNet packed weights." - }, - { - "left": "issue:43450", - "right": "issue:45701", - "accept": false, - "reason": "Incorrect video batch shapes are unrelated to tokenization changing across versions." + "reason": "torch.compile SDPA failure in Bamba and packed-weight unpacking failure in BitNet are different model-loading/runtime bugs." }, { "left": "issue:44423", "right": "issue:45406", "accept": false, - "reason": "Both affect serve paths, but one crashes on multimodal continuous batching and the other lacks Gemma4Processor._tokenizer." + "reason": "Both crash in serving, but one is continuous-batching multimodal input handling and the other is Gemma4Processor missing _tokenizer." }, { "left": "issue:45632", "right": "issue:45684", "accept": false, - "reason": "One is a cache-path collision for local models, the other is permission propagation in save_pretrained; distinct filesystem bugs." + "reason": "Cache-path collision for trust_remote_code and read-only permission propagation in save_pretrained are unrelated." }, { "left": "issue:41720", - "right": "issue:45161", + "right": "issue:42617", "accept": false, - "reason": "Both concern Qwen/GPT-OSS parallelism, but one is an auto device-map CUDA assert and the other is TP not working for GPT-OSS MoE." + "reason": "Different problems: Qwen3 auto device mapping assert versus a separate 3d_parallel.py execution failure." }, { "left": "issue:44479", "right": "issue:44918", "accept": false, - "reason": "Qwen video-input regression and TRL SFT embedding unpacking failure are different code paths and symptoms." + "reason": "Video-input regression for Qwen models and SFT embedding unpacking failure are not the same bug." }, { "left": "issue:44610", "right": "issue:44898", "accept": false, - "reason": "Different vision preprocessing bugs: OmDet-Turbo produces the wrong resolution, while Perceiver fails on non-default resolution despite interpolate_pos_encoding." + "reason": "Both involve image sizes, but one is a processor/model size mismatch and the other is a Perceiver interpolation failure." }, { "left": "issue:43550", "right": "issue:43606", "accept": false, - "reason": "Both involve device/compile behavior, but Bamba SDPA compile failure is not the same as suno/bark-small CPU-offload device mismatch." + "reason": "Bamba SDPA compile failure and Bark CPU-offload device mismatch are unrelated." }, { "left": "issue:44186", "right": "issue:44610", "accept": false, - "reason": "Tokenizer batching/truncation crash and image processor resolution mismatch are unrelated." + "reason": "LayoutLMv2 tokenizer crash and OmDet-Turbo processor resolution mismatch are different subsystems and failure modes." }, { "left": "issue:42915", "right": "issue:43317", "accept": false, - "reason": "Qwen3Moe FineGrainedFP8 loading and dequantized-model CPU/GPU offload failure are distinct bugs." + "reason": "Both are model loading/offload issues, but one is Qwen3Moe FineGrainedFP8Config and the other is dequantized model loading with gpu+cpu offload." }, { "left": "issue:43295", "right": "issue:45701", "accept": false, - "reason": "Processor.tokenizer regression is not the same as broader tokenization changes across versions." + "reason": "Regression in processor.tokenizer/images handling is not the same as a broader tokenization-version change." }, { "left": "issue:43526", "right": "issue:43881", "accept": false, - "reason": "A BeitImageProcessorFast label reduction bug is unrelated to glm-4v-9b loading failure." + "reason": "BeitImageProcessorFast reduce_labels bug and glm-4v-9b loading failure are unrelated." }, { - "left": "issue:44671", - "right": "issue:44743", + "left": "issue:41720", + "right": "issue:45161", "accept": false, - "reason": "CamemBERT masked LM prediction errors and Qwen3.5 recurrent-state reset are different model-specific issues." + "reason": "Both concern device/sharding behavior, but the concrete failures differ: cuda assert on A800 versus only tensor parallel not working." }, { - "left": "issue:45081", - "right": "issue:45812", + "left": "issue:44671", + "right": "issue:44743", "accept": false, - "reason": "Both are tokenizer-related, but one is a Mistral regex patch crash and the other is wrong token IDs for Granite models; different root causes." + "reason": "CamemBERT masked LM regression and Qwen3.5 recurrent-state reset bug are unrelated model behaviors." }, { "left": "issue:36010", "right": "issue:42617", "accept": false, - "reason": "GenerationMixin import error is unrelated to running 3d_parallel.py." + "reason": "ImportError for GenerationMixin and 3d_parallel.py execution failure have no shared underlying bug." + }, + { + "left": "issue:45081", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer-related regressions, but one is Mistral regex patching and the other is Granite token ID generation; different code paths and models." } ] }, @@ -4250,7 +4194,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:29159", "issue:30064", @@ -4259,6 +4203,7 @@ "issue:34634", "issue:35707", "issue:36032", + "issue:36331", "issue:41720", "issue:42490", "issue:42915", @@ -4278,7 +4223,6 @@ "issue:43782", "issue:43873", "issue:43927", - "issue:44077", "issue:44186", "issue:44361", "issue:44451", @@ -4308,16 +4252,17 @@ "issue:42915|issue:43322", "issue:43421|issue:45812", "issue:44186|issue:44361", - "issue:43388|issue:45059", + "issue:36331|issue:41720", "issue:29159|issue:36032", + "issue:43388|issue:45059", "issue:45406|issue:45464", "issue:33357|issue:35707", "issue:30064|issue:34634", "issue:41720|issue:43746", "issue:43606|issue:43720", "issue:43550|issue:43653", - "issue:43421|issue:45701", "issue:43873|issue:45704", + "issue:43421|issue:45701", "issue:44492|issue:44509", "issue:43606|issue:43653", "issue:34634|issue:41720", @@ -4328,221 +4273,220 @@ "issue:44625|issue:45479", "issue:43421|issue:43927", "issue:44898|issue:45072", - "issue:43782|issue:45381", "issue:44451|issue:44991", - "issue:44077|issue:44625" + "issue:43782|issue:45381" ], - "prepared_review_unit_hash": "83016af477d902585c2d2c6c832137cd9acbae67bda6a240d62bb8ca0653b457", + "prepared_review_unit_hash": "9b55c0f519cab024e3e7f669471115564adfdb8336b3d7b08cca4866caf594a3", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 29, - "serialized_chars": 36509, - "estimated_input_tokens": 9128, - "estimated_eval_tokens": 18512 + "serialized_chars": 36540, + "estimated_input_tokens": 9135, + "estimated_eval_tokens": 18526 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous issue reports, not a single duplicate set. The only clear duplicate pair is the Qwen2_5_VLProcessor.apply_chat_template padding=False crash; the rest only share broad subsystem/model-family similarity.", - "confidence": 0.97, - "canonical_issue_reason": "No single issue cleanly represents the whole cluster; the only true duplicate subcluster is issue:44514/issue:44545, and issue:44545 is the best anchor because it has the stronger discussion/inbound reference signal for the same exact bug.", + "summary": "Mostly heterogeneous cluster of issue reports across unrelated tokenizer, config, processor, loading, and training paths. The only clear duplicate pair in the packet is 44514/44545, which share the same title about `Qwen2_5_VLProcessor.apply_chat_template` crashing on batched input with `padding=False`.", + "confidence": 0.82, + "canonical_issue_reason": "44514 is the better canonical issue because it is the earlier of the exact title match with 44545.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44545 is the strongest issue candidate because it exactly matches issue:44514's bug report and has slightly more triage signal, making it the best dedupe target for that subcluster.", + "best_issue_reason": "44514 is the strongest representative issue because it is the earlier exact duplicate pair in the cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43531", "right": "issue:43572", "accept": false, - "reason": "Both are model/config generation bugs, but they affect different models and different parameters; not the same underlying defect." + "reason": "Different titles and model areas: Qwen3-MoE `sliding_window` vs StableLmConfig `pad_token_idx`." }, { "left": "issue:43316", "right": "issue:44913", "accept": false, - "reason": "Both concern config behavior, but one is a Gemma3TextConfig API mismatch and the other is rotary_pct persistence on reload; different bug paths." + "reason": "Both are config-related, but they describe different fields and different models." }, { "left": "issue:43540", "right": "issue:43782", "accept": false, - "reason": "Different multimodal Qwen bugs: one is video-input processing, the other is from_pretrained weight_only loading." + "reason": "Both mention Qwen models, but one is about video input processing and the other about `from_pretrained` weight loading." }, { "left": "issue:42915", "right": "issue:43322", "accept": false, - "reason": "Unrelated failures in different models and code paths; one is FP8 config loading, the other a Llava Next segfault." + "reason": "Different model families and failure types: FineGrainedFP8Config vs loading Llava Next models." }, { "left": "issue:43421", "right": "issue:45812", "accept": false, - "reason": "Both are tokenizer-related, but one is runtime post-processor refresh and the other is a silent token-id regression for Granite models." + "reason": "Tokenizer-related, but one is runtime post-processor updates and the other is a tokenizer loading regression for Granite models." }, { "left": "issue:44186", "right": "issue:44361", "accept": false, - "reason": "Both are tokenizer task crashes, but on different tokenizer implementations and different failure modes." + "reason": "Both are tokenizer issues, but the titles point to different tokenizer classes and different failures." }, { - "left": "issue:43388", - "right": "issue:45059", + "left": "issue:36331", + "right": "issue:41720", "accept": false, - "reason": "These are unrelated: metric gathering label truncation versus SAM3 text/bounding-box behavior." + "reason": "Trainer loss-signature error vs auto device mapping CUDA assert are unrelated." }, { "left": "issue:29159", "right": "issue:36032", "accept": false, - "reason": "Both mention tokenizers, but one is slow/fast inconsistency and the other is a T5 loading AttributeError; different bugs." + "reason": "Both are tokenizer issues, but one is slow/fast behavior inconsistency and the other is a T5Tokenizer load-time error." + }, + { + "left": "issue:43388", + "right": "issue:45059", + "accept": false, + "reason": "Different subsystems: metric gathering vs SAM3 text/bounding-box behavior." }, { "left": "issue:45406", "right": "issue:45464", "accept": false, - "reason": "Serving crashes in different places: Gemma4Processor missing _tokenizer versus Qwen3.5 streaming inference failure." + "reason": "Different components and symptoms: Gemma4Processor missing `_tokenizer` vs Qwen3.5 streaming API failure." }, { "left": "issue:33357", "right": "issue:35707", "accept": false, - "reason": "Different failures entirely: MacOS CLIP bus error versus generation with inputs_embeds/past_key_values." + "reason": "MacOS CLIP bus error vs progressive generation with `inputs_embeds`/`past_key_values` are separate issues." }, { "left": "issue:30064", "right": "issue:34634", "accept": false, - "reason": "Different processors and symptoms; image segmentation-map handling is unrelated to Bark voice_preset handling." + "reason": "Different processors and modalities: segmentation maps vs Bark voice preset handling." }, { "left": "issue:41720", "right": "issue:43746", "accept": false, - "reason": "Different model/loading problems with no shared concrete code path." + "reason": "CUDA assert during device mapping vs PEFT local checkpoint loading are distinct problems." }, { "left": "issue:43606", "right": "issue:43720", "accept": false, - "reason": "Both involve accelerate/CI loading, but one is CPU offload device mismatch and the other is packed-weight unpacking." + "reason": "Both involve loading/offloading, but the titles describe different model paths and failures." }, { "left": "issue:43550", "right": "issue:43653", "accept": false, - "reason": "Different subsystems: torch.compile/SDPA versus tokenizer special-token registration." + "reason": "torch.compile/SDPA vs tokenizer special-token registration are unrelated." }, { - "left": "issue:43421", - "right": "issue:45701", + "left": "issue:43873", + "right": "issue:45704", "accept": false, - "reason": "Similar broad tokenizer theme, but 45701 is a generic version regression while 43421 is a runtime post-processor update bug." + "reason": "Quantization offloading vs T5/apex memory leak are different issues." }, { - "left": "issue:43873", - "right": "issue:45704", + "left": "issue:43421", + "right": "issue:45701", "accept": false, - "reason": "Unrelated issues: quantized offloading versus a T5 RMSNorm memory leak." + "reason": "Both relate to tokenization broadly, but one is runtime special-token updates and the other is a version-wide tokenization change report." }, { "left": "issue:44492", "right": "issue:44509", "accept": false, - "reason": "Both are documentation-ish, but they concern different content and different fixes." + "reason": "A typo in cache strategies is unrelated to outdated pipeline task documentation." }, { "left": "issue:43606", "right": "issue:43653", "accept": false, - "reason": "Distinct bugs in different models/components; no shared underlying defect." + "reason": "Device offload/loading mismatch vs tokenizer special-token bug are different code paths." }, { "left": "issue:34634", "right": "issue:41720", "accept": false, - "reason": "Different model/runtime failures with no common code path." + "reason": "Voice preset handling vs CUDA assert on auto device mapping are unrelated." }, { "left": "issue:43531", "right": "issue:45759", "accept": false, - "reason": "Both touch Qwen3 model config behavior, but sliding_window handling and text_config unwrapping are separate bugs." + "reason": "Both mention Qwen3-family models, but the titles describe different config issues." }, { "left": "issue:42490", "right": "issue:43329", "accept": false, - "reason": "Completely different issues: trailing-slash local model import warning versus multimodal token counting in video branch." + "reason": "Trailing-slash path warning is unrelated to multimodal token counting." }, { "left": "issue:34567", "right": "issue:35707", "accept": false, - "reason": "TrainerState token counting and progressive generation are unrelated." + "reason": "TrainerState token counter vs progressive generation are different features." }, { "left": "issue:44514", "right": "issue:44545", "accept": true, - "reason": "Exact same crash description and same code path in Qwen2_5_VLProcessor.apply_chat_template with batched input and padding=False." + "reason": "Same title and same reported crash condition for `Qwen2_5_VLProcessor.apply_chat_template` with batched input and `padding=False`." }, { "left": "issue:44625", "right": "issue:45479", "accept": false, - "reason": "Config propagation bug versus a cross-model loss-degeneration problem; not the same bug." + "reason": "Different sequence-classification reports: `num_labels` propagation vs zero-loss behavior." }, { "left": "issue:43421", "right": "issue:43927", "accept": false, - "reason": "Both involve special-token/config persistence, but one is runtime post-processor syncing and the other is saved custom token IDs being lost." + "reason": "Runtime tokenizer post-processing update vs save/load loss of custom token IDs are different metadata issues." }, { "left": "issue:44898", "right": "issue:45072", "accept": false, - "reason": "Different model failures: interpolation on Perceiver image classification versus bfloat16 dtype mismatches." - }, - { - "left": "issue:43782", - "right": "issue:45381", - "accept": false, - "reason": "Both are Qwen VL-related, but one is a load-time weight_only error and the other is wrong video vision_position_ids." + "reason": "Perceiver resolution failure vs bfloat16 dtype mismatch are unrelated." }, { "left": "issue:44451", "right": "issue:44991", "accept": false, - "reason": "Different tokenizer-loading regressions affecting different models; not the same underlying issue." + "reason": "Both are tokenizer-loading regressions, but they refer to different models and titles." }, { - "left": "issue:44077", - "right": "issue:44625", + "left": "issue:43782", + "right": "issue:45381", "accept": false, - "reason": "PatchTSMixer post_init validation and Qwen3.5 num_labels propagation are unrelated." + "reason": "Qwen vision-language load error vs Qwen2.5-VL video position IDs issue are different." } ] }, "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative. The only clear duplicate pair in the evidence is issue:44514/issue:44545, and the choice of issue:44545 as the anchor is supported by its slightly higher inbound/discussion signal. The soft-edge rejections are also cautious and generally consistent with the titles and descriptions provided." + "accept": false, + "feedback": "The overall cluster summary is mostly grounded, but the justification is a bit too assertive for the packet. In particular, the reasons for 44514/44545 claim \"precise repro details\" and \"more detailed report\" without body text evidence; from the packet you can safely say they have the same title and 44514 is earlier. A few soft-edge reasons also infer specific root causes beyond what the titles support. Please keep the verdicts and reasons tighter to the observable metadata." }, "evaluator_used": true, - "retried": false, + "retried": true, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -4558,7 +4502,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:30064", "issue:36010", @@ -4571,10 +4515,8 @@ "issue:43531", "issue:43540", "issue:43596", - "issue:43618", "issue:43645", "issue:43653", - "issue:43697", "issue:43720", "issue:43746", "issue:43819", @@ -4583,12 +4525,14 @@ "issue:43994", "issue:44008", "issue:44062", + "issue:44077", "issue:44186", "issue:44220", "issue:44368", "issue:44451", "issue:44589", "issue:44610", + "issue:44625", "issue:44661", "issue:44671", "issue:44843", @@ -4609,25 +4553,26 @@ "issue:46050" ], "soft_pairs": [ + "issue:44077|issue:44625", "issue:45759|issue:45859", "issue:43531|issue:44589", - "issue:44368|issue:45357", "issue:44987|issue:45042", + "issue:44368|issue:45357", "issue:44062|issue:44451", "issue:45588|issue:45759", - "issue:39692|issue:44610", "issue:43746|issue:46050", + "issue:39692|issue:44610", "issue:45704|issue:45923", "issue:44918|issue:44936", "issue:43421|issue:43653", "issue:45663|issue:45923", - "issue:42886|issue:44843", "issue:43381|issue:43844", + "issue:42886|issue:44843", "issue:43421|issue:44186", "issue:45704|issue:45859", "issue:43994|issue:44671", - "issue:41720|issue:45704", "issue:43531|issue:43645", + "issue:41720|issue:45704", "issue:43746|issue:43873", "issue:45081|issue:45356", "issue:39692|issue:43873", @@ -4636,232 +4581,234 @@ "issue:45356|issue:45907", "issue:30064|issue:36010", "issue:43720|issue:43819", - "issue:43653|issue:43720", "issue:44220|issue:44661", - "issue:43540|issue:44008", - "issue:43618|issue:43697" + "issue:43653|issue:43720", + "issue:43540|issue:44008" ], - "prepared_review_unit_hash": "9ff48fa0394695b65daf12c29ed7a5c0554e5f279194e3a83bbb3aa3f2c47593", + "prepared_review_unit_hash": "495696192fbb85804da218aaccc56383ae1c115a4c02541079891d64d1f32714", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 31, - "serialized_chars": 36808, - "estimated_input_tokens": 9202, - "estimated_eval_tokens": 18660 + "serialized_chars": 36823, + "estimated_input_tokens": 9206, + "estimated_eval_tokens": 18668 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous: the soft pairs share superficial model/tokenizer/offload wording, but they describe different bugs and code paths, so none should be deduplicated as the same underlying change or regression.", - "confidence": 0.94, - "canonical_issue_reason": "Issue 43873 is the closest representative of the cluster because it is the most discussed/high-signal item and sits in the broad quantization/offloading theme that recurs in a few nearby issues.", + "summary": "This cluster is mostly heterogeneous model/tokenizer bugs. Only one soft duplicate looks plausible: the HF_HUB_OFFLINE tokenizer-loading regression pair.", + "confidence": 0.59, + "canonical_issue_reason": "issue:44843 is the most concrete, root-caused representative of the only plausible duplicate pair: it pinpoints the offline tokenizer failure to _patch_mistral_regex/model_info.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43873 is the best single issue to anchor the cluster: it has the strongest engagement and is the most broadly framed, actionable bug among otherwise unrelated reports.", + "best_issue_reason": "issue:44843 is the best overall issue here because it is actionable, specific, and ties the symptom to a concrete code path.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44077", + "right": "issue:44625", + "accept": false, + "reason": "Different problems: patchtsmixer post-init policy vs Qwen3.5 num_labels propagation." + }, { "left": "issue:45759", "right": "issue:45859", "accept": false, - "reason": "Same Qwen family, but different failures: composite config unwrapping vs CPU-offload rotary embedding behavior." + "reason": "Different code paths: composite config unwrapping vs CPU offload rotary embedding compatibility." }, { "left": "issue:43531", "right": "issue:44589", "accept": false, - "reason": "Qwen3-MoE sliding-window handling and missing Float8 storage are unrelated bugs." + "reason": "Unrelated failures: Qwen3-MoE sliding_window behavior vs Float8 storage lookup." }, { - "left": "issue:44368", - "right": "issue:45357", + "left": "issue:44987", + "right": "issue:45042", "accept": false, - "reason": "One is a tie_word_embeddings warning; the other is a save_pretrained key regression for visual encoder weights." + "reason": "Different subsystems and symptoms: loading a specific model vs PIL backend wrongly requiring torchvision." }, { - "left": "issue:44987", - "right": "issue:45042", + "left": "issue:44368", + "right": "issue:45357", "accept": false, - "reason": "Different subsystems: loading a model repo versus PIL image processors incorrectly requiring torchvision." + "reason": "One is a warning about tied embeddings, the other is incorrect visual encoder keys on save_pretrained." }, { "left": "issue:44062", "right": "issue:44451", "accept": false, - "reason": "AddedToken constructor duplication and inability to load ScandiBERT are not the same issue." + "reason": "Both are tokenizer-related, but one is an AddedToken argument error and the other is a model loading failure for ScandiBERT." }, { "left": "issue:45588", "right": "issue:45759", "accept": false, - "reason": "flash_attention s_aux handling and Qwen multimodal text_config unwrapping are separate code paths." + "reason": "Different issues: flash-attention sink handling vs from_config text_config unwrapping." }, { - "left": "issue:39692", - "right": "issue:44610", + "left": "issue:43746", + "right": "issue:46050", "accept": false, - "reason": "Both are processor/model issues, but one is a SigLIP2 docs/model mismatch and the other is an OmDet-Turbo image-size mismatch." + "reason": "Different load/save bugs: PEFT local checkpoint loading vs quantized model save_pretrained/from_pretrained behavior." }, { - "left": "issue:43746", - "right": "issue:46050", + "left": "issue:39692", + "right": "issue:44610", "accept": false, - "reason": "Local checkpoint loading with PEFT adapters and quantized sinq save/load corruption are different persistence bugs." + "reason": "Both mention processor/model mismatch, but they concern different models and different failure modes." }, { "left": "issue:45704", "right": "issue:45923", "accept": false, - "reason": "Apex RMSNorm memory leak and a missing supports_gradient_checkpointing flag are unrelated." + "reason": "Different topics: apex RMSNorm memory leak vs missing supports_gradient_checkpointing flag." }, { "left": "issue:44918", "right": "issue:44936", "accept": false, - "reason": "Trainer embedding unpacking and evaluate-after-train failure do not share the same root cause." + "reason": "Different trainer failures: SFT embedding unpacking vs evaluate-after-train behavior." }, { "left": "issue:43421", "right": "issue:43653", "accept": false, - "reason": "Both touch special tokens, but runtime post-processor refresh and BigBird mask-token registration are distinct problems." + "reason": "Both touch special tokens, but one is a runtime post-processor update feature and the other is a BigBirdTokenizer CI bug." }, { "left": "issue:45663", "right": "issue:45923", "accept": false, - "reason": "Gemma4 FSDP2 shared_kv_states KeyError is unrelated to a missing gradient-checkpointing capability flag." - }, - { - "left": "issue:42886", - "right": "issue:44843", - "accept": false, - "reason": "Both involve offline/tokenizer behavior, but one is generic cache loading and the other is a specific _patch_mistral_regex model_info call." + "reason": "Different model internals: Gemma4 FSDP2 shared_kv_states bug vs a missing gradient-checkpointing capability flag." }, { "left": "issue:43381", "right": "issue:43844", "accept": false, - "reason": "Eval-mode gradient checkpointing and ZeRO-3 gradient growth are different training failures." + "reason": "Not the same bug: eval-mode checkpointing restriction vs abnormal gradient growth under ZeRO-3." + }, + { + "left": "issue:42886", + "right": "issue:44843", + "accept": true, + "reason": "Both describe tokenizer loading failures in HF_HUB_OFFLINE mode; 44843 provides the concrete Mistral-regex/model_info root cause." }, { "left": "issue:43421", "right": "issue:44186", "accept": false, - "reason": "Special-token post-processor updates and LayoutLMv2 NER/padding crashes are separate tokenizer bugs." + "reason": "Shared tokenization theme, but different bugs: dynamic special-token post-processing vs LayoutLMv2 NER/batching crashes." }, { "left": "issue:45704", "right": "issue:45859", "accept": false, - "reason": "T5 RMSNorm memory leak and Qwen offload incompatibility are unrelated." + "reason": "Different issues: T5 apex RMSNorm leak vs Qwen3_5MoeTextRotaryEmbedding CPU-offload compatibility." }, { "left": "issue:43994", "right": "issue:44671", "accept": false, - "reason": "Different models and symptoms: SigLIP2 nonsensical outputs versus CamemBERT masked-LM regressions." + "reason": "Different models and failure signatures: SigLIP2 nonsensical outputs vs CamemBERT masked LM regression." }, { - "left": "issue:41720", - "right": "issue:45704", + "left": "issue:43531", + "right": "issue:43645", "accept": false, - "reason": "Qwen3 device-mapping CUDA asserts and a T5 RMSNorm memory leak are not the same bug." + "reason": "Different problems: Qwen3-MoE sliding_window handling vs custom model initialization in Jupyter notebooks." }, { - "left": "issue:43531", - "right": "issue:43645", + "left": "issue:41720", + "right": "issue:45704", "accept": false, - "reason": "Qwen3-MoE sliding-window behavior and Jupyter custom-model initialization are unrelated." + "reason": "Different subsystems: Qwen3 auto device mapping CUDA assert vs T5 RMSNorm memory leak." }, { "left": "issue:43746", "right": "issue:43873", "accept": false, - "reason": "Checkpoint loading with PEFT adapters and quantization/offloading behavior are different code paths." + "reason": "Both involve loading/offloading, but one is PEFT checkpoint loading and the other is quantization offloading behavior." }, { "left": "issue:45081", "right": "issue:45356", "accept": false, - "reason": "Both are tokenizer regressions, but one is _patch_mistral_regex crash behavior and the other is Kimi-K2.5 codec handling/warning issues." + "reason": "Related tokenizer regex area, but not clearly the same bug: one crashes on missing backend_tokenizer, the other is a codec/regression report." }, { "left": "issue:39692", "right": "issue:43873", "accept": false, - "reason": "SigLIP2 example errors and quantization offloading problems are unrelated." + "reason": "Different scopes: documentation/example errors vs quantization offloading behavior." }, { "left": "issue:40444", "right": "issue:43746", "accept": false, - "reason": "Qwen2.5-VL multi-image iterable-dataset finetuning and local checkpoint loading with PEFT are different bugs." + "reason": "Different model pipelines: multi-image IterableDataset fine-tuning vs PEFT local checkpoint loading." }, { "left": "issue:43596", "right": "issue:44220", "accept": false, - "reason": "ZeRO-3/BertModel init failure and _torch_extract_fbank_features are unrelated." + "reason": "Completely different failures: Deepspeed ZeRO-3/BertModel indexing vs audio fbank extraction." }, { "left": "issue:45356", "right": "issue:45907", "accept": false, - "reason": "Kimi tokenizer regression and list_repo_files revision forwarding are not the same issue." + "reason": "Different areas: tokenizer codec/regression vs Hub API revision forwarding." }, { "left": "issue:30064", "right": "issue:36010", "accept": false, - "reason": "Image processor void-segmentation-map failure and GenerationMixin import error are unrelated." + "reason": "Unrelated bugs: image processor segmentation-map handling vs GenerationMixin import error." }, { "left": "issue:43720", "right": "issue:43819", "accept": false, - "reason": "BitNet packed-weight loading and DAC forward/from_latents mismatch are different model bugs." - }, - { - "left": "issue:43653", - "right": "issue:43720", - "accept": false, - "reason": "BigBird special-token registration and BitNet packed-weight loading are unrelated." + "reason": "Different code paths: accelerate loading of packed BitNet weights vs DAC.from_latents/STE mismatch." }, { "left": "issue:44220", "right": "issue:44661", "accept": false, - "reason": "Audio fbank extraction and add-new-model-like/tokenizer-mapping behavior are different problems." + "reason": "No clear overlap: fbank feature extraction vs add-new-model-like failing inside TOKENIZER_MAPPING_NAMES." }, { - "left": "issue:43540", - "right": "issue:44008", + "left": "issue:43653", + "right": "issue:43720", "accept": false, - "reason": "Video-input processing in Qwen3OmniMoe and Gemma3n audio_mel_mask variable collision are separate multimodal bugs." + "reason": "Different tokenizer CI bug vs BitNet packed-weight loading bug." }, { - "left": "issue:43618", - "right": "issue:43697", + "left": "issue:43540", + "right": "issue:44008", "accept": false, - "reason": "Missing CLIPOutput attentions and RTDetrV2 output drift in v5 are distinct regressions." + "reason": "Different modalities and models: Qwen3OmniMoe video processing vs Gemma 3n audio_mel_mask name collision." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "The assessment is conservative and well grounded in the packet. The only accepted soft pair, issue:42886 with issue:44843, is plausibly the same HF_HUB_OFFLINE tokenizer-loading regression, while the rest of the rejections are appropriately cautious given the differing titles and problem descriptions. No evidence of overstatement or mergeability issues." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -4876,7 +4823,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:30064", "issue:36331", @@ -4891,11 +4838,11 @@ "issue:43540", "issue:43550", "issue:43577", + "issue:43618", "issue:43643", - "issue:43644", "issue:43653", + "issue:43697", "issue:43716", - "issue:43749", "issue:43756", "issue:43782", "issue:43818", @@ -4928,224 +4875,224 @@ "issue:46032" ], "soft_pairs": [ + "issue:43618|issue:43697", "issue:45183|issue:45479", "issue:43550|issue:45072", - "issue:43388|issue:46032", "issue:43295|issue:45834", "issue:43550|issue:43819", - "issue:43716|issue:44008", + "issue:43388|issue:46032", "issue:44062|issue:44488", + "issue:43716|issue:44008", "issue:43322|issue:45685", "issue:43335|issue:43756", "issue:44186|issue:44898", "issue:43653|issue:43819", - "issue:43950|issue:45987", "issue:43531|issue:43643", + "issue:43950|issue:45987", "issue:44843|issue:45081", "issue:43643|issue:44877", "issue:43540|issue:45381", - "issue:44448|issue:44671", "issue:30064|issue:36331", + "issue:44448|issue:44671", "issue:43421|issue:44811", + "issue:41720|issue:44991", "issue:43577|issue:43818", "issue:43782|issue:44977", - "issue:41720|issue:44991", "issue:39692|issue:45834", "issue:45584|issue:45834", "issue:44821|issue:45084", - "issue:44186|issue:44442", - "issue:43644|issue:43749" + "issue:44186|issue:44442" ], - "prepared_review_unit_hash": "00fc4dfb87215b40e11935b4ad638dadfed10602ef525b7e71134ad4a409b294", + "prepared_review_unit_hash": "622e4d1b4968df95fe761173a9cd5ee20abc46bbcf0f9191edb6b997ee9dbd50", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 27, - "serialized_chars": 36180, - "estimated_input_tokens": 9045, - "estimated_eval_tokens": 18346 + "serialized_chars": 36205, + "estimated_input_tokens": 9052, + "estimated_eval_tokens": 18360 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "All proposed soft edges are false positives: they span different models, subsystems, and failure modes rather than the same underlying bug or change. There is no clear canonical duplicate target in this set.", - "confidence": 0.92, - "canonical_issue_reason": "No single issue is a credible canonical representative; the items are a heterogeneous mix of unrelated tokenizer, multimodal, cache, loading, and dtype bugs.", + "summary": "This cluster is a loose mix of mostly unrelated transformer regressions and loading bugs. The soft links are mostly superficial (same tokenizer/processor/model-loading vocabulary) but the concrete failure paths, affected models, and code paths differ, so I would not merge any of them as duplicates.", + "confidence": 0.93, + "canonical_issue_reason": "Issue #44843 is the strongest representative to anchor this cluster because it has a concrete, reproducible tokenizer-loading regression with a clear root cause (`_patch_mistral_regex` / offline behavior) and broader relevance to the surrounding tokenizer/config loading reports.", "canonical_pr_reason": null, - "best_issue_reason": "No issue stands out as a global duplicate target for the cluster, because the cluster does not collapse to one concrete defect.", + "best_issue_reason": "Issue #44843 is the best single issue in the set because it is well-scoped, clearly described, and points to a specific code path that can be fixed and validated. The other issues are mostly separate bugs rather than duplicates of one another.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43618", + "right": "issue:43697", + "accept": false, + "reason": "Different bugs: CLIPOutput attentions assignment vs RTDetrV2 output drift in v5; separate models and code paths." + }, { "left": "issue:45183", "right": "issue:45479", "accept": false, - "reason": "Both involve validation/classification behavior, but one is input-argument XOR checking across models and the other is a zero-loss bug for num_labels=1; different defects." + "reason": "One is an input validation/XOR error, the other is a zero-loss classification bug with `num_labels=1`; not the same underlying issue." }, { "left": "issue:43550", "right": "issue:45072", "accept": false, - "reason": "Same general area of inference/runtime errors, but Bamba SDPA + torch.compile and dtype mismatches in SwitchTransformers/TimmWrapperModel are different code paths and failures." - }, - { - "left": "issue:43388", - "right": "issue:46032", - "accept": false, - "reason": "gather_for_metrics label truncation and Mamba2Mixer cache corruption are unrelated subsystems with different symptoms." + "reason": "Bamba `torch.compile`+SDPA failure and SwitchTransformers/TimmWrapper dtype mismatch are unrelated failures." }, { "left": "issue:43295", "right": "issue:45834", "accept": false, - "reason": "Processor.tokenizer regression and Kosmos2.5 long-OCR index error are different multimodal loading/processing bugs." + "reason": "Processor/tokenizer access regression vs Kosmos2.5 long-OCR index error; different models and failure modes." }, { "left": "issue:43550", "right": "issue:43819", "accept": false, - "reason": "Bamba torch.compile/SDPA failure and DAC.from_latents mismatch are unrelated model-specific bugs." + "reason": "Bamba compile/SDPA bug is unrelated to DAC `from_latents` vs forward mismatch." }, { - "left": "issue:43716", - "right": "issue:44008", + "left": "issue:43388", + "right": "issue:46032", "accept": false, - "reason": "Mistral-3 image preprocessor dtype mismatch is not the same as Gemma3n's variable-name collision in forward()." + "reason": "`gather_for_metrics` last-batch label truncation and Mamba2 cache corruption are distinct issues." }, { "left": "issue:44062", "right": "issue:44488", "accept": false, - "reason": "AddedToken special-argument duplication and a tokenizer load failure for cjvt/sleng-bert are distinct tokenizer issues." + "reason": "`AddedToken(special=...)` argument collision is a tokenizer API bug, while `sleng-bert` is a separate model-loading failure." + }, + { + "left": "issue:43716", + "right": "issue:44008", + "accept": false, + "reason": "BLIP/Mistral image-preprocessor dtype mismatch vs Gemma3n variable-name collision in forward; different root causes." }, { "left": "issue:43322", "right": "issue:45685", "accept": false, - "reason": "Llava Next loading segfault and MPS histogram on Int in moe are different failure modes in different paths." + "reason": "Llava Next load segfault and MPS histogram-on-Int error are unrelated model/runtime bugs." }, { "left": "issue:43335", "right": "issue:43756", "accept": false, - "reason": "SwitchTransformers sparse-layer construction and Smollm3 RoPE-layer dropping are different model/config bugs." + "reason": "SwitchTransformers sparse-layer config bug is not the same as Smollm3 RoPE-layer dropping." }, { "left": "issue:44186", "right": "issue:44898", "accept": false, - "reason": "LayoutLMv2Tokenizer NER/padding crash and Perceiver non-default-resolution failure are unrelated." + "reason": "LayoutLMv2 tokenizer crash on NER/padding and Perceiver interpolation failure are separate bugs." }, { "left": "issue:43653", "right": "issue:43819", "accept": false, - "reason": "BigBirdTokenizer special-token registration and DAC.from_latents/forward mismatch do not share a concrete code-path bug." + "reason": "BigBirdTokenizer special-token registration and DAC latent/forward mismatch do not share the same code path." }, { - "left": "issue:43950", - "right": "issue:45987", + "left": "issue:43531", + "right": "issue:43643", "accept": false, - "reason": "Non-persistent buffer corruption on from_pretrained and StaticCache.get_seq_length returning a tensor are separate regression classes." + "reason": "Qwen3-MoE sliding_window behavior and `trust_remote_code` config field loss are unrelated." }, { - "left": "issue:43531", - "right": "issue:43643", + "left": "issue:43950", + "right": "issue:45987", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior and trust_remote_code AutoConfig field loss are unrelated issues." + "reason": "Non-persistent buffer corruption on `from_pretrained` is different from `StaticCache.get_seq_length()` returning a tensor." }, { "left": "issue:44843", "right": "issue:45081", "accept": false, - "reason": "Both mention Mistral regex patching, but one breaks offline mode via model_info() and the other crashes on a backend_tokenizer attribute assumption; not the same bug." + "reason": "Both involve Mistral tokenizer patching, but one is an unconditional `model_info()` offline regression and the other is a missing `backend_tokenizer` attribute; not the same bug." }, { "left": "issue:43643", "right": "issue:44877", "accept": false, - "reason": "Missing config fields with trust_remote_code and strict config rejection for granite_speech are different config-loading problems." + "reason": "`trust_remote_code` missing fields and strict config blocking `granite_speech` are different configuration-loading problems." }, { "left": "issue:43540", "right": "issue:45381", "accept": false, - "reason": "Qwen3OmniMoe video processing ValueError and Qwen2.5-VL video vision_position_ids mismatch are different model-specific video bugs." + "reason": "Qwen3OmniMoe video-input ValueError and qwen2.5-vl video position-id bug affect different models and logic." }, { - "left": "issue:44448", - "right": "issue:44671", + "left": "issue:30064", + "right": "issue:36331", "accept": false, - "reason": "Pegasus v4/v5 output differences and CamemBERT MLM prediction errors are unrelated model behavior regressions." + "reason": "Image processor void-segmentation failure and `CustomTrainer.compute_loss()` signature mismatch are completely unrelated." }, { - "left": "issue:30064", - "right": "issue:36331", + "left": "issue:44448", + "right": "issue:44671", "accept": false, - "reason": "Image processor void-segmentation handling and CustomTrainer.compute_loss keyword-arg failure are unrelated." + "reason": "Pegasus v4/v5 output drift and CamemBERT masked-LM regression are separate model-specific bugs." }, { "left": "issue:43421", "right": "issue:44811", "accept": false, - "reason": "Runtime special-token post-processor updates and Whisper batch_decode skip_special_tokens handling are different layers and symptoms." + "reason": "Runtime post-processor updates for special tokens and Whisper `batch_decode()` ignoring `skip_special_tokens` are different tokenizer/processor issues." + }, + { + "left": "issue:41720", + "right": "issue:44991", + "accept": false, + "reason": "Qwen3 auto-device-map CUDA assert and tokenizer-loading failure for `est-roberta` are unrelated." }, { "left": "issue:43577", "right": "issue:43818", "accept": false, - "reason": "Blip2 dtype persistence and Video-LLaVA missing temporal attention/shared weights are unrelated defects." + "reason": "BLIP2 dtype propagation and Video-LLaVA temporal-attention/weight-sharing issues are distinct." }, { "left": "issue:43782", "right": "issue:44977", "accept": false, - "reason": "Qwen3VL weight_only loading failure and Qwen3.5 flash-attention generation bug are distinct model/runtime issues." - }, - { - "left": "issue:41720", - "right": "issue:44991", - "accept": false, - "reason": "A800 cudaErrorAssert under auto device mapping and tokenizer load failure for est-roberta have no shared underlying code path." + "reason": "Qwen3VL `weight_only=True` loading error and Qwen3.5 flash-attention generation failure are different concrete problems." }, { "left": "issue:39692", "right": "issue:45834", "accept": false, - "reason": "SigLIP2 docs example errors and Kosmos2.5 long OCR index error are unrelated." + "reason": "SigLIP2 documentation example errors are documentation/usage issues, not the same as Kosmos2.5 OCR index failure." }, { "left": "issue:45584", "right": "issue:45834", "accept": false, - "reason": "Whisper empty-transcription generation failure and Kosmos2.5 OCR indexing are different modalities and bugs." + "reason": "Whisper empty transcription after `align_special_tokens` and Kosmos2.5 OCR index error are unrelated." }, { "left": "issue:44821", "right": "issue:45084", "accept": false, - "reason": "AutoImageProcessor-from-URL loading and non-template-node compilation errors are unrelated." + "reason": "AutoImageProcessor URL loading and a template-node compile error do not share an underlying bug." }, { "left": "issue:44186", "right": "issue:44442", "accept": false, - "reason": "LayoutLMv2Tokenizer NER crash and AutoTokenizer loading FastSpeech2ConformerTokenizer are different tokenizer failures." - }, - { - "left": "issue:43644", - "right": "issue:43749", - "accept": false, - "reason": "Non-persistent buffer corruption and broken FSDP CPU RAM efficient loading are separate regressions." + "reason": "LayoutLMv2 tokenizer crash and AutoTokenizer failing to load FastSpeech2ConformerTokenizer are separate tokenizer bugs." } ] }, @@ -5167,7 +5114,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:28218", "issue:29159", @@ -5180,6 +5127,7 @@ "issue:43577", "issue:43582", "issue:43606", + "issue:43644", "issue:43650", "issue:43653", "issue:43697", @@ -5209,211 +5157,209 @@ "issue:45020", "issue:45072", "issue:45081", - "issue:45084", "issue:45325", "issue:45406", - "issue:45538", "issue:45701", "issue:45834", "issue:45987", "issue:46192" ], "soft_pairs": [ + "issue:43644|issue:43749", "issue:44561|issue:45020", "issue:43606|issue:45072", "issue:44479|issue:45834", "issue:43825|issue:43994", "issue:34634|issue:36010", "issue:43577|issue:43582", - "issue:45987|issue:46192", "issue:44805|issue:44936", + "issue:45987|issue:46192", "issue:44485|issue:44509", - "issue:43825|issue:43827", "issue:44671|issue:45701", + "issue:43825|issue:43827", "issue:28218|issue:29159", "issue:44610|issue:45072", - "issue:43782|issue:45325", "issue:43720|issue:45072", + "issue:43782|issue:45325", "issue:42175|issue:45081", "issue:43749|issue:44291", "issue:45081|issue:45406", "issue:43582|issue:44857", - "issue:43650|issue:43906", "issue:43262|issue:43819", + "issue:43650|issue:43906", "issue:43526|issue:43697", - "issue:44060|issue:44368", "issue:34634|issue:36331", + "issue:44060|issue:44368", "issue:43653|issue:44912", - "issue:43526|issue:44554", "issue:43742|issue:45020", - "issue:45084|issue:45538" + "issue:43526|issue:44554" ], - "prepared_review_unit_hash": "7b9d8ac8bfa88298c138081ecd3e815c3c6475ef469708c09451cb763070a4c7", + "prepared_review_unit_hash": "774763107c560c200136fac80cb8173d70108106852d730265213758465b7f0f", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { - "node_count": 48, - "item_count": 48, + "node_count": 47, + "item_count": 47, "soft_pair_count": 28, - "serialized_chars": 36305, - "estimated_input_tokens": 9077, - "estimated_eval_tokens": 18410 + "serialized_chars": 35776, + "estimated_input_tokens": 8944, + "estimated_eval_tokens": 18144 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This is a noisy grab-bag of unrelated Transformers issues across tokenization, processors, model loading, training, and docs. I don\u2019t see a single underlying bug/change that unifies the cluster, so there\u2019s no strong canonical item.", - "confidence": 0.96, - "canonical_issue_reason": null, + "summary": "Mostly unrelated issue cluster spanning many distinct regressions. The only strong duplicate candidate is the tokenizer added-token spacing vs slow/fast tokenizer inconsistency pair; the rest are separate model, loading, docs, or runtime bugs.", + "confidence": 0.58, + "canonical_issue_reason": "issue:28218 is the most specific and concrete report of the tokenizer added-token spacing regression, and it plausibly anchors the only true duplicate-style pair in the set.", "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "issue:28218 is the best global issue anchor because it is specific, symptom-focused, and the clearest duplicate target among the tokenizer-related items.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43644", + "right": "issue:43749", + "accept": false, + "reason": "Both concern loading/runtime behavior, but one is junk non-persistent buffers and the other is FSDP CPU RAM-efficient loading; different bugs and code paths." + }, { "left": "issue:44561", "right": "issue:45020", "accept": false, - "reason": "Both mention remote_code breakage, but one is a specific v5 removal of is_torch_fx_available and the other is a broad report about recent versions; not clearly the same concrete bug." + "reason": "Both mention remote_code breakage in v5, but they describe different failure modes and likely different underlying compatibility issues." }, { "left": "issue:43606", "right": "issue:45072", "accept": false, - "reason": "Both involve dtype/device mismatches, but they affect different models and code paths (CPU offload vs bfloat16 inference)." + "reason": "Different models and different mismatch classes (device offload vs dtype/bfloat16); too broad to be the same fix." }, { "left": "issue:44479", "right": "issue:45834", "accept": false, - "reason": "Different model families and failures: a video-input regression in Qwen VL models versus a long-OCR index error in Kosmos2.5." + "reason": "Separate model-specific input regressions: video input handling for Qwen VL variants versus OCR index errors in Kosmos2.5." }, { "left": "issue:43825", "right": "issue:43994", "accept": false, - "reason": "One is an error-message regression around removed translation tasks; the other is a bad AutoModel/pipeline result for SigLIP2. Different bugs." + "reason": "One is an error-message/docs issue about removed translation tasks; the other is a model output quality regression. Not the same bug." }, { "left": "issue:34634", "right": "issue:36010", "accept": false, - "reason": "Completely different failures: BarkProcessor voice_preset handling versus GenerationMixin import errors." + "reason": "BarkProcessor voice_preset failure and GenerationMixin import failure are unrelated." }, { "left": "issue:43577", "right": "issue:43582", "accept": false, - "reason": "Unrelated issues: BLIP2 dtype propagation versus an Apple Silicon allocator warmup TypeError." + "reason": "Blip2 dtype propagation and Apple Silicon caching allocator warmup TypeError are unrelated runtime problems." }, { - "left": "issue:45987", - "right": "issue:46192", + "left": "issue:44805", + "right": "issue:44936", "accept": false, - "reason": "Different API surfaces and symptoms; one is StaticCache seq-length return type, the other is text_kwargs/return_tensors handling." + "reason": "Mask/index shape mismatch in tensor ops versus trainer evaluate-after-train failure; no shared concrete code path." }, { - "left": "issue:44805", - "right": "issue:44936", + "left": "issue:45987", + "right": "issue:46192", "accept": false, - "reason": "A tensor mask shape mismatch is not the same bug as trainer.evaluate() failing after train()." + "reason": "StaticCache return type contract and text_kwargs/return_tensors handling are different API bugs." }, { "left": "issue:44485", "right": "issue:44509", "accept": false, - "reason": "RoPE implementation discussion is unrelated to docs still referencing removed pipeline tasks." + "reason": "One is a RoPE implementation discussion, the other is docs referencing removed pipeline tasks; different issues." }, { - "left": "issue:43825", - "right": "issue:43827", + "left": "issue:44671", + "right": "issue:45701", "accept": false, - "reason": "Both are about v5 pipeline removals, but one concerns runtime messaging and the other documentation; not the same concrete issue." + "reason": "CamemBERT masked-LM regression and a broad tokenization-version complaint are not the same underlying defect." }, { - "left": "issue:44671", - "right": "issue:45701", + "left": "issue:43825", + "right": "issue:43827", "accept": false, - "reason": "CamemBERT masked-LM regressions and version-dependent tokenization changes are too broad and not clearly the same bug." + "reason": "Both relate to v5 pipeline removals, but one is an error message and the other is docs drift; separate fixes." }, { "left": "issue:28218", "right": "issue:29159", - "accept": false, - "reason": "Both are tokenizer complaints, but the titles don\u2019t establish the same root cause; one is added-token spacing, the other slow/fast inconsistency." + "accept": true, + "reason": "Both describe the same tokenizer added-token spacing inconsistency, likely the same slow-vs-fast tokenizer bug." }, { "left": "issue:44610", "right": "issue:45072", "accept": false, - "reason": "Different models and failure modes: OmDet-Turbo processor size mismatch versus dtype mismatches in SwitchTransformers/TimmWrapperModel." + "reason": "OmDet-Turbo processor input-size mismatch and dtype mismatch in other models are unrelated." }, { - "left": "issue:43782", - "right": "issue:45325", + "left": "issue:43720", + "right": "issue:45072", "accept": false, - "reason": "One is a Qwen3VL weight_only load error, the other a Qwen2.5-VL rope-index scaling bug; different code paths and symptoms." + "reason": "BitNet packed-weight loading and dtype mismatch inference are different failure modes." }, { - "left": "issue:43720", - "right": "issue:45072", + "left": "issue:43782", + "right": "issue:45325", "accept": false, - "reason": "BitNet packed-weight loading is unrelated to bfloat16 dtype mismatch issues in other models." + "reason": "Different Qwen VL issues with different symptoms and likely different fixes." }, { "left": "issue:42175", "right": "issue:45081", "accept": false, - "reason": "Backend/package install configuration is unrelated to the Mistral tokenizer regex patch crash." + "reason": "Package/backend dependency omission is unrelated to a Mistral tokenizer regex crash." }, { "left": "issue:43749", "right": "issue:44291", "accept": false, - "reason": "Different loading mechanisms and failures: FSDP CPU RAM efficient loading versus init_empty_weights receiving an unexpected argument." + "reason": "FSDP CPU RAM-efficient loading and init_empty_weights/_is_hf_initialized are distinct loading bugs." }, { "left": "issue:45081", "right": "issue:45406", "accept": false, - "reason": "Tokenizer regex patching and Gemma4Processor missing _tokenizer are different loading/processor bugs." + "reason": "Tokenizer backend regex crash and Gemma4Processor missing _tokenizer are separate processor/tokenizer initialization problems." }, { "left": "issue:43582", "right": "issue:44857", "accept": false, - "reason": "AppleSilicon warmup TypeError is unrelated to a CUDA/AMP crash in LwDetrImageLoss." - }, - { - "left": "issue:43650", - "right": "issue:43906", - "accept": false, - "reason": "These titles are not about the same bug; one is nonspecific 'ADD THE DATA', the other is an isolated reproduction of another issue." + "reason": "Apple Silicon warmup TypeError and CUDA float16 loss crash are unrelated platform-specific bugs." }, { "left": "issue:43262", "right": "issue:43819", "accept": false, - "reason": "Audio chat-template sampling-rate defaults and DAC from_latents/STE mismatch are unrelated." + "reason": "Audio chat-template sampling-rate defaulting and DAC.from_latents STE mismatch are different subsystems and symptoms." }, { - "left": "issue:43526", - "right": "issue:43697", + "left": "issue:43650", + "right": "issue:43906", "accept": false, - "reason": "BeitImageProcessorFast reduce_labels behavior and RTDetrV2 output differences are different model-specific bugs." + "reason": "Placeholder issue text and an isolated reproduction of another bug are not duplicates." }, { - "left": "issue:44060", - "right": "issue:44368", + "left": "issue:43526", + "right": "issue:43697", "accept": false, - "reason": "Both mention Qwen3/Qwen3.5 warnings, but one is a tied-weights warning bug and the other is a separate lora fine-tuning warning; not the same issue." + "reason": "BeitImageProcessorFast reduce_labels and RTDetrV2 output drift are different model/data-processing bugs." }, { "left": "issue:34634", @@ -5422,35 +5368,38 @@ "reason": "BarkProcessor voice_preset and CustomTrainer.compute_loss signature mismatch are unrelated." }, { - "left": "issue:43653", - "right": "issue:44912", + "left": "issue:44060", + "right": "issue:44368", "accept": false, - "reason": "BigBirdTokenizer special-token decode failure is unrelated to MXFP4 quantization fallback." + "reason": "Both mention tied-weights warnings, but one is a Qwen3-Next incorrect tying bug and the other is a LoRA warning nuisance; not the same concrete issue." }, { - "left": "issue:43526", - "right": "issue:44554", + "left": "issue:43653", + "right": "issue:44912", "accept": false, - "reason": "A Beit image-processor label reduction bug is unrelated to an MPS attention correctness issue." + "reason": "BigBirdTokenizer special-token decoding and MXFP4 quantization fallback are unrelated." }, { "left": "issue:43742", "right": "issue:45020", "accept": false, - "reason": "Loading facebook/MobileLLM-125M key errors and remote_code breakages are different failure classes." + "reason": "KeyError on MobileLLM loading and broad remote_code breakage are not the same specific bug." }, { - "left": "issue:45084", - "right": "issue:45538", + "left": "issue:43526", + "right": "issue:44554", "accept": false, - "reason": "Template compilation errors are unrelated to CLIPTokenizer model_max_length handling." + "reason": "BeitImageProcessorFast label reduction and MPS attention correctness are unrelated." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "The analysis is grounded in the packet and stays conservative on the soft edges. The only accepted pair, issue:28218 vs issue:29159, is a plausible tokenizer duplicate based on the titles, and the rest are reasonably separated by symptom/code path. The summary does not overstate evidence." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -5465,7 +5414,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:29159", "issue:34567", @@ -5502,25 +5451,26 @@ "issue:44610", "issue:44756", "issue:44811", - "issue:44849", "issue:44912", "issue:44936", "issue:44977", "issue:44991", "issue:45042", + "issue:45084", "issue:45356", "issue:45459", + "issue:45538", "issue:45600", - "issue:45701", "issue:45759", "issue:45803", "issue:45859" ], "soft_pairs": [ + "issue:45084|issue:45538", "issue:43329|issue:45600", "issue:43746|issue:44811", - "issue:43452|issue:44991", "issue:44589|issue:45042", + "issue:43452|issue:44991", "issue:43638|issue:44936", "issue:43550|issue:44912", "issue:45459|issue:45803", @@ -5532,10 +5482,10 @@ "issue:38175|issue:44610", "issue:43720|issue:44610", "issue:36010|issue:36331", - "issue:43257|issue:43696", "issue:43454|issue:43577", - "issue:43262|issue:44811", "issue:43531|issue:45042", + "issue:43262|issue:44811", + "issue:43257|issue:43696", "issue:42490|issue:43257", "issue:43329|issue:44479", "issue:43643|issue:45759", @@ -5545,217 +5495,216 @@ "issue:34567|issue:40990", "issue:44568|issue:45356", "issue:43257|issue:43931", - "issue:29159|issue:34567", - "issue:44849|issue:45701" + "issue:29159|issue:34567" ], - "prepared_review_unit_hash": "cbe35caf3d26713b03d5195fcaf6eebe671272bba13e85f8bce8540dfde6dee1", + "prepared_review_unit_hash": "33c530de1100908d00b417d38048a713fe989b9bfcedc317d310b1cac34a0e9f", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 36943, - "estimated_input_tokens": 9236, - "estimated_eval_tokens": 18728 + "serialized_chars": 36933, + "estimated_input_tokens": 9234, + "estimated_eval_tokens": 18724 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is highly heterogeneous. The soft pairs mostly connect superficially similar Transformers issues across unrelated areas (tokenizers, loading, training, multimodal/video, offload, quantization), so none look like true duplicates.", - "confidence": 0.89, - "canonical_issue_reason": "issue:43329 is the most concrete, code-path-specific report in the densest soft-similarity pocket (multimodal/video token counting), so it is the best representative if a canonical must be chosen.", + "summary": "The cluster is highly heterogeneous: tokenizer, trainer, loading, multimodal, quantization, and model-specific bugs are all mixed together. None of the soft pairs look like the same underlying defect or change, so they should all remain separate.", + "confidence": 0.98, + "canonical_issue_reason": "Issue 43329 is the most concrete code-path bug report in the set and is broad enough to serve as an anchor if a single issue must be chosen, but the cluster itself is not a true duplicate set.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43329 is the clearest representative of the only semi-coherent subtheme, but the cluster overall is not a true duplicate set.", + "best_issue_reason": "Issue 43329 is the strongest standalone issue: it names a specific failing branch, concrete undefined variables, and a clear reproduction surface across multiple VLM processors.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:45084", + "right": "issue:45538", + "accept": false, + "reason": "Different problems: template compilation error vs tokenizer max_length configuration." + }, { "left": "issue:43329", "right": "issue:45600", "accept": false, - "reason": "Video token-counting undefined-variable bug vs removed config reference breaking CI; different subsystems and failure modes." + "reason": "Multimodal token counting bug vs stale auto_mappings reference; unrelated code paths." }, { "left": "issue:43746", "right": "issue:44811", "accept": false, - "reason": "PEFT adapter local-checkpoint loading vs Whisper batch_decode skip_special_tokens behavior; unrelated code paths." + "reason": "Local PEFT checkpoint loading vs Whisper batch_decode skip_special_tokens behavior." }, { - "left": "issue:43452", - "right": "issue:44991", + "left": "issue:44589", + "right": "issue:45042", "accept": false, - "reason": "gguf_file loader breakage vs tokenizer codec handling regression for a specific model; not the same bug." + "reason": "Storage lookup/type issue vs PIL backend dependency regression; not the same bug." }, { - "left": "issue:44589", - "right": "issue:45042", + "left": "issue:43452", + "right": "issue:44991", "accept": false, - "reason": "Float8 storage lookup error vs PIL backend unexpectedly requiring torchvision; distinct import/runtime issues." + "reason": "gguf_file loading breakage vs tokenizer loading failure for a specific model." }, { "left": "issue:43638", "right": "issue:44936", "accept": false, - "reason": "Deepspeed ZeRO-3 init index error vs trainer.evaluate failing after train; different trainer lifecycle bugs." + "reason": "DeepSpeed Zero3 index error vs trainer.evaluate() failure after train()." }, { "left": "issue:43550", "right": "issue:44912", "accept": false, - "reason": "torch.compile + SDPA failure on Bamba vs MXFP4 quantization fallback on gpt-oss; not the same concrete path." + "reason": "torch.compile/SDPA failure in Bamba vs MXFP4 quantization fallback in gpt-oss." }, { "left": "issue:45459", "right": "issue:45803", "accept": false, - "reason": "Tokenizer protobuf import-error masking vs bare except in FuyuBatchFeature conversion; both are error-handling issues, but not the same defect." + "reason": "Exception handling around protobuf decode vs bare except in Fuyu tensor conversion." }, { "left": "issue:43819", "right": "issue:43927", "accept": false, - "reason": "DAC latent reconstruction mismatch vs DiaConfig custom token IDs lost on save/load; different models and bug classes." + "reason": "DAC latent/from-forward mismatch vs DiaConfig save/load token ID loss." }, { "left": "issue:36010", "right": "issue:43645", "accept": false, - "reason": "GenerationMixin import regression vs custom-model initialization in Jupyter; unrelated initialization/import behavior." + "reason": "GenerationMixin import error vs Jupyter custom model initialization regression." }, { "left": "issue:43257", "right": "issue:43329", "accept": false, - "reason": "Qwen3-MoE loading/conversion with accelerate+deepspeed vs multimodal video token counting undefined variables; different failure points." + "reason": "Qwen3 MoE weight conversion/loading issue vs multimodal token counting video-branch bug." }, { "left": "issue:43854", "right": "issue:44977", "accept": false, - "reason": "Unit-test model loading for GLM-4.7 vs Qwen3.5 flash-attention generation bug; not the same underlying issue." + "reason": "Unit test load failure for GLM-4.7-Flash vs Qwen3.5 flash-attention generation bug." }, { "left": "issue:39692", "right": "issue:44912", "accept": false, - "reason": "SigLIP2 doc example/model-processor mismatch vs MXFP4 quantization fallback; one is documentation/examples, the other model loading/quantization." + "reason": "SigLIP2 docs example errors vs quantization fallback/loading issue; different surfaces." }, { "left": "issue:38175", "right": "issue:44610", "accept": false, - "reason": "Unexpected zero probabilities in SigLIP2 vs OmDet-Turbo processor image-size mismatch; different models and symptoms." + "reason": "Unexpected zero probabilities in SigLIP2 vs OmDet-Turbo processor/model input size mismatch." }, { "left": "issue:43720", "right": "issue:44610", "accept": false, - "reason": "BitNet packed-weight unpacking during accelerate load vs processor output-size mismatch; not the same code path." + "reason": "BitNet packed-weight unpacking during accelerate loading vs OmDet-Turbo shape/size mismatch." }, { "left": "issue:36010", "right": "issue:36331", "accept": false, - "reason": "GenerationMixin import failure vs CustomTrainer.compute_loss signature mismatch; unrelated trainer/import problems." + "reason": "ImportError for GenerationMixin vs custom trainer compute_loss signature mismatch." }, { - "left": "issue:43257", - "right": "issue:43696", + "left": "issue:43454", + "right": "issue:43577", "accept": false, - "reason": "Model weight conversion/load bug vs CUDA OOM on GPT-oss-20b; different root causes." + "reason": "AyaVision lm_head tying bug vs Blip2 dtype propagation problem." }, { - "left": "issue:43454", - "right": "issue:43577", + "left": "issue:43531", + "right": "issue:45042", "accept": false, - "reason": "lm_head weight tying bug vs dtype propagation issue in BLIP2; both model-loading bugs, but not the same defect." + "reason": "Qwen3-MoE sliding_window issue vs PIL image processor torchvision dependency regression." }, { "left": "issue:43262", "right": "issue:44811", "accept": false, - "reason": "Audio chat template sample-rate default bug vs Whisper batch_decode skip_special_tokens handling; separate processor APIs." + "reason": "Audio chat template sampling-rate default vs Whisper batch_decode special-token handling." }, { - "left": "issue:43531", - "right": "issue:45042", - "accept": false, - "reason": "Qwen3-MoE sliding_window behavior vs PIL backend torchvision dependency regression; unrelated areas." + "left": "issue:43257", + "right": "issue:43696", + "accept": false, + "reason": "MoE weight conversion/loading vs plain CUDA OOM on GPT-oss-20b." }, { "left": "issue:42490", "right": "issue:43257", "accept": false, - "reason": "Trailing-slash local-path import warning vs Qwen3-MoE accelerate/deepspeed load failure; not the same issue." + "reason": "Trailing-slash local path warning/loading issue vs Qwen3 MoE accelerate/deepspeed weight conversion." }, { "left": "issue:43329", "right": "issue:44479", "accept": false, - "reason": "Undefined multimodal video helper variables vs broad v5.3.0 video-input regression; overlapping topic, but not the same concrete bug." + "reason": "Undefined video token-counting branch variables vs v5.3.0 video input regression across Qwen VL models." }, { "left": "issue:43643", "right": "issue:45759", "accept": false, - "reason": "AutoConfig trust_remote_code missing fields vs AutoModelForCausalLM.from_config not unwrapping text_config; related config handling, but distinct." + "reason": "trust_remote_code config field loss vs from_config not unwrapping text_config in multimodal Qwen configs." }, { "left": "issue:43749", "right": "issue:44756", "accept": false, - "reason": "FSDP CPU RAM efficient loading regression vs Strix Halo mmap OOM mitigation; different memory-loading issues." + "reason": "FSDP CPU RAM efficient loading regression vs mmap/OOM issue on Strix Halo." }, { "left": "issue:43329", "right": "issue:43450", "accept": false, - "reason": "Undefined video-token helper names vs batched video processor shape error; both multimodal/video, but separate bugs." + "reason": "Video token counting bug vs batched video processor output shape bug; separate failures." }, { "left": "issue:43606", "right": "issue:45859", "accept": false, - "reason": "Bark CPU-offload device mismatch vs Qwen3-MoE rotary embedding CPU-offload incompatibility; same general theme, different models/code paths." + "reason": "CPU offload device mismatch in Bark vs Qwen3_5 MoE rotary embedding CPU-offload incompatibility." }, { "left": "issue:34567", "right": "issue:40990", "accept": false, - "reason": "TrainerState token counter not updating vs high perplexity on GPT-oss-20b; no concrete overlap." + "reason": "TrainerState token counter not updating vs extremely high perplexity on GPT-oss-20b." }, { "left": "issue:44568", "right": "issue:45356", "accept": false, - "reason": "Tokenizer add_special_tokens regression vs Kimi-K2.5 codec handling regression; both tokenizer issues, but different mechanics." + "reason": "add_special_tokens BOS/EOS regression vs Kimi-K2.5 tokenizer codec/warning regression." }, { "left": "issue:43257", "right": "issue:43931", "accept": false, - "reason": "Qwen3-MoE load/conversion issue vs Qwen3-VL-30B weight-shape mismatch; both model-loading problems, but not the same bug." + "reason": "Qwen3 MoE loading/conversion issue vs Qwen3-VL-30B-A3B weight shape mismatch." }, { "left": "issue:29159", "right": "issue:34567", "accept": false, - "reason": "Slow/fast tokenizer inconsistency vs TrainerState num_input_tokens_seen not updating; unrelated subsystems." - }, - { - "left": "issue:44849", - "right": "issue:45701", - "accept": false, - "reason": "Qwen3.5 hidden-states bug vs broad tokenization changes across versions; too generic and not the same defect." + "reason": "Tokenizer slow/fast inconsistency vs TrainerState num_input_tokens_seen not updating." } ] }, @@ -5777,7 +5726,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:24643", "issue:28282", @@ -5792,7 +5741,6 @@ "issue:42915", "issue:43257", "issue:43317", - "issue:43404", "issue:43452", "issue:43540", "issue:43577", @@ -5812,6 +5760,7 @@ "issue:44560", "issue:44568", "issue:44821", + "issue:44849", "issue:44898", "issue:44912", "issue:44987", @@ -5824,270 +5773,262 @@ "issue:45405", "issue:45488", "issue:45538", - "issue:45823", - "issue:45907", - "issue:45987" + "issue:45701", + "issue:45907" ], "soft_pairs": [ - "issue:44568|issue:45488", + "issue:44849|issue:45701", "issue:42915|issue:43742", "issue:44291|issue:45042", - "issue:43697|issue:45357", + "issue:44568|issue:45488", "issue:42915|issue:44821", "issue:41720|issue:43540", "issue:44987|issue:45538", - "issue:44479|issue:45381", + "issue:43697|issue:45357", "issue:43452|issue:43582", + "issue:44479|issue:45381", "issue:43927|issue:44912", "issue:42915|issue:45538", "issue:33357|issue:34567", "issue:43540|issue:44479", - "issue:43540|issue:44560", "issue:42175|issue:43824", + "issue:43540|issue:44560", "issue:43317|issue:45538", "issue:44987|issue:45907", "issue:44062|issue:44991", - "issue:43257|issue:43756", "issue:24643|issue:29159", "issue:45137|issue:45405", + "issue:43257|issue:43756", "issue:28282|issue:34689", "issue:43577|issue:45072", - "issue:42915|issue:43749", "issue:43742|issue:44291", - "issue:43906|issue:45381", "issue:42175|issue:44488", + "issue:42915|issue:43749", "issue:28282|issue:29127", "issue:38175|issue:44898", "issue:43582|issue:43782", - "issue:43404|issue:45987", - "issue:43540|issue:45823" + "issue:43906|issue:45381" ], - "prepared_review_unit_hash": "97a25fd0508cfd78976e09eccf492e73a38df24fdf91ed86433874c03a9df201", + "prepared_review_unit_hash": "b0a2169d4bbc8f35e2753d6cb879268338d312caa0d8fdf6fb2674303f1f777c", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 32, - "serialized_chars": 37373, - "estimated_input_tokens": 9344, - "estimated_eval_tokens": 18944 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "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 mostly heterogeneous issue reports spanning unrelated models and subsystems. I found one plausible duplicate pair around Qwen video-input regression; the rest look like separate bugs and should not be merged.", - "confidence": 0.78, - "canonical_issue_reason": "issue:44479 is the best canonical issue because it describes the broader video-input regression across multiple Qwen model variants, while the paired report is a narrower symptom/reproduction.", + "summary": "These items are mostly unrelated issues across different subsystems and models. Only one soft pair looks like the same underlying bug: the Qwen video-input regression around qwen2.5-vl/qwen3-vl position handling.", + "confidence": 0.82, + "canonical_issue_reason": "issue:45488 is the strongest canonical representative here: it has the most concrete tokenizer regression description, good discussion/inbound references, and a broad downstream impact on DeepSeek V3/R1 loading behavior.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44479 is the strongest representative of the only likely duplicate thread in the cluster and has the broadest, most actionable bug description.", + "best_issue_reason": "issue:45488 is the best single issue to anchor the set because it is specific enough to be actionable yet broad enough to represent the tokenizer regression theme better than the more generic or narrower alternatives.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44568", - "right": "issue:45488", + "left": "issue:44849", + "right": "issue:45701", "accept": false, - "reason": "Both are tokenizer regressions, but they affect different tokenizer code paths and different models; not the same underlying bug." + "reason": "Different problems: hidden-states output bug in Qwen3.5 vs a broad tokenization-change report." }, { "left": "issue:42915", "right": "issue:43742", "accept": false, - "reason": "Different failure modes and model-loading paths: FineGrainedFP8Config vs a key error for MobileLLM." + "reason": "Different models and failures: Qwen3Moe FP8 loading vs MobileLLM key error." }, { "left": "issue:44291", "right": "issue:45042", "accept": false, - "reason": "Unrelated subsystems: init_empty_weights loading bug vs PIL image processor torchvision dependency." + "reason": "Different code paths: init_empty_weights argument handling vs PIL image processor torchvision dependency." }, { - "left": "issue:43697", - "right": "issue:45357", + "left": "issue:44568", + "right": "issue:45488", "accept": false, - "reason": "Different bugs in different areas: RTDetrV2 output drift vs incorrect visual encoder keys on save_pretrained." + "reason": "Both tokenizer regressions, but on different tokenizers and mechanisms; not the same concrete bug." }, { "left": "issue:42915", "right": "issue:44821", "accept": false, - "reason": "These are unrelated model/config issues; no evidence they share the same code-path or root cause." + "reason": "Unrelated: FP8 model loading vs AutoImageProcessor URL loading." }, { "left": "issue:41720", "right": "issue:43540", "accept": false, - "reason": "Both mention Qwen and runtime failures, but one is auto device mapping CUDA assert and the other is video-input handling in Qwen3OmniMoe." + "reason": "Different subsystems: auto device mapping cuda assert vs video input parsing in Qwen3OmniMoe." }, { "left": "issue:44987", "right": "issue:45538", "accept": false, - "reason": "Different problems: one is a model load failure, the other is tokenizer max_length behavior." + "reason": "Different bugs: model load regression for a specific repo vs CLIPTokenizer max_length behavior." }, { - "left": "issue:44479", - "right": "issue:45381", - "accept": true, - "reason": "Same underlying Qwen video-input regression; 45381 appears to be a narrower reproduction of the broader v5.3.0 video-position bug described in 44479." + "left": "issue:43697", + "right": "issue:45357", + "accept": false, + "reason": "Different issues: RTDetrV2 output drift vs incorrect visual encoder keys on save_pretrained." }, { "left": "issue:43452", "right": "issue:43582", "accept": false, - "reason": "Unrelated: gguf_file tokenizer/model loading breakage vs an Apple Silicon allocator warmup TypeError." + "reason": "Unrelated: gguf_file tokenizer/model loading breakage vs Apple Silicon allocator TypeError." + }, + { + "left": "issue:44479", + "right": "issue:45381", + "accept": true, + "reason": "45381 is a concrete narrower instance of the same Qwen2.5-VL/Qwen3-VL video-input position regression described broadly in 44479." }, { "left": "issue:43927", "right": "issue:44912", "accept": false, - "reason": "Different issues: custom token IDs lost on save/load vs MXFP4 quantization fallback during model loading." + "reason": "Different bugs: DiaConfig save/load token IDs vs MXFP4 quantization falling back to bf16." }, { "left": "issue:42915", "right": "issue:45538", "accept": false, - "reason": "Completely different topics: FP8 config loading for Qwen3Moe vs CLIPTokenizer max_length handling." + "reason": "Different failure modes: Qwen3Moe FP8 loading vs CLIPTokenizer model_max_length behavior." }, { "left": "issue:33357", "right": "issue:34567", "accept": false, - "reason": "One is a MacOS bus error on CLIP model loading; the other is TrainerState token counting not updating." + "reason": "Unrelated: Mac bus error with CLIP model vs TrainerState token-count tracking." }, { "left": "issue:43540", "right": "issue:44479", "accept": false, - "reason": "Both are video-related, but they involve different Qwen model families and different failure modes; not the same bug." + "reason": "Both mention video inputs, but they involve different Qwen model families and likely different failures." }, { - "left": "issue:43540", - "right": "issue:44560", + "left": "issue:42175", + "right": "issue:43824", "accept": false, - "reason": "Same broad model family and video inputs, but the reported errors and likely code paths differ." + "reason": "Different problems: packaging backend contents vs missing import/export for Qwen2_5_VL class." }, { - "left": "issue:42175", - "right": "issue:43824", + "left": "issue:43540", + "right": "issue:44560", "accept": false, - "reason": "Both are import/backend availability problems, but one is TensorFlow packaging and the other is a missing Qwen class export." + "reason": "Different Qwen video bugs with different symptoms and model variants; not clearly the same underlying defect." }, { "left": "issue:43317", "right": "issue:45538", "accept": false, - "reason": "Different areas: device-map/offload dequantization failure vs tokenizer max_length behavior." + "reason": "Unrelated: dequantized model offload loading vs tokenizer max_length default." }, { "left": "issue:44987", "right": "issue:45907", "accept": false, - "reason": "Unrelated: model loading failure vs a helper function not forwarding the revision argument." + "reason": "Different scopes: model loading regression vs list_repo_files not forwarding revision." }, { "left": "issue:44062", "right": "issue:44991", "accept": false, - "reason": "Both concern tokenizers, but one is an AddedToken argument collision and the other is a specific model tokenizer load failure." - }, - { - "left": "issue:43257", - "right": "issue:43756", - "accept": false, - "reason": "Different Qwen3Moe loading/conversion issue vs a RoPE-layer configuration bug in Smollm3." + "reason": "Both tokenizer-related, but one is an AddedToken TypeError and the other is a model-specific tokenizer load failure." }, { "left": "issue:24643", "right": "issue:29159", "accept": false, - "reason": "No shared root cause: DeepSpeed training weight-shape error vs slow/fast tokenizer inconsistency." + "reason": "Unrelated: DeepSpeed training weight shape error vs tokenizer slow/fast inconsistency." }, { "left": "issue:45137", "right": "issue:45405", "accept": false, - "reason": "Totally unrelated: ZeRO3 deque underflow vs an unreleased PEFT version bump." + "reason": "Different bugs: ZeRO3 deque error vs PEFT version pin mismatch." + }, + { + "left": "issue:43257", + "right": "issue:43756", + "accept": false, + "reason": "Different model-specific loading/configuration issues with no clear shared code-path." }, { "left": "issue:28282", "right": "issue:34689", "accept": false, - "reason": "Different import/load errors for different models and environment states; not the same issue." + "reason": "Different failures: missing PyTorch dependency detection vs Llama 3.2 vision model loading regression." }, { "left": "issue:43577", "right": "issue:45072", "accept": false, - "reason": "Different dtype-related bugs affecting different model classes and code paths." - }, - { - "left": "issue:42915", - "right": "issue:43749", - "accept": false, - "reason": "Different topics: Qwen3Moe FP8 config failure vs FSDP CPU RAM efficient loading regression." + "reason": "Both are dtype-related, but they affect different models and inference paths." }, { "left": "issue:43742", "right": "issue:44291", "accept": false, - "reason": "Different mechanisms and subsystems; no evidence of a common underlying bug." + "reason": "Different issues: MobileLLM key error vs init_empty_weights argument mismatch." }, { - "left": "issue:43906", - "right": "issue:45381", + "left": "issue:42175", + "right": "issue:44488", "accept": false, - "reason": "The second is a Qwen video-position bug; the first is only an isolated reproduction reference and does not establish the same root cause." + "reason": "Unrelated: packaging/backends issue vs a specific model loading failure." }, { - "left": "issue:42175", - "right": "issue:44488", + "left": "issue:42915", + "right": "issue:43749", "accept": false, - "reason": "Packaging/backend installation issue vs a specific model-loading regression; not duplicates." + "reason": "Different topics: Qwen3Moe FP8 load failure vs FSDP CPU RAM efficient loading breakage." }, { "left": "issue:28282", "right": "issue:29127", "accept": false, - "reason": "Different bugs: missing PyTorch import vs a LayoutLMv3 box-content error message clarity issue." + "reason": "Unrelated: PyTorch import availability vs LayoutLMv3 error-message clarity." }, { "left": "issue:38175", "right": "issue:44898", "accept": false, - "reason": "Different models and behaviors: unexpected zero probabilities vs Perceiver non-default resolution failure." + "reason": "Different vision-model bugs affecting different architectures and failure modes." }, { "left": "issue:43582", "right": "issue:43782", "accept": false, - "reason": "Apple Silicon allocator warmup TypeError is unrelated to Qwen3VL weight_only loading failure." - }, - { - "left": "issue:43404", - "right": "issue:45987", - "accept": false, - "reason": "Different model families and different bugs: lm_head weight tying vs StaticCache sequence length return type." + "reason": "Unrelated: Apple Silicon allocator TypeError vs Qwen3VL weight_only load error." }, { - "left": "issue:43540", - "right": "issue:45823", + "left": "issue:43906", + "right": "issue:45381", "accept": false, - "reason": "Different device/runtime bugs in different models; not the same code-path problem." + "reason": "One is a reproduction of an older issue; the other is a Qwen2.5-VL video regression. No clear identity." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative. The only plausible duplicate pair supported by the titles is 44479/45381, and the rest of the soft-edge rejections are appropriately cautious given the available evidence. No overstatement stands out." + "feedback": "The summary is well grounded in the packet, and the only accepted soft pair (44479/45381) is plausibly the same Qwen video-position regression. The other pair verdicts stay conservative and do not overclaim shared bugs." }, "evaluator_used": true, "retried": false, @@ -6106,24 +6047,25 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:24643", "issue:29127", "issue:34567", "issue:36331", "issue:41762", + "issue:43404", "issue:43452", "issue:43493", "issue:43526", "issue:43531", + "issue:43540", "issue:43643", - "issue:43688", "issue:43697", "issue:43720", "issue:43742", - "issue:43749", "issue:43756", + "issue:43906", "issue:43994", "issue:44062", "issue:44291", @@ -6134,7 +6076,6 @@ "issue:44737", "issue:44792", "issue:44821", - "issue:44843", "issue:44877", "issue:44898", "issue:44913", @@ -6143,28 +6084,30 @@ "issue:45042", "issue:45081", "issue:45216", - "issue:45290", "issue:45325", "issue:45357", - "issue:45372", "issue:45375", "issue:45381", "issue:45405", "issue:45479", "issue:45588", "issue:45600", + "issue:45823", "issue:45920", + "issue:45987", "issue:46121", - "issue:46170" + "issue:46202" ], "soft_pairs": [ + "issue:43404|issue:45987", + "issue:43540|issue:45823", "issue:44737|issue:45588", "issue:43526|issue:45479", - "issue:43756|issue:45325", "issue:43493|issue:43994", + "issue:43756|issue:45325", "issue:34567|issue:36331", - "issue:44913|issue:46121", "issue:44291|issue:44821", + "issue:44913|issue:46121", "issue:44062|issue:45081", "issue:44792|issue:44964", "issue:45357|issue:45920", @@ -6172,203 +6115,194 @@ "issue:43452|issue:44488", "issue:43742|issue:44589", "issue:43643|issue:45375", - "issue:45405|issue:45600", "issue:43531|issue:44821", + "issue:45405|issue:45600", "issue:44625|issue:44877", + "issue:43906|issue:46202", "issue:43697|issue:45216", - "issue:43720|issue:44898", "issue:24643|issue:29127", + "issue:43720|issue:44898", "issue:44514|issue:45381", - "issue:45372|issue:46170", - "issue:41762|issue:44936", - "issue:43688|issue:43749", - "issue:43452|issue:44843", - "issue:44514|issue:45290" + "issue:41762|issue:44936" ], - "prepared_review_unit_hash": "ecd87d52674b92ce5117d09baf5021e8c7696e2b05a3d3a1c511fdb900195d75", + "prepared_review_unit_hash": "8314ad4d62f8dff8bb3a4652ed3e450176131603af3295ad2442a64e697c887d", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 26, - "serialized_chars": 36040, - "estimated_input_tokens": 9010, - "estimated_eval_tokens": 18276 + "soft_pair_count": 25, + "serialized_chars": 35640, + "estimated_input_tokens": 8910, + "estimated_eval_tokens": 18076 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is highly heterogeneous: the soft pairs mostly share only broad themes like loading, configs, or trainer behavior, but they point to different models/code paths and should not be merged as duplicates.", - "confidence": 0.94, - "canonical_issue_reason": null, + "summary": "This cluster is a set of mostly unrelated Transformers bugs and regressions spanning tokenization, model loading, config serialization, training APIs, and multimodal processors. Despite some surface-level similarity, none of the listed pairs look like the same underlying bug or change.", + "confidence": 0.96, + "canonical_issue_reason": "issue:45920 is the strongest representative: it is an open, broad regression affecting tokenization across multiple models, with clear user impact and multiple references.", "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "issue:45920 is the best overall issue candidate because it is broad, current, and actionable, and it likely subsumes the highest-value bug report in the set.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43404", + "right": "issue:45987", + "accept": false, + "reason": "Different subsystems: tied-weight loading bug in Mistral3 vs. a cache length return-type bug." + }, + { + "left": "issue:43540", + "right": "issue:45823", + "accept": false, + "reason": "Both are multimodal, but one is a video-input processing error in Qwen3OmniMoe and the other is a device placement mismatch in Gemma4 PLE." + }, { "left": "issue:44737", "right": "issue:45588", "accept": false, - "reason": "XLNet CPU placement bug vs. flash-attention sinkless-model AttributeError; unrelated subsystems and failure modes." + "reason": "XLNet CPU/device inefficiency is unrelated to a flash-attention crash on sink-less models." }, { "left": "issue:43526", "right": "issue:45479", "accept": false, - "reason": "BEiT fast processor label reduction bug vs. sequence-classification loss degeneracy; different APIs and code paths." + "reason": "Beit image label reduction bug is unrelated to the sequence-classification zero-loss issue across several models." }, { - "left": "issue:43756", - "right": "issue:45325", + "left": "issue:43493", + "right": "issue:43994", "accept": false, - "reason": "Smollm3 RoPE-layer truncation vs. Qwen2.5-VL position-id scaling; both are RoPE-related but for different models and bugs." + "reason": "Same model family, but one is a HF-vs-JAX implementation discrepancy and the other is bad AutoModel/pipeline outputs for a specific checkpoint." }, { - "left": "issue:43493", - "right": "issue:43994", + "left": "issue:43756", + "right": "issue:45325", "accept": false, - "reason": "Both are SigLIP2-related, but one is an HF-vs-JAX discrepancy and the other is a checkpoint/pipeline output issue; not clearly the same concrete bug." + "reason": "Both mention Qwen/rope behavior, but they describe different RoPE bugs in different models and code paths." }, { "left": "issue:34567", "right": "issue:36331", "accept": false, - "reason": "TrainerState token counting update bug vs. custom compute_loss signature break; different trainer internals." + "reason": "Trainer state token counter not updating is separate from a custom compute_loss signature breakage." }, { - "left": "issue:44913", - "right": "issue:46121", + "left": "issue:44291", + "right": "issue:44821", "accept": false, - "reason": "Config reload default reset vs. TypeError converting JSON-loaded rope ignore keys; distinct config handling problems." + "reason": "Unexpected model init argument during init_empty_weights is unrelated to loading AutoImageProcessor from a URL." }, { - "left": "issue:44291", - "right": "issue:44821", + "left": "issue:44913", + "right": "issue:46121", "accept": false, - "reason": "init_empty_weights/_is_hf_initialized loading bug vs. loading AutoImageProcessor from URL; unrelated failures." + "reason": "Config reload losing rotary_pct is a different bug from rope validation rejecting JSON-loaded lists." }, { "left": "issue:44062", "right": "issue:45081", "accept": false, - "reason": "AddedToken duplicate-special kwarg error vs. mistral regex/backend_tokenizer crash; both tokenizer-related but different code paths." + "reason": "Tokenizer AddedToken keyword collision is unrelated to the Mistral regex patch crash." }, { "left": "issue:44792", "right": "issue:44964", "accept": false, - "reason": "Janus image-generation test failure vs. Phi-4 multimodal load failure; different models and symptoms." + "reason": "Both involve model loading/testing failures, but they affect different models and failure modes." }, { "left": "issue:45357", "right": "issue:45920", "accept": false, - "reason": "Qwen3.5 save_pretrained key mismatch vs. AutoTokenizer wrong token IDs across many models; different bugs and components." + "reason": "Qwen3.5 save_pretrained serialization bug is distinct from the broader AutoTokenizer token-ID regression." }, { "left": "issue:45042", "right": "issue:45081", "accept": false, - "reason": "PIL backend torchvision dependency regression vs. mistral regex crash; no shared underlying fix." + "reason": "PIL backend torchvision dependency regression is unrelated to Mistral tokenizer regex handling." }, { "left": "issue:43452", "right": "issue:44488", "accept": false, - "reason": "gguf_file loader regression vs. specific sleng-bert loading failure; too broad and not same bug." + "reason": "Both are loading failures, but one is about gguf_file handling in AutoTokenizer/AutoModel and the other is a specific model load failure." }, { "left": "issue:43742", "right": "issue:44589", "accept": false, - "reason": "MobileLLM key lookup failure vs. Float8 storage lookup error; both are load-time issues but unrelated." + "reason": "MobileLLM key lookup failure and Float8 storage lookup failure are separate loading/runtime issues." }, { "left": "issue:43643", "right": "issue:45375", "accept": false, - "reason": "AutoConfig trust_remote_code field loss vs. Qwen3_5MoeVisionConfig strict-field drop; different mechanisms and models." + "reason": "AutoConfig missing fields with trust_remote_code is a different config-loading issue from strict-dropping a Qwen3_5MoeVisionConfig field." }, { - "left": "issue:45405", - "right": "issue:45600", + "left": "issue:43531", + "right": "issue:44821", "accept": false, - "reason": "Version pin mismatch vs. removed config references in auto_mappings; unrelated maintenance issues." + "reason": "Qwen3-MoE sliding_window behavior is unrelated to loading an image processor from a URL." }, { - "left": "issue:43531", - "right": "issue:44821", + "left": "issue:45405", + "right": "issue:45600", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior vs. AutoImageProcessor URL loading; no shared code path." + "reason": "Unreleased PEFT version bump is a dependency metadata issue, not the same as stale auto_mappings references breaking CI." }, { "left": "issue:44625", "right": "issue:44877", "accept": false, - "reason": "num_labels propagation bug in Qwen3.5 vs. strict config blocking granite_speech loading; different config surfaces." + "reason": "Qwen3.5 num_labels propagation bug is distinct from strict config blocking granite_speech loading." }, { - "left": "issue:43697", - "right": "issue:45216", + "left": "issue:43906", + "right": "issue:46202", "accept": false, - "reason": "RTDetrV2 output regression vs. Qwen3.5 save_pretrained regression; different model families and behavior." + "reason": "An isolated reproduction of another issue is not the same as the Gemma pipeline roundtrip failure." }, { - "left": "issue:43720", - "right": "issue:44898", + "left": "issue:43697", + "right": "issue:45216", "accept": false, - "reason": "BitNet packed-weight loading bug vs. Perceiver non-default-res interpolation failure; unrelated model-loading problems." + "reason": "RTDetrV2 output drift in v5 is unrelated to Qwen3.5 save_pretrained checkpoint corruption." }, { "left": "issue:24643", "right": "issue:29127", "accept": false, - "reason": "DeepSpeed training weight-shape runtime error vs. LayoutLMv3 error-message clarity issue; one is a bug, the other a UX/reporting issue." + "reason": "DeepSpeed training RuntimeError and LayoutLMv3 box-count error are completely different problems." }, { - "left": "issue:44514", - "right": "issue:45381", + "left": "issue:43720", + "right": "issue:44898", "accept": false, - "reason": "Qwen2.5-VL chat-template batch crash vs. Qwen2.5-VL video position-id bug; same family but different inputs and code paths." + "reason": "BitNet packed-weight loading failure is unrelated to Perceiver interpolation on non-default image sizes." }, { - "left": "issue:45372", - "right": "issue:46170", + "left": "issue:44514", + "right": "issue:45381", "accept": false, - "reason": "Gemma 4 processor import failure vs. Windows/ROCm torch.distributed dependency issue; unrelated platform/library problems." + "reason": "Both are Qwen2.5-VL-related, but one is processor chat-template batching and the other is video vision_position_ids scaling." }, { "left": "issue:41762", "right": "issue:44936", "accept": false, - "reason": "Gemma3 ZeRO-3 loading IndexError vs. trainer.evaluate after train; different stack traces and lifecycle stages." - }, - { - "left": "issue:43688", - "right": "issue:43749", - "accept": false, - "reason": "Aux-loss normalization bug vs. FSDP CPU RAM-efficient loading regression; different model/training subsystems." - }, - { - "left": "issue:43452", - "right": "issue:44843", - "accept": false, - "reason": "General gguf loading breakage vs. mistral_regex offline-model_info call; both loading-related but not the same issue." - }, - { - "left": "issue:44514", - "right": "issue:45290", - "accept": false, - "reason": "apply_chat_template batched-padding crash vs. tool-call/no-content assistant crash; both chat-template issues but distinct triggers and fixes." + "reason": "Gemma3 ZeRO-3 load failure is unrelated to trainer.evaluate() failing after trainer.train()." } ] }, @@ -6390,7 +6324,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:28282", "issue:29159", @@ -6403,14 +6337,11 @@ "issue:41720", "issue:43295", "issue:43452", - "issue:43531", - "issue:43550", "issue:43577", "issue:43646", "issue:43653", "issue:43688", "issue:43697", - "issue:43742", "issue:43749", "issue:43819", "issue:43906", @@ -6421,16 +6352,18 @@ "issue:44466", "issue:44484", "issue:44493", + "issue:44514", "issue:44568", "issue:44704", "issue:44743", "issue:44811", "issue:44843", "issue:44936", - "issue:44977", "issue:44991", "issue:45005", + "issue:45290", "issue:45356", + "issue:45372", "issue:45440", "issue:45491", "issue:45542", @@ -6439,248 +6372,256 @@ "issue:45823", "issue:46002", "issue:46050", + "issue:46170", "issue:46178" ], "soft_pairs": [ - "issue:44466|issue:45005", + "issue:45372|issue:46170", + "issue:43688|issue:43749", "issue:45542|issue:46178", + "issue:43452|issue:44843", + "issue:44466|issue:45005", "issue:43452|issue:43577", "issue:44493|issue:46050", "issue:43819|issue:44811", - "issue:30064|issue:33666", + "issue:44514|issue:45290", "issue:44936|issue:45823", + "issue:30064|issue:33666", "issue:43295|issue:45356", "issue:44484|issue:44704", - "issue:43653|issue:44361", "issue:28282|issue:32090", + "issue:43653|issue:44361", "issue:44361|issue:44442", - "issue:41720|issue:43906", "issue:28282|issue:33357", "issue:44464|issue:44743", "issue:38175|issue:43295", "issue:28282|issue:35141", + "issue:41720|issue:43906", "issue:45491|issue:46002", "issue:43653|issue:44568", "issue:43577|issue:43697", "issue:43688|issue:45704", "issue:44843|issue:44991", - "issue:43688|issue:45440", "issue:43646|issue:43749", + "issue:43688|issue:45440", "issue:29159|issue:33357", "issue:43688|issue:45701", - "issue:43653|issue:43927", - "issue:43531|issue:43742", - "issue:44464|issue:44977", - "issue:43550|issue:43927" + "issue:43653|issue:43927" ], - "prepared_review_unit_hash": "81a19ac26b882e5ca85bd7b3a7bf754cd53b3116800a85c2ca28687eda58d247", + "prepared_review_unit_hash": "1d781ad054998710fb69225f2303ede736533f692f0d60c1ca6240ff87302dbc", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 30, - "serialized_chars": 36719, - "estimated_input_tokens": 9180, - "estimated_eval_tokens": 18616 + "soft_pair_count": 31, + "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 set is highly heterogeneous: it mixes unrelated tokenizer regressions, generation bugs, training errors, backend/config issues, and model-loading problems. I do not see any convincing duplicate pairs; most similarities are only at the subsystem level. Issue 45701 is the broadest umbrella-style issue in the set, but the cluster does not read like one single bug family.", - "confidence": 0.84, - "canonical_issue_reason": "Issue 45701 is the most umbrella-like and currently open item; it best matches the broad version-dependent tokenization regression theme that appears in a few nearby issues.", + "summary": "This cluster is mostly heterogeneous: tokenizer loading/serialization regressions, training/device-map bugs, model-specific numerical issues, and backend/dependency errors. I don\u2019t see any soft pair that is clearly the same underlying bug/change.", + "confidence": 0.78, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Issue 45701 is the best anchor for triage because it is broad, active, and representative of the only recurring theme that shows up across multiple items (tokenization behavior changing across versions).", + "best_issue_reason": "Issue 45701 is the broadest open report and has the most inbound references, so it is the closest thing to an umbrella issue here, but the cluster is too mixed for a true duplicate canonical.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44466", - "right": "issue:45005", + "left": "issue:45372", + "right": "issue:46170", + "accept": false, + "reason": "Both are import/dependency failures, but they stem from different packages and code paths (mistral_common ReasoningEffort vs torch.distributed on Windows/ROCm)." + }, + { + "left": "issue:43688", + "right": "issue:43749", "accept": false, - "reason": "Both mention tied weights, but one is a concrete serialization/device-dependent lm_head.weight issue while the other is a broader translation-model v5 regression." + "reason": "Aux-loss normalization and FSDP CPU RAM efficient loading are unrelated bugs in different subsystems." }, { "left": "issue:45542", "right": "issue:46178", "accept": false, - "reason": "Both are backend/TensorFlow related, but the failure modes differ: missing TensorFlow with tensorboard vs tensorflow_text not being in BACKENDS_MAPPING." + "reason": "These are both backend-related, but one is a TensorBoard/TensorFlow availability issue and the other is a tensorflow_text backend mapping error." + }, + { + "left": "issue:43452", + "right": "issue:44843", + "accept": false, + "reason": "Both involve loading paths, but gguf_file breakage and the unconditional model_info() call in _patch_mistral_regex are different failures." + }, + { + "left": "issue:44466", + "right": "issue:45005", + "accept": false, + "reason": "Both mention tied weights, but one is device-dependent lm_head serialization and the other is a broader translation-model tied-weights report without the same concrete code path." }, { "left": "issue:43452", "right": "issue:43577", "accept": false, - "reason": "Different subsystems: gguf tokenizer/model loading vs BLIP2 dtype propagation for qformer/model." + "reason": "GGUF loading breakage and BLIP2 dtype staying float32 are unrelated." }, { "left": "issue:44493", "right": "issue:46050", "accept": false, - "reason": "Different bugs: unexpected position-id key handling versus quantized model save/load corruption after sinq." + "reason": "Unexpected position-id keys and NaNs in classification heads are different symptoms with no shared bug mechanism." }, { "left": "issue:43819", "right": "issue:44811", "accept": false, - "reason": "DAC latent conversion with missing STE is unrelated to Whisper batch_decode ignoring skip_special_tokens." + "reason": "DAC.from_latents mismatch and Whisper batch_decode skip_special_tokens handling are unrelated processor/model behaviors." }, { - "left": "issue:30064", - "right": "issue:33666", + "left": "issue:44514", + "right": "issue:45290", "accept": false, - "reason": "Image segmentation map processing and Qwen2-VL multi-GPU training are unrelated." + "reason": "Both hit apply_chat_template, but the triggering conditions differ: batched padding=False vs assistant tool-call messages with no content." }, { "left": "issue:44936", "right": "issue:45823", "accept": false, - "reason": "Trainer.evaluate() after train() is a training-loop bug, not the Gemma4 device-mismatch forward issue." + "reason": "trainer.evaluate() after train and Gemma4 PLE device mismatch under auto device_map are different bugs." + }, + { + "left": "issue:30064", + "right": "issue:33666", + "accept": false, + "reason": "Image segmentation-map processing and Qwen2-VL multi-GPU training are unrelated." }, { "left": "issue:43295", "right": "issue:45356", "accept": false, - "reason": "Both are tokenizer/processor regressions, but one is processor.tokenizer/images passthrough and the other is Kimi codec/fix_mistral_regex behavior." + "reason": "These are different tokenizer/processor regressions affecting different models and code paths." }, { "left": "issue:44484", "right": "issue:44704", "accept": false, - "reason": "Max shard size default sizing and AutoProcessor kwargs forwarding are unrelated." - }, - { - "left": "issue:43653", - "right": "issue:44361", - "accept": false, - "reason": "Both are tokenizer issues, but the concrete failures differ: BigBird special-token decode vs MLukeTokenizer AttributeError." + "reason": "A save_pretrained shard-size question and an AutoProcessor kwargs-passing bug are not the same issue." }, { "left": "issue:28282", "right": "issue:32090", "accept": false, - "reason": "Missing PyTorch import error and Trainer _gpu_broadcast_one NoneType error are unrelated." + "reason": "Missing PyTorch for AutoModel and a Trainer _gpu_broadcast_one NoneType TypeError are unrelated." }, { - "left": "issue:44361", - "right": "issue:44442", + "left": "issue:43653", + "right": "issue:44361", "accept": false, - "reason": "Both concern tokenizers, but they hit different tokenizer classes with different loading/runtime failures." + "reason": "Two tokenizer bugs, but on different tokenizers and different failure modes." }, { - "left": "issue:41720", - "right": "issue:43906", + "left": "issue:44361", + "right": "issue:44442", "accept": false, - "reason": "Qwen3 auto device-map cudaErrorAssert is not the same as the separate isolated reproduction of issue 38071." + "reason": "MLukeTokenizer AttributeError and AutoTokenizer failing to load FastSpeech2ConformerTokenizer are separate loading/tokenization issues." }, { "left": "issue:28282", "right": "issue:33357", "accept": false, - "reason": "PyTorch import failure and MacOS bus error with a CLIP model are unrelated." + "reason": "Missing PyTorch import and a MacOS bus error on a CLIP model do not share a concrete root cause." }, { "left": "issue:44464", "right": "issue:44743", "accept": false, - "reason": "Both involve generation/caching, but chunked generation with compiled forward is a different code path from recurrent-state reset with seq_len>1." + "reason": "Both concern generation/cache behavior, but chunked generation with compiled forward and Qwen3 recurrent-state resets are different code paths and models." }, { "left": "issue:38175", "right": "issue:43295", "accept": false, - "reason": "Siglip2 zero probabilities are unrelated to the processor.tokenizer regression." + "reason": "Unexpected zero probabilities in SigLIP2 is unrelated to processor.tokenizer regressions in custom model code." }, { "left": "issue:28282", "right": "issue:35141", "accept": false, - "reason": "ImportError for missing PyTorch is unrelated to post_init reinitializing output embeddings after resize." + "reason": "A missing PyTorch import error is unrelated to embedding reinitialization in post_init." }, { - "left": "issue:45491", - "right": "issue:46002", + "left": "issue:41720", + "right": "issue:43906", + "accept": false, + "reason": "Qwen3 auto device mapping cudaErrorAssert and an isolated reproduction of another issue are not enough to establish the same bug." + }, + { + "left": "issue:45491", + "right": "issue:46002", "accept": false, - "reason": "Both mention NaNs, but one is mixed-length sliding-window attention on Gemma3 and the other is classification-head NaNs after checkout/init." + "reason": "Both mention NaNs, but one is a Gemma3 sliding-window attention problem and the other is a classification-head init/checkpoint issue." }, { "left": "issue:43653", "right": "issue:44568", "accept": false, - "reason": "Both are special-token/tokenizer issues, but they are different models and different behaviors (mask token registration vs BOS/EOS insertion)." + "reason": "Both are tokenizer special-token regressions, but they affect different tokenizers and likely different code paths." }, { "left": "issue:43577", "right": "issue:43697", "accept": false, - "reason": "Dtype staying float32 in BLIP2 is unrelated to RTDetrV2 output divergence in v5." + "reason": "A dtype-loading bug in BLIP2 and an RTDetrV2 output divergence are unrelated." }, { "left": "issue:43688", "right": "issue:45704", "accept": false, - "reason": "Auxiliary-loss normalization in MoE models is unrelated to T5 silently using apex FusedRMSNorm and leaking memory." + "reason": "Aux-loss normalization and a T5/apex RMSNorm memory leak are different problems." }, { "left": "issue:44843", "right": "issue:44991", "accept": false, - "reason": "Both are tokenizer-loading regressions, but one is an offline model_info call bug and the other is a specific tokenizer load failure for est-roberta." + "reason": "Both are tokenizer-loading regressions, but one is offline model_info() behavior in _patch_mistral_regex and the other is a tokenizer load failure for EMBEDDIA/est-roberta." }, { - "left": "issue:43688", - "right": "issue:45440", + "left": "issue:43646", + "right": "issue:43749", "accept": false, - "reason": "Both touch MoE models, but auxiliary-loss normalization and DeepseekV3MoE divergence are not the same concrete bug." + "reason": "Custom model initialization breakage in v5 and FSDP CPU RAM efficient loading are unrelated." }, { - "left": "issue:43646", - "right": "issue:43749", + "left": "issue:43688", + "right": "issue:45440", "accept": false, - "reason": "Custom model initialization breakage and FSDP CPU RAM efficient loading are different failure modes." + "reason": "Aux-loss normalization and DeepseekV3MoE divergence from remote implementation are different bugs." }, { "left": "issue:29159", "right": "issue:33357", "accept": false, - "reason": "Slow/fast tokenizer inconsistency is unrelated to the MacOS bus error report." + "reason": "Slow/fast tokenizer inconsistency and a MacOS CLIP bus error do not appear to share the same underlying defect." }, { "left": "issue:43688", "right": "issue:45701", "accept": false, - "reason": "MoE auxiliary-loss normalization is unrelated to version-dependent tokenization behavior." + "reason": "Aux-loss normalization and a generic tokenization-change report are unrelated." }, { "left": "issue:43653", "right": "issue:43927", "accept": false, - "reason": "BigBird special-token decode and DiaConfig losing custom token IDs after save/load are different tokenizer/config bugs." - }, - { - "left": "issue:43531", - "right": "issue:43742", - "accept": false, - "reason": "Qwen3-MoE sliding_window behavior and MobileLLM-125M loading key error are unrelated." - }, - { - "left": "issue:44464", - "right": "issue:44977", - "accept": false, - "reason": "Both mention generation, but compiled-forward chunked generation and flash-attention failure on Qwen3.5 are different code-path problems." - }, - { - "left": "issue:43550", - "right": "issue:43927", - "accept": false, - "reason": "torch.compile+SDPA failure in Bamba and DiaConfig custom token ID loss are unrelated." + "reason": "BigBirdTokenizer special-token registration and DiaConfig losing custom token IDs after save/load are different config/tokenizer persistence bugs." } ] }, @@ -6702,7 +6643,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:28218", "issue:32090", @@ -6712,7 +6653,6 @@ "issue:36010", "issue:36331", "issue:41720", - "issue:43122", "issue:43262", "issue:43278", "issue:43295", @@ -6720,6 +6660,7 @@ "issue:43493", "issue:43504", "issue:43525", + "issue:43531", "issue:43550", "issue:43572", "issue:43577", @@ -6730,7 +6671,6 @@ "issue:43742", "issue:43756", "issue:43825", - "issue:43906", "issue:43927", "issue:43994", "issue:44361", @@ -6745,6 +6685,7 @@ "issue:44821", "issue:44849", "issue:44913", + "issue:44977", "issue:45357", "issue:45588", "issue:45823", @@ -6753,14 +6694,16 @@ "issue:46192" ], "soft_pairs": [ + "issue:43531|issue:43742", + "issue:44464|issue:44977", + "issue:43550|issue:43927", "issue:43643|issue:44561", "issue:44479|issue:44625", "issue:43550|issue:44361", "issue:41720|issue:44464", - "issue:43122|issue:43906", - "issue:43577|issue:44554", "issue:43577|issue:45588", "issue:32090|issue:34567", + "issue:43577|issue:44554", "issue:43504|issue:43550", "issue:43504|issue:43720", "issue:43504|issue:44610", @@ -6772,236 +6715,245 @@ "issue:43452|issue:44451", "issue:43720|issue:43927", "issue:43606|issue:43927", - "issue:43278|issue:43688", - "issue:43994|issue:46192", "issue:43262|issue:43295", + "issue:43994|issue:46192", + "issue:43278|issue:43688", "issue:43525|issue:43572", - "issue:44625|issue:46002", "issue:33666|issue:36331", + "issue:44625|issue:46002", "issue:43720|issue:44361", - "issue:43756|issue:44913", "issue:44849|issue:45357", + "issue:43756|issue:44913", "issue:43493|issue:43825", "issue:28218|issue:33357" ], - "prepared_review_unit_hash": "a361b2d36e60a78c7ce317badf55be84e18c6bf988ca247fcac96a93d046b106", + "prepared_review_unit_hash": "f064ea31720a4900e0f617599bd957da9363f6a9a817310a90578e1cae8436f9", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 47, "item_count": 47, - "soft_pair_count": 30, - "serialized_chars": 36168, - "estimated_input_tokens": 9042, - "estimated_eval_tokens": 18340 + "soft_pair_count": 32, + "serialized_chars": 36710, + "estimated_input_tokens": 9178, + "estimated_eval_tokens": 18612 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is mostly heterogeneous with many unrelated bug reports. The only credible duplicate-style overlap is the pair about v5 config losing pad-token fields on reload; the rest are distinct code paths and should stay separate.", - "confidence": 0.8, - "canonical_issue_reason": "issue:43525 is the clearest representative of the pad-token config regression, with the most generic title and a direct match to the shared underlying load/reload bug.", + "summary": "This cluster is very noisy: the issues span unrelated bugs across tokenization, training, loading, generation, config serialization, and model-specific regressions. The soft links mostly reflect superficial theme overlap rather than the same underlying defect, so I would not merge any pair.", + "confidence": 0.23, + "canonical_issue_reason": "issue:43927 is the closest hub in the noisy save/load/config-regression subgroup, but it still is not a true duplicate representative of the whole set.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43525 best captures the recurring config-field-loss problem and is the strongest anchor for the one accepted duplicate pair.", + "best_issue_reason": "issue:43927 is the best single representative only because it has the strongest soft connectivity among the mostly unrelated issues; it still does not justify duplicate clustering.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43531", + "right": "issue:43742", + "accept": false, + "reason": "Different problems: Qwen3-MoE sliding-window behavior vs a MobileLLM load key error." + }, + { + "left": "issue:44464", + "right": "issue:44977", + "accept": false, + "reason": "Both concern generation, but one is compiled chunked decoding and the other is flash-attention on Qwen3.5; different code paths and symptoms." + }, + { + "left": "issue:43550", + "right": "issue:43927", + "accept": false, + "reason": "Torch.compile/SDPA failure in Bamba-9B-v2 is unrelated to DiaConfig losing custom token IDs on save/load." + }, { "left": "issue:43643", "right": "issue:44561", "accept": false, - "reason": "Both involve trust_remote_code/v5 breakage, but they describe different root causes: missing config fields vs removal of a helper used by remote-code models." + "reason": "Both mention trust_remote_code, but one is missing fields from AutoConfig and the other is removal of is_torch_fx_available breaking remote-code models." }, { "left": "issue:44479", "right": "issue:44625", "accept": false, - "reason": "Video-input regression and num_labels propagation are unrelated model bugs." + "reason": "Video-input regression for Qwen VL models vs num_labels propagation bug; not the same defect." }, { "left": "issue:43550", "right": "issue:44361", "accept": false, - "reason": "Different subsystems and failures: SDPA/torch.compile on Bamba vs tokenizer AttributeError on tasks." + "reason": "Bamba torch.compile/SDPA issue is unrelated to MLukeTokenizer task AttributeError." }, { "left": "issue:41720", "right": "issue:44464", "accept": false, - "reason": "Qwen3 auto device mapping cuda assert and chunked generation compiled-forward inconsistency are separate issues." - }, - { - "left": "issue:43122", - "right": "issue:43906", - "accept": false, - "reason": "Tokenization-version change and an isolated reproduction of an older issue are not enough to show the same underlying bug." - }, - { - "left": "issue:43577", - "right": "issue:44554", - "accept": false, - "reason": "Different problems: dtype handling in BLIP2 loading vs an MPS attention correctness issue." + "reason": "CUDA assert under auto device mapping for Qwen3 is not the same as inconsistent outputs in compiled chunked generation." }, { "left": "issue:43577", "right": "issue:45588", "accept": false, - "reason": "BLIP2 dtype mismatch and flash_attention s_aux=None crash are unrelated." + "reason": "Model dtype-loading bug for Blip2 is unrelated to flash_attention crashing on s_aux=None." }, { "left": "issue:32090", "right": "issue:34567", "accept": false, - "reason": "Trainer broadcast NoneType error and num_input_tokens_seen not updating are distinct trainer bugs." + "reason": "Both are Trainer-related, but one is a GPU broadcast TypeError and the other is a token-counting state update bug." + }, + { + "left": "issue:43577", + "right": "issue:44554", + "accept": false, + "reason": "Different subsystems: Blip2 dtype handling vs MPS attention correctness with mismatched head dims." }, { "left": "issue:43504", "right": "issue:43550", "accept": false, - "reason": "Legacy-field model loading failure vs torch.compile SDPA failure are different code paths." + "reason": "Legacy-field pretrained loading bug is unrelated to Bamba torch.compile/SDPA failure." }, { "left": "issue:43504", "right": "issue:43720", "accept": false, - "reason": "Both are loading-related, but one is a legacy preset field issue and the other is about unpacking packed weights during accelerate loading." + "reason": "Both involve loading, but one is a legacy preset field and the other is packed-weight unpacking during accelerate loading; different bugs." }, { "left": "issue:43504", "right": "issue:44610", "accept": false, - "reason": "Different model families and failures: legacy preset loading vs processor size mismatch." + "reason": "Model preset loading bug is unrelated to OmDet-Turbo processor producing the wrong image size." }, { "left": "issue:44466", "right": "issue:46050", "accept": false, - "reason": "Both mention save/load behavior, but one is lm_head serialization inconsistency and the other is quantized sinq model restore breakage." + "reason": "Both touch save/load behavior, but one is tied-weight serialization by device and the other is quantized sinq checkpoint restoration." }, { "left": "issue:32090", "right": "issue:33666", "accept": false, - "reason": "Trainer GPU broadcast failure and Qwen2-VL multi-GPU training are not the same bug." + "reason": "Trainer broadcast failure is unrelated to Qwen2-VL multi-GPU training support." }, { "left": "issue:33666", "right": "issue:36010", "accept": false, - "reason": "Multi-GPU training and GenerationMixin import failure are unrelated." + "reason": "Multi-GPU training request vs GenerationMixin import error; unrelated issues." }, { "left": "issue:43742", "right": "issue:44821", "accept": false, - "reason": "KeyError loading one model and inability to load AutoImageProcessor from URL are different loading issues." + "reason": "MobileLLM checkpoint key error is unrelated to AutoImageProcessor URL loading." }, { "left": "issue:45823", "right": "issue:46050", "accept": false, - "reason": "Device-map forward mismatch and sinq save/load breakage are unrelated." + "reason": "Device-mismatch forward bug in Gemma4 PLE is unrelated to sinq save/load corruption." }, { "left": "issue:43452", "right": "issue:44451", "accept": false, - "reason": "Generic tokenizer/model loading failure and inability to load a specific model are too broad to treat as the same bug." + "reason": "gguf_file from_pretrained breakage and ScandiBERT loading failure are separate loading problems with different causes." }, { "left": "issue:43720", "right": "issue:43927", "accept": false, - "reason": "Packed-weight loading and DiaConfig token-id loss are different serialization problems." + "reason": "Packed-weight unpacking during accelerate loading is not the same as DiaConfig custom token ID persistence." }, { "left": "issue:43606", "right": "issue:43927", "accept": false, - "reason": "CPU offload device mismatch and config token-id loss are unrelated." + "reason": "CPU-offload device mismatch in bark-small is unrelated to config token ID loss." }, { - "left": "issue:43278", - "right": "issue:43688", + "left": "issue:43262", + "right": "issue:43295", "accept": false, - "reason": "Embedding dtype drift in evaluate and auxiliary-loss normalization are separate issues." + "reason": "Audio chat-template sampling-rate default bug is unrelated to processor.tokenizer / image-passing regression." }, { "left": "issue:43994", "right": "issue:46192", "accept": false, - "reason": "SigLIP2 output problems and return_tensors being ignored are unrelated API bugs." + "reason": "SigLIP2 nonsensical outputs and return_tensors being ignored are different API bugs." }, { - "left": "issue:43262", - "right": "issue:43295", + "left": "issue:43278", + "right": "issue:43688", "accept": false, - "reason": "Audio processor sampling-rate defaulting and processor/tokenizer image-handling regression are different behaviors." + "reason": "Embedding dtype drift in evaluation is unrelated to auxiliary-loss normalization in OLMoE/GPT Oss." }, { "left": "issue:43525", "right": "issue:43572", - "accept": true, - "reason": "Both report v5 config reload losing pad-token fields; they appear to be the same underlying config-propagation regression with different field names/model classes." - }, - { - "left": "issue:44625", - "right": "issue:46002", "accept": false, - "reason": "num_labels propagation and NaNs in classification heads are not the same defect." + "reason": "Similar symptom class, but different models and fields; not enough evidence of the same underlying bug." }, { "left": "issue:33666", "right": "issue:36331", "accept": false, - "reason": "Multi-GPU training and custom compute_loss signature mismatch are unrelated trainer issues." + "reason": "Multi-GPU training request vs custom compute_loss kwarg incompatibility are unrelated." }, { - "left": "issue:43720", - "right": "issue:44361", + "left": "issue:44625", + "right": "issue:46002", "accept": false, - "reason": "Packed-weight loading and MLukeTokenizer task AttributeError are different failures." + "reason": "num_labels propagation bug is unrelated to NaNs in classification heads after checkout/init." }, { - "left": "issue:43756", - "right": "issue:44913", + "left": "issue:43720", + "right": "issue:44361", "accept": false, - "reason": "Smollm3 RoPE-layer count mismatch and GPTNeoX rotary_pct reload regression are only loosely related to rotary settings, not the same bug." + "reason": "Packed-weight loading bug and MLukeTokenizer AttributeError do not share a code path." }, { "left": "issue:44849", "right": "issue:45357", "accept": false, - "reason": "Qwen3.5 hidden-states bug and incorrect visual encoder key serialization are different issues." + "reason": "Qwen3.5 hidden-states bug and incorrect visual-encoder key serialization are distinct regressions." + }, + { + "left": "issue:43756", + "right": "issue:44913", + "accept": false, + "reason": "Smollm3 RoPE-layer omission is not the same as GPTNeoXConfig rotary_pct not persisting on reload." }, { "left": "issue:43493", "right": "issue:43825", "accept": false, - "reason": "SigLIP2 implementation discrepancy and pipeline translation-message regression are unrelated." + "reason": "SigLIP2 implementation mismatch and pipeline translation-task error messaging are unrelated." }, { "left": "issue:28218", "right": "issue:33357", "accept": false, - "reason": "Tokenizer extra-space behavior and a MacOS bus error on a CLIP model are unrelated." + "reason": "Tokenizer extra-space behavior is unrelated to the MacOS CLIP bus error." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The summary is well grounded in the packet, and the only accepted pair is the one soft edge that plausibly represents the same v5 config reload regression. The other verdicts remain conservative and do not overclaim duplicate status." - }, - "evaluator_used": true, + "evaluator_result": null, + "evaluator_used": false, "retried": false, - "accepted_nontrivial_soft_edge": true, + "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null }, @@ -7016,7 +6968,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:33357", "issue:33666", @@ -7038,6 +6990,7 @@ "issue:43756", "issue:43824", "issue:43844", + "issue:43873", "issue:43927", "issue:43994", "issue:44112", @@ -7059,33 +7012,32 @@ "issue:45200", "issue:45229", "issue:45405", - "issue:45406", "issue:45520", "issue:45584", "issue:45759", "issue:45812", "issue:45823", - "issue:46121" + "issue:46050" ], "soft_pairs": [ "issue:44568|issue:45812", - "issue:39692|issue:43493", "issue:44964|issue:45405", + "issue:39692|issue:43493", "issue:43540|issue:44977", - "issue:45200|issue:45229", "issue:44488|issue:44843", + "issue:45200|issue:45229", "issue:43334|issue:43572", - "issue:43493|issue:43844", "issue:43278|issue:43844", + "issue:43493|issue:43844", "issue:43257|issue:43299", "issue:43334|issue:45759", "issue:43756|issue:45083", "issue:39692|issue:43295", + "issue:43646|issue:44466", "issue:45229|issue:45823", "issue:43824|issue:44589", - "issue:43646|issue:44466", - "issue:43504|issue:43606", "issue:33357|issue:33666", + "issue:43504|issue:43606", "issue:43927|issue:44361", "issue:44589|issue:45520", "issue:43572|issue:44291", @@ -7097,216 +7049,216 @@ "issue:44792|issue:45405", "issue:43994|issue:44493", "issue:44423|issue:44734", - "issue:45406|issue:46121" + "issue:43873|issue:46050" ], - "prepared_review_unit_hash": "d33fef169d33194cc24c0a32053a8914aae2cbfd5f5b92be6bb2799ecd217644", + "prepared_review_unit_hash": "097ec11d0ff9b53230ed663a3b3982a026e3d5c9dcb3d7c76529adf2ec533c7c", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 36957, - "estimated_input_tokens": 9240, - "estimated_eval_tokens": 18736 + "serialized_chars": 36879, + "estimated_input_tokens": 9220, + "estimated_eval_tokens": 18696 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is highly heterogeneous: it mixes unrelated tokenizer, multimodal, serving, training, config, and CI regressions. None of the soft pairs appears to describe the same concrete bug or change, so all soft edges should be rejected.", - "confidence": 0.97, - "canonical_issue_reason": "No single canonical issue stands out; the items span distinct models and failure modes, so any duplicate anchor would be arbitrary.", + "summary": "This set is mostly a grab-bag of unrelated regression reports. A few pairs share a broad theme (v5 tokenizer/config/model-loading regressions, Qwen/Gemma/Multimodal issues), but the concrete failure modes and code paths differ too much to merge.", + "confidence": 0.7, + "canonical_issue_reason": "Issue 45812 is the clearest representative: it is a concrete, user-visible v4\u2192v5 regression affecting a broad family of models (Granite) and points to a specific tokenizer path rather than a vague symptom.", "canonical_pr_reason": null, - "best_issue_reason": "No globally best issue candidate is evident because the cluster is not centered on one underlying defect.", + "best_issue_reason": "45812 is the best standalone issue to anchor the cluster because it describes a specific, reproducible regression with wide impact and a clear affected surface.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44568", "right": "issue:45812", "accept": false, - "reason": "Different tokenizer regressions: missing BOS/EOS on mdeberta-v3 vs wrong token IDs on Granite." + "reason": "Both are tokenizer regressions in v5, but one is about add_special_tokens on mdeberta-v3 and the other is about Granite token IDs; different model-specific code paths." }, { - "left": "issue:39692", - "right": "issue:43493", + "left": "issue:44964", + "right": "issue:45405", "accept": false, - "reason": "Docs/example errors in SigLIP2 vs an implementation discrepancy with the original JAX model." + "reason": "Unrelated: model loading failure for Phi-4 multimodal vs a version-bump/package availability issue for MIN_PEFT_VERSION." }, { - "left": "issue:44964", - "right": "issue:45405", + "left": "issue:39692", + "right": "issue:43493", "accept": false, - "reason": "Loading Phi-4 multimodal breaks vs a PEFT version bump; unrelated failure modes." + "reason": "Both mention SigLIP2, but one is a docs/example mismatch and quantization problem while the other is an implementation-vs-JAX discrepancy." }, { "left": "issue:43540", "right": "issue:44977", "accept": false, - "reason": "Video-input processing error in Qwen3OmniMoe vs flash-attention generation issues in Qwen3.5." + "reason": "Different bugs: Qwen3OmniMoe video input processing ValueError vs Qwen3.5 flash-attention generation behavior." }, { - "left": "issue:45200", - "right": "issue:45229", + "left": "issue:44488", + "right": "issue:44843", "accept": false, - "reason": "Text-only mm_token_type_ids behavior in Gemma 4 vs multi-GPU CUDA OOM in Gemma4 31B." + "reason": "Different failure modes: loading cjvt/sleng-bert vs offline-mode breakage caused by an unconditional model_info() call." }, { - "left": "issue:44488", - "right": "issue:44843", + "left": "issue:45200", + "right": "issue:45229", "accept": false, - "reason": "Model loading failure for sleng-bert vs offline-mode breakage from an unconditional hub call." + "reason": "Not the same bug: mm_token_type_ids defaulting for text-only fine-tuning vs Gemma4 multi-GPU OOM." }, { "left": "issue:43334", "right": "issue:43572", "accept": false, - "reason": "Missing pad_token_id in Qwen3-VL config vs missing pad_token_idx in StableLmConfig." + "reason": "Both are missing config fields, but they affect different models and different attributes (pad_token_id vs pad_token_idx)." }, { - "left": "issue:43493", + "left": "issue:43278", "right": "issue:43844", "accept": false, - "reason": "SigLIP2 implementation mismatch vs exploding gradients under ZeRO-3; different bugs." + "reason": "Embedding dtype drift in eval is unrelated to the ZeRO-3 gradient growth problem." }, { - "left": "issue:43278", + "left": "issue:43493", "right": "issue:43844", "accept": false, - "reason": "Dtype drift between train/eval vs gradient instability under DeepSpeed ZeRO-3." + "reason": "SigLIP2 implementation mismatch and ZeRO-3 gradient anomalies are distinct issues." }, { "left": "issue:43257", "right": "issue:43299", "accept": false, - "reason": "Accelerate/DeepSpeed weight conversion issue vs dev-version load failure for Qwen3VL MoE models." + "reason": "Both involve Qwen3 MoE, but one is about weight conversion with accelerate+deepspeed and the other is a model-loading regression in dev." }, { "left": "issue:43334", "right": "issue:45759", "accept": false, - "reason": "Pad-token config bug in Qwen3-VL vs composite config unwrapping for Qwen 3.5/3.6." + "reason": "Missing pad_token_id on Qwen3-VL config is unrelated to AutoModelForCausalLM.from_config not unwrapping text_config." }, { "left": "issue:43756", "right": "issue:45083", "accept": false, - "reason": "RoPE layer dropout in Smollm3 vs a feat-extract helper bug in qwen3_omni_moe." + "reason": "Smollm3 RoPE-layer count bug and qwen3_omni_moe feature-length helper behavior are unrelated." }, { "left": "issue:39692", "right": "issue:43295", "accept": false, - "reason": "SigLIP2 doc example problems vs processor.tokenizer/image-tokenizer regression." + "reason": "SigLIP2 docs/example errors do not match the processor.tokenizer regression in custom model code." + }, + { + "left": "issue:43646", + "right": "issue:44466", + "accept": false, + "reason": "Custom model initialization breakage and lm_head.weight serialization inconsistency are separate problems." }, { "left": "issue:45229", "right": "issue:45823", "accept": false, - "reason": "OOM during Gemma4 inference vs device mismatch with device_map='auto'." + "reason": "Same model family, different bugs: multi-GPU inference OOM vs device mismatch with device_map=auto." }, { "left": "issue:43824", "right": "issue:44589", "accept": false, - "reason": "Import error for Qwen2_5_VLForConditionalGeneration vs Float8 storage lookup failure." + "reason": "Import error for Qwen2_5_VL is unrelated to the Float8 storage lookup failure." }, { - "left": "issue:43646", - "right": "issue:44466", + "left": "issue:33357", + "right": "issue:33666", "accept": false, - "reason": "Custom model init breakage in v5 vs device-dependent lm_head serialization inconsistency." + "reason": "Different subsystems and symptoms: MacOS CLIP bus error vs Qwen2-VL multi-GPU training." }, { "left": "issue:43504", "right": "issue:43606", "accept": false, - "reason": "Legacy field prevents BEiT segmentation load vs Bark-small CPU offload device mismatch." - }, - { - "left": "issue:33357", - "right": "issue:33666", - "accept": false, - "reason": "MacOS bus error on CLIP model load vs Qwen2-VL multi-GPU training; unrelated." + "reason": "BEiT legacy-field loading and bark-small CPU offload device mismatch are unrelated." }, { "left": "issue:43927", "right": "issue:44361", "accept": false, - "reason": "DiaConfig save/load token-id loss vs MLukeTokenizer AttributeError on tasks." + "reason": "DiaConfig save/load token ID loss and MLukeTokenizer AttributeError are different tokenizer/config bugs." }, { "left": "issue:44589", "right": "issue:45520", "accept": false, - "reason": "Float8 storage type lookup failure vs Python 3.13 flash_attn import key error." + "reason": "Float8 storage lookup and flash_attn import handling on Python 3.13 are unrelated." }, { "left": "issue:43572", "right": "issue:44291", "accept": false, - "reason": "Missing StableLmConfig field vs init_empty_weights signature mismatch; distinct initialization bugs." + "reason": "Both are initialization/config regressions, but the concrete defects differ (_pad_token_idx missing vs unexpected _is_hf_initialized argument)." }, { "left": "issue:44464", "right": "issue:45584", "accept": false, - "reason": "Compiled-forward chunked generation inconsistency vs Whisper empty-transcription failure." + "reason": "Chunked generation with compiled forward is a different code path from Whisper empty-transcription failure after align_special_tokens." }, { "left": "issue:43504", "right": "issue:43653", "accept": false, - "reason": "BEiT legacy config load failure vs BigBirdTokenizer special-token registration issue." + "reason": "Legacy-field load failure in BEiT and BigBirdTokenizer special-token registration are unrelated." }, { "left": "issue:43606", "right": "issue:44112", "accept": false, - "reason": "Runtime device mismatch in Bark-small vs a stale GraniteSpeech CI test." + "reason": "Both mention devices/CI, but they target different models and different failure modes; not the same bug." }, { "left": "issue:43278", "right": "issue:43701", "accept": false, - "reason": "Embedding dtype regression vs resume_from_checkpoint key mismatch." + "reason": "Evaluation dtype drift and resume_from_checkpoint key mismatch are unrelated." }, { "left": "issue:43575", "right": "issue:45405", "accept": false, - "reason": "Tensor-parallel OOM on Qwen2-57B vs unreleased PEFT version bump." + "reason": "TP-induced OOM on Qwen2-57B is unrelated to a dependency version bump." }, { "left": "issue:44792", "right": "issue:45405", "accept": false, - "reason": "Janus image-generation test failure vs PEFT dependency versioning; unrelated." + "reason": "janus image-generation test failure is unrelated to the PEFT version availability issue." }, { "left": "issue:43994", "right": "issue:44493", "accept": false, - "reason": "SigLIP2 nonsense outputs vs unexpected position-id key warnings across models." + "reason": "Nonsensical SigLIP2 outputs and unexpected position-id keys in many models are too different to be the same underlying bug." }, { "left": "issue:44423", "right": "issue:44734", "accept": false, - "reason": "Two different serve crashes: string .to() error vs wrong KV-cache indexing." + "reason": "Different serve paths and failures: multimodal continuous batching crashes on .to() vs KV-cache continuation indexing bug." }, { - "left": "issue:45406", - "right": "issue:46121", + "left": "issue:43873", + "right": "issue:46050", "accept": false, - "reason": "Gemma4Processor missing _tokenizer in serve vs rope-parameter validation TypeError." + "reason": "Offloading-not-working-with-quantization and quantized-model save/load breakage are related only at a high level, not the same concrete bug." } ] }, @@ -7328,7 +7280,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:15354", "issue:28218", @@ -7352,7 +7304,6 @@ "issue:43701", "issue:43824", "issue:43844", - "issue:43873", "issue:43957", "issue:44186", "issue:44315", @@ -7370,21 +7321,23 @@ "issue:45290", "issue:45325", "issue:45356", + "issue:45406", "issue:45446", "issue:45520", "issue:45588", "issue:45823", "issue:46050", + "issue:46121", "issue:46178", "issue:46192" ], "soft_pairs": [ - "issue:43873|issue:46050", + "issue:45406|issue:46121", "issue:29942|issue:30333", "issue:45588|issue:46050", "issue:42490|issue:43696", - "issue:44521|issue:45290", "issue:43844|issue:44964", + "issue:44521|issue:45290", "issue:28218|issue:34567", "issue:29159|issue:32090", "issue:43582|issue:44977", @@ -7392,8 +7345,8 @@ "issue:45084|issue:45520", "issue:43540|issue:45200", "issue:15354|issue:38175", - "issue:45200|issue:45823", "issue:45072|issue:45198", + "issue:45200|issue:45823", "issue:37428|issue:43957", "issue:43232|issue:44849", "issue:44186|issue:46192", @@ -7401,223 +7354,223 @@ "issue:45823|issue:46192", "issue:44315|issue:44849", "issue:43295|issue:44610", - "issue:44554|issue:45356", "issue:43295|issue:43450", + "issue:44554|issue:45356", "issue:43572|issue:44987", + "issue:37428|issue:43824", + "issue:43572|issue:43957", "issue:45200|issue:45325", "issue:39692|issue:46192", - "issue:43572|issue:43957", - "issue:37428|issue:43824", "issue:45520|issue:46178" ], - "prepared_review_unit_hash": "b3e926f781aa5bf3c86469b60c31927d08d046b5e8c15ebe820e9fefe1f81be3", + "prepared_review_unit_hash": "41a86659b29789e33f9696424e5dc27d80127dbea2d2e2f40d6794ba251cbdfa", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { - "node_count": 47, - "item_count": 47, + "node_count": 48, + "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 36155, - "estimated_input_tokens": 9039, - "estimated_eval_tokens": 18334 + "serialized_chars": 36816, + "estimated_input_tokens": 9204, + "estimated_eval_tokens": 18664 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is highly heterogeneous: most items are unrelated tokenizer, multimodal processor, flash-attention, loading, training, or quantization bugs. The soft edges are mostly embedding-level similarities rather than true duplicates, so none should be merged.", - "confidence": 0.62, - "canonical_issue_reason": "No single canonical issue is safe here because the cluster is over-broad. If one representative must be chosen, issue:43295 is the closest concrete, user-facing regression among the few multimodal/processor-related items, but it does not represent the whole cluster.", + "summary": "This cluster is not a duplicate set; it is a loose collection of unrelated transformers issues with only superficial title similarity. None of the soft edges should be merged.", + "confidence": 0.97, + "canonical_issue_reason": "No single canonical issue fits well: the items cover unrelated failures across tokenization, chat templates, flash-attention, model loading, training state, and backend/import behavior.", "canonical_pr_reason": null, - "best_issue_reason": "Issue:43295 is the best representative of the densest coherent subtheme in this cluster: a regression around processor/tokenizer behavior in multimodal code paths. It is more concrete than the broader, noisier entries and has the strongest structural similarity to the few nearby processor-related issues.", + "best_issue_reason": "No issue is a good global representative for the whole cluster; picking one would hide the fact that the pairwise matches are mostly incidental.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43873", - "right": "issue:46050", + "left": "issue:45406", + "right": "issue:46121", "accept": false, - "reason": "Different bugs: quantization/offloading behavior versus save/load correctness for a quantized model. Same broad area, not same underlying defect." + "reason": "Gemma4 processor `_tokenizer` attribute error is unrelated to rope validation TypeError." }, { "left": "issue:29942", "right": "issue:30333", "accept": false, - "reason": "Completely unrelated subsystems: Flash Attention tests versus MLFlow reporting on failed jobs." + "reason": "Flash Attention 2 test failures and MLFlow job reporting are different subsystems and bugs." }, { "left": "issue:45588", "right": "issue:46050", "accept": false, - "reason": "Different code paths: flash_attention sink-less crash versus sinq quantized model serialization/deserialization." + "reason": "Sinkless flash-attention `s_aux=None` crash is unrelated to sinq save/load breakage." }, { "left": "issue:42490", "right": "issue:43696", "accept": false, - "reason": "Local-path import warning is unrelated to CUDA OOM during GPT-oss loading." + "reason": "Trailing-slash local import warning and CUDA OOM are not the same underlying issue." }, { - "left": "issue:44521", - "right": "issue:45290", + "left": "issue:43844", + "right": "issue:44964", "accept": false, - "reason": "Both involve apply_chat_template, but one is multimodal assistant masks and the other is tool-call tokenization crash; these are distinct failures." + "reason": "ZeRO-3 gradient anomaly and Phi-4 multimodal loading failure are different code paths." }, { - "left": "issue:43844", - "right": "issue:44964", + "left": "issue:44521", + "right": "issue:45290", "accept": false, - "reason": "Unrelated: ZeRO-3 gradient anomaly versus loading failure for a specific multimodal model." + "reason": "Both involve chat templates, but one is all-zero assistant masks for multimodal inputs and the other is a crash on tool-call messages; not the same bug." }, { "left": "issue:28218", "right": "issue:34567", "accept": false, - "reason": "Tokenizer spacing bug and TrainerState token counter update are unrelated." + "reason": "Tokenizer spacing after added tokens is unrelated to `num_input_tokens_seen` tracking." }, { "left": "issue:29159", "right": "issue:32090", "accept": false, - "reason": "Slow/fast tokenizer inconsistency is unrelated to a Trainer GPU broadcast NoneType error." + "reason": "Slow/fast tokenizer inconsistency and `_gpu_broadcast_one` NoneType errors are unrelated." }, { "left": "issue:43582", "right": "issue:44977", "accept": false, - "reason": "Apple Silicon allocator warmup TypeError and Qwen3.5 flash-attention generation bug are different problems." + "reason": "Apple Silicon allocator TypeError is unrelated to Qwen3.5 flash-attention generation failure." }, { "left": "issue:44554", "right": "issue:45446", "accept": false, - "reason": "Both touch attention/flex_attention, but one is an MPS correctness issue and the other is a version-check import bug." + "reason": "MPS attention correctness and a PyTorch version check bug are different issues." }, { "left": "issue:45084", "right": "issue:45520", "accept": false, - "reason": "Compiler/template-node error is unrelated to the Python 3.13 flash_attn import KeyError." + "reason": "Non-template-node compile error and Python 3.13 flash_attn import KeyError are unrelated." }, { "left": "issue:43540", "right": "issue:45200", "accept": false, - "reason": "Both are multimodal, but one is video-input processing in Qwen3OmniMoe and the other is a Gemma4 token-type-id defaulting issue." + "reason": "Qwen3OmniMoe video-processing error and Gemma4 token-type-id defaulting are different bugs." }, { "left": "issue:15354", "right": "issue:38175", "accept": false, - "reason": "TorchScript GeneratorExp export failure and SigLIP2 zero probabilities are unrelated model behaviors." + "reason": "TorchScript GeneratorExp export failure is unrelated to SigLIP2 zero probabilities." }, { - "left": "issue:45200", - "right": "issue:45823", + "left": "issue:45072", + "right": "issue:45198", "accept": false, - "reason": "Same model family (Gemma4) but different bugs: required mm_token_type_ids versus device-map forward mismatch." + "reason": "bf16 dtype mismatch CI failure and Wav2Vec2 save/tokenization failure are not the same problem." }, { - "left": "issue:45072", - "right": "issue:45198", + "left": "issue:45200", + "right": "issue:45823", "accept": false, - "reason": "Different failures in different models: dtype mismatch in inference versus save_pretrained/tokenization breakage." + "reason": "Gemma4 mm_token_type_ids handling and PLE device-mapping mismatch are distinct forward-pass issues." }, { "left": "issue:37428", "right": "issue:43957", "accept": false, - "reason": "Flash-attention import symbol error and meta-device model-loading breakage are distinct issues." + "reason": "Different import/load failures affecting different symbols and model-loading paths." }, { "left": "issue:43232", "right": "issue:44849", "accept": false, - "reason": "Generation kwargs sync issue and Qwen3.5 hidden-states bug are separate generation-path defects." + "reason": "Generation kwargs sync bug and Qwen3.5 hidden-states bug are unrelated." }, { "left": "issue:44186", "right": "issue:46192", "accept": false, - "reason": "NER/batched-padding tokenizer crash is not the same as silently ignored return_tensors when text_kwargs is passed." + "reason": "LayoutLMv2 NER/padding crash and `return_tensors` being ignored are different tokenizer behaviors." }, { "left": "issue:43493", "right": "issue:43701", "accept": false, - "reason": "SigLIP2 implementation discrepancy and checkpoint resume key mismatch are unrelated." + "reason": "SigLIP2 implementation mismatch and checkpoint resume key mismatch do not share a code-path." }, { "left": "issue:45823", "right": "issue:46192", "accept": false, - "reason": "Device-map mismatch in Gemma4 and ignored return_tensors in multimodal kwargs are different bugs." + "reason": "Gemma4 device mismatch and `return_tensors` ignore are unrelated processing bugs." }, { "left": "issue:44315", "right": "issue:44849", "accept": false, - "reason": "Liger Kernel application with model_init is unrelated to Qwen3.5 output_hidden_states behavior." + "reason": "Liger Kernel not applied via `model_init` is unrelated to Qwen3.5 hidden-state output behavior." }, { "left": "issue:43295", "right": "issue:44610", "accept": false, - "reason": "Both involve multimodal processing, but the first is a processor.tokenizer regression and the second is a video processor output-shape bug; not the same underlying defect." + "reason": "Processor/tokenizer API regression and OmDet processor image-size mismatch are different model families and failures." }, { - "left": "issue:44554", - "right": "issue:45356", + "left": "issue:43295", + "right": "issue:43450", "accept": false, - "reason": "MPS attention correctness and Kimi-K2.5 tokenizer codec regression are unrelated." + "reason": "Processor/tokenizer regression and batched video shape bug are unrelated." }, { - "left": "issue:43295", - "right": "issue:43450", + "left": "issue:44554", + "right": "issue:45356", "accept": false, - "reason": "Processor.tokenizer regression and batched video processor shape bug are different code paths and would not be merged into one fix." + "reason": "MPS attention correctness bug and Kimi-K2.5 tokenizer codec regression are unrelated." }, { "left": "issue:43572", "right": "issue:44987", "accept": false, - "reason": "StableLmConfig pad_token_idx regression is unrelated to physical-intelligence/fast loading failure." + "reason": "StableLm config `pad_token_idx` regression and physical-intelligence/fast load failure are different issues." }, { - "left": "issue:45200", - "right": "issue:45325", + "left": "issue:37428", + "right": "issue:43824", "accept": false, - "reason": "Both are multimodal model issues, but one is missing/default mm_token_type_ids and the other is a Qwen2.5-VL rope-index scaling bug." + "reason": "Both are import errors, but they involve different missing symbols and model paths; not the same bug." }, { - "left": "issue:39692", - "right": "issue:46192", + "left": "issue:43572", + "right": "issue:43957", "accept": false, - "reason": "SigLIP2 documentation errors and ignored return_tensors are unrelated." + "reason": "Missing `pad_token_idx` in StableLmConfig is unrelated to meta-device model loading breakage." }, { - "left": "issue:43572", - "right": "issue:43957", + "left": "issue:45200", + "right": "issue:45325", "accept": false, - "reason": "Pad token config regression and meta-device model-loading failure are not the same bug." + "reason": "Gemma4 token-type defaults and Qwen2.5-VL temporal RoPE scaling are different mechanisms." }, { - "left": "issue:37428", - "right": "issue:43824", + "left": "issue:39692", + "right": "issue:46192", "accept": false, - "reason": "Flash-attention utility import error and Qwen2.5-VL class import error are separate import problems with different missing symbols." + "reason": "SigLIP2 documentation errors are unrelated to `return_tensors` being ignored." }, { "left": "issue:45520", "right": "issue:46178", "accept": false, - "reason": "Both are import/configuration errors, but flash_attn KeyError on Python 3.13 and tensorflow_text backend mapping are unrelated." + "reason": "flash_attn backend KeyError on Python 3.13 and tensorflow_text backend lookup error are unrelated import/config issues." } ] }, @@ -7639,7 +7592,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:28218", "issue:35141", @@ -7691,30 +7644,30 @@ "issue:46192" ], "soft_pairs": [ - "issue:44898|issue:45412", - "issue:44466|issue:45127", "issue:43295|issue:43873", + "issue:44898|issue:45412", "issue:43550|issue:43844", + "issue:44466|issue:45127", "issue:43334|issue:43525", "issue:44792|issue:45563", "issue:43824|issue:43975", "issue:42915|issue:43824", "issue:43388|issue:43526", "issue:43450|issue:43575", - "issue:43278|issue:43856", "issue:42490|issue:43493", - "issue:43975|issue:45520", + "issue:43278|issue:43856", "issue:28218|issue:35141", - "issue:43653|issue:44112", - "issue:38175|issue:43493", + "issue:43975|issue:45520", "issue:43526|issue:46192", + "issue:38175|issue:43493", + "issue:43653|issue:44112", "issue:44442|issue:45198", "issue:44514|issue:44521", "issue:45520|issue:46170", "issue:38175|issue:45412", "issue:44206|issue:45584", - "issue:43827|issue:43901", "issue:43262|issue:43450", + "issue:43827|issue:43901", "issue:43819|issue:44112", "issue:44610|issue:44857", "issue:43819|issue:45083", @@ -7722,214 +7675,214 @@ "issue:43335|issue:43550", "issue:43606|issue:45083" ], - "prepared_review_unit_hash": "391218718bb8c247740b4efd9963e0a30109b5e7e3a07cf0cce28d249aca013a", + "prepared_review_unit_hash": "caa5e63a998710f41cd432d5acba6f51093bb8978109f7d08ed51981ab96b841", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 36907, - "estimated_input_tokens": 9227, - "estimated_eval_tokens": 18710 + "serialized_chars": 36918, + "estimated_input_tokens": 9230, + "estimated_eval_tokens": 18716 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous: the soft pairs are largely same-subsystem but not same-bug matches, so I reject them all. There is no strong duplicate canonical issue; if an anchor is needed, issue 44521 is the broadest and most active issue in the closest thematic area (multimodal apply_chat_template).", - "confidence": 0.86, - "canonical_issue_reason": null, + "summary": "This cluster is highly heterogeneous: most pairs only share a broad subsystem or model family, not the same concrete bug. I would not merge any of the soft-edge candidates. If one issue has to stand in as the representative, `issue:44521` is the strongest due to higher activity and inbound references, but the cluster does not look like a true duplicate set.", + "confidence": 0.78, + "canonical_issue_reason": "`issue:44521` has the most inbound references/discussion and is a user-facing bug in a broadly reused path (`apply_chat_template` for multimodal inputs), so it is the best representative of the noisy cluster.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 44521 has the broadest scope and the most traction among the only plausible subcluster (multimodal apply_chat_template regressions), so it is the best anchor even though the cluster is not a true duplicate set.", + "best_issue_reason": "`issue:44521` is the most impactful and central issue in the set based on activity and references, even though the surrounding items are not true duplicates.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43295", + "right": "issue:43873", + "accept": false, + "reason": "Different failures: processor/tokenizer regression vs quantization/offloading behavior. Same general area, not the same bug." + }, { "left": "issue:44898", "right": "issue:45412", "accept": false, - "reason": "Different bugs: image-resolution handling vs memory not being released on deletion." + "reason": "Unrelated components: Perceiver interpolation shape handling vs RT-DETR memory release." + }, + { + "left": "issue:43550", + "right": "issue:43844", + "accept": false, + "reason": "Different code paths: torch.compile+SDPA on Bamba vs ZeRO-3 gradient growth in DeepSpeed." }, { "left": "issue:44466", "right": "issue:45127", "accept": false, - "reason": "One is tied-weight serialization/device-dependent behavior; the other is LoRA merge collapse with extended vocab. Related theme, different failure." - }, - { - "left": "issue:43295", - "right": "issue:43873", - "accept": false, - "reason": "Processor API regression and quantization/offload behavior are unrelated code paths." - }, - { - "left": "issue:43550", - "right": "issue:43844", - "accept": false, - "reason": "Torch.compile/SDPA failure is not the same as a ZeRO-3 gradient growth issue." + "reason": "Both mention tied weights, but one is serialization/device-dependent and the other is LoRA merge collapse with extended vocab. Not the same defect." }, { "left": "issue:43334", "right": "issue:43525", "accept": false, - "reason": "Both mention missing pad_token_id, but they are model-specific config failures and not clearly one shared bug." + "reason": "Same symptom class (`pad_token_id` missing) but on different model configs and likely separate fixes." }, { "left": "issue:44792", "right": "issue:45563", "accept": false, - "reason": "Janus image-generation test failure and a paged-generate warning are distinct issues." + "reason": "Janus image-generation test failure is unrelated to a stale warning about `num_return_sequences`." }, { "left": "issue:43824", "right": "issue:43975", "accept": false, - "reason": "ImportError for a missing class and a detokenization regression are different failures." + "reason": "ImportError for a missing class vs incorrect detokenization in a specific model; different problems." }, { "left": "issue:42915", "right": "issue:43824", "accept": false, - "reason": "FineGrainedFP8Config failure is unrelated to a missing Qwen2.5-VL import." + "reason": "Qwen3 MoE FP8 failure and Qwen2.5-VL import error are unrelated." }, { "left": "issue:43388", "right": "issue:43526", "accept": false, - "reason": "Different layers: metric gathering vs image-processor label reduction." + "reason": "Both involve labels, but one is gather/evaluation batching and the other is image-processor label reduction. Different bugs." }, { "left": "issue:43450", "right": "issue:43575", "accept": false, - "reason": "Batched video shape bug and tensor-parallel OOM are not the same underlying problem." - }, - { - "left": "issue:43278", - "right": "issue:43856", - "accept": false, - "reason": "Training/eval dtype mismatch is unrelated to MoE memory usage." + "reason": "Video processor batch-shape bug vs tensor-parallel OOM when loading a large model." }, { "left": "issue:42490", "right": "issue:43493", "accept": false, - "reason": "Local-path import warning and SigLIP2 implementation discrepancy are unrelated." + "reason": "Import warning for a trailing-slash path is unrelated to SigLIP2 implementation discrepancies." }, { - "left": "issue:43975", - "right": "issue:45520", + "left": "issue:43278", + "right": "issue:43856", "accept": false, - "reason": "Detokenization regression and flash_attn import-time KeyError are unrelated." + "reason": "Embedding dtype drift and MoE memory usage are different issues." }, { "left": "issue:28218", "right": "issue:35141", "accept": false, - "reason": "Tokenizer spacing bug and embedding reinit after resize are different code paths." + "reason": "Tokenizer spacing bug and embedding reinitialization after resizing are distinct tokenizer/model-init issues." }, { - "left": "issue:43653", - "right": "issue:44112", + "left": "issue:43975", + "right": "issue:45520", + "accept": false, + "reason": "Detokenization regression and Python 3.13 flash-attn import handling are unrelated." + }, + { + "left": "issue:43526", + "right": "issue:46192", "accept": false, - "reason": "Special-token registration bug and a stale CI test are not duplicates." + "reason": "Image label reduction bug vs `text_kwargs` silently overriding `return_tensors`; different API paths." }, { "left": "issue:38175", "right": "issue:43493", "accept": false, - "reason": "Both involve SigLIP2, but zero probabilities vs JAX discrepancy are not clearly the same concrete bug." + "reason": "Same model family, but one report is zero probabilities and the other is a general HF-vs-JAX discrepancy; not enough evidence of the same concrete bug." }, { - "left": "issue:43526", - "right": "issue:46192", + "left": "issue:43653", + "right": "issue:44112", "accept": false, - "reason": "Label reduction behavior and text_kwargs/return_tensors handling are unrelated." + "reason": "BigBird tokenizer special-token registration and a GraniteSpeech CI test issue are unrelated." }, { "left": "issue:44442", "right": "issue:45198", "accept": false, - "reason": "Different tokenizer/processor failures in different model families." + "reason": "Different tokenizers and different failure modes; not duplicates." }, { "left": "issue:44514", "right": "issue:44521", "accept": false, - "reason": "Same API area, but one is a batched padding=False crash and the other is all-zero assistant masks; not the same concrete failure." + "reason": "Both hit `apply_chat_template`, but one crashes on batched padding=False input while the other returns zero assistant masks. Related area, different bug." }, { "left": "issue:45520", "right": "issue:46170", "accept": false, - "reason": "Different import/platform dependency problems on different stacks." + "reason": "Different platform/import failures: flash-attn on Python 3.13 vs Windows ROCm distributed dependency." }, { "left": "issue:38175", "right": "issue:45412", "accept": false, - "reason": "SigLIP2 probability issue and RT-DETR memory leak are unrelated." + "reason": "SigLIP2 zero-probability behavior is unrelated to RT-DETR memory reclamation." }, { "left": "issue:44206", "right": "issue:45584", "accept": false, - "reason": "Unsupported center argument in feature extraction is unrelated to empty-transcription failure after align_special_tokens." + "reason": "Audio feature extractor argument regression vs Whisper empty-transcription generation failure are distinct issues." }, { - "left": "issue:43827", - "right": "issue:43901", + "left": "issue:43262", + "right": "issue:43450", "accept": false, - "reason": "Both are docs issues, but they cover different APIs and deprecations." + "reason": "Audio chat-template sampling-rate default and batched video processor shape are unrelated." }, { - "left": "issue:43262", - "right": "issue:43450", + "left": "issue:43827", + "right": "issue:43901", "accept": false, - "reason": "Audio sampling-rate default bug and video batched-shape bug are unrelated." + "reason": "Both are docs-related, but they cover different APIs and different stale references." }, { "left": "issue:43819", "right": "issue:44112", "accept": false, - "reason": "DAC latent reconstruction mismatch and a stale CI test are unrelated." + "reason": "DAC latent conversion mismatch and GraniteSpeech CI device override test are unrelated." }, { "left": "issue:44610", "right": "issue:44857", "accept": false, - "reason": "Processor input-size mismatch and AMP/CUDA loss crash are different problems." + "reason": "Wrong processor image size and AMP/CUDA loss crash are different problems." }, { "left": "issue:43819", "right": "issue:45083", "accept": false, - "reason": "Latent decoding mismatch and feature-length helper behavior are not the same bug." + "reason": "DAC STE mismatch vs Qwen3 Omni-MoE feature-length helper behavior are unrelated." }, { "left": "issue:37428", "right": "issue:43425", "accept": false, - "reason": "Missing import for a model class and Torch version incompatibility are unrelated." + "reason": "A missing internal import and Torch 2.10 incompatibility are different release issues." }, { "left": "issue:43335", "right": "issue:43550", "accept": false, - "reason": "Sparse-layer config bug and torch.compile/SDPA failure are different issues." + "reason": "SwitchTransformers config bug and Bamba torch.compile/SDPA failure are unrelated." }, { "left": "issue:43606", "right": "issue:45083", "accept": false, - "reason": "CPU-offload device mismatch and feature-length helper behavior are unrelated." + "reason": "CPU-offload device mismatch and Qwen3 Omni-MoE helper behavior are not the same bug." } ] }, @@ -7951,7 +7904,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:29127", "issue:29942", @@ -8004,15 +7957,15 @@ ], "soft_pairs": [ "issue:44857|issue:45593", - "issue:45290|issue:45381", "issue:44448|issue:44743", + "issue:45290|issue:45381", "issue:45127|issue:45245", "issue:29942|issue:32090", "issue:45200|issue:45588", - "issue:43278|issue:43825", "issue:37428|issue:44351", - "issue:44206|issue:45823", + "issue:43278|issue:43825", "issue:43335|issue:43653", + "issue:44206|issue:45823", "issue:43611|issue:43931", "issue:43550|issue:44112", "issue:43819|issue:44493", @@ -8026,233 +7979,239 @@ "issue:39692|issue:44493", "issue:43720|issue:44112", "issue:43335|issue:45072", - "issue:45920|issue:46192", + "issue:44448|issue:44779", "issue:43335|issue:44112", "issue:44360|issue:44561", - "issue:44448|issue:44779", + "issue:45920|issue:46192", "issue:42490|issue:43854", "issue:44977|issue:45229", - "issue:38175|issue:44493", - "issue:43606|issue:44857" + "issue:43606|issue:44857", + "issue:38175|issue:44493" ], - "prepared_review_unit_hash": "85e61ef1745c23f4b1e4d9e5803f09b992e03a86c7403686d7e135e120e0de52", + "prepared_review_unit_hash": "5c361e0f0d7949927c8792b3d313b6fc7ec88a8fc23f120bab0c8a823d72ffdf", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 31, - "serialized_chars": 37145, - "estimated_input_tokens": 9287, - "estimated_eval_tokens": 18830 + "serialized_chars": 37157, + "estimated_input_tokens": 9290, + "estimated_eval_tokens": 18836 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly unrelated singleton issues. There is one very similar pair (45310/45478) with matching titles, but the evidence is still soft, so the cluster should not be treated as a confirmed duplicate set.", - "confidence": 0.68, - "canonical_issue_reason": "Issue 45310 is the best representative for the shared Qwen3.5 Moe from_pretrained theme, but the evidence only supports a soft similarity, not a confirmed duplicate cluster.", + "summary": "This set is mostly a heterogeneous grab-bag of closed bug reports across unrelated subsystems, with only one clear duplicate pair: the Qwen3.5 MoE from_pretrained regression reports.", + "confidence": 0.87, + "canonical_issue_reason": "No single issue cleanly represents the whole set because the reports cover unrelated failures; among the items, 45310 is the clearest local canonical only for the exact Qwen3.5 MoE duplicate pair.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45310 is the strongest issue representative because it is earlier and matches 45478 most closely, but it should be treated as a likely topic match rather than a proven duplicate.", + "best_issue_reason": "issue:45310 is the best issue candidate because it is the earlier, more central report for the only true duplicate pair, and 45478 is essentially the same bug report with a later timestamp.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44857", "right": "issue:45593", "accept": false, - "reason": "Different failures: AMP/CUDA loss crash vs missing auxiliary losses." + "reason": "Both are model-specific training losses, but one is an AMP/CUDA crash and the other is denoising/aux-loss behavior; different bug surfaces." }, { - "left": "issue:45290", - "right": "issue:45381", + "left": "issue:44448", + "right": "issue:44743", "accept": false, - "reason": "Tool-call chat-template crash and video vision_position_ids bug are unrelated." + "reason": "Both mention v4/v5 differences, but one is a Pegasus output regression and the other is a recurrent-state reset bug in modular_qwen3_5.py." }, { - "left": "issue:44448", - "right": "issue:44743", + "left": "issue:45290", + "right": "issue:45381", "accept": false, - "reason": "Pegasus output drift and Qwen3 recurrent-state reset affect different code paths." + "reason": "These are different pipeline areas: tokenization crashes on tool-call messages versus wrong vision_position_ids for Qwen2.5-VL video input." }, { "left": "issue:45127", "right": "issue:45245", "accept": false, - "reason": "LoRA/vocab collapse and category-count limit are distinct bugs." + "reason": "LoRA merge collapse with tied embeddings is unrelated to the category-cardinality runtime error." }, { "left": "issue:29942", "right": "issue:32090", "accept": false, - "reason": "Flash Attention test failures and NoneType GPU broadcast error are different problems." + "reason": "One is failing Flash Attention 2 tests; the other is a Trainer/_gpu_broadcast_one NoneType error. Different failure modes." }, { "left": "issue:45200", "right": "issue:45588", "accept": false, - "reason": "Gemma4 token-type handling and flash_attention s_aux=None crash are unrelated." - }, - { - "left": "issue:43278", - "right": "issue:43825", - "accept": false, - "reason": "BF16/FP32 dtype regression and pipeline task-support messaging do not share a code path." + "reason": "Gemma4 mm_token_type_ids defaults and flash_attention s_aux=None handling are separate code paths and problems." }, { "left": "issue:37428", "right": "issue:44351", "accept": false, - "reason": "Both are import errors, but they involve different missing symbols and likely different fixes." + "reason": "These are different import-level API breakages: a missing flash-attention helper versus missing HybridCache export." }, { - "left": "issue:44206", - "right": "issue:45823", + "left": "issue:43278", + "right": "issue:43825", "accept": false, - "reason": "Unsupported center argument in feature extractor and Gemma4 device mismatch are unrelated." + "reason": "Embedding dtype drift during evaluate is not the same as pipeline() advertising unsupported translation tasks." }, { "left": "issue:43335", "right": "issue:43653", "accept": false, - "reason": "Sparse-layer config bug and tokenizer special-token registration bug affect different components." + "reason": "SwitchTransformers sparse-layer creation and BigBirdTokenizer special-token registration are unrelated bugs." + }, + { + "left": "issue:44206", + "right": "issue:45823", + "accept": false, + "reason": "Both are Gemma4-related, but one is a feature-extractor arg regression and the other is a device-map forward mismatch." }, { "left": "issue:43611", "right": "issue:43931", "accept": false, - "reason": "base_model_prefix loading breakage and Qwen3-VL shape mismatch are not the same defect." + "reason": "Base_model_prefix loading breakage and Qwen3-VL weight-shape mismatch are distinct model-loading failures." }, { "left": "issue:43550", "right": "issue:44112", "accept": false, - "reason": "torch.compile SDPA failure and CI device override failure are different issues." + "reason": "Torch.compile+SDPA failure in Bamba is unrelated to the GraniteSpeech stale device-override CI test." }, { "left": "issue:43819", "right": "issue:44493", "accept": false, - "reason": "DAC from_latents mismatch and unexpected position-id warnings are unrelated model bugs." + "reason": "DAC.from_latents/STE mismatch is a model-specific forward-vs-latents bug, not the broad position-id key issue." }, { "left": "issue:44855", "right": "issue:45083", "accept": false, - "reason": "Python 3.13 import parsing failure and qwen3_omni_moe helper behavior are different problems." + "reason": "Python 3.13 IndentationError in DebertaV2 import is unrelated to qwen3_omni_moe feature-extraction length behavior." }, { "left": "issue:43335", "right": "issue:43504", "accept": false, - "reason": "Sparse layer creation bug and BEiT legacy-field loading bug are unrelated." + "reason": "SwitchTransformers sparse-layer creation and BEiT semantic-segmentation legacy-field loading are different subsystems and defects." }, { "left": "issue:45588", "right": "issue:45859", "accept": false, - "reason": "Both mention offload/flash attention, but the concrete failures differ." + "reason": "Both involve offload/flash-related behavior, but one is an AttributeError on s_aux=None and the other is a CPU-offload incompatibility in rotary embedding." }, { "left": "issue:29127", "right": "issue:32090", "accept": false, - "reason": "LayoutLMv3 error-message clarity and Trainer broadcast NoneType error are unrelated." + "reason": "LayoutLMv3 box-info error messaging and Trainer GPU broadcast NoneType are clearly unrelated." }, { "left": "issue:43335", "right": "issue:45083", "accept": false, - "reason": "SwitchTransformers config bug and qwen3_omni_moe helper bug are unrelated." + "reason": "SwitchTransformers sparse-layer config and qwen3_omni_moe length helper behavior do not describe the same bug." }, { "left": "issue:39692", "right": "issue:43526", "accept": false, - "reason": "SigLIP2 docs/example errors and BeitImageProcessorFast reduce_labels bug are different problems." + "reason": "SigLIP2 doc example errors and BEiT Fast image processor label reduction are unrelated issues." }, { "left": "issue:45310", "right": "issue:45478", - "accept": false, - "reason": "Titles are near-identical, but the packet only provides soft similarity and no strong duplicate evidence." + "accept": true, + "reason": "Same exact reported bug: transformers>=5.4.0 breaks Qwen3.5 MoE from_pretrained; 45478 is a later duplicate of 45310." }, { "left": "issue:39692", "right": "issue:44493", "accept": false, - "reason": "SigLIP2 documentation/model mismatch and unexpected position-id keys are unrelated." + "reason": "Documentation example failures are not the same as a general unexpected key/position-id issue across models." }, { "left": "issue:43720", "right": "issue:44112", "accept": false, - "reason": "BitNet packed-weight loading and GraniteSpeech device-override CI issues are different." + "reason": "BitNet packed-weight unpacking during accelerate loading is unrelated to the GraniteSpeech CI device-override test." }, { "left": "issue:43335", "right": "issue:45072", "accept": false, - "reason": "Sparse-layer construction and bfloat16 dtype mismatch are unrelated." + "reason": "A sparse-layer config bug is not the same as dtype mismatches in SwitchTransformers/TimmWrapperModel inference." }, { - "left": "issue:45920", - "right": "issue:46192", + "left": "issue:44448", + "right": "issue:44779", "accept": false, - "reason": "Tokenizer wrong-token-IDs regression and return_tensors handling bug are different API issues." + "reason": "Pegasus v4/v5 output differences and Deepseek tokenizer regressions are separate model/tokenizer bugs." + }, + { + "left": "issue:43335", + "right": "issue:44112", + "accept": false, + "reason": "SwitchTransformers sparse-layer creation and a GraniteSpeech CI test failure are not the same underlying problem." }, { "left": "issue:44360", "right": "issue:44561", "accept": false, - "reason": "DSA indexer discussion and removal of is_torch_fx_available are unrelated." + "reason": "A discussion about the DSA indexer lacking ReLU is not the same as trust_remote_code breakage from removing is_torch_fx_available." }, { - "left": "issue:44448", - "right": "issue:44779", + "left": "issue:45920", + "right": "issue:46192", "accept": false, - "reason": "Pegasus output differences and DeepSeek tokenizer regression are different subsystems." + "reason": "Both involve tokenizer/text kwargs behavior, but one is wrong token IDs across multiple models and the other is return_tensors being ignored when text_kwargs is passed." }, { "left": "issue:42490", "right": "issue:43854", "accept": false, - "reason": "Local-path import warning and GLM-4.7-Flash load failure are unrelated." + "reason": "A local-path import warning and a unit-test model loading failure for GLM-4.7-Flash are different issues." }, { "left": "issue:44977", "right": "issue:45229", "accept": false, - "reason": "Qwen3.5 flash-attention generation bug and Gemma4 CUDA OOM are unrelated." + "reason": "Qwen3.5 flash-attention generation issues and Gemma4 multi-GPU CUDA OOM are different failure modes." }, { - "left": "issue:38175", - "right": "issue:44493", + "left": "issue:43606", + "right": "issue:44857", "accept": false, - "reason": "SigLIP2 zero-probabilities and position-id key warnings are unrelated." + "reason": "CPU-offload device mismatch in bark-small and LwDetrImageLoss AMP/CUDA crash are unrelated." }, { - "left": "issue:43606", - "right": "issue:44857", + "left": "issue:38175", + "right": "issue:44493", "accept": false, - "reason": "CPU offload device mismatch in bark-small and AMP crash in LwDetrImageLoss are unrelated." + "reason": "Unexpected zero probabilities in siglip2-base-patch16-224 is not the same as a general unexpected position-id key issue." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The summary is too strong for the packet. Although issue 45310 and 45478 have the highest similarity and matching titles, the packet marks that pair as deterministic_accept=false, so it does not support calling it a clear/true duplicate pair. There are no explicit links or stronger evidence establishing any duplicate cluster, so the claim of \"the only clear duplicate pair\" and the 0.97 confidence overstate the evidence. A more conservative read would be that the cluster is mostly singleton-like with one highly similar issue pair, not a confirmed duplicate." + "accept": true, + "feedback": "The summary is grounded in the packet: the set is heterogeneous, and the only accepted soft pair is 45310/45478, which are near-identical Qwen3.5 MoE from_pretrained reports. The other pairwise rejections are conservative and the reasons stay aligned with the issue titles." }, "evaluator_used": true, - "retried": true, - "accepted_nontrivial_soft_edge": false, + "retried": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -8267,7 +8226,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:10000", "issue:15354", @@ -8327,43 +8286,43 @@ "issue:43701|issue:45083", "issue:43723|issue:44554", "issue:29942|issue:35141", - "issue:43550|issue:45083", "issue:32090|issue:33357", - "issue:43873|issue:45229", + "issue:43550|issue:45083", "issue:44561|issue:44779", + "issue:43873|issue:45229", "issue:43927|issue:45698", + "issue:37428|issue:44987", "issue:44462|issue:44561", "issue:41720|issue:45229", - "issue:37428|issue:44987", "issue:44977|issue:45563", "issue:43278|issue:43329", - "issue:44568|issue:45491", "issue:42490|issue:43575", - "issue:45372|issue:45588", "issue:10000|issue:15354", + "issue:44568|issue:45491", + "issue:45372|issue:45588", "issue:45198|issue:45803", - "issue:43412|issue:45588", - "issue:45372|issue:45406", "issue:44857|issue:45588", + "issue:43412|issue:45588", "issue:43976|issue:45440", + "issue:45372|issue:45406", + "issue:43278|issue:43381", "issue:45459|issue:45712", - "issue:45588|issue:45823", - "issue:43278|issue:43381" + "issue:45588|issue:45823" ], - "prepared_review_unit_hash": "dc37b8bed06cac499fef760da2a986dddc02b2f31e1755541a2fcf30e6442f0e", + "prepared_review_unit_hash": "abbe3156575e09aca9c1d08f1ffbcef69a286916204599f69de0f94fb85cc993", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 36869, + "serialized_chars": 36872, "estimated_input_tokens": 9218, "estimated_eval_tokens": 18692 }, @@ -8372,192 +8331,192 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is highly heterogeneous: the pairs share broad themes like loading, tokenization, attention, or dtype issues, but they do not appear to be the same underlying bug/change. I would not merge any of the soft edges.", - "confidence": 0.94, - "canonical_issue_reason": "If a single representative is needed, issue:45698 is the broadest and most centrally discussed loading-related bug in the set (custom module resolution after save/load).", + "summary": "These items are largely unrelated issues; the soft pairs mostly share only broad subsystem keywords (tokenizers, attention, loading, dtype, Gemma/Qwen, etc.) but not the same concrete bug. No pull requests are present.", + "confidence": 0.97, + "canonical_issue_reason": "Issue #43873 is the best canonical issue candidate: it is open, has the strongest cross-references among the set, and describes a broader, actively discussed quantization/offloading malfunction.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45698 is the best single issue candidate because it has the strongest discussion/inbound-reference signal and a general save_pretrained/from_pretrained failure mode that is easier to use as an umbrella reference than the other, more specialized reports.", + "best_issue_reason": "#43873 is the best representative issue because it is open and appears to be the most central/highly referenced problem in this set.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:34689", "right": "issue:35141", "accept": false, - "reason": "Different bugs: model loading for Llama 3.2 Vision vs embedding reinitialization after resizing tokens." + "reason": "One is a model-loading regression for Llama 3.2 Vision; the other is a post-init embedding reinitialization bug. Different code paths and failure modes." }, { "left": "issue:44857", "right": "issue:45072", "accept": false, - "reason": "Both involve dtype/AMP, but they hit different models and failure modes: LwDetr float16 CUDA crash vs bfloat16 inference mismatch." + "reason": "Both mention dtype problems, but they affect different models and distinct behaviors (loss crash vs inference mismatches). Not the same bug." }, { "left": "issue:44448", "right": "issue:44977", "accept": false, - "reason": "Different models and code paths: Pegasus v4/v5 output drift vs Qwen3.5 flash-attention generation failure." + "reason": "Different models and different symptoms: Pegasus output drift across versions vs Qwen3.5 flash-attention generation failure." }, { "left": "issue:40444", "right": "issue:43526", "accept": false, - "reason": "Different layers: Qwen2.5-VL iterable-dataset multi-image failure vs BeitImageProcessorFast reduce_labels bug." + "reason": "IterableDataset multi-image finetuning failure is unrelated to BeitImageProcessorFast reduce_labels behavior." }, { "left": "issue:28218", "right": "issue:32090", "accept": false, - "reason": "Tokenizer added-space behavior is unrelated to the Trainer _gpu_broadcast_one NoneType error." + "reason": "Tokenizer spacing after added tokens and Trainer/_gpu_broadcast_one NoneType errors are unrelated." }, { "left": "issue:43701", "right": "issue:45083", "accept": false, - "reason": "Checkpoint resume key mismatch is unrelated to the qwen3_omni_moe helper-length bug." + "reason": "Checkpoint resume key mismatch is unrelated to a Qwen3 Omni feature-length helper bug." }, { "left": "issue:43723", "right": "issue:44554", "accept": false, - "reason": "AutoTokenizer v5 loading regression is unrelated to the MPS attention head-dimension correctness issue." + "reason": "Tokenizer loading in v5 and an MPS attention correctness issue are different subsystems and failure modes." }, { "left": "issue:29942", "right": "issue:35141", "accept": false, - "reason": "Flash Attention 2 test failures are unrelated to post_init reinitializing resized embeddings." + "reason": "Flash Attention 2 test failures are unrelated to embedding reinitialization in post_init." + }, + { + "left": "issue:32090", + "right": "issue:33357", + "accept": false, + "reason": "Trainer broadcast TypeError and MacOS bus error with a CLIP model are not the same underlying defect." }, { "left": "issue:43550", "right": "issue:45083", "accept": false, - "reason": "torch.compile/SDPA failure on Bamba-9B-v2 is not the same as a qwen3_omni_moe feature-length helper bug." + "reason": "torch.compile/SDPA failure for Bamba is unrelated to the qwen3_omni_moe helper-length bug." }, { - "left": "issue:32090", - "right": "issue:33357", + "left": "issue:44561", + "right": "issue:44779", "accept": false, - "reason": "Trainer broadcast type error and MacOS bus error on a CLIP model are different failures." + "reason": "A v5 remote-code compatibility break is not the same as DeepSeek tokenizer incorrect results." }, { "left": "issue:43873", "right": "issue:45229", "accept": false, - "reason": "Quantization/offloading behavior and Gemma4 multi-GPU CUDA OOM are distinct problems." + "reason": "Quantization/offloading issues and a Gemma4 multi-GPU OOM are both memory-related but not the same bug." }, { - "left": "issue:44561", - "right": "issue:44779", + "left": "issue:43927", + "right": "issue:45698", "accept": false, - "reason": "Removal of is_torch_fx_available breaking trust_remote_code is unrelated to DeepSeek tokenizer correctness." + "reason": "DiaConfig token-ID persistence and wrong custom module loading after save/load are related to serialization, but they are different concrete failures." }, { - "left": "issue:43927", - "right": "issue:45698", + "left": "issue:37428", + "right": "issue:44987", "accept": false, - "reason": "Both involve save/load behavior, but one is custom token IDs in config and the other is wrong custom module resolution; different root causes." + "reason": "Import error for a flash-attention helper and a model load failure in transformers>=5.1.0 are different incompatibilities." }, { "left": "issue:44462", "right": "issue:44561", "accept": false, - "reason": "AutoTokenizer ignoring tokenizer.json is unrelated to the v5 removal of is_torch_fx_available." + "reason": "AutoTokenizer ignoring tokenizer.json is unrelated to the removal of is_torch_fx_available." }, { "left": "issue:41720", "right": "issue:45229", "accept": false, - "reason": "Qwen3 auto device-mapping cuda assert is not the same bug as Gemma4 multi-GPU OOM." - }, - { - "left": "issue:37428", - "right": "issue:44987", - "accept": false, - "reason": "Missing _flash_supports_window_size import and loading physical-intelligence/fast on 5.1.0 are not clearly the same concrete failure." + "reason": "Qwen3 device-mapping cudaErrorAssert and Gemma4 multi-GPU OOM are separate runtime failures." }, { "left": "issue:44977", "right": "issue:45563", "accept": false, - "reason": "Flash-attention generation corruption and a stale num_return_sequences warning are unrelated." + "reason": "Flash-attention generation malfunction and a stale warning in paged generate() are not the same issue." }, { "left": "issue:43278", "right": "issue:43329", "accept": false, - "reason": "Embedding dtype drift in eval mode is unrelated to the undefined helper variables in the video token-count path." + "reason": "Embedding dtype drift in evaluation is unrelated to an undefined-variable bug in multimodal token counting." }, { - "left": "issue:44568", - "right": "issue:45491", + "left": "issue:42490", + "right": "issue:43575", "accept": false, - "reason": "Tokenizer add_special_tokens regression is unrelated to Gemma3 NaN embeddings from sliding-window attention." + "reason": "Local-path import warning and tensor-parallel OOM when loading Qwen2-57B are different problems." }, { - "left": "issue:42490", - "right": "issue:43575", + "left": "issue:10000", + "right": "issue:15354", "accept": false, - "reason": "Import warning for trailing-slash local paths and tp-related OOM on Qwen2-57B are different issues." + "reason": "German DistilBertModel issue and torch.jit GeneratorExp export failure for ViT are unrelated." }, { - "left": "issue:45372", - "right": "issue:45588", + "left": "issue:44568", + "right": "issue:45491", "accept": false, - "reason": "Gemma4 processor import failure from mistral_common is unrelated to flash_attention crashing on s_aux=None." + "reason": "Tokenizer special-token insertion bug and Gemma3 NaN embeddings with sliding-window attention are unrelated." }, { - "left": "issue:10000", - "right": "issue:15354", + "left": "issue:45372", + "right": "issue:45588", "accept": false, - "reason": "German DistilBertModel issue and GeneratorExp/jit.script export failure are unrelated." + "reason": "Gemma4 processor import failure and flash_attention.py crashing on s_aux=None are distinct bugs." }, { "left": "issue:45198", "right": "issue:45803", "accept": false, - "reason": "Wav2Vec2 save_pretrained/tokenization failure is unrelated to the bare except swallowing errors in FuyuBatchFeature.convert_to_tensors()." + "reason": "Wav2Vec2 save/tokenization failure and a bare-except issue in Fuyu tensor conversion are different code paths." + }, + { + "left": "issue:44857", + "right": "issue:45588", + "accept": false, + "reason": "Float16 AMP crash in LwDetrImageLoss and sink-less flash_attention AttributeError are unrelated." }, { "left": "issue:43412", "right": "issue:45588", "accept": false, - "reason": "Gemma3n executorch export problems are unrelated to the flash_attention s_aux=None crash." + "reason": "Executorch export failures for gemma3n and flash_attention s_aux=None crashes are unrelated." }, { - "left": "issue:45372", - "right": "issue:45406", + "left": "issue:43976", + "right": "issue:45440", "accept": false, - "reason": "Both are Gemma4-related, but one is a processor import error and the other is a missing _tokenizer attribute in serve; different concrete bugs." + "reason": "Python version compatibility break and DeepSeekV3MoE divergence from remote implementation are different issues." }, { - "left": "issue:44857", - "right": "issue:45588", + "left": "issue:45372", + "right": "issue:45406", "accept": false, - "reason": "LwDetr float16 CUDA crash is unrelated to the flash_attention s_aux=None AttributeError." + "reason": "Gemma4 processor loading import error and Gemma4 serve missing _tokenizer are separate failures." }, { - "left": "issue:43976", - "right": "issue:45440", + "left": "issue:43278", + "right": "issue:43381", "accept": false, - "reason": "Python-version compatibility breakage is unrelated to DeepseekV3MoE diverging from remote implementation." + "reason": "BF16/FP32 dtype drift during evaluate and gradient checkpointing in eval mode are not the same bug." }, { "left": "issue:45459", "right": "issue:45712", "accept": false, - "reason": "Hidden tokenizer errors from protobuf handling are unrelated to leftover dummy classes in dummy_pt_objects.py." + "reason": "Tokenizer error masking when protobuf is absent and leftover dummy classes in dummy_pt_objects.py are unrelated." }, { "left": "issue:45588", "right": "issue:45823", "accept": false, - "reason": "flash_attention sink-less-model crash and Gemma4 PLE device mismatch under auto device map are different code paths." - }, - { - "left": "issue:43278", - "right": "issue:43381", - "accept": false, - "reason": "Embedding dtype regression in eval mode is unrelated to gradient checkpointing being disallowed in eval mode." + "reason": "Gemma4 flash-attention AttributeError and Gemma4 PLE device-mapping mismatch affect different parts of the model stack." } ] }, @@ -8579,7 +8538,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:25251", "issue:29127", @@ -8635,20 +8594,20 @@ "issue:45245|issue:45563", "issue:43653|issue:44743", "issue:25251|issue:32090", - "issue:43065|issue:43994", "issue:44206|issue:44479", + "issue:43065|issue:43994", "issue:45372|issue:45459", "issue:44186|issue:45198", "issue:43065|issue:45412", - "issue:43611|issue:46121", "issue:44871|issue:44977", + "issue:43611|issue:46121", "issue:44361|issue:45198", - "issue:42915|issue:42994", - "issue:42490|issue:43873", "issue:32090|issue:33290", + "issue:42490|issue:43873", + "issue:42915|issue:42994", "issue:33357|issue:39692", - "issue:29942|issue:30064", "issue:29127|issue:34567", + "issue:29942|issue:30064", "issue:43994|issue:45412", "issue:44265|issue:45198", "issue:43066|issue:44462", @@ -8660,202 +8619,202 @@ "issue:44610|issue:45412", "issue:43824|issue:44279" ], - "prepared_review_unit_hash": "25107c1da88ee4c6c20c70e063f7659e4b7fb1f3a40fbc575cfdced30ecfe85b", + "prepared_review_unit_hash": "b56ac7102ffbd5e201e0cdfebe12109ead5409c6b3afc2d9b4c674bc9cd59590", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 28, - "serialized_chars": 36089, - "estimated_input_tokens": 9023, - "estimated_eval_tokens": 18302 + "serialized_chars": 36084, + "estimated_input_tokens": 9021, + "estimated_eval_tokens": 18298 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is a grab bag of unrelated Transformers issues; none of the soft pairs look like true duplicates or the same fix. I\u2019d use the core tokenizer-loading bug as the representative issue, but with low confidence because the set is highly heterogeneous.", - "confidence": 0.44, - "canonical_issue_reason": "issue:44462 is the clearest, most generally useful concrete bug report here: a core AutoTokenizer loading problem with a specific failure mode and broad relevance across models.", + "summary": "The items are a heterogeneous set of unrelated bugs/features. None of the soft pairs look like the same underlying issue, so all candidate duplicate links should be rejected.", + "confidence": 0.93, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:44462 is the best representative issue because it is specific, reproducible, and centered on a core library code path rather than a model-specific edge case or an ancillary regression.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44448", "right": "issue:44466", "accept": false, - "reason": "Different problems: output divergence for a model checkpoint vs inconsistent lm_head.weight serialization/device-dependent saving." + "reason": "Different regressions: Pegasus output differences vs lm_head.weight serialization/tied-weights behavior." }, { "left": "issue:45245", "right": "issue:45563", "accept": false, - "reason": "Unrelated failures: category cardinality error in preprocessing vs a stale warning in paged generate()." + "reason": "Unrelated: category-count overflow error vs stale num_return_sequences warning in paged generate()." }, { "left": "issue:43653", "right": "issue:44743", "accept": false, - "reason": "Different subsystems: BigBirdTokenizer special-token registration vs Qwen3.5 recurrent-state caching behavior." + "reason": "Different components and failure modes: BigBirdTokenizer special-token decode vs Qwen3.5 recurrent state reset." }, { "left": "issue:25251", "right": "issue:32090", "accept": false, - "reason": "Top-k pipeline nesting bug is unrelated to Trainer broadcast errors involving NoneType." + "reason": "Top-k pipeline nested-list output is unrelated to Trainer NoneType broadcast errors." }, { - "left": "issue:43065", - "right": "issue:43994", + "left": "issue:44206", + "right": "issue:44479", "accept": false, - "reason": "Sam3PixelDecoder dummy Conv2d issue is not the same as SigLIP2 bad outputs from AutoModel/pipeline loading." + "reason": "Different subsystems: LasrFeatureExtractor center-arg crash vs Qwen VL video-input regression." }, { - "left": "issue:44206", - "right": "issue:44479", + "left": "issue:43065", + "right": "issue:43994", "accept": false, - "reason": "Feature extractor center-arg crash and Qwen VL video regression are different code paths and failure modes." + "reason": "Sam3PixelDecoder dummy Conv2d is unrelated to SigLIP2 AutoModel/pipeline bad results." }, { "left": "issue:45372", "right": "issue:45459", "accept": false, - "reason": "Gemma 4 loading import error from mistral_common is distinct from tokenizer error masking when protobuf is missing." + "reason": "Separate tokenizer/processor import issues: ReasoningEffort missing vs protobuf-decode errors being hidden." }, { "left": "issue:44186", "right": "issue:45198", "accept": false, - "reason": "LayoutLMv2Tokenizer NER/padding crash is unrelated to Wav2Vec2 save_pretrained/tokenization failure." + "reason": "Different tokenizers and failures: LayoutLMv2 NER/padding crash vs Wav2Vec2 save/tokenization failure." }, { "left": "issue:43065", "right": "issue:45412", "accept": false, - "reason": "A dummy layer in Sam3PixelDecoder is not the same as RT-DETR models leaking memory after deletion." + "reason": "Model architecture placeholder vs RT-DETR memory not being released." }, { - "left": "issue:43611", - "right": "issue:46121", + "left": "issue:44871", + "right": "issue:44977", "accept": false, - "reason": "Base-model-prefix loading breakage in v5 is unrelated to convert_rope_params_to_dict rejecting a JSON-loaded list." + "reason": "EOS config mismatch is unrelated to Qwen3.5 flash-attention generation bugs." }, { - "left": "issue:44871", - "right": "issue:44977", + "left": "issue:43611", + "right": "issue:46121", "accept": false, - "reason": "Gemma eos_token_id mismatch and Qwen3.5 flash-attention generation issues are separate model/config problems." + "reason": "Base-model-prefix loading regression is distinct from rope validation TypeError on JSON-loaded lists." }, { "left": "issue:44361", "right": "issue:45198", "accept": false, - "reason": "MLukeTokenizer AttributeError on tasks is not the same as Wav2Vec2 save/tokenization failure." + "reason": "MLukeTokenizer AttributeError and Wav2Vec2 save/tokenization problems are different code paths." }, { - "left": "issue:42915", - "right": "issue:42994", + "left": "issue:32090", + "right": "issue:33290", "accept": false, - "reason": "FineGrainedFP8Config conversion failure and quantized model saving are different quantization workflows." + "reason": "Trainer broadcast NoneType error is unrelated to AdaFactor + DeepSpeed OOM." }, { "left": "issue:42490", "right": "issue:43873", "accept": false, - "reason": "Trailing-slash local model import warning is unrelated to offloading behavior with quantization." + "reason": "Local-path import warning and quantization offloading behavior are separate issues." }, { - "left": "issue:32090", - "right": "issue:33290", + "left": "issue:42915", + "right": "issue:42994", "accept": false, - "reason": "NoneType broadcast error in Trainer is unrelated to Adafactor/deepspeed OOM." + "reason": "FineGrainedFP8Config failure for Qwen3MoE is different from quantized model saving failure." }, { "left": "issue:33357", "right": "issue:39692", "accept": false, - "reason": "MacOS bus error for a pretrained CLIP model is not the same as a documentation example with model/processor mismatch and quantization issues." + "reason": "MacOS bus error with a CLIP model is unrelated to SigLIP2 documentation example mistakes." }, { - "left": "issue:29942", - "right": "issue:30064", + "left": "issue:29127", + "right": "issue:34567", "accept": false, - "reason": "Flash Attention 2 test failures and void segmentation-map processing are different failures in different areas." + "reason": "LayoutLMv3 error-message clarity and TrainerState token counter updating are unrelated." }, { - "left": "issue:29127", - "right": "issue:34567", + "left": "issue:29942", + "right": "issue:30064", "accept": false, - "reason": "LayoutLMv3 error-message clarity is unrelated to TrainerState num_input_tokens_seen not updating." + "reason": "Flash Attention 2 test failures do not match void segmentation-map processing failures." }, { "left": "issue:43994", "right": "issue:45412", "accept": false, - "reason": "SigLIP2 nonsense outputs and RT-DETR memory retention are unrelated bugs." + "reason": "SigLIP2 inference mismatch is unrelated to RT-DETR memory cleanup." }, { "left": "issue:44265", "right": "issue:45198", "accept": false, - "reason": "torch.export exportability with torch_compilable_check is not the same as Wav2Vec2 tokenization/save_pretrained failure." + "reason": "torch.export.export with torch_compilable_check is a different bug from Wav2Vec2 tokenization/save issues." }, { "left": "issue:43066", "right": "issue:44462", "accept": false, - "reason": "Wrong tokenizer decoder type in v5 and ignoring tokenizer.json from the repo are both tokenizer-related but not the same underlying defect." + "reason": "Tokenizer decoder type bug is unrelated to AutoTokenizer ignoring tokenizer.json." }, { "left": "issue:43756", "right": "issue:45440", "accept": false, - "reason": "Smollm3 RoPE-layer dropping and DeepseekV3MoE divergence are separate architecture/implementation mismatches." + "reason": "Smollm3 RoPE-layer count mismatch and DeepseekV3MoE divergence are different model bugs." }, { "left": "issue:43257", "right": "issue:43278", "accept": false, - "reason": "Qwen3 MOE weight conversion with accelerate/deepspeed is unrelated to embedding dtype changing in evaluation." + "reason": "MoE weight conversion with accelerate/deepspeed is unrelated to embedding dtype drift in eval." }, { "left": "issue:43421", "right": "issue:45491", "accept": false, - "reason": "Runtime special-token post-processor staleness and Gemma3 NaN embeddings in mixed-length batches are different bugs." + "reason": "Runtime post-processor updates and Gemma3 NaN embeddings are separate tokenizer/model problems." }, { "left": "issue:43653", "right": "issue:44442", "accept": false, - "reason": "BigBirdTokenizer decode-output bug and AutoTokenizer failing to load FastSpeech2ConformerTokenizer are distinct tokenizer issues." + "reason": "BigBirdTokenizer mask-token decode bug is not the same as AutoTokenizer failing to load FastSpeech2ConformerTokenizer." }, { "left": "issue:43381", "right": "issue:43701", "accept": false, - "reason": "Gradient checkpointing in eval mode and resume_from_checkpoint key mismatch do not share the same failure mechanism." + "reason": "Gradient checkpointing in eval mode is unrelated to resume_from_checkpoint key mismatches." }, { "left": "issue:44610", "right": "issue:45412", "accept": false, - "reason": "Processor/model image-size mismatch is unrelated to RT-DETR memory not being released." + "reason": "OmDet-Turbo processor size mismatch is unrelated to RT-DETR memory leaks." }, { "left": "issue:43824", "right": "issue:44279", "accept": false, - "reason": "Missing Qwen2_5_VLForConditionalGeneration import is a specific API availability bug, not the generic dependency issue described by the other report." + "reason": "Missing Qwen2.5-VL import is a specific API break, not the same as a generic dependency issue." } ] }, @@ -8877,7 +8836,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:29127", "issue:29942", @@ -8906,17 +8865,16 @@ "issue:44387", "issue:44442", "issue:44464", - "issue:44479", "issue:44625", "issue:44743", "issue:44811", "issue:44857", + "issue:44898", "issue:44977", "issue:45003", "issue:45072", "issue:45103", "issue:45245", - "issue:45290", "issue:45372", "issue:45440", "issue:45479", @@ -8932,8 +8890,8 @@ "issue:45440|issue:45593", "issue:29127|issue:33357", "issue:29942|issue:36010", - "issue:43761|issue:45859", "issue:43526|issue:45834", + "issue:43761|issue:45859", "issue:43526|issue:44186", "issue:45103|issue:45372", "issue:44625|issue:45584", @@ -8943,192 +8901,192 @@ "issue:44977|issue:45245", "issue:42915|issue:43931", "issue:43526|issue:44857", - "issue:44464|issue:45491", "issue:42490|issue:43381", "issue:43575|issue:43701", "issue:43262|issue:44206", "issue:43575|issue:44387", - "issue:44743|issue:44811", + "issue:44464|issue:45491", "issue:43646|issue:44077", + "issue:44743|issue:44811", "issue:43441|issue:45588", "issue:44062|issue:45907", "issue:43761|issue:44079", "issue:45003|issue:45440", "issue:43723|issue:45479", - "issue:44479|issue:45290" + "issue:44442|issue:44898" ], - "prepared_review_unit_hash": "37613528d34c6cf8bf92e37cf50bff71ee9a8a0dbd169f9dcfc33492c5d57937", + "prepared_review_unit_hash": "63dce8e618a9013cd4464f71e8e187a704bd0398dc28b23d8ab176f2d77606f8", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { - "node_count": 48, - "item_count": 48, + "node_count": 47, + "item_count": 47, "soft_pair_count": 27, - "serialized_chars": 35861, - "estimated_input_tokens": 8966, - "estimated_eval_tokens": 18188 + "serialized_chars": 35252, + "estimated_input_tokens": 8813, + "estimated_eval_tokens": 17882 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "All proposed soft edges look like false positives: the issues span unrelated models, tokenizers, processors, generation paths, and utility bugs rather than the same underlying defect.", - "confidence": 0.96, - "canonical_issue_reason": "No canonical issue stands out because this is not a true duplicate cluster; the items cover many unrelated subsystems and symptoms.", + "summary": "This cluster is a mixed bag of unrelated Transformers bugs/regressions across model families, tokenizers, generation, audio, and utility code. None of the soft pairs look like the same underlying issue, so no duplicate merge is justified.", + "confidence": 0.9, + "canonical_issue_reason": "Issue 45479 is the clearest representative: it describes a concrete, reproducible regression with broader cross-model impact than the other items.", "canonical_pr_reason": null, - "best_issue_reason": "If forced to pick one representative issue, issue 43761 is a clear, well-scoped regression report, but it is not representative of the rest of the heterogeneous set.", + "best_issue_reason": "Issue 45479 is the best standalone bug report here because it is self-contained, specific, and clearly framed as a general sequence-classification regression.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45440", "right": "issue:45593", "accept": false, - "reason": "Both are MoE-related, but one is a model-implementation divergence and the other is an auxiliary-loss behavior change; different bugs." + "reason": "Different bugs in different model paths: DeepseekV3MoE divergence vs D-FINE auxiliary loss handling." }, { "left": "issue:29127", "right": "issue:33357", "accept": false, - "reason": "LayoutLMv3 error messaging vs. a CLIP Mac bus error are unrelated issues in different models and failure modes." + "reason": "Unrelated failures: LayoutLMv3 error messaging vs a MacOS CLIP bus error." }, { "left": "issue:29942", "right": "issue:36010", "accept": false, - "reason": "FlashAttention 2 test failures and a GenerationMixin import error are different code paths and symptoms." + "reason": "Flash Attention 2 test failure and GenerationMixin import error are separate subsystems." }, { - "left": "issue:43761", - "right": "issue:45859", + "left": "issue:43526", + "right": "issue:45834", "accept": false, - "reason": "Both are regressions, but CLIPVision hidden_states handling and Qwen3_5Moe CPU-offload rotary embedding are separate bugs." + "reason": "BEiTImageProcessorFast label reduction bug vs Kosmos2.5 OCR index error; different code paths." }, { - "left": "issue:43526", - "right": "issue:45834", + "left": "issue:43761", + "right": "issue:45859", "accept": false, - "reason": "BEiT reduce_labels behavior and Kosmos2.5 OCR index errors affect different processors and failure mechanisms." + "reason": "CLIPVisionModel hidden_states regression and Qwen3_5Moe rotary CPU-offload failure are unrelated." }, { "left": "issue:43526", "right": "issue:44186", "accept": false, - "reason": "These are different image/text processor bugs; they do not point to the same underlying defect." + "reason": "Both are preprocessing issues, but they affect different processors and failure modes." }, { "left": "issue:45103", "right": "issue:45372", "accept": false, - "reason": "Auto-docstring crashes with future annotations is unrelated to the Gemma 4/ReasoningEffort import failure." + "reason": "auto_docstring annotation parsing crash vs ReasoningEffort import failure; unrelated." }, { "left": "issue:44625", "right": "issue:45584", "accept": false, - "reason": "Qwen3.5 num_labels propagation and Whisper empty-transcription generation are unrelated bugs." + "reason": "Qwen3.5 num_labels propagation and Whisper empty-transcription generation are different bugs." }, { "left": "issue:29127", "right": "issue:35141", "accept": false, - "reason": "One is about clearer validation errors in LayoutLMv3; the other is output embedding reinitialization after resize." + "reason": "LayoutLMv3 error clarity and token-embedding reinitialization are unrelated issues." }, { "left": "issue:44442", "right": "issue:45072", "accept": false, - "reason": "Tokenizer loading failure and bfloat16 dtype mismatch are different issues with no shared concrete code path." + "reason": "Tokenizer loading failure vs dtype mismatch in inference; no shared concrete code-path bug." }, { "left": "issue:43334", "right": "issue:43531", "accept": false, - "reason": "Both mention Qwen models, but one is a pad_token_id/config loading bug and the other is a sliding_window runtime issue." + "reason": "Both are Qwen3-family issues, but one is a missing config attr and the other is sliding-window behavior." }, { "left": "issue:44977", "right": "issue:45245", "accept": false, - "reason": "Flash-attention generation regression and the 2^24 category limit error are unrelated." + "reason": "Flash-attention generation bug and category-count limit error are unrelated." }, { "left": "issue:42915", "right": "issue:43931", "accept": false, - "reason": "FineGrainedFP8Config failure and Qwen3-VL weight-shape mismatch are separate loading problems." + "reason": "FP8 config failure in Qwen3Moe and Qwen3-VL weight-shape mismatch are distinct load-time problems." }, { "left": "issue:43526", "right": "issue:44857", "accept": false, - "reason": "BEiT label reduction and LwDetrImageLoss AMP crash are unrelated vision bugs." - }, - { - "left": "issue:44464", - "right": "issue:45491", - "accept": false, - "reason": "Compiled-forward chunked generation inconsistency and Gemma3 NaNs with sliding-window attention are different problems." + "reason": "Different models and failure mechanisms: label reduction vs float16 AMP crash." }, { "left": "issue:42490", "right": "issue:43381", "accept": false, - "reason": "Local-path import warnings and gradient checkpointing being disallowed in eval mode are unrelated." + "reason": "Local-path import warning and gradient-checkpointing eval-mode restriction are separate." }, { "left": "issue:43575", "right": "issue:43701", "accept": false, - "reason": "Tensor-parallel OOM and resume_from_checkpoint key mismatch are unrelated training/loading bugs." + "reason": "Tensor-parallel OOM and resume_from_checkpoint key mismatch are unrelated training/load issues." }, { "left": "issue:43262", "right": "issue:44206", "accept": false, - "reason": "Audio chat-template sample-rate defaulting and an unsupported feature-extractor arg are different APIs and bugs." + "reason": "Audio chat-template sampling-rate default and LasrFeatureExtractor center-arg crash are different bugs." }, { "left": "issue:43575", "right": "issue:44387", "accept": false, - "reason": "Both involve memory, but one is load-time OOM with tensor parallelism and the other is int4 CUDA reserved-memory growth." + "reason": "Both mention memory, but one is tp OOM on a specific model and the other is int4 reserved-memory growth; not the same bug." }, { - "left": "issue:44743", - "right": "issue:44811", + "left": "issue:44464", + "right": "issue:45491", "accept": false, - "reason": "Qwen3.5 recurrent-state reset and Whisper batch_decode skip_special_tokens handling are unrelated." + "reason": "Chunked generation inconsistency with compiled forward is unrelated to Gemma3 NaN embeddings from sliding-window attention." }, { "left": "issue:43646", "right": "issue:44077", "accept": false, - "reason": "Custom model initialization breakage and patchtsmixer post_init policy are not the same issue." + "reason": "Custom-model init breakage in v5 and patchtsmixer post_init policy are different issues." + }, + { + "left": "issue:44743", + "right": "issue:44811", + "accept": false, + "reason": "Recurrent-state reset with cache and Whisper batch_decode skip_special_tokens are unrelated." }, { "left": "issue:43441", "right": "issue:45588", "accept": false, - "reason": "Ministral-3 FlashAttention failure and sink-less-model s_aux=None crash are different flash-attention bugs." + "reason": "Both involve flash attention, but they hit different models and distinct crash conditions." }, { "left": "issue:44062", "right": "issue:45907", "accept": false, - "reason": "AddedToken special-argument duplication and list_repo_files revision forwarding are unrelated utility issues." + "reason": "AddedToken keyword conflict and list_repo_files revision forwarding are separate API bugs." }, { "left": "issue:43761", "right": "issue:44079", "accept": false, - "reason": "CLIPVision hidden_states regression and ModelOutput key assignment are different output-handling bugs." + "reason": "Hidden_states regression in CLIPVisionModel is not the same as ModelOutput key assignment issues." }, { "left": "issue:45003", @@ -9140,13 +9098,13 @@ "left": "issue:43723", "right": "issue:45479", "accept": false, - "reason": "AutoTokenizer loading failure and zero-loss single-label classification are different bug classes." + "reason": "Tokenizer loading failure and zero-loss sequence-classification regression do not share the same bug." }, { - "left": "issue:44479", - "right": "issue:45290", + "left": "issue:44442", + "right": "issue:44898", "accept": false, - "reason": "Qwen video-input regression and apply_chat_template tool-call crashes are separate code paths." + "reason": "FastSpeech2ConformerTokenizer loading and Perceiver non-default resolution failure are different code paths." } ] }, @@ -9168,7 +9126,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:25251", "issue:28282", @@ -9188,9 +9146,9 @@ "issue:43388", "issue:43493", "issue:43525", - "issue:43540", "issue:43611", "issue:43643", + "issue:43650", "issue:43720", "issue:43749", "issue:43761", @@ -9204,29 +9162,29 @@ "issue:44442", "issue:44479", "issue:44496", - "issue:44514", "issue:44617", "issue:44743", "issue:44855", "issue:44871", - "issue:44898", "issue:44913", "issue:44987", "issue:45137", "issue:45216", + "issue:45290", "issue:45698", "issue:45759", "issue:45803", - "issue:46178" + "issue:46178", + "issue:46202" ], "soft_pairs": [ - "issue:43232|issue:43388", - "issue:44442|issue:44898", - "issue:33290|issue:34567", "issue:33290|issue:34689", - "issue:43316|issue:43525", + "issue:33290|issue:34567", + "issue:43232|issue:43388", + "issue:44479|issue:45290", "issue:33290|issue:35141", "issue:42490|issue:44743", + "issue:43316|issue:43525", "issue:43381|issue:43873", "issue:43761|issue:44188", "issue:44442|issue:45803", @@ -9235,223 +9193,223 @@ "issue:43720|issue:44442", "issue:44077|issue:44479", "issue:43931|issue:45216", - "issue:42907|issue:45698", "issue:43493|issue:43827", + "issue:42907|issue:45698", "issue:34689|issue:36010", - "issue:43316|issue:45759", "issue:33290|issue:36331", + "issue:43316|issue:45759", "issue:43749|issue:43931", "issue:43873|issue:44871", + "issue:43650|issue:46202", "issue:43643|issue:44913", "issue:44190|issue:44496", "issue:44855|issue:45137", - "issue:43540|issue:44514", "issue:25251|issue:28282", - "issue:43295|issue:43825", - "issue:43065|issue:44617" + "issue:43065|issue:44617", + "issue:43295|issue:43825" ], - "prepared_review_unit_hash": "759edfabeb50972a369751d5e60860d6b63ae084478b931481be73a1703c8538", + "prepared_review_unit_hash": "1984db3e7c7754d3733638ba4ca5fc5ed1093e07e3b76e702f5f4ddf3254e17f", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 29, - "serialized_chars": 36622, - "estimated_input_tokens": 9156, - "estimated_eval_tokens": 18568 + "serialized_chars": 36551, + "estimated_input_tokens": 9138, + "estimated_eval_tokens": 18532 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is highly heterogeneous: the items span unrelated bugs in loading, generation, training, quantization, vision/video, and docs. None of the soft pairs looks like the same concrete underlying issue, so I would not merge any of them.", - "confidence": 0.98, - "canonical_issue_reason": "issue:43611 is the broadest representative of the cluster\u2019s dominant loading/regression theme, but even it is not a true duplicate of the others; the rest are mostly separate bugs across different subsystems.", + "summary": "This cluster is heterogeneous: the items span unrelated Transformers issues across loading, training, generation, quantization, vision, docs, and model config. None of the soft pairs look like the same underlying bug/change, so no merges are justified.", + "confidence": 0.95, + "canonical_issue_reason": "No single issue cleanly represents a shared underlying defect; the cluster is a semantic grab-bag of distinct problems rather than a true duplicate set.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43611 is the best single representative because it targets a general model-loading regression with wider applicability than the more model-specific or peripheral reports.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43232", - "right": "issue:43388", - "accept": false, - "reason": "Generation kwargs after sync_gpus is unrelated to metric gathering dropping tuple labels." - }, - { - "left": "issue:44442", - "right": "issue:44898", + "left": "issue:33290", + "right": "issue:34689", "accept": false, - "reason": "Tokenizer loading failure and Perceiver interpolation failure are different code paths." + "reason": "Different failures: DeepSpeed/Adafactor OOM vs Llama 3.2 Vision model loading regression." }, { "left": "issue:33290", "right": "issue:34567", "accept": false, - "reason": "Deepspeed/Adafactor OOM is not the same as TrainerState token-count bookkeeping." + "reason": "Optimizer memory blow-up is unrelated to TrainerState token-count tracking." }, { - "left": "issue:33290", - "right": "issue:34689", + "left": "issue:43232", + "right": "issue:43388", "accept": false, - "reason": "Optimizer OOM and model-loading regression are different failure modes." + "reason": "Generation kwargs update after sync_gpus is unrelated to metric gathering dropping tuple labels." }, { - "left": "issue:43316", - "right": "issue:43525", + "left": "issue:44479", + "right": "issue:45290", "accept": false, - "reason": "Gemma3 config API mismatch and missing Llama4 pad_token_id are distinct config bugs." + "reason": "Video-input regression in v5.3.0 is not the same as chat-template tool-call crash." }, { "left": "issue:33290", "right": "issue:35141", "accept": false, - "reason": "Training OOM does not match embedding reinitialization in post_init." + "reason": "Adafactor OOM in deepspeed and embedding reinit on resize are different code paths." }, { "left": "issue:42490", "right": "issue:44743", "accept": false, - "reason": "Local-path import warning is unrelated to Qwen3.5 recurrent-state reset behavior." + "reason": "Path-with-slash warning and Qwen recurrent-state cache reset are unrelated." + }, + { + "left": "issue:43316", + "right": "issue:43525", + "accept": false, + "reason": "Both are config-related, but Gemma3TextConfig API mismatch and Llama4 missing pad_token_id are distinct bugs." }, { "left": "issue:43381", "right": "issue:43873", "accept": false, - "reason": "Gradient checkpointing in eval mode is separate from quantization offloading behavior." + "reason": "Gradient checkpointing in eval mode and offloading with quantization do not share the same bug." }, { "left": "issue:43761", "right": "issue:44188", "accept": false, - "reason": "CLIP hidden_states regression and attention-kernel divergence are different issues." + "reason": "CLIPVision hidden_states regression is unrelated to torch.compile attention-kernel divergence." }, { "left": "issue:44442", "right": "issue:45803", "accept": false, - "reason": "Tokenizer loading failure is not the same as a bare-except bug in tensor conversion." + "reason": "Tokenizer load failure and bare-except swallowing errors in Fuyu conversion are different issues." }, { "left": "issue:34689", "right": "issue:43611", "accept": false, - "reason": "Both are loading-related, but they concern different regressions and different triggering conditions/models." + "reason": "Both involve loading, but one is a specific Llama vision model break while the other is a generic base_model_prefix regression." }, { "left": "issue:44987", "right": "issue:46178", "accept": false, - "reason": "Model loading failure for a specific repo is unrelated to backend mapping missing tensorflow_text." + "reason": "Model loading failure with transformers>=5.1.0 is unrelated to missing BACKENDS_MAPPING entry for tensorflow_text." }, { "left": "issue:43720", "right": "issue:44442", "accept": false, - "reason": "Packed-weight unpacking in BitNet is unrelated to AutoTokenizer failing for FastSpeech2ConformerTokenizer." + "reason": "Packed-weight unpacking during accelerate loading is unrelated to AutoTokenizer failing on FastSpeech2ConformerTokenizer." }, { "left": "issue:44077", "right": "issue:44479", "accept": false, - "reason": "Optional post_init enforcement and video-input regression are separate changes." + "reason": "Optional post_init policy for patchtsmixer and a video-input regression are not the same issue." }, { "left": "issue:43931", "right": "issue:45216", "accept": false, - "reason": "Weight-shape mismatch at load time is different from save_pretrained producing a bad checkpoint." + "reason": "Qwen3-VL shape mismatch on load and Qwen3.5 save_pretrained checkpoint corruption are different lifecycle stages and causes." }, { - "left": "issue:42907", - "right": "issue:45698", + "left": "issue:43493", + "right": "issue:43827", "accept": false, - "reason": "Saving dequantized models and loading the wrong custom module after save_pretrained are distinct bugs." + "reason": "SigLIP2 implementation discrepancy and stale docs referencing pipeline() are unrelated." }, { - "left": "issue:43493", - "right": "issue:43827", + "left": "issue:42907", + "right": "issue:45698", "accept": false, - "reason": "Implementation discrepancy in SigLIP2 is unrelated to stale docs referencing pipeline()." + "reason": "Dequantized save failure and wrong custom module loaded after save_pretrained are both serialization-related but not the same defect." }, { "left": "issue:34689", "right": "issue:36010", "accept": false, - "reason": "Model-loading regression and GenerationMixin import error are different API breakages." + "reason": "Model loading break for a specific Llama model is unrelated to GenerationMixin import errors." }, { - "left": "issue:43316", - "right": "issue:45759", + "left": "issue:33290", + "right": "issue:36331", "accept": false, - "reason": "Config API discrepancy is not the same as failing to unwrap text_config in from_config." + "reason": "OOM with Adafactor/DeepSpeed is unrelated to CustomTrainer.compute_loss signature breakage." }, { - "left": "issue:33290", - "right": "issue:36331", + "left": "issue:43316", + "right": "issue:45759", "accept": false, - "reason": "OOM in DeepSpeed/Adafactor does not match a compute_loss signature break." + "reason": "Gemma3TextConfig API discrepancy and missing text_config unwrap in AutoModelForCausalLM.from_config are distinct multimodal config bugs." }, { "left": "issue:43749", "right": "issue:43931", "accept": false, - "reason": "FSDP CPU-efficient loading and Qwen3-VL weight mismatch are both loading-related but not the same bug." + "reason": "FSDP CPU RAM efficient loading failure and Qwen3-VL weight-shape mismatch are different load-time problems." }, { "left": "issue:43873", "right": "issue:44871", "accept": false, - "reason": "Quantization offloading is unrelated to eos_token_id configuration inconsistency." + "reason": "Quantization/offloading behavior and eos_token_id list-vs-scalar inconsistency are unrelated." + }, + { + "left": "issue:43650", + "right": "issue:46202", + "accept": false, + "reason": "A vague data request issue is not the same as Gemma pipeline roundtrip failure on the \u2581 token." }, { "left": "issue:43643", "right": "issue:44913", "accept": false, - "reason": "trust_remote_code missing fields and GPTNeoX rotary_pct reload behavior are separate config issues." + "reason": "trust_remote_code missing fields and GPTNeoX rotary_pct reset on reload are separate config-roundtrip bugs." }, { "left": "issue:44190", "right": "issue:44496", "accept": false, - "reason": "Dataset loading in an example script is unrelated to an unrecognized model config." + "reason": "Local dataset loading in an example script is unrelated to unrecognized model_type in config.json." }, { "left": "issue:44855", "right": "issue:45137", "accept": false, - "reason": "Python 3.13 TorchScript parsing and ZeRO3 deque underflow are different runtime failures." - }, - { - "left": "issue:43540", - "right": "issue:44514", - "accept": false, - "reason": "Video-input processing in Qwen3OmniMoe is unrelated to batched chat-template padding crash." + "reason": "Python 3.13 JIT parsing error and DeepSpeed ZeRO3 deque underflow are entirely different failures." }, { "left": "issue:25251", "right": "issue:28282", "accept": false, - "reason": "Pipeline top_k nesting bug and missing PyTorch import are entirely unrelated." + "reason": "Pipeline top_k nesting bug and missing PyTorch ImportError are unrelated." }, { - "left": "issue:43295", - "right": "issue:43825", + "left": "issue:43065", + "right": "issue:44617", "accept": false, - "reason": "processor.tokenizer regression is not the same as an error-message/doc wording bug about translation tasks." + "reason": "Dummy Conv2d in Sam3PixelDecoder and Sam3Video CUDA OOM are not the same code-path problem." }, { - "left": "issue:43065", - "right": "issue:44617", + "left": "issue:43295", + "right": "issue:43825", "accept": false, - "reason": "Dummy Conv2d in Sam3PixelDecoder and Sam3Video OOM are different defects." + "reason": "Processor/tokenizer regression and an incorrect pipeline translation-support error message are different v5 issues." } ] }, @@ -9473,7 +9431,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:16998", "issue:22355", @@ -9489,6 +9447,7 @@ "issue:43452", "issue:43475", "issue:43504", + "issue:43540", "issue:43550", "issue:43572", "issue:43575", @@ -9502,9 +9461,9 @@ "issue:43761", "issue:44077", "issue:44162", - "issue:44242", "issue:44479", "issue:44496", + "issue:44514", "issue:44534", "issue:44617", "issue:44734", @@ -9516,7 +9475,6 @@ "issue:45127", "issue:45200", "issue:45406", - "issue:45563", "issue:45584", "issue:45698", "issue:45803", @@ -9525,231 +9483,224 @@ "issue:46178" ], "soft_pairs": [ + "issue:43540|issue:44514", "issue:43316|issue:43716", + "issue:43550|issue:43701", "issue:43316|issue:44877", "issue:44162|issue:44792", - "issue:43550|issue:43701", - "issue:44077|issue:44534", "issue:43606|issue:43701", + "issue:44077|issue:44534", "issue:45803|issue:46170", "issue:43404|issue:43441", + "issue:42617|issue:43575", "issue:16998|issue:22355", "issue:44871|issue:45584", - "issue:42617|issue:43575", "issue:43673|issue:44743", "issue:43575|issue:43742", - "issue:43388|issue:43688", "issue:41950|issue:43475", - "issue:43761|issue:44479", "issue:43295|issue:44871", + "issue:43761|issue:44479", + "issue:43388|issue:43688", "issue:43452|issue:44496", "issue:45127|issue:45200", - "issue:44871|issue:46050", "issue:43646|issue:44913", + "issue:44871|issue:46050", "issue:43572|issue:46178", + "issue:32090|issue:35141", "issue:43504|issue:45698", "issue:44734|issue:45406", - "issue:32090|issue:35141", - "issue:44617|issue:45584", - "issue:45563|issue:45584", - "issue:43761|issue:44242" + "issue:44617|issue:45584" ], - "prepared_review_unit_hash": "21a990489c997cac759d47a7a392da335992600365c86b1872f5798ff2212148", + "prepared_review_unit_hash": "0c46592f3d61d1e369fa97beae739b64664a8f4beca8a482e18f99e771c66da4", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 28, - "serialized_chars": 36076, - "estimated_input_tokens": 9019, - "estimated_eval_tokens": 18294 + "soft_pair_count": 27, + "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": "This cluster is heterogeneous: the issues span unrelated loading/config regressions, model-specific bugs, and serving/training edge cases. I don\u2019t see a single underlying duplicate bug or change set tying them together.", - "confidence": 0.96, - "canonical_issue_reason": null, + "summary": "The cluster is very heterogeneous: it mixes unrelated Transformers bugs across loading, generation, vision/video, config, training, and distributed/runtime paths. None of the soft pairs look like true duplicates, so they should stay separate.", + "confidence": 0.92, + "canonical_issue_reason": "Issue 43646 is the broadest representative in the set because it concerns a generic Transformers v5.0 custom-model initialization regression, but the cluster is too mixed to have a real canonical duplicate.", "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "Issue 43646 is the closest thing to a cluster representative, but only as a loose umbrella for init/load regressions; it does not subsume the other reports.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43540", + "right": "issue:44514", + "accept": false, + "reason": "Different failures in different processor/model paths: Qwen3OmniMoe video input processing vs Qwen2_5_VL batched chat-template padding." + }, { "left": "issue:43316", "right": "issue:43716", "accept": false, - "reason": "Both are Gemma-related API complaints, but one is a config discrepancy and the other is an image/text dtype mismatch; different code paths." + "reason": "Gemma3TextConfig API mismatch and Mistral-3 image-preprocessor dtype mismatch are unrelated bugs." + }, + { + "left": "issue:43550", + "right": "issue:43701", + "accept": false, + "reason": "torch.compile/SDPA failure is a runtime/model bug; resume_from_checkpoint key mismatch is a separate checkpoint-loading issue." }, { "left": "issue:43316", "right": "issue:44877", "accept": false, - "reason": "Config/API mismatch in Gemma3TextConfig vs strict config loading for granite_speech are unrelated failures." + "reason": "Both are config-related, but they affect different models and different symptoms: Gemma3TextConfig discrepancy vs granite_speech loading strictness." }, { "left": "issue:44162", "right": "issue:44792", "accept": false, - "reason": "ESM2 training/runtime breakage and a Janus image-generation test failure are different model pipelines and bugs." + "reason": "ESM2 breakage and a janus test failure are not the same underlying bug." }, { - "left": "issue:43550", + "left": "issue:43606", "right": "issue:43701", "accept": false, - "reason": "torch.compile/SDPA failure in Bamba is unrelated to resume_from_checkpoint key mismatches." + "reason": "CPU offload device mismatch is unrelated to checkpoint key mismatch on resume." }, { "left": "issue:44077", "right": "issue:44534", "accept": false, - "reason": "Optional post_init enforcement in patchtsmixer and non-persistent buffer junk in v5 are distinct initialization issues." - }, - { - "left": "issue:43606", - "right": "issue:43701", - "accept": false, - "reason": "CPU offload device mismatch and checkpoint key mismatch are separate runtime/loading problems." + "reason": "Both touch v5 behavior, but one is about optional post_init policy and the other about non-persistent buffer initialization." }, { "left": "issue:45803", "right": "issue:46170", "accept": false, - "reason": "Bare except swallowing errors in FuyuBatchFeature is unrelated to Windows ROCm torch.distributed import/type issues." + "reason": "Fuyu exception handling and Windows ROCm/torch.distributed import issues are separate code paths." }, { "left": "issue:43404", "right": "issue:43441", "accept": false, - "reason": "LM head tying bug in Mistral3 and FlashAttention failure in Ministral-3 are different model-specific regressions." + "reason": "Weight tying in Mistral3ForConditionalGeneration and FlashAttention failures in Ministral-3 are different concrete defects." + }, + { + "left": "issue:42617", + "right": "issue:43575", + "accept": false, + "reason": "3d_parallel execution failure and tensor-parallel OOM are different symptoms with no shared bug evidence." }, { "left": "issue:16998", "right": "issue:22355", "accept": false, - "reason": "model_max_length discussion for DeBERTa-V3 is unrelated to the missing transformers.onnx module import error." + "reason": "A model_max_length question and a missing transformers.onnx module are unrelated." }, { "left": "issue:44871", "right": "issue:45584", "accept": false, - "reason": "Gemma eos_token_id config inconsistency and Whisper empty-transcription failure are unrelated generation bugs." - }, - { - "left": "issue:42617", - "right": "issue:43575", - "accept": false, - "reason": "3d_parallel.py execution failure and Qwen tensor-parallel OOM are different symptoms with different causes." + "reason": "EOS token config inconsistency and Whisper empty-transcription handling are different bugs." }, { "left": "issue:43673", "right": "issue:44743", "accept": false, - "reason": "Chunked-prefill cache missing and recurrent state reset in modular_qwen3_5 are different cache-related defects." + "reason": "Both involve cache, but one is missing GenerationMixin cache in chunked_prefill while the other is recurrent-state reset in a specific modular model." }, { "left": "issue:43575", "right": "issue:43742", "accept": false, - "reason": "Tensor-parallel OOM for a large Qwen model is unrelated to a MobileLLM config loading KeyError." + "reason": "Tensor-parallel OOM and MobileLLM key errors are unrelated load/runtime problems." }, { - "left": "issue:43388", - "right": "issue:43688", + "left": "issue:41950", + "right": "issue:43475", "accept": false, - "reason": "Metric gathering label truncation and auxiliary-loss normalization are separate training/eval bugs." + "reason": "Video-classification processor selection and SAM3 vision encoder attribute access are different failure modes." }, { - "left": "issue:41950", - "right": "issue:43475", + "left": "issue:43295", + "right": "issue:44871", "accept": false, - "reason": "Video-classification processor lookup and SAM3 video missing attribute are different video-model issues." + "reason": "Processor.tokenizer regression and Gemma-3 EOS config mismatch are not the same bug." }, { "left": "issue:43761", "right": "issue:44479", "accept": false, - "reason": "CLIPVision hidden_states regression and Qwen video-input regression affect different architectures and code paths." + "reason": "CLIPVision hidden_states regression and Qwen VL video-input regression affect different models and code paths." }, { - "left": "issue:43295", - "right": "issue:44871", + "left": "issue:43388", + "right": "issue:43688", "accept": false, - "reason": "processor.tokenizer regression in custom code is unrelated to Gemma eos_token_id list-vs-scalar mismatch." + "reason": "Label truncation in gather_for_metrics is unrelated to auxiliary-loss normalization." }, { "left": "issue:43452", "right": "issue:44496", "accept": false, - "reason": "GGUF loading breakage and unrecognized-model/config model_type errors are both loading-related but not the same bug." + "reason": "Both are loading issues, but gguf_file breakage and missing model_type in config.json have different causes." }, { "left": "issue:45127", "right": "issue:45200", "accept": false, - "reason": "LoRA merge collapse with tied embeddings and missing mm_token_type_ids default are distinct model fine-tuning problems." + "reason": "LoRA merge collapse and Gemma 4 mm_token_type_ids defaults are unrelated." }, { - "left": "issue:44871", - "right": "issue:46050", + "left": "issue:43646", + "right": "issue:44913", "accept": false, - "reason": "Gemma eos_token configuration mismatch and quantized save/load breakage are unrelated persistence issues." + "reason": "Generic custom-model initialization break and rotary_pct reload default are both config/init-adjacent, but not the same underlying defect." }, { - "left": "issue:43646", - "right": "issue:44913", + "left": "issue:44871", + "right": "issue:46050", "accept": false, - "reason": "Custom model initialization breakage in v5 and rotary_pct reload regression are different config/init bugs." + "reason": "EOS token inconsistency and quantized save/load corruption are distinct serialization/config problems." }, { "left": "issue:43572", "right": "issue:46178", "accept": false, - "reason": "StableLmConfig pad_token_idx regression and tensorflow_text backend mapping error are unrelated." + "reason": "Missing pad_token_idx in StableLmConfig and tensorflow_text backend mapping errors are unrelated." + }, + { + "left": "issue:32090", + "right": "issue:35141", + "accept": false, + "reason": "GPU broadcast NoneType failure and embedding reinitialization after resize are different bugs." }, { "left": "issue:43504", "right": "issue:45698", "accept": false, - "reason": "Legacy field preventing Beit preset load and wrong custom module after save/load are different serialization issues." + "reason": "Legacy-field preset loading and wrong custom-module loading after save_pretrained are both loading-related, but not the same concrete issue." }, { "left": "issue:44734", "right": "issue:45406", "accept": false, - "reason": "KV-cache continuation tensor indexing crash and Gemma4Processor missing _tokenizer are separate serve bugs." - }, - { - "left": "issue:32090", - "right": "issue:35141", - "accept": false, - "reason": "GPU broadcast NoneType error in Trainer and output embedding reinit after resize are unrelated training/model-init issues." + "reason": "KV-cache continuation indexing and Gemma4Processor missing _tokenizer are separate serve/processor bugs." }, { "left": "issue:44617", "right": "issue:45584", "accept": false, - "reason": "SAM3 video OOM and Whisper empty-transcription regression do not share a root cause." - }, - { - "left": "issue:45563", - "right": "issue:45584", - "accept": false, - "reason": "A stale warning in paged generate() is different from Whisper failing on empty transcription after special-token alignment." - }, - { - "left": "issue:43761", - "right": "issue:44242", - "accept": false, - "reason": "CLIPVision forward regression and load-balancing loss omission are separate model behaviors." + "reason": "CUDA OOM in Sam3Video and Whisper empty-transcription handling are unrelated." } ] }, @@ -9771,7 +9722,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:35141", "issue:41720", @@ -9783,16 +9734,16 @@ "issue:43540", "issue:43550", "issue:43644", + "issue:43761", "issue:43827", - "issue:43906", "issue:43931", "issue:43976", "issue:43994", "issue:44060", "issue:44077", - "issue:44079", "issue:44112", "issue:44190", + "issue:44242", "issue:44462", "issue:44464", "issue:44479", @@ -9803,6 +9754,7 @@ "issue:44737", "issue:44792", "issue:44855", + "issue:44877", "issue:44913", "issue:44933", "issue:44964", @@ -9814,26 +9766,27 @@ "issue:45362", "issue:45381", "issue:45563", + "issue:45584", "issue:45588", "issue:45600", "issue:45803", "issue:45907", - "issue:45987", - "issue:46082", - "issue:46121" + "issue:45987" ], "soft_pairs": [ + "issue:45563|issue:45584", + "issue:43761|issue:44242", "issue:43525|issue:43531", "issue:44792|issue:44977", "issue:43931|issue:44060", "issue:44479|issue:44734", - "issue:44464|issue:45563", "issue:44534|issue:44913", - "issue:43906|issue:45290", "issue:44190|issue:44964", + "issue:44464|issue:45563", + "issue:44792|issue:45600", "issue:44521|issue:45381", "issue:43827|issue:43994", - "issue:44792|issue:45600", + "issue:43540|issue:45290", "issue:41720|issue:45245", "issue:45803|issue:45987", "issue:43065|issue:44610", @@ -9841,220 +9794,219 @@ "issue:35141|issue:42490", "issue:44933|issue:45362", "issue:43335|issue:44855", - "issue:44077|issue:44079", + "issue:44077|issue:44877", "issue:43976|issue:44855", - "issue:43550|issue:44190", "issue:43644|issue:44913", + "issue:43550|issue:44190", "issue:43540|issue:44734", "issue:45127|issue:45357", "issue:44737|issue:45803", "issue:44462|issue:45907", "issue:44112|issue:45600", - "issue:43335|issue:44190", - "issue:46082|issue:46121" + "issue:43335|issue:44190" ], - "prepared_review_unit_hash": "7752f49269afdf16ecf863625f2503bfa6d44d1c938c35ca213b57ef31df7eee", + "prepared_review_unit_hash": "52451cabab33906c249ddca2fd95319d094e29348ef833045f8dd0bf01204d44", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 29, - "serialized_chars": 36463, - "estimated_input_tokens": 9116, - "estimated_eval_tokens": 18488 + "soft_pair_count": 30, + "serialized_chars": 36705, + "estimated_input_tokens": 9177, + "estimated_eval_tokens": 18610 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is a grab bag of unrelated issues; none of the soft pairs look like the same underlying bug/change, so all soft edges should be rejected. There are no PRs in the cluster.", + "summary": "All proposed soft edges look like false positives. The cluster is a grab-bag of unrelated issues across model bugs, config/loading regressions, docs, and CI/test failures, not a duplicate set.", "confidence": 0.98, - "canonical_issue_reason": null, + "canonical_issue_reason": "No single canonical issue fits: the items span many unrelated code paths and failure modes, so there is no clear duplicate anchor.", "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "No issue is globally representative enough to serve as a canonical duplicate target for this cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:45563", + "right": "issue:45584", + "accept": false, + "reason": "Both are generation-related, but one is a stale warning and the other is an empty-transcription crash after token alignment; different bugs." + }, + { + "left": "issue:43761", + "right": "issue:44242", + "accept": false, + "reason": "CLIPVision hidden_states regression and MoE load-balancing loss omission are unrelated model-path issues." + }, { "left": "issue:43525", "right": "issue:43531", "accept": false, - "reason": "Different model/config bugs: missing pad_token_id vs sliding_window handling." + "reason": "Missing pad_token_id on Llama4Config and Qwen3-MoE sliding_window behavior are distinct config/model bugs." }, { "left": "issue:44792", "right": "issue:44977", "accept": false, - "reason": "Unrelated failures: janus test failure vs Qwen3.5 flash-attention generation." + "reason": "A failing Janus image-generation test and Qwen3.5 flash-attention generation issue are different code paths." }, { "left": "issue:43931", "right": "issue:44060", "accept": false, - "reason": "Both Qwen-related, but different problems: load-time weight shape mismatch vs tied-weights warning." + "reason": "Weight-shape mismatch on model load is not the same as an incorrect tied-weights warning in Qwen3-Next." }, { "left": "issue:44479", "right": "issue:44734", "accept": false, - "reason": "Different code paths: multimodal video regression vs serve KV-cache indexing." + "reason": "Video-input regression in several Qwen VL models and KV-cache continuation crash in serve are unrelated." }, { - "left": "issue:44464", - "right": "issue:45563", + "left": "issue:44534", + "right": "issue:44913", "accept": false, - "reason": "Chunked generation inconsistency is not the same as a stale warning about num_return_sequences." + "reason": "Non-persistent buffer initialization bug and GPTNeoX rotary_pct reload bug are separate issues." }, { - "left": "issue:44534", - "right": "issue:44913", + "left": "issue:44190", + "right": "issue:44964", "accept": false, - "reason": "Different bugs: non-persistent buffer init vs GPTNeoX config reload behavior." + "reason": "Local dataset loading failure in an example script is unrelated to loading Phi-4-multimodal-instruct." }, { - "left": "issue:43906", - "right": "issue:45290", + "left": "issue:44464", + "right": "issue:45563", "accept": false, - "reason": "Insufficient overlap; one is an isolated reproduction of another issue, the other is a chat template tool-call crash." + "reason": "Compiled-forward chunked generation inconsistency and a stale num_return_sequences warning are different behaviors." }, { - "left": "issue:44190", - "right": "issue:44964", + "left": "issue:44792", + "right": "issue:45600", "accept": false, - "reason": "Dataset-loading example failure vs model-loading failure; different subsystems." + "reason": "A Janus test failure does not match a CI break from removed Sam3LiteText config references." }, { "left": "issue:44521", "right": "issue:45381", "accept": false, - "reason": "Both multimodal, but assistant mask generation and vision_position_ids are different bugs." + "reason": "All-zero assistant masks in chat templating and wrong vision_position_ids for Qwen2.5-VL video inputs are different bugs." }, { "left": "issue:43827", "right": "issue:43994", "accept": false, - "reason": "Docs referencing removed pipeline APIs is unrelated to SigLIP inference quality." + "reason": "Docs still referencing pipeline() and SigLIP2 nonsensical outputs are not the same issue." }, { - "left": "issue:44792", - "right": "issue:45600", + "left": "issue:43540", + "right": "issue:45290", "accept": false, - "reason": "Test failure in a model path vs CI break from removed auto_mappings entries." + "reason": "Video processing ValueError in Qwen3OmniMoe and chat-template crashes on tool-call messages are unrelated." }, { "left": "issue:41720", "right": "issue:45245", "accept": false, - "reason": "CUDA assert on Qwen3 auto device mapping is unrelated to the 2^24 category limit error." + "reason": "Qwen3 auto device mapping cuda assert and category-count runtime error do not share a code path." }, { "left": "issue:45803", "right": "issue:45987", "accept": false, - "reason": "Different behaviors: exception handling in Fuyu batching vs cache length return type." + "reason": "Bare except swallowing interrupts in Fuyu batch conversion and StaticCache return-type mismatch are unrelated." }, { "left": "issue:43065", "right": "issue:44610", "accept": false, - "reason": "Dummy Conv2d in Sam3PixelDecoder is unrelated to OmDet-Turbo input size mismatch." + "reason": "Dummy Conv2d in Sam3PixelDecoder and processor/model image-size mismatch are different problems." }, { "left": "issue:44855", "right": "issue:45588", "accept": false, - "reason": "Python 3.13 import/parse error is unrelated to flash_attention s_aux=None crash." + "reason": "Python 3.13 import parsing failure in DebertaV2 and flash_attention sink-less AttributeError are unrelated." }, { "left": "issue:35141", "right": "issue:42490", "accept": false, - "reason": "Embedding reinit on resize is unrelated to path-trailing-slash import warning." + "reason": "Embedding reinitialization in post_init and trailing-slash local model loading warning are different loading behaviors." }, { "left": "issue:44933", "right": "issue:45362", "accept": false, - "reason": "Missing import from image_utils is unrelated to Qwen3.5 chat crash." + "reason": "Missing image_utils import and Qwen3.5 chat crash are not the same bug." }, { "left": "issue:43335", "right": "issue:44855", "accept": false, - "reason": "SwitchTransformers sparse-layer creation bug is unrelated to Python 3.13 indentation/parsing." + "reason": "Sparse-layer creation in SwitchTransformersConfig and DebertaV2 import parsing error are unrelated." }, { "left": "issue:44077", - "right": "issue:44079", + "right": "issue:44877", "accept": false, - "reason": "Different object-model issues: optional post_init vs ModelOutput key assignment." + "reason": "Optional post_init deprecation and strict-config loading failure are different config validation issues." }, { "left": "issue:43976", "right": "issue:44855", "accept": false, - "reason": "Python version incompatibility at 5.1.0 is a different issue than a decorator/comment parsing failure." - }, - { - "left": "issue:43550", - "right": "issue:44190", - "accept": false, - "reason": "torch.compile/SDPA model failure is unrelated to a local dataset loading problem." + "reason": "Python version support regression and DebertaV2 import parsing failure are unrelated." }, { "left": "issue:43644", "right": "issue:44913", "accept": false, - "reason": "Non-persistent buffer initialization bug is unrelated to GPTNeoX config persistence." + "reason": "Non-persistent buffer junk in v5 and GPTNeoX rotary_pct reload defaulting are separate bugs." }, { - "left": "issue:43540", - "right": "issue:44734", + "left": "issue:43550", + "right": "issue:44190", "accept": false, - "reason": "Video-input ValueError in Qwen3OmniMoe is unrelated to serve KV-cache tensor indexing." + "reason": "torch.compile SDPA failure in Bamba and local dataset loading failure are unrelated." }, { "left": "issue:45127", "right": "issue:45357", "accept": false, - "reason": "LoRA merge with extended vocab is unrelated to incorrect visual encoder keys on save_pretrained." + "reason": "LoRA merge with extended vocab corrupting tied embeddings and incorrect visual encoder keys on save_pretrained are different code paths." }, { "left": "issue:44737", "right": "issue:45803", "accept": false, - "reason": "XLNet device placement bug is unrelated to broad exception swallowing in Fuyu batching." + "reason": "CPU device omission in XLNet positional encoding and Fuyu bare-except error masking are unrelated." }, { "left": "issue:44462", "right": "issue:45907", "accept": false, - "reason": "AutoTokenizer ignoring tokenizer.json is unrelated to list_repo_files not forwarding revision." + "reason": "Tokenizer.json being ignored and list_repo_files not forwarding revision are separate Hub-loading issues." }, { "left": "issue:44112", "right": "issue:45600", "accept": false, - "reason": "Both are CI-related, but one is a stale GraniteSpeech test and the other is a broken auto_mappings reference." + "reason": "GraniteSpeech CI device-override test flake and auto_mappings references to removed configs are different CI problems." }, { "left": "issue:43335", "right": "issue:44190", "accept": false, - "reason": "SwitchTransformers config bug is unrelated to dataset loading in the training script." - }, - { - "left": "issue:46082", - "right": "issue:46121", - "accept": false, - "reason": "Llama head_dim validation and rope-param JSON list handling are different configuration validation bugs." + "reason": "SwitchTransformers sparse-layer bug and local dataset loading issue do not share a concrete failure path." } ] }, @@ -10076,7 +10028,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:36246", "issue:38175", @@ -10100,7 +10052,6 @@ "issue:43901", "issue:43976", "issue:44016", - "issue:44062", "issue:44112", "issue:44186", "issue:44190", @@ -10115,7 +10066,6 @@ "issue:44964", "issue:44987", "issue:45003", - "issue:45042", "issue:45216", "issue:45245", "issue:45276", @@ -10125,255 +10075,250 @@ "issue:45542", "issue:45584", "issue:45600", - "issue:45632" + "issue:45632", + "issue:46082", + "issue:46121" ], "soft_pairs": [ + "issue:46082|issue:46121", "issue:44938|issue:45542", "issue:39692|issue:44190", "issue:43479|issue:45375", "issue:45276|issue:45584", - "issue:43295|issue:45276", "issue:36246|issue:41628", - "issue:43650|issue:44220", + "issue:43295|issue:45276", "issue:45245|issue:45584", - "issue:41950|issue:44016", + "issue:43650|issue:44220", "issue:44186|issue:44734", + "issue:41950|issue:44016", "issue:36246|issue:38617", "issue:42175|issue:44279", - "issue:44683|issue:45446", "issue:44246|issue:45003", + "issue:44683|issue:45446", "issue:43404|issue:45216", - "issue:44016|issue:44220", "issue:38175|issue:43065", + "issue:44016|issue:44220", "issue:43643|issue:44496", "issue:44734|issue:45632", "issue:43854|issue:44964", "issue:44964|issue:45600", - "issue:44561|issue:45632", "issue:44112|issue:44964", + "issue:44561|issue:45632", "issue:43976|issue:44987", "issue:42907|issue:43441", - "issue:42490|issue:45632", "issue:43531|issue:45600", + "issue:42490|issue:45632", "issue:43295|issue:45335", - "issue:43526|issue:43901", - "issue:44496|issue:45042", - "issue:44016|issue:44062" + "issue:43526|issue:43901" ], - "prepared_review_unit_hash": "5ae5dc67ee6c80ff190e2d8f064a55eb7be17438d1b67f1902c63307126a99da", + "prepared_review_unit_hash": "d7500632ffd1006b1d1ec7cea492a4eb0b231ef51f490f0b7a0c20d63b108d4d", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 31, - "serialized_chars": 36923, - "estimated_input_tokens": 9231, - "estimated_eval_tokens": 18718 + "soft_pair_count": 30, + "serialized_chars": 36663, + "estimated_input_tokens": 9166, + "estimated_eval_tokens": 18588 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is heterogeneous: most items are unrelated model-loading/import/config regressions across different models and subsystems. I did not find any soft pair that looks like the same concrete bug/change, so all soft edges are rejected.", - "confidence": 0.94, - "canonical_issue_reason": "Issue 44561 is the broadest, most cross-cutting regression-style report in the set: a v5 compatibility break impacting trust_remote_code models. It is a better anchor than the many model-specific import/load/config complaints here.", + "summary": "Mostly same broad Transformers regression family, but the individual reports are about different APIs, models, and failure modes. I would not deduplicate any of the soft pairs.", + "confidence": 0.84, + "canonical_issue_reason": "issue:44964 is the clearest concrete, user-facing loading regression with a specific model and version context, so it is the best representative issue in this mixed set.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 44561 is the best representative of the cluster\u2019s main theme (Transformers v5 regressions affecting remote-code/model-loading paths) and has the clearest general duplicate-target potential.", + "best_issue_reason": "It is specific, reproducible, and representative of the common \"latest Transformers breaks model loading\" theme.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:46082", + "right": "issue:46121", + "accept": false, + "reason": "Different bugs: LlamaConfig head_dim validation vs. rope-parameter JSON list handling." + }, { "left": "issue:44938", "right": "issue:45542", "accept": false, - "reason": "Different failure domains: Python 3.14 import/load issue vs missing TensorFlow backend when only tensorboard is installed." + "reason": "Unrelated failures: Python 3.14 import/load issue vs. missing TensorFlow backend dependency." }, { "left": "issue:39692", "right": "issue:44190", "accept": false, - "reason": "Different problems: SigLIP2 docs/example errors vs local dataset loading in a training script." + "reason": "Docs/example errors for SigLIP2 vs. local dataset loading failure in a training script." }, { "left": "issue:43479", "right": "issue:45375", "accept": false, - "reason": "Both are config-related, but they affect different models and different fields; not the same underlying bug." + "reason": "Different model configs and different missing/defaulted fields; not the same bug." }, { "left": "issue:45276", "right": "issue:45584", "accept": false, - "reason": "Unrelated code paths: token embedding resize behavior in Gemma4 vs Whisper generation after special-token alignment." - }, - { - "left": "issue:43295", - "right": "issue:45276", - "accept": false, - "reason": "Different regressions: processor/tokenizer API behavior vs embedding resize propagation." + "reason": "Gemma4 embedding resize bug is unrelated to Whisper empty-transcription generation failure." }, { "left": "issue:36246", "right": "issue:41628", "accept": false, - "reason": "Both are import errors, but for different symbols and different modules; not the same bug." + "reason": "Both are import errors, but they concern different symbols and different API breakages." }, { - "left": "issue:43650", - "right": "issue:44220", + "left": "issue:43295", + "right": "issue:45276", "accept": false, - "reason": "One is a placeholder/data request issue; the other is a specific audio feature extraction bug." + "reason": "Processor/tokenizer regression is a different code path from token embedding resizing." }, { "left": "issue:45245", "right": "issue:45584", "accept": false, - "reason": "Category-count runtime error is unrelated to Whisper empty-transcription generation failure." + "reason": "Category-count runtime error and Whisper empty-output bug are unrelated." }, { - "left": "issue:41950", - "right": "issue:44016", + "left": "issue:43650", + "right": "issue:44220", "accept": false, - "reason": "Video-classification processor lookup bug vs notebook syntax error; no shared code-path." + "reason": "Placeholder data issue vs. audio feature extraction bug; no common underlying defect." }, { "left": "issue:44186", "right": "issue:44734", "accept": false, - "reason": "Tokenizer/padding crash and server KV-cache indexing crash are different components and failures." + "reason": "Tokenizer padding/truncation crash is unrelated to serve KV-cache indexing." + }, + { + "left": "issue:41950", + "right": "issue:44016", + "accept": false, + "reason": "Pipeline processor lookup bug vs. notebook syntax error; completely different problems." }, { "left": "issue:36246", "right": "issue:38617", "accept": false, - "reason": "Both are import-related but for different missing names and different areas of the package." + "reason": "Both are import failures, but they are for different removed/missing symbols in different modules." }, { "left": "issue:42175", "right": "issue:44279", "accept": false, - "reason": "Packaging/backends dependency complaint vs a generic dependency issue; too vague and not the same concrete problem." + "reason": "Specific missing TensorFlow backend dependency vs. vague dependency issue; not the same fix." }, { - "left": "issue:44683", - "right": "issue:45446", + "left": "issue:44246", + "right": "issue:45003", "accept": false, - "reason": "Both touch flex_attention, but one is a compiled-kernel failure on newer torch and the other is a version-check/import guard bug." + "reason": "Import performance regression is not the same as unsafe sys.modules access." }, { - "left": "issue:44246", - "right": "issue:45003", + "left": "issue:44683", + "right": "issue:45446", "accept": false, - "reason": "Import performance regression and unsafe sys.modules access are not the same concrete bug." + "reason": "Both mention flex_attention, but one is a compiled-kernel failure and the other is a version-check/import gating bug." }, { "left": "issue:43404", "right": "issue:45216", "accept": false, - "reason": "Different models and failures: untied lm_head weights vs incorrect save_pretrained checkpoint serialization." + "reason": "Mistral3 weight-tying bug and Qwen3.5 save_pretrained regression are different model-specific issues." }, { - "left": "issue:44016", - "right": "issue:44220", + "left": "issue:38175", + "right": "issue:43065", "accept": false, - "reason": "Notebook syntax error is unrelated to audio feature extraction code." + "reason": "SigLIP2 probability behavior and Sam3PixelDecoder dummy conv are unrelated model bugs." }, { - "left": "issue:38175", - "right": "issue:43065", + "left": "issue:44016", + "right": "issue:44220", "accept": false, - "reason": "Different model families and different issues: SigLIP2 zero probabilities vs SAM3 decoder dummy layer." + "reason": "Notebook syntax error vs. audio feature extraction bug; no overlap in code path." }, { "left": "issue:43643", "right": "issue:44496", "accept": false, - "reason": "Both involve config/model loading, but one is missing fields with trust_remote_code and the other is an unrecognized model_type error; distinct root causes." + "reason": "trust_remote_code field loss and unrecognized model_type are different config-loading failures." }, { "left": "issue:44734", "right": "issue:45632", "accept": false, - "reason": "Server tensor indexing crash vs local trust_remote_code cache-path collision are different failure modes." + "reason": "Serve KV-cache continuation crash is unrelated to local-model cache-path collision." }, { "left": "issue:43854", "right": "issue:44964", "accept": false, - "reason": "Different models and symptoms: GLM unit-test loading issue vs Phi-4 multimodal loading issue." + "reason": "Different models and likely different root causes; both are load failures but not the same bug." }, { "left": "issue:44964", "right": "issue:45600", "accept": false, - "reason": "Model loading failure for Phi-4 multimodal is unrelated to stale auto_mappings references and CI breakage." + "reason": "Model loading regression vs. auto_mappings CI breakage from removed configs." }, { - "left": "issue:44561", - "right": "issue:45632", + "left": "issue:44112", + "right": "issue:44964", "accept": false, - "reason": "Both mention trust_remote_code, but one is a v5 API removal regression and the other is a cache-path collision; not the same bug." + "reason": "CI test flake in GraniteSpeech is unrelated to Phi-4 multimodal loading." }, { - "left": "issue:44112", - "right": "issue:44964", + "left": "issue:44561", + "right": "issue:45632", "accept": false, - "reason": "CI test flake in GraniteSpeech is unrelated to Phi-4 multimodal model loading." + "reason": "Trust-remote-code breakage from removed helper is different from cache-path collision." }, { "left": "issue:43976", "right": "issue:44987", "accept": false, - "reason": "General Python-version compatibility complaint vs a specific model-loading failure; not the same underlying issue." + "reason": "Python version compatibility issue vs. a specific model loading failure." }, { "left": "issue:42907", "right": "issue:43441", "accept": false, - "reason": "Different Ministral issues: saving dequantized models vs FlashAttention failure." + "reason": "Saving dequantized Ministral/Devstral and FlashAttention failures are different failure modes." }, { - "left": "issue:42490", - "right": "issue:45632", + "left": "issue:43531", + "right": "issue:45600", "accept": false, - "reason": "Both are local-path related, but one is a warning on trailing slashes and the other is a cache collision for same leaf names." + "reason": "Qwen3-MoE sliding_window bug is unrelated to Sam3LiteText auto-mapping CI breakage." }, { - "left": "issue:43531", - "right": "issue:45600", + "left": "issue:42490", + "right": "issue:45632", "accept": false, - "reason": "Qwen3-MoE sliding-window behavior vs Sam3LiteText auto-mapping removal are unrelated." + "reason": "Trailing-slash import warning and leaf-directory cache collision are different path-handling issues." }, { "left": "issue:43295", "right": "issue:45335", "accept": false, - "reason": "Both involve resize_token_embeddings, but on different architectures and different propagation bugs." + "reason": "Processor-tokenizer regression is unrelated to t5gemma embedding resize propagation." }, { "left": "issue:43526", "right": "issue:43901", "accept": false, - "reason": "Image processor label reduction bug vs text-classification docs/behavior mismatch are unrelated." - }, - { - "left": "issue:44496", - "right": "issue:45042", - "accept": false, - "reason": "Unrecognized model config loading vs PIL image processors requiring torchvision are different code paths." - }, - { - "left": "issue:44016", - "right": "issue:44062", - "accept": false, - "reason": "Notebook syntax error and AddedToken keyword collision are unrelated." + "reason": "BeitImageProcessorFast label reduction bug and a docs/behavior mismatch for text classification are not duplicates." } ] }, @@ -10395,7 +10340,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:38175", "issue:39692", @@ -10404,7 +10349,6 @@ "issue:43299", "issue:43335", "issue:43381", - "issue:43450", "issue:43479", "issue:43525", "issue:43577", @@ -10414,10 +10358,11 @@ "issue:43854", "issue:43901", "issue:43976", + "issue:44016", + "issue:44062", "issue:44075", "issue:44242", "issue:44279", - "issue:44297", "issue:44336", "issue:44351", "issue:44368", @@ -10429,6 +10374,7 @@ "issue:44779", "issue:44933", "issue:45020", + "issue:45042", "issue:45081", "issue:45200", "issue:45216", @@ -10446,6 +10392,8 @@ "issue:46132" ], "soft_pairs": [ + "issue:44496|issue:45042", + "issue:44016|issue:44062", "issue:43673|issue:44336", "issue:43335|issue:45593", "issue:43824|issue:44933", @@ -10463,228 +10411,226 @@ "issue:44351|issue:45278", "issue:43577|issue:45216", "issue:41950|issue:45020", - "issue:43976|issue:45405", "issue:38175|issue:44617", "issue:41950|issue:45823", "issue:44779|issue:45812", - "issue:39692|issue:43901", "issue:44279|issue:45405", + "issue:39692|issue:43901", "issue:44683|issue:45542", "issue:43295|issue:44779", + "issue:43976|issue:45405", "issue:43299|issue:43854", "issue:43650|issue:46132", - "issue:44462|issue:45081", - "issue:43450|issue:44279", - "issue:44297|issue:44462" + "issue:44462|issue:45081" ], - "prepared_review_unit_hash": "2b57409df080534f53c133ed5ca0b285ae4fdfa64e2a3c591fd3072a1d1b6e6a", + "prepared_review_unit_hash": "8aab79cfa70a733fea1d6ae08b2745f2829d233ee373f2ad9e45c735c9bc9d0f", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { - "node_count": 47, - "item_count": 47, + "node_count": 48, + "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 36129, - "estimated_input_tokens": 9033, - "estimated_eval_tokens": 18322 + "serialized_chars": 36712, + "estimated_input_tokens": 9178, + "estimated_eval_tokens": 18612 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is highly heterogeneous: it mixes unrelated bugs in tokenizer handling, multimodal configs, model loading/saving, pipelines, docs, and dependency/version compatibility. I found no true duplicate pairs; all soft edges are false positives.", - "confidence": 0.93, - "canonical_issue_reason": null, + "summary": "No soft-edge pair looks like a true duplicate or the same fix; the set is mostly heterogeneous regressions, docs issues, and tokenizer/import bugs across different models and code paths.", + "confidence": 0.94, + "canonical_issue_reason": "issue:44521 is the most central user-facing bug in the set: it is open, has the most inbound references, and reports a broad multimodal chat-template failure.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43299 is the closest representative because it is a concrete, high-signal regression in a major model-loading path, but it still does not serve as a true duplicate hub for this mixed cluster.", + "best_issue_reason": "issue:44521 is the best representative issue to keep because it is actionable, well-scoped, and impacts a common multimodal API path.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44496", + "right": "issue:45042", + "accept": false, + "reason": "Different bugs: model-loading/config resolution versus PIL image processor dependency handling." + }, + { + "left": "issue:44016", + "right": "issue:44062", + "accept": false, + "reason": "Unrelated failures: a notebook syntax error versus an AddedToken constructor keyword collision." + }, { "left": "issue:43673", "right": "issue:44336", "accept": false, - "reason": "Different subsystems and symptoms: chunked_prefill cache handling vs ANSI formatting in loading_report." + "reason": "Different subsystems and symptoms: chunked prefill cache plumbing versus ANSI output formatting." }, { "left": "issue:43335", "right": "issue:45593", "accept": false, - "reason": "Unrelated model logic: SwitchTransformers sparse-layer initialization vs D-FINE auxiliary-loss behavior." + "reason": "Different model paths and behaviors: SwitchTransformers sparse-layer construction versus D-FINE auxiliary-loss handling." }, { "left": "issue:43824", "right": "issue:44933", "accept": false, - "reason": "Both are import problems, but for different missing symbols in different modules and with different causes." + "reason": "Both are import-related, but they concern different missing symbols/modules and different underlying fixes." }, { "left": "issue:44075", "right": "issue:44368", "accept": false, - "reason": "Optimizer argument handling is unrelated to the tie_word_embeddings warning in a Qwen LoRA setup." + "reason": "Optimizer argument usage and a tie_word_embeddings warning are unrelated issues." }, { "left": "issue:43299", "right": "issue:45216", "accept": false, - "reason": "One is a model-loading failure; the other is a save_pretrained checkpoint serialization regression." + "reason": "Different regression surfaces: Qwen3VL model loading versus Qwen3.5 save_pretrained checkpoint content." }, { "left": "issue:43976", "right": "issue:44279", "accept": false, - "reason": "Python-version compatibility and a generic dependency issue are too broad to be the same bug." + "reason": "The first is a Python-version compatibility claim; the second is a vague dependency issue with no matching concrete failure." }, { "left": "issue:43381", "right": "issue:45593", "accept": false, - "reason": "Gradient-checkpointing eval-mode behavior is unrelated to D-FINE denoising/auxiliary losses." + "reason": "Gradient-checkpointing eval-mode behavior is unrelated to D-FINE auxiliary losses." }, { "left": "issue:43901", "right": "issue:44496", "accept": false, - "reason": "Docs mismatch vs a model/config loading error; different failure modes and code paths." + "reason": "Docs mention of return_all_scores is unrelated to a model import/config error." }, { "left": "issue:44496", "right": "issue:45759", "accept": false, - "reason": "Both involve model configuration, but one is unrecognized-model config metadata and the other is from_config unwrapping for composite Qwen configs." + "reason": "Both involve model resolution, but one is a missing model_type import failure and the other is a composite-config unwrap bug." }, { "left": "issue:45335", "right": "issue:45584", "accept": false, - "reason": "T5Gemma embedding resizing and Whisper empty-transcription generation are unrelated bugs." + "reason": "Tokenizer embedding resize and Whisper empty-transcription generation are different code paths." }, { "left": "issue:43479", "right": "issue:43525", "accept": false, - "reason": "Different config fields and failures: missing default vision/audio configs vs missing pad_token_id." + "reason": "Different config initialization bug versus a missing pad_token_id attribute error." }, { "left": "issue:44521", "right": "issue:45325", "accept": false, - "reason": "Both are multimodal, but assistant mask generation and rope-index scaling are separate code paths." + "reason": "Assistant-mask generation in chat templates and rope-index temporal scaling are distinct multimodal bugs." }, { "left": "issue:44242", "right": "issue:45200", "accept": false, - "reason": "MoE load-balancing loss logic is unrelated to Gemma4 mm_token_type_ids defaults." + "reason": "Load-balancing loss gating and mm_token_type_ids defaults are separate model-loss/config issues." }, { "left": "issue:43299", "right": "issue:45357", "accept": false, - "reason": "Loading regression vs save_pretrained writing incorrect visual-encoder keys; not the same concrete bug." + "reason": "Both are Qwen3.5-related, but one is a loading regression and the other is incorrect save_pretrained key serialization." }, { "left": "issue:44351", "right": "issue:45278", "accept": false, - "reason": "A specific HybridCache import error is not the same as broad import errors after version upgrades." + "reason": "A specific HybridCache import failure is not the same as a broad collection of import errors." }, { "left": "issue:43577", "right": "issue:45216", "accept": false, - "reason": "Blip2 dtype propagation and Qwen3.5 checkpoint saving are different subsystems and symptoms." + "reason": "BLIP2 dtype propagation and Qwen3.5 checkpoint saving are unrelated regressions." }, { "left": "issue:41950", "right": "issue:45020", "accept": false, - "reason": "Video-classification processor selection and remote_code model breakage are unrelated." - }, - { - "left": "issue:43976", - "right": "issue:45405", - "accept": false, - "reason": "Python support/versioning and a PEFT minimum-version bump are not the same bug." + "reason": "Video-classification processor lookup and remote_code model breakage do not share the same concrete bug." }, { "left": "issue:38175", "right": "issue:44617", "accept": false, - "reason": "SigLIP2 zero probabilities and Sam3Video OOM are completely different problems." + "reason": "Zero probabilities in SigLIP2 and Sam3Video OOM are unrelated symptoms and fixes." }, { "left": "issue:41950", "right": "issue:45823", "accept": false, - "reason": "Pipeline processor lookup vs Gemma4 device placement mismatch are unrelated failures." + "reason": "Image-processor lookup in video classification is unrelated to Gemma4 device-map placement." }, { "left": "issue:44779", "right": "issue:45812", "accept": false, - "reason": "Both are tokenizer regressions, but they affect different model families and likely different tokenizer code paths." + "reason": "Different tokenizer regressions affecting different model families; not the same underlying bug." }, { - "left": "issue:39692", - "right": "issue:43901", + "left": "issue:44279", + "right": "issue:45405", "accept": false, - "reason": "SigLIP2 docs example errors and a TextClassificationPipeline docs note are unrelated documentation issues." + "reason": "A general dependency issue is not the same as a PEFT minimum-version bump." }, { - "left": "issue:44279", - "right": "issue:45405", + "left": "issue:39692", + "right": "issue:43901", "accept": false, - "reason": "Generic dependency trouble and a specific unreleased PEFT version bump are different issues." + "reason": "Both are documentation-related, but they refer to different docs and different failures." }, { "left": "issue:44683", "right": "issue:45542", "accept": false, - "reason": "torch flex_attention compilation failure is unrelated to the TensorFlow/tensorboard backend error." + "reason": "Compiled flex_attention on torch>=2.9 and a missing TensorFlow backend are unrelated." }, { "left": "issue:43295", "right": "issue:44779", "accept": false, - "reason": "Custom model processor/tokenizer regression is different from Deepseek tokenizer output corruption." + "reason": "Processor/tokenizer API regression versus Deepseek tokenization output regression are different bugs." + }, + { + "left": "issue:43976", + "right": "issue:45405", + "accept": false, + "reason": "Python support mismatch and unreleased PEFT version pin are unrelated dependency problems." }, { "left": "issue:43299", "right": "issue:43854", "accept": false, - "reason": "They are both model-loading reports, but for different models and different failure points." + "reason": "Different Qwen-related loading/import failures for different models and failure modes." }, { "left": "issue:43650", "right": "issue:46132", "accept": false, - "reason": "Noise/placeholder issue title vs an AttentionInterface.register behavior change; no shared bug." + "reason": "A placeholder data issue and an AttentionInterface.register behavior change are unrelated." }, { "left": "issue:44462", "right": "issue:45081", "accept": false, - "reason": "AutoTokenizer ignoring tokenizer.json and a Mistral regex patch crash are separate tokenizer-loading bugs." - }, - { - "left": "issue:43450", - "right": "issue:44279", - "accept": false, - "reason": "Batched video processor output shape and a dependency issue have no concrete overlap." - }, - { - "left": "issue:44297", - "right": "issue:44462", - "accept": false, - "reason": "Saving the wrong tokenizer_class and ignoring tokenizer.json are different serialization/loading defects." + "reason": "Tokenizer.json precedence and a Mistral regex patch crash are different tokenizer-loading bugs." } ] }, @@ -10706,7 +10652,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:33290", "issue:41950", @@ -10716,7 +10662,7 @@ "issue:43262", "issue:43317", "issue:43441", - "issue:43525", + "issue:43450", "issue:43650", "issue:43653", "issue:43673", @@ -10724,7 +10670,6 @@ "issue:43761", "issue:43784", "issue:43824", - "issue:43881", "issue:43901", "issue:43976", "issue:43994", @@ -10732,11 +10677,14 @@ "issue:44162", "issue:44261", "issue:44263", + "issue:44279", "issue:44291", "issue:44297", "issue:44361", + "issue:44462", "issue:44466", "issue:44521", + "issue:44617", "issue:44623", "issue:44671", "issue:44683", @@ -10745,7 +10693,6 @@ "issue:44898", "issue:45081", "issue:45276", - "issue:45290", "issue:45397", "issue:45542", "issue:45593", @@ -10757,224 +10704,231 @@ "issue:45907" ], "soft_pairs": [ - "issue:44016|issue:44291", + "issue:43450|issue:44279", + "issue:44297|issue:44462", "issue:45081|issue:45907", - "issue:41950|issue:43650", + "issue:44016|issue:44291", "issue:43441|issue:45834", + "issue:41950|issue:43650", "issue:44466|issue:45276", "issue:45600|issue:45712", "issue:42994|issue:43317", "issue:33290|issue:45656", - "issue:43650|issue:45290", + "issue:43653|issue:45593", "issue:44623|issue:44749", "issue:44623|issue:45397", - "issue:43653|issue:45593", "issue:43065|issue:44898", "issue:44261|issue:44263", "issue:43441|issue:44683", "issue:44016|issue:45823", - "issue:43262|issue:44521", "issue:44361|issue:45593", - "issue:42175|issue:43976", "issue:43723|issue:44162", + "issue:42175|issue:43976", "issue:44671|issue:44779", + "issue:43262|issue:44521", "issue:43901|issue:43994", "issue:43673|issue:43761", "issue:43784|issue:45542", "issue:43824|issue:43976", "issue:44297|issue:45397", - "issue:43525|issue:43881" + "issue:43450|issue:44617" ], - "prepared_review_unit_hash": "fe8d52f42a9911139d324c5f7fcde60063736d008beb26e3fa11ae2d96915bfc", + "prepared_review_unit_hash": "fbae76c87136d040cc365101d3d2bb364b54bd1d1d2fe78612ae157c4fce5da9", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 27, - "serialized_chars": 35215, - "estimated_input_tokens": 8804, - "estimated_eval_tokens": 17864 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 35994, + "estimated_input_tokens": 8999, + "estimated_eval_tokens": 18254 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is highly heterogeneous: the soft-linked issues cover unrelated tokenizer, model, pipeline, packaging, CI, and notebook problems. None of the candidate soft edges look like true duplicates or a single shared fix.", - "confidence": 0.98, - "canonical_issue_reason": "No clear canonical issue: the cluster mixes unrelated bugs across many subsystems, so there is no single issue that represents the underlying problem.", + "summary": "This is a very heterogeneous similarity cluster: tokenizer I/O, processor/chat-template bugs, quantization/load issues, vision/audio regressions, DeepSpeed optimizer problems, and unrelated docs/CI items. None of the soft-edge pairs look like the same underlying bug/change, so I would not merge any of them as duplicates.", + "confidence": 0.93, + "canonical_issue_reason": "There is no strong single canonical issue for the whole cluster; if forced to anchor a subgroup, issue 44462 (\"AutoTokenizer ignores tokenizer.json from the repository\") is the most concrete and broadly representative tokenizer-loading regression. Even so, the cluster is too mixed to treat it as the true canonical for all items.", "canonical_pr_reason": null, - "best_issue_reason": "No strong best issue candidate for deduplication purposes; the issues are too diverse to safely treat one as the representative fix target.", + "best_issue_reason": "Issue 44462 is the best issue anchor only in a narrow tokenizer-loading sense: it is concrete, user-facing, and closest to the other tokenizer-related reports. It is not a good global representative of this cluster because most items are unrelated.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44016", - "right": "issue:44291", + "left": "issue:43450 \u2013 Video processors return incorrect shape when input is batched", + "right": "issue:44279 \u2013 Dependency issue with transformers", "accept": false, - "reason": "Notebook syntax error vs. init_empty_weights argument mismatch; different failure modes and code paths." + "reason": "Different problem domains: a batched video-processor shape bug vs a generic dependency complaint. No shared code-path." }, { - "left": "issue:45081", - "right": "issue:45907", + "left": "issue:44297 \u2013 tokenizer.save_pretrained: tokenizer_class in tokenizer_config.json doesn't match the original", + "right": "issue:44462 \u2013 AutoTokenizer ignores tokenizer.json from the repository", "accept": false, - "reason": "Mistral tokenizer regex crash vs. list_repo_files revision forwarding; unrelated areas." + "reason": "Both are tokenizer-related, but one is save/serialization metadata and the other is load-time file selection. Related area, not the same bug." }, { - "left": "issue:41950", - "right": "issue:43650", + "left": "issue:45081 \u2013 _patch_mistral_regex crashes with AttributeError on loading Mistral tokenizer with fix_mistral_regex=True", + "right": "issue:45907 \u2013 list_repo_files should forward the revision argument", "accept": false, - "reason": "Video-classification processor bug vs. an unrelated issue titled \"ADD THE DATA\"; no shared bug." + "reason": "Unrelated utility/CI issue vs tokenizer regex patch crash. Different APIs and failure modes." }, { - "left": "issue:43441", - "right": "issue:45834", + "left": "issue:44016 \u2013 Syntax error in Transformer section 3 notebook", + "right": "issue:44291 \u2013 TypeError when loading model with init_empty_weights due to unexpected _is_hf_initialized argument", "accept": false, - "reason": "Ministral FlashAttention regression vs. Kosmos2.5 OCR index error; different models and symptoms." + "reason": "Docs/notebook syntax issue vs model-loading API regression. Not the same underlying bug." }, { - "left": "issue:44466", - "right": "issue:45276", + "left": "issue:43441 \u2013 Ministral-3 fails with FlashAttention in Transformers v5 RC", + "right": "issue:45834 \u2013 Kosmos2.5: index error on long ocr input", "accept": false, - "reason": "lm_head.weight serialization inconsistency vs. Gemma4 embedding resize behavior; not the same bug." + "reason": "Both are model runtime failures, but the model, trigger, and stack are different; no evidence of a shared code-path." }, { - "left": "issue:45600", - "right": "issue:45712", + "left": "issue:41950 \u2013 video-classification pipeline looks for image processors", + "right": "issue:43650 \u2013 ADD THE DATA", "accept": false, - "reason": "Sam3LiteText auto-mapping CI break vs. leftover dummy classes in dummy_pt_objects; separate cleanup issues." + "reason": "The second issue is too vague and does not describe the same concrete pipeline bug." }, { - "left": "issue:42994", - "right": "issue:43317", + "left": "issue:44466 \u2013 Inconsistent serialization of lm_head.weight depending on model device", + "right": "issue:45276 \u2013 resize_token_embeddings does not affect embed_tokens_per_layer or output_embeddings", "accept": false, - "reason": "Quantized model saving failure vs. dequantized model loading/offload failure; opposite workflows, different bugs." + "reason": "Both touch Gemma4/model weight handling, but one is serialization/tied-weights behavior and the other is embedding resize propagation. Different defects." }, { - "left": "issue:33290", - "right": "issue:45656", + "left": "issue:45600 \u2013 auto_mappings.py references removed Sam3LiteText configs", + "right": "issue:45712 \u2013 leftover dummy classes in dummy_pt_objects.py fail check_repo.py", "accept": false, - "reason": "Adafactor OOM under deepspeed vs. optimizer.step called twice under deepspeed; related subsystem but different concrete defects." + "reason": "Both are maintenance/CI cleanup issues, but they involve different files and independent breakages." }, { - "left": "issue:43650", - "right": "issue:45290", + "left": "issue:42994 \u2013 quantized model saving failed", + "right": "issue:43317 \u2013 device_map=auto fails to load the dequantized model on gpu+cpu offload", "accept": false, - "reason": "Unrelated issue text vs. apply_chat_template crash on tool-call assistant messages." + "reason": "Save-time quantization failure vs load-time/offload placement failure. Same broad area, not the same bug." }, { - "left": "issue:44623", - "right": "issue:44749", + "left": "issue:33290 \u2013 oom when using adafactor optimizer in deepspeed", + "right": "issue:45656 \u2013 Optimizer step being called 2 times when using deepspeed", "accept": false, - "reason": "processor.save_pretrained missing files vs. Chinese-language performance regression report; unrelated." + "reason": "Both mention DeepSpeed, but one is OOM with Adafactor and the other is double-stepping. Different concrete issues." }, { - "left": "issue:44623", - "right": "issue:45397", + "left": "issue:43653 \u2013 BigBirdTokenizer mask token not registered as special token, gives empty decode output", + "right": "issue:45593 \u2013 D-FINE not using any auxiliary losses when denoising is turned off", "accept": false, - "reason": "Missing processor files on save vs. gemma-4 zero3 from_pretrained failure; different code paths." + "reason": "Tokenizer special-token registration bug vs model training-loss behavior. No shared bug." }, { - "left": "issue:43653", - "right": "issue:45593", + "left": "issue:44623 \u2013 processor.save_pretrained(...) missing files", + "right": "issue:44749 \u2013 Transformer upgrade makes filtering data much slower", "accept": false, - "reason": "BigBirdTokenizer special-token registration bug vs. D-FINE auxiliary-loss behavior; unrelated models/features." + "reason": "Save-pretrained file emission vs performance regression in filtering. Unrelated." }, { - "left": "issue:43065", - "right": "issue:44898", + "left": "issue:44623 \u2013 processor.save_pretrained(...) missing files", + "right": "issue:45397 \u2013 gemma-4 zero3 from_pretrained", "accept": false, - "reason": "Sam3PixelDecoder dummy Conv2d vs. Perceiver non-default-resolution interpolation bug; different components." + "reason": "Processor save bug vs Gemma-4 DeepSpeed zero3 loading issue. Different code paths." }, { - "left": "issue:44261", - "right": "issue:44263", + "left": "issue:43065 \u2013 Dummy nn.Conv2d in Sam3PixelDecoder", + "right": "issue:44898 \u2013 Perceiver image classification non-default res fails even with interpolate_pos_encoding=True", "accept": false, - "reason": "MLA q_a_layernorm precision/config issue vs. torch.split return values in GlmMoeDsaIndexer; unrelated defects." + "reason": "Both are vision-model bugs, but one is a dummy layer placeholder and the other is resolution/interpolation handling. Not the same issue." }, { - "left": "issue:43441", - "right": "issue:44683", + "left": "issue:44261 \u2013 MLA q_a_layernorm missing config.rms_norm_eps", + "right": "issue:44263 \u2013 The torch.split() return values in GlmMoeDsaIndexer", "accept": false, - "reason": "FlashAttention failure for Ministral vs. compiled flex_attention failure on torch>=2.9; both attention-related but not the same bug." + "reason": "Unrelated model-specific numerical/config bug vs tensor split semantics." }, { - "left": "issue:44016", - "right": "issue:45823", + "left": "issue:43441 \u2013 Ministral-3 fails with FlashAttention in Transformers v5 RC", + "right": "issue:44683 \u2013 Compiled flex_attention fails on torch >= 2.9", "accept": false, - "reason": "Notebook syntax error vs. Gemma4 PLE device mismatch; no shared underlying issue." + "reason": "Both involve attention backends, but one is a model-specific FlashAttention regression and the other is a torch-version compiled flex_attention incompatibility." }, { - "left": "issue:43262", - "right": "issue:44521", + "left": "issue:44016 \u2013 Syntax error in Transformer section 3 notebook", + "right": "issue:45823 \u2013 Gemma4 PLE device mismatch with device_map=\"auto\" during forward", "accept": false, - "reason": "Audio apply_chat_template sampling-rate default vs. multimodal assistant_masks bug; same API surface, different bug." + "reason": "Notebook syntax/docs issue vs runtime device-placement bug. Different artifacts." }, { - "left": "issue:44361", - "right": "issue:45593", + "left": "issue:44361 \u2013 MLukeTokenizer fails with AttributeError on tasks", + "right": "issue:45593 \u2013 D-FINE not using any auxiliary losses when denoising is turned off", "accept": false, - "reason": "MLukeTokenizer AttributeError vs. D-FINE loss configuration issue; unrelated." + "reason": "Tokenizer task failure vs detection-loss behavior. No meaningful overlap." }, { - "left": "issue:42175", - "right": "issue:43976", + "left": "issue:43723 \u2013 Issue loading tokenizer using AutoTokenizer.from_pretrained in v5", + "right": "issue:44162 \u2013 ESM2 is broken, impacting 1000s of scientists workflows", "accept": false, - "reason": "Missing TensorFlow in torch-only install vs. Python version compatibility failure; different packaging problems." + "reason": "Tokenizer-loading regression vs ESM2 model breakage. Same library, different underlying defects." }, { - "left": "issue:43723", - "right": "issue:44162", + "left": "issue:42175 \u2013 Tensorflow not include in the backend when using pip install '.[torch]'", + "right": "issue:43976 \u2013 Transformers 5.1.0 does not work with Python3.9+ but Python3.10+", "accept": false, - "reason": "AutoTokenizer loading problem in v5 vs. ESM2 broken inference; distinct models and symptoms." + "reason": "Dependency/extras installation issue vs Python-version compatibility issue. Not the same bug." }, { - "left": "issue:44671", - "right": "issue:44779", + "left": "issue:44671 \u2013 CamemBERT produces incorrect masked LM predictions in v5", + "right": "issue:44779 \u2013 Deepseek tokenizer produces incorrect results as of v5", "accept": false, - "reason": "CamemBERT masked-LM regression vs. Deepseek tokenizer regression; both v5 regressions, but different code paths." + "reason": "Both are v5 regressions, but one is CamemBERT masked-LM predictions and the other is Deepseek tokenizer behavior. Different failure surfaces." }, { - "left": "issue:43901", - "right": "issue:43994", + "left": "issue:43262 \u2013 Audio processors: apply_chat_template() defaults to 16kHz sampling rate", + "right": "issue:44521 \u2013 apply_chat_template returns all-zero assistant_masks for multimodal inputs", "accept": false, - "reason": "Documentation mismatch for return_all_scores vs. SigLIP2 bad model/pipeline outputs; unrelated." + "reason": "Both mention apply_chat_template, but one is audio sampling-rate defaulting and the other is multimodal assistant-mask generation. Different bugs." }, { - "left": "issue:43673", - "right": "issue:43761", + "left": "issue:43901 \u2013 TextClassificationPipeline docs still mention return_all_scores, but behavior differs", + "right": "issue:43994 \u2013 google/siglip2-base-patch16-224 produces nonsensical results with AutoModel and pipeline", "accept": false, - "reason": "GenerationMixin chunked_prefill cache issue vs. CLIPVisionModel hidden_states bug; unrelated model internals." + "reason": "Docs mismatch vs incorrect model output. The shared pipeline mention is too broad to treat as a duplicate." }, { - "left": "issue:43784", - "right": "issue:45542", + "left": "issue:43673 \u2013 GenerationMixin cache missing in v5.0.0 during chunked_prefill", + "right": "issue:43761 \u2013 CLIPVisionModel.forward returns hidden_states=None even when output_hidden_states=True", "accept": false, - "reason": "Missing nn import in sentence-transformers integration vs. TensorBoard/TensorFlow backend confusion; different dependency issues." + "reason": "Both are v5 regressions, but one is generation cache handling and the other is vision model hidden-state outputs. Different code paths." }, { - "left": "issue:43824", - "right": "issue:43976", + "left": "issue:43784 \u2013 NameError: name 'nn' is not defined when importing sentence-transformers with latest transformers", + "right": "issue:45542 \u2013 Only tensorboard is installed without TensorFlow, causing undefined tf backend error", "accept": false, - "reason": "Qwen2.5-VL import error vs. Python 3.9/3.10 compatibility issue; unrelated." + "reason": "Both are optional-backend/import issues, but they involve different missing dependencies and different failure points." }, { - "left": "issue:44297", - "right": "issue:45397", + "left": "issue:43824 \u2013 ImportError: cannot import name 'Qwen2_5_VLForConditionalGeneration' from 'transformers'", + "right": "issue:43976 \u2013 Transformers 5.1.0 does not work with Python3.9+ but Python3.10+", "accept": false, - "reason": "tokenizer.save_pretrained metadata mismatch vs. gemma-4 zero3 loading failure; different functionality." + "reason": "Missing class export/import issue vs Python version compatibility issue. Not duplicates." }, { - "left": "issue:43525", - "right": "issue:43881", + "left": "issue:44297 \u2013 tokenizer.save_pretrained: tokenizer_class in tokenizer_config.json doesn't match the original", + "right": "issue:45397 \u2013 gemma-4 zero3 from_pretrained", + "accept": false, + "reason": "Tokenizer serialization metadata bug vs model loading with zero3. Different concerns." + }, + { + "left": "issue:43450 \u2013 Video processors return incorrect shape when input is batched", + "right": "issue:44617 \u2013 Sam3Video: CUDA out of memory", "accept": false, - "reason": "Llama4Config missing pad_token_id vs. GLM-4V-9B loading failure; different models and bugs." + "reason": "Both are video-related, but one is an output-shape bug and the other is memory exhaustion. No shared underlying defect." } ] }, @@ -10996,7 +10950,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:36246", "issue:41628", @@ -11006,13 +10960,13 @@ "issue:42886", "issue:43299", "issue:43352", - "issue:43450", "issue:43525", "issue:43526", "issue:43531", "issue:43596", "issue:43643", "issue:43673", + "issue:43881", "issue:43901", "issue:43976", "issue:44162", @@ -11028,16 +10982,17 @@ "issue:44496", "issue:44561", "issue:44589", - "issue:44617", "issue:44749", "issue:44779", "issue:44857", "issue:44871", + "issue:44877", "issue:45003", "issue:45200", "issue:45250", "issue:45292", "issue:45362", + "issue:45375", "issue:45397", "issue:45412", "issue:45561", @@ -11047,14 +11002,14 @@ "issue:46132" ], "soft_pairs": [ - "issue:43450|issue:44617", - "issue:43525|issue:43643", + "issue:43525|issue:43881", "issue:43901|issue:44246", + "issue:43525|issue:43643", "issue:44188|issue:44336", - "issue:41628|issue:43976", "issue:44589|issue:45362", - "issue:45561|issue:45563", + "issue:41628|issue:43976", "issue:42491|issue:43299", + "issue:45561|issue:45563", "issue:44336|issue:44373", "issue:44295|issue:45397", "issue:44242|issue:45593", @@ -11066,226 +11021,240 @@ "issue:36246|issue:42757", "issue:36246|issue:44351", "issue:44336|issue:44485", - "issue:45003|issue:45561", "issue:44246|issue:44871", + "issue:45003|issue:45561", "issue:43673|issue:44561", "issue:44242|issue:44857", - "issue:44295|issue:44749", "issue:36246|issue:43596", - "issue:43352|issue:45250", "issue:44779|issue:45292", + "issue:44295|issue:44749", + "issue:43352|issue:45250", "issue:44162|issue:45200", "issue:43901|issue:45003", - "issue:45412|issue:46123" + "issue:45412|issue:46123", + "issue:44496|issue:45003", + "issue:44877|issue:45375" ], - "prepared_review_unit_hash": "053fcbee34f06dc052053ce62370aee7aaad2420619ab2ac9f97aa5d46bb8d4e", + "prepared_review_unit_hash": "cf4eacca07be7cf678fef5b190342fe6c1d7f1459e4e856e1f7af2486ce325e7", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 30, - "serialized_chars": 35818, - "estimated_input_tokens": 8955, - "estimated_eval_tokens": 18166 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 36987, + "estimated_input_tokens": 9247, + "estimated_eval_tokens": 18750 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly a loose grab-bag of unrelated issues: import/export regressions, model-specific loading bugs, pipeline behavior, performance, docs, and test infrastructure. There is no clear duplicate cluster; only a few items are superficially similar around import failures or version regressions.", - "confidence": 0.69, - "canonical_issue_reason": "41628 is the closest broad representative of the import/export regression subset (`Cannot import name 'AutoImageProcessor' from 'transformers'`), which is the nearest shared theme here, though the overall cluster is still heterogeneous.", + "summary": "The cluster is highly heterogeneous: most pairs are only superficially similar (imports, config loading, or generic model bugs) but do not describe the same underlying defect or change. No soft pair is a safe duplicate merge.", + "confidence": 0.87, + "canonical_issue_reason": "Issue 44246 is the broadest, most cross-cutting report in the set; it is the closest thing to a cluster anchor, but the surrounding issues are not true duplicates of it.", "canonical_pr_reason": null, - "best_issue_reason": "41628 is the best global issue candidate because it is a generic top-level import failure and most plausibly serves as the broad representative of the small import-API regression subset.", + "best_issue_reason": "Issue 44246 is the most generally representative and high-impact issue here, though the cluster overall is not a single duplicate family.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:43450", - "right": "issue:44617", - "accept": false, - "reason": "Both involve video/model behavior, but one is a batched video-processor shape bug and the other is a Sam3Video OOM issue; different failure modes and fixes." - }, { "left": "issue:43525", - "right": "issue:43643", + "right": "issue:43881", "accept": false, - "reason": "A missing `pad_token_id` attribute in `Llama4Config` is not the same as missing fields from `AutoConfig.from_pretrained(..., trust_remote_code=True)`." + "reason": "Different models and different failures: Llama4 config attr error vs GLM-4V loading failure." }, { "left": "issue:43901", "right": "issue:44246", "accept": false, - "reason": "Docs mismatch for `return_all_scores` and intermittent import slowness are unrelated." + "reason": "Docs mismatch for TextClassificationPipeline vs import-time performance complaint; unrelated bugs." + }, + { + "left": "issue:43525", + "right": "issue:43643", + "accept": false, + "reason": "Both are config-related, but one is a missing pad_token_id attr and the other is trust_remote_code dropping fields; not the same bug." }, { "left": "issue:44188", "right": "issue:44336", "accept": false, - "reason": "Attention-kernel divergence under `torch.compile` is unrelated to ANSI codes emitted by loading report utilities." - }, - { - "left": "issue:41628", - "right": "issue:43976", - "accept": false, - "reason": "Both mention compatibility/import problems, but one is a missing `AutoImageProcessor` export and the other is a Python-version support issue." + "reason": "Attention-kernel divergence under torch.compile is unrelated to ANSI codes in loading_report." }, { "left": "issue:44589", "right": "issue:45362", "accept": false, - "reason": "A missing float8 storage type and a Qwen3.5 chat crash are different concrete bugs." + "reason": "Different runtime errors on different model paths; no shared code-path bug is evident." }, { - "left": "issue:45561", - "right": "issue:45563", + "left": "issue:41628", + "right": "issue:43976", "accept": false, - "reason": "Pytest-xdist file race and a stale `num_return_sequences` warning do not share the same code path." + "reason": "ImportError for AutoImageProcessor is not the same as Python-version compatibility breaking Transformers." }, { "left": "issue:42491", "right": "issue:43299", "accept": false, - "reason": "Both are Qwen/MoE-related regressions, but they affect different model families and loading paths; not the same bug." + "reason": "Both mention Qwen3 MoE, but one is an hf4.x/hf5.x LoRA compatibility issue and the other is a v5.0.0.dev0 Qwen3VL loading breakage." + }, + { + "left": "issue:45561", + "right": "issue:45563", + "accept": false, + "reason": "A pytest-xdist file race and a stale generation warning are unrelated." }, { "left": "issue:44336", "right": "issue:44373", "accept": false, - "reason": "ANSI escape codes in loading reports and a wrong docstring for `position_ids` are unrelated." + "reason": "Terminal ANSI output bug vs a wrong docstring; not the same underlying change." }, { "left": "issue:44295", "right": "issue:45397", "accept": false, - "reason": "A `position_ids` buffer access error and a Gemma-4 Zero3 `from_pretrained` issue are distinct failures." + "reason": "Position_ids buffer access error and gemma-4 zero3 loading are different code paths." }, { "left": "issue:44242", "right": "issue:45593", "accept": false, - "reason": "Missing auxiliary loss in MoE routing and missing auxiliary losses for D-FINE denoising off are different model-specific training bugs." + "reason": "Both concern missing loss terms, but they affect different models and mechanisms; too broad to merge." }, { "left": "issue:44246", "right": "issue:44496", "accept": false, - "reason": "Import performance and an unrecognized model/config error are unrelated." + "reason": "Import performance issue vs unrecognized model/config_type error; unrelated." }, { "left": "issue:41950", "right": "issue:44220", "accept": false, - "reason": "Video-classification processor lookup and `_torch_extract_fbank_features()` are different subsystems and bugs." + "reason": "Video-classification image-processor lookup and audio fbank extraction are different pipelines." }, { "left": "issue:43531", "right": "issue:45362", "accept": false, - "reason": "Both reference Qwen, but one is a `sliding_window` bug in MoE models and the other is a chat crash on Qwen3.5-35B; not the same fix." + "reason": "Both involve Qwen variants, but one is a sliding_window bug and the other is a chat crash; different fixes." }, { "left": "issue:43526", "right": "issue:45003", "accept": false, - "reason": "A Beit image processor label-reduction bug is unrelated to unsafe `sys.modules[]` access in `modeling_utils`." + "reason": "BeitImageProcessorFast label reduction bug is unrelated to sys.modules access in modeling_utils." }, { "left": "issue:42886", "right": "issue:46132", "accept": false, - "reason": "Offline cache loading and `AttentionInterface.register` behavior changes are different problems." + "reason": "Offline cache loading and AttentionInterface.register behavior are unrelated." }, { "left": "issue:36246", "right": "issue:42757", "accept": false, - "reason": "Both are import errors, but they come from different packages and symbols (`transformers.models.qwen2_5_vl` vs `huggingface_hub`)." + "reason": "Both are import errors, but for different symbols and different subsystems." }, { "left": "issue:36246", "right": "issue:44351", "accept": false, - "reason": "Missing `Qwen2_5_VLImageProcessor` and missing `HybridCache` exports are separate API regressions." + "reason": "Different missing exports: Qwen2_5_VLImageProcessor vs HybridCache." }, { "left": "issue:44336", "right": "issue:44485", "accept": false, - "reason": "Loading-report ANSI output and GLM-5 RoPE implementation are unrelated." + "reason": "ANSI rendering bug vs GLM-5 RoPE implementation discussion; no shared defect." }, { - "left": "issue:45003", - "right": "issue:45561", + "left": "issue:44246", + "right": "issue:44871", "accept": false, - "reason": "Unsafe `sys.modules[]` access and a pytest-xdist file race do not describe the same bug." + "reason": "Import-time slowdown and Gemma eos_token_id inconsistency are unrelated." }, { - "left": "issue:44246", - "right": "issue:44871", + "left": "issue:45003", + "right": "issue:45561", "accept": false, - "reason": "Import slowness is unrelated to Gemma-3 `eos_token_id` config inconsistency." + "reason": "Unsafe sys.modules access and xdist file races are unrelated." }, { "left": "issue:43673", "right": "issue:44561", "accept": false, - "reason": "Missing GenerationMixin cache in chunked prefill and removal of `is_torch_fx_available` breaking trust-remote-code models are different regressions." + "reason": "Generation cache missing in chunked_prefill and removal of is_torch_fx_available break different APIs." }, { "left": "issue:44242", "right": "issue:44857", "accept": false, - "reason": "Different auxiliary-loss/loss-scaling bugs in different models; no shared concrete code path." + "reason": "Different auxiliary-loss/AMP crashes in different models; not the same bug." }, { - "left": "issue:44295", - "right": "issue:44749", + "left": "issue:36246", + "right": "issue:43596", "accept": false, - "reason": "A `position_ids` buffer error and a slow data-filtering regression after upgrade are unrelated." + "reason": "ImportError for a vision processor is unrelated to a Deepspeed/BertModel index error." }, { - "left": "issue:36246", - "right": "issue:43596", + "left": "issue:44779", + "right": "issue:45292", "accept": false, - "reason": "An import error for a vision processor and an index error in `BertModel` are unrelated." + "reason": "Tokenizer regression and resize_token_embeddings not updating output embeddings are different issues." }, { - "left": "issue:43352", - "right": "issue:45250", + "left": "issue:44295", + "right": "issue:44749", "accept": false, - "reason": "One is a model-specific unsupported Flash Attention 2 issue; the other is only a generic Flash Attention 2 topic." + "reason": "Position_ids buffer handling and data-filtering slowdown are unrelated." }, { - "left": "issue:44779", - "right": "issue:45292", + "left": "issue:43352", + "right": "issue:45250", "accept": false, - "reason": "Deepseek tokenizer correctness and `resize_token_embeddings` not updating output embeddings are different bugs." + "reason": "Model-specific Flash Attention unsupported vs a generic Flash Attention 2.0 topic; not the same fix." }, { "left": "issue:44162", "right": "issue:45200", "accept": false, - "reason": "ESM2 breakage and Gemma 4 `mm_token_type_ids` defaults concern different models and code paths." + "reason": "ESM2 breakage and Gemma 4 mm_token_type_ids defaulting are unrelated model bugs." }, { "left": "issue:43901", "right": "issue:45003", "accept": false, - "reason": "A pipeline docs mismatch and unsafe `sys.modules[]` access are unrelated." + "reason": "Pipeline docs issue vs sys.modules access bug; different code areas." }, { "left": "issue:45412", "right": "issue:46123", "accept": false, - "reason": "RT-DETR memory release and MaskGenerationPipeline dropping partial-batch results are different runtime bugs." + "reason": "Memory cleanup after deletion and partial-batch is_last handling are unrelated." + }, + { + "left": "issue:44496", + "right": "issue:45003", + "accept": false, + "reason": "Unrecognized model/config loading and sys.modules access are different failure modes." + }, + { + "left": "issue:44877", + "right": "issue:45375", + "accept": false, + "reason": "Both involve strict config, but one blocks granite_speech loading while the other silently drops a field in Qwen3_5MoeVisionConfig; not the same bug." } ] }, @@ -11307,7 +11276,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:42886", "issue:43065", @@ -11323,12 +11292,13 @@ "issue:44060", "issue:44077", "issue:44162", + "issue:44188", "issue:44246", "issue:44336", "issue:44368", "issue:44466", "issue:44479", - "issue:44496", + "issue:44483", "issue:44530", "issue:44734", "issue:44877", @@ -11336,7 +11306,6 @@ "issue:44977", "issue:44987", "issue:44995", - "issue:45003", "issue:45137", "issue:45200", "issue:45229", @@ -11355,241 +11324,242 @@ "issue:45987", "issue:46082", "issue:46123", - "issue:46170" + "issue:46170", + "issue:46202" ], "soft_pairs": [ - "issue:44877|issue:45375", "issue:45987|issue:46082", - "issue:44496|issue:45003", - "issue:45375|issue:45759", "issue:43262|issue:44246", - "issue:45292|issue:45584", + "issue:45375|issue:45759", "issue:43257|issue:45137", + "issue:45292|issue:45584", "issue:45292|issue:45701", "issue:44987|issue:45459", "issue:43232|issue:44336", - "issue:43065|issue:43408", "issue:44995|issue:45200", "issue:44479|issue:46170", + "issue:43065|issue:43408", "issue:43475|issue:43540", - "issue:42886|issue:45229", "issue:44466|issue:45335", + "issue:44483|issue:46202", + "issue:42886|issue:45229", "issue:45397|issue:45656", + "issue:44188|issue:46202", "issue:44060|issue:44077", "issue:43653|issue:44162", - "issue:44368|issue:44977", "issue:44995|issue:45588", - "issue:44368|issue:45563", + "issue:44368|issue:44977", "issue:45137|issue:45600", + "issue:44368|issue:45563", "issue:44877|issue:46170", "issue:43673|issue:44734", "issue:43931|issue:44368", - "issue:43065|issue:46123", "issue:44530|issue:46170", + "issue:43065|issue:46123", "issue:44933|issue:45459" ], - "prepared_review_unit_hash": "1b457941161f3e28ab34de6e36bf0d02941ed7e7990abf66dfc9b0d6cd4e3e73", + "prepared_review_unit_hash": "e1f61cacba98cbecd17dcba9ae163712b92d20e1895ec4f0c8375c55fb74d60a", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { - "node_count": 47, - "item_count": 47, + "node_count": 48, + "item_count": 48, "soft_pair_count": 29, - "serialized_chars": 35852, - "estimated_input_tokens": 8963, - "estimated_eval_tokens": 18182 + "serialized_chars": 36417, + "estimated_input_tokens": 9105, + "estimated_eval_tokens": 18466 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This is not a true duplicate cluster: the items span many unrelated bugs and features (tokenizers, generation/cache, SAM3, Qwen, DeepSpeed, config loading, etc.). The soft pairs mostly share broad subsystems or keywords, but not the same concrete bug or change.", + "summary": "These are mostly unrelated bug reports with title-level keyword overlap only. None of the soft pairs look like the same underlying issue or fix path, so there is no true duplicate cluster here.", "confidence": 0.95, - "canonical_issue_reason": null, + "canonical_issue_reason": "No single canonical issue: the items span unrelated areas (tokenizers, generation/cache, multimodal configs, SAM3, DeepSpeed, import/runtime warnings), so there is no clear duplicate anchor.", "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "No issue is a good global representative because the cluster is heterogeneous; any one choice would misrepresent the rest.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:44877", - "right": "issue:45375", - "accept": false, - "reason": "Both mention config strictness, but they are different models and different missing-field failures." - }, { "left": "issue:45987", "right": "issue:46082", "accept": false, - "reason": "Cache return type and Llama head_dim validation are unrelated issues." + "reason": "Cache-return type bug vs LlamaConfig head_dim validation; different components and failure modes." }, { - "left": "issue:44496", - "right": "issue:45003", + "left": "issue:43262", + "right": "issue:44246", "accept": false, - "reason": "Model auto-loading failure and unsafe sys.modules access are different problems." + "reason": "Audio chat-template sampling-rate default vs import-time performance; unrelated concerns." }, { "left": "issue:45375", "right": "issue:45759", "accept": false, - "reason": "Both are multimodal Qwen config issues, but they affect different fields and code paths." + "reason": "Missing config field dropped by @strict vs from_config unwrapping composite text_config; both config-related but different bugs." }, { - "left": "issue:43262", - "right": "issue:44246", + "left": "issue:43257", + "right": "issue:45137", "accept": false, - "reason": "Audio sampling-rate handling and import slowness are unrelated." + "reason": "MOE weight conversion under accelerate+deepspeed vs ZeRO3 deque IndexError; different code paths and symptoms." }, { "left": "issue:45292", "right": "issue:45584", "accept": false, - "reason": "resize_token_embeddings bug and Whisper empty-transcription failure are different bugs." - }, - { - "left": "issue:43257", - "right": "issue:45137", - "accept": false, - "reason": "DeepSpeed appears in both, but one is weight conversion and the other is a ZeRO3 deque error." + "reason": "Embedding resize propagation vs Whisper empty-transcription generation failure; unrelated." }, { "left": "issue:45292", "right": "issue:45701", "accept": false, - "reason": "Embedding resize behavior and tokenization version drift are not the same issue." + "reason": "resize_token_embeddings propagation bug vs version-dependent tokenization changes; not the same issue." }, { "left": "issue:44987", "right": "issue:45459", "accept": false, - "reason": "Model loading regression and protobuf decode-error masking are unrelated." + "reason": "Model load failure for a specific repo vs tokenizer error masking when protobuf is absent; different root causes." }, { "left": "issue:43232", "right": "issue:44336", "accept": false, - "reason": "Generation kwargs handling and ANSI output formatting are unrelated." - }, - { - "left": "issue:43065", - "right": "issue:43408", - "accept": false, - "reason": "Both are SAM3-related, but one is a dummy conv module and the other is a model-type mismatch warning." + "reason": "Generation kwargs update after sync_gpus vs ANSI output formatting in loading_report; unrelated." }, { "left": "issue:44995", "right": "issue:45200", "accept": false, - "reason": "A stale indexer cache crash and missing mm_token_type_ids are different bugs." + "reason": "GlmMoeDsa stale cache on second forward vs Gemma4 mm_token_type_ids defaulting; different subsystems." }, { "left": "issue:44479", "right": "issue:46170", "accept": false, - "reason": "A video-input regression and a Windows/ROCm distributed import error are unrelated." + "reason": "Video-input regression in Qwen models vs Windows ROCm import/dependency issue; unrelated." }, { - "left": "issue:43475", - "right": "issue:43540", + "left": "issue:43065", + "right": "issue:43408", "accept": false, - "reason": "SAM3 vision encoder output and Qwen3OmniMoe video processing failures are different code paths." + "reason": "Dummy Conv2d in SAM3 pixel decoder vs SAM3 model-type warning; same broad family but not the same bug." }, { - "left": "issue:42886", - "right": "issue:45229", + "left": "issue:43475", + "right": "issue:43540", "accept": false, - "reason": "Tokenizer offline-cache loading and Gemma4 CUDA OOM are unrelated." + "reason": "Missing Sam3VisionEncoderOutput attribute vs Qwen3OmniMoe video processing ValueError; different models and failures." }, { "left": "issue:44466", "right": "issue:45335", "accept": false, - "reason": "Both involve tied/embedding weights, but the concrete failures are different." + "reason": "Device-dependent tied-weight serialization vs resize_token_embeddings not updating decoder embeddings; related theme, different concrete bugs." + }, + { + "left": "issue:44483", + "right": "issue:46202", + "accept": false, + "reason": "Chat/completions request rejection vs Gemma pipeline roundtrip tokenization failure; unrelated API vs tokenizer bug." + }, + { + "left": "issue:42886", + "right": "issue:45229", + "accept": false, + "reason": "Offline tokenizer cache load failure vs Gemma4 multi-GPU CUDA OOM; clearly different problems." }, { "left": "issue:45397", "right": "issue:45656", "accept": false, - "reason": "Both involve DeepSpeed, but one is from_pretrained loading and the other is double optimizer stepping." + "reason": "Gemma4 zero3 from_pretrained issue vs optimizer.step called twice under deepspeed; different deepspeed behavior." + }, + { + "left": "issue:44188", + "right": "issue:46202", + "accept": false, + "reason": "torch.compile attention-kernel divergence vs token roundtrip failure; unrelated." }, { "left": "issue:44060", "right": "issue:44077", "accept": false, - "reason": "Qwen3-Next tied-weight warning and PatchTSMixer post_init policy are unrelated." + "reason": "Incorrect tied-weights warning vs patchtsmixer post_init policy; different validation paths." }, { "left": "issue:43653", "right": "issue:44162", "accept": false, - "reason": "BigBirdTokenizer special-token registration and ESM2 breakage are different issues." - }, - { - "left": "issue:44368", - "right": "issue:44977", - "accept": false, - "reason": "One is a config warning about tie_word_embeddings; the other is a flash-attention generation regression." + "reason": "BigBirdTokenizer special-token registration bug vs ESM2 model breakage; unrelated." }, { "left": "issue:44995", "right": "issue:45588", "accept": false, - "reason": "Stale cache crash and flash_attention s_aux=None crash are unrelated." + "reason": "Stale indexer cache on second forward vs flash_attention AttributeError on s_aux=None; different bugs." }, { "left": "issue:44368", - "right": "issue:45563", + "right": "issue:44977", "accept": false, - "reason": "A tied-weights warning and a stale num_return_sequences warning are different bugs." + "reason": "Warning about tie_word_embeddings in fine-tuning vs actual flash-attention generation failure; not the same issue." }, { "left": "issue:45137", "right": "issue:45600", "accept": false, - "reason": "DeepSpeed ZeRO3 deque failure and Sam3LiteText auto-mapping CI breakage are unrelated." + "reason": "DeepSpeed ZeRO3 deque error vs auto_mappings referencing removed SAM3LiteText configs; unrelated." + }, + { + "left": "issue:44368", + "right": "issue:45563", + "accept": false, + "reason": "Tie-word-embeddings warning vs stale num_return_sequences warning in paged generate; different warnings and triggers." }, { "left": "issue:44877", "right": "issue:46170", "accept": false, - "reason": "Strict config loading and Windows ROCm distributed import errors are unrelated." + "reason": "Strict config rejecting granite_speech vs Windows ROCm distributed import failure; unrelated." }, { "left": "issue:43673", "right": "issue:44734", "accept": false, - "reason": "Both mention cache/generation, but they fail in different components and modes." + "reason": "Missing cache in GenerationMixin during chunked_prefill vs wrong tensor indexing in /v1/responses KV continuation; both cache-related but distinct bugs." }, { "left": "issue:43931", "right": "issue:44368", "accept": false, - "reason": "A Qwen3-VL weight-shape mismatch and a tie_word_embeddings warning are unrelated." + "reason": "Qwen3-VL weight-shape mismatch on load vs tie_word_embeddings warning in Qwen3.5 fine-tuning; unrelated." }, { - "left": "issue:43065", - "right": "issue:46123", + "left": "issue:44530", + "right": "issue:46170", "accept": false, - "reason": "SAM3 dummy layer handling and MaskGenerationPipeline partial-batch behavior are unrelated." + "reason": "PagedAttentionCache invalid group type on Qwen3.5 vs Windows ROCm import error; different layers entirely." }, { - "left": "issue:44530", - "right": "issue:46170", + "left": "issue:43065", + "right": "issue:46123", "accept": false, - "reason": "PagedAttentionCache linear_attention error and Windows ROCm torch.distributed import failure are unrelated." + "reason": "SAM3 pixel decoder dummy layer vs MaskGenerationPipeline final-batch result drop; unrelated." }, { "left": "issue:44933", "right": "issue:45459", "accept": false, - "reason": "Missing image_utils import and protobuf decode-error masking are unrelated." + "reason": "Nonexistent image_utils import vs protobuf error masking in tokenizer load; different modules and failures." } ] }, @@ -11611,11 +11581,10 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:28282", "issue:30990", - "issue:36010", "issue:41628", "issue:42371", "issue:42673", @@ -11655,12 +11624,13 @@ "issue:45375", "issue:45381", "issue:45397", + "issue:45406", "issue:45478", "issue:45656", - "issue:45753", "issue:46077", "issue:46123", - "issue:46132" + "issue:46132", + "issue:46202" ], "soft_pairs": [ "issue:44297|issue:44623", @@ -11670,258 +11640,244 @@ "issue:43232|issue:43673", "issue:44623|issue:45656", "issue:44749|issue:45656", - "issue:43673|issue:45278", "issue:44871|issue:46132", + "issue:43673|issue:45278", "issue:43701|issue:44749", - "issue:43475|issue:45381", "issue:42994|issue:43482", + "issue:43475|issue:45381", "issue:45230|issue:45397", "issue:43475|issue:43643", "issue:28282|issue:30990", "issue:44038|issue:44623", + "issue:45406|issue:46202", "issue:46077|issue:46123", "issue:41628|issue:44933", "issue:42371|issue:45092", "issue:43475|issue:44661", "issue:45375|issue:45478", - "issue:45081|issue:45103", "issue:42994|issue:43525", + "issue:45081|issue:45103", "issue:45310|issue:45375", "issue:43873|issue:44945", - "issue:43232|issue:44188", "issue:41628|issue:44351", + "issue:43232|issue:44188", "issue:42673|issue:43704", - "issue:42831|issue:44222", - "issue:44945|issue:45753", - "issue:36010|issue:41628", - "issue:44222|issue:45310" + "issue:42831|issue:44222" ], - "prepared_review_unit_hash": "cd1499c83d15e10908153d230f2a7e0b1ac66d58262725a155d9dacd2a936356", + "prepared_review_unit_hash": "44a2fd77b4ff511baa1ca76b5d3cd5f2a6a702975a43f3bb5fc4b8139142c89b", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 32, - "serialized_chars": 36963, - "estimated_input_tokens": 9241, - "estimated_eval_tokens": 18738 + "soft_pair_count": 30, + "serialized_chars": 36389, + "estimated_input_tokens": 9098, + "estimated_eval_tokens": 18452 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly unrelated Transformers issues connected only by broad themes like imports, generation, saving/loading, or model-family regressions. There are two clear exact duplicate pairs in the packet: issue:42673/issue:43704 (Qwen3ForCausalLM VRAM leak in multiple dataloader threads) and issue:45310/issue:45478 (Qwen3.5 MoE from_pretrained error). The remaining soft edges look like conservative false positives rather than true duplicates.", - "confidence": 0.91, - "canonical_issue_reason": "issue:42673 is the strongest canonical for its exact duplicate pair because it is the earlier, fuller report of the Qwen3ForCausalLM VRAM leak; issue:43704 is an exact duplicate. Note that the packet also contains a separate exact duplicate pair, issue:45310/issue:45478, so this cluster is not a single duplicate set.", + "summary": "Mostly a heterogeneous Transformers issue cluster spanning import errors, tokenizer/config regressions, generation bugs, and model-specific failures. There are at least two duplicate-like pockets: the Qwen3ForCausalLM VRAM-leak pair (42673/43704) and an exact Qwen3.5 Moe title duplicate pair (45310/45478), but most other pairs are not the same underlying bug.", + "confidence": 0.79, + "canonical_issue_reason": "issue:42673 is the strongest canonical anchor for one true duplicate pocket because it has the clearest, most specific bug description (Qwen3ForCausalLM VRAM leak in multiple dataloader threads) and a later duplicate in 43704. The cluster also contains an exact Qwen3.5 Moe duplicate pair (45310/45478), but that is a separate smaller pocket.", "canonical_pr_reason": null, - "best_issue_reason": "issue:42673 is the best representative overall because it has the fullest discussion/history among the exact duplicate pairs and is the clearest stable reference point for triage.", + "best_issue_reason": "issue:45278 is the best global representative because it is the broadest umbrella-style regression report in the set and sits near the center of the upgrade/import-failure theme, while many others are narrower model- or path-specific bugs.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44297", "right": "issue:44623", "accept": false, - "reason": "Both mention save_pretrained, but one is a tokenizer_config mismatch and the other is missing processor files; different failure modes and code paths." + "reason": "Both involve save_pretrained, but one is a tokenizer_config mismatch and the other is missing processor files; different bugs." }, { "left": "issue:44869", "right": "issue:45356", "accept": false, - "reason": "Both are tokenizer/codec-related, but one is a Whisper timestamp decode crash and the other is a Kimi-K2.5 tokenizer regression with a different warning/codec issue." + "reason": "Whisper timestamp decoding crash and Kimi tokenizer regression are unrelated code paths." }, { "left": "issue:44361", "right": "issue:44749", "accept": false, - "reason": "Different problems: MLukeTokenizer task AttributeError vs a general performance slowdown after upgrade." + "reason": "MLukeTokenizer AttributeError and a 10x filtering slowdown are different failure modes." }, { "left": "issue:43646", "right": "issue:44162", "accept": false, - "reason": "Both are Transformers v5 regressions, but one is custom model initialization and the other is ESM2-specific breakage; not the same underlying bug." + "reason": "Custom model initialization breakage and ESM2 being broken are separate model-specific issues." }, { "left": "issue:43232", "right": "issue:43673", "accept": false, - "reason": "Both involve generation internals, but one is sync_gpus/update_model_kwargs behavior and the other is chunked_prefill cache handling; distinct code paths." + "reason": "Both touch generation, but sync_gpus kwargs handling and missing GenerationMixin cache in chunked_prefill are distinct problems." }, { "left": "issue:44623", "right": "issue:45656", "accept": false, - "reason": "processor.save_pretrained file issues are unrelated to a deepspeed optimizer-step counting bug." + "reason": "Processor save_pretrained file loss and deepspeed optimizer stepping are unrelated." }, { "left": "issue:44749", "right": "issue:45656", "accept": false, - "reason": "A data-filtering slowdown after upgrade is unrelated to optimizer.step being called twice." + "reason": "A filtering performance regression is not the same as the deepspeed double-step bug." }, { - "left": "issue:43673", - "right": "issue:45278", + "left": "issue:44871", + "right": "issue:46132", "accept": false, - "reason": "One is a specific GenerationMixin cache regression; the other is a broad import-error report after upgrade." + "reason": "Gemma eos_token_id inconsistency and AttentionInterface.register behavior changes are different issues." }, { - "left": "issue:44871", - "right": "issue:46132", + "left": "issue:43673", + "right": "issue:45278", "accept": false, - "reason": "Gemma eos_token_id inconsistency is unrelated to AttentionInterface.register changing registered-function behavior." + "reason": "A specific generation-cache bug is not the same as broad import failures after upgrade." }, { "left": "issue:43701", "right": "issue:44749", "accept": false, - "reason": "Checkpoint resume key mismatch is unrelated to dataset filtering performance." + "reason": "Checkpoint key mismatch and dataloader filtering slowdown are unrelated." }, { - "left": "issue:43475", - "right": "issue:45381", + "left": "issue:42994", + "right": "issue:43482", "accept": false, - "reason": "Both are vision/video model issues, but one is a missing SAM3 attribute and the other is incorrect Qwen2.5-VL video position IDs." + "reason": "Quantized model saving failure and Qwen2.5-GGUF loading failure are different code paths." }, { - "left": "issue:42994", - "right": "issue:43482", + "left": "issue:43475", + "right": "issue:45381", "accept": false, - "reason": "Quantized model saving failure is different from Qwen2.5-GGUF loading failure." + "reason": "SAM3 vision encoder missing attribute and Qwen2.5-VL video position-id bug are unrelated models." }, { "left": "issue:45230", "right": "issue:45397", "accept": false, - "reason": "issue:45230 is too generic to establish a shared bug, while 45397 is a specific gemma-4 zero3 from_pretrained problem." + "reason": "The generic bug report does not establish the same issue as the Gemma-4 ZeRO3 from_pretrained failure." }, { "left": "issue:43475", "right": "issue:43643", "accept": false, - "reason": "Different failures: SAM3 output attribute missing vs trust_remote_code returning missing fields from AutoConfig." + "reason": "Different problems: missing fpn_position_embeddings vs trust_remote_code returning incomplete configs." }, { "left": "issue:28282", "right": "issue:30990", "accept": false, - "reason": "An ImportError about PyTorch missing is unrelated to Sentence Transformers getting stuck during load." + "reason": "Missing PyTorch import error and Sentence Transformers hanging on load are not the same bug." }, { "left": "issue:44038", "right": "issue:44623", "accept": false, - "reason": "Qwen3-VL-Moe v5 incompatibility and processor.save_pretrained missing files are unrelated issues." + "reason": "Qwen3-VL-Moe v5 incompatibility and processor.save_pretrained missing files are unrelated." + }, + { + "left": "issue:45406", + "right": "issue:46202", + "accept": false, + "reason": "Gemma4Processor missing _tokenizer and Gemma pipeline roundtrip failure are different issues." }, { "left": "issue:46077", "right": "issue:46123", "accept": false, - "reason": "Gemma4 causal-mask construction and MaskGenerationPipeline final-batch handling are different bugs." + "reason": "Bidirectional-attention masking and partial-batch result dropping are different pipeline behaviors." }, { "left": "issue:41628", "right": "issue:44933", "accept": false, - "reason": "Both are import errors, but for different symbols/modules and likely different fixes." + "reason": "Both are import errors, but they refer to different missing symbols/modules and do not appear to share one fix." }, { "left": "issue:42371", "right": "issue:45092", "accept": false, - "reason": "TF32 API guidance is unrelated to remote-code checkpoint meta-initialization incompatibility." + "reason": "TF32 settings guidance and InternVL2 meta-initialization incompatibility are unrelated." }, { "left": "issue:43475", "right": "issue:44661", "accept": false, - "reason": "A SAM3 video attribute error is unrelated to add-new-model-like failing on TOKENIZER_MAPPING_NAMES." + "reason": "A model output attribute bug and a tokenizer-mapping add-new-model-like failure are different code paths." }, { "left": "issue:45375", "right": "issue:45478", "accept": false, - "reason": "Both involve Qwen3.5 MoE, but one is a missing vision-config field and the other is a general from_pretrained error; not enough to treat as the same bug." + "reason": "Related Qwen3.5 Moe titles, but one is a specific config-field loss under strict serialization and the other is a broader from_pretrained failure; not enough to call them the same bug." }, { - "left": "issue:45081", - "right": "issue:45103", + "left": "issue:42994", + "right": "issue:43525", "accept": false, - "reason": "Mistral regex patching and auto_docstring future-annotations crashes are unrelated AttributeErrors in different subsystems." + "reason": "Quantized save failure and Llama4Config missing pad_token_id are separate regressions." }, { - "left": "issue:42994", - "right": "issue:43525", + "left": "issue:45081", + "right": "issue:45103", "accept": false, - "reason": "Quantized model saving failure is different from Llama4Config missing pad_token_id." + "reason": "Mistral regex patch crash and auto_docstring future-annotations crash are unrelated AttributeErrors." }, { "left": "issue:45310", "right": "issue:45375", "accept": false, - "reason": "Both are Qwen3.5 MoE-related, but one is a from_pretrained error and the other is a missing vision-config field; not clearly the same underlying defect." + "reason": "Both are Qwen3.5 Moe related, but one is a general from_pretrained error while the other is a specific missing config field; too little evidence they are the same underlying bug." }, { "left": "issue:43873", "right": "issue:44945", "accept": false, - "reason": "Quantization/offloading behavior is unrelated to incorrect pipeline-parallel LLM outputs." + "reason": "Quantization offloading behavior and pipeline-parallel LLM output correctness are different problems." }, { - "left": "issue:43232", - "right": "issue:44188", + "left": "issue:41628", + "right": "issue:44351", "accept": false, - "reason": "Generation kwargs after sync_gpus is unrelated to attention-kernel divergence under torch.compile." + "reason": "Two import errors, but for different missing names with no clear shared root cause." }, { - "left": "issue:41628", - "right": "issue:44351", + "left": "issue:43232", + "right": "issue:44188", "accept": false, - "reason": "Different missing imports: AutoImageProcessor vs HybridCache." + "reason": "Generation kwargs syncing and attention-kernel divergence under torch.compile are distinct issues." }, { "left": "issue:42673", "right": "issue:43704", "accept": true, - "reason": "Exact same title and same reported bug: Qwen3ForCausalLM VRAM leak in multiple dataloader threads." + "reason": "Same Qwen3ForCausalLM VRAM leak in multiple dataloader threads; 43704 is a later duplicate of 42673." }, { "left": "issue:42831", "right": "issue:44222", "accept": false, - "reason": "Both are FP8-related, but one is an accuracy issue and the other is save_pretrained for moe models." - }, - { - "left": "issue:44945", - "right": "issue:45753", - "accept": false, - "reason": "Pipeline-parallel wrong output is unrelated to a Qwen3_5 infinite loop on a specific image." - }, - { - "left": "issue:36010", - "right": "issue:41628", - "accept": false, - "reason": "Different import failures: GenerationMixin import vs AutoImageProcessor import." - }, - { - "left": "issue:44222", - "right": "issue:45310", - "accept": false, - "reason": "FP8 moe save_pretrained and Qwen3.5-Moe from_pretrained errors are different bugs." + "reason": "FineGrainedFP8 accuracy loss and FP8 save_pretrained failure are different bugs." } ] }, "evaluator_result": { "accept": false, - "feedback": "The summary is not fully grounded: the packet contains another exact duplicate pair besides 42673/43704, namely issue:45310 and issue:45478, which have the same title and clearly describe the same Qwen3.5 MoE from_pretrained error. Because the response says there is only one clear duplicate pair, it overstates the evidence. The other soft-edge rejections are generally conservative, but the missing duplicate makes the overall assessment imprecise." + "feedback": "The soft-edge false verdicts are mostly conservative and grounded in the titles, but the summary is not fully grounded: the packet also contains an exact duplicate Qwen3.5 Moe pair (`issue:45310` and `issue:45478`) with identical titles, so saying the only clear duplicate pair is the Qwen3ForCausalLM VRAM leak overstates the uniqueness of that pair. The cluster is still largely heterogeneous, but the duplicate-summary claim should be toned down or expanded." }, "evaluator_used": true, "retried": true, @@ -11940,12 +11896,14 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:30333", "issue:30990", "issue:33290", "issue:35141", + "issue:36010", + "issue:41628", "issue:42175", "issue:42222", "issue:42898", @@ -11963,11 +11921,10 @@ "issue:43874", "issue:43976", "issue:44038", - "issue:44060", "issue:44079", "issue:44188", + "issue:44222", "issue:44242", - "issue:44373", "issue:44448", "issue:44496", "issue:44568", @@ -11977,266 +11934,266 @@ "issue:44792", "issue:44869", "issue:44933", + "issue:44945", "issue:44964", "issue:45092", "issue:45103", - "issue:45125", "issue:45137", "issue:45200", "issue:45310", "issue:45356", - "issue:45405", "issue:45561", "issue:45712", + "issue:45753", "issue:45812" ], "soft_pairs": [ + "issue:44945|issue:45753", + "issue:36010|issue:41628", + "issue:44222|issue:45310", "issue:42994|issue:43824", "issue:44964|issue:45137", "issue:43232|issue:44792", - "issue:43673|issue:44188", "issue:44038|issue:45310", + "issue:43673|issue:44188", "issue:42175|issue:45712", "issue:43526|issue:45561", - "issue:43504|issue:45561", "issue:44496|issue:45561", + "issue:43504|issue:45561", "issue:43377|issue:44242", "issue:42175|issue:44933", - "issue:42222|issue:45200", "issue:42898|issue:44568", + "issue:42222|issue:45200", "issue:43976|issue:44933", "issue:30990|issue:35141", "issue:43479|issue:44869", - "issue:43479|issue:44079", "issue:43278|issue:45137", + "issue:43479|issue:44079", "issue:44623|issue:45310", - "issue:42898|issue:45812", - "issue:44188|issue:44373", "issue:30333|issue:33290", + "issue:42898|issue:45812", "issue:43784|issue:43824", "issue:44734|issue:45103", "issue:43723|issue:44568", - "issue:42898|issue:45356", "issue:42898|issue:44779", + "issue:42898|issue:45356", "issue:43874|issue:45092", - "issue:45405|issue:45712", - "issue:42898|issue:44448", - "issue:44060|issue:45125" + "issue:42898|issue:44448" ], - "prepared_review_unit_hash": "673af8d6d3170d33f11597bec5cacef15485e4eaa6cfc5e2c4b19ee73c0b8383", + "prepared_review_unit_hash": "e277b2826e1380358e66e0ec26401b24c66ae541286927effdfbe4ffaf9ce89c", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { - "node_count": 47, - "item_count": 47, + "node_count": 48, + "item_count": 48, "soft_pair_count": 31, - "serialized_chars": 36549, - "estimated_input_tokens": 9138, - "estimated_eval_tokens": 18532 + "serialized_chars": 37049, + "estimated_input_tokens": 9263, + "estimated_eval_tokens": 18782 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly a grab bag of unrelated issues, with a loose concentration around tokenizer/v5 regressions and multimodal/model-loading bugs; none of the soft pairs look like true duplicates. I would anchor the issue cluster on the broad tokenizer regression report, with a more concrete tokenizer bug as the strongest representative.", - "confidence": 0.74, - "canonical_issue_reason": "Issue #42898 is the broadest and most central regression report in the set: it describes a v5 tokenizer behavior change and is thematically closest to several nearby tokenizer-related reports.", + "summary": "The cluster is heterogeneous: it mixes unrelated import/load, tokenizer, multimodal, generation, and training/runtime bugs. Despite some superficial overlap around Transformers v5 regressions, none of the soft edges look like the same underlying issue, so all candidate duplicate links should be rejected.", + "confidence": 0.9, + "canonical_issue_reason": "issue:42898 is the broadest, most central v5-regression report in the set and a plausible anchor for the cluster, but it is still only a representative issue rather than an exact duplicate of the others.", "canonical_pr_reason": null, - "best_issue_reason": "Issue #45812 is the cleanest high-signal report: it has a concrete, model-specific tokenizer failure with a clear silent regression from v4 to v5.", + "best_issue_reason": "issue:42898 is the best single issue to anchor the cluster because it is a general user-facing regression report that overlaps thematically with several tokenizer/version-change complaints, even though the underlying bugs differ.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44945", + "right": "issue:45753", + "accept": false, + "reason": "Pipeline-parallel output mismatch and a Qwen3_5 image loop are different symptoms, models, and code paths." + }, + { + "left": "issue:36010", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but for different symbols and different missing/exported APIs." + }, + { + "left": "issue:44222", + "right": "issue:45310", + "accept": false, + "reason": "FP8 save_pretrained for MoE is a save-path bug; Qwen3.5 from_pretrained failure is a load-path bug on a different model family." + }, { "left": "issue:42994", "right": "issue:43824", "accept": false, - "reason": "Quantized model saving and a missing Qwen2.5-VL import symbol are unrelated failures." + "reason": "Quantized save failure and a Qwen2.5-VL import error are unrelated subsystems." }, { "left": "issue:44964", "right": "issue:45137", "accept": false, - "reason": "Phi-4 multimodal loading and a DeepSpeed ZeRO3 deque error affect different code paths." + "reason": "Phi-4 multimodal load failure and DeepSpeed ZeRO3 deque underflow are unrelated." }, { "left": "issue:43232", "right": "issue:44792", "accept": false, - "reason": "Generation kwargs syncing and the janus image-generation test failure are different bugs." - }, - { - "left": "issue:43673", - "right": "issue:44188", - "accept": false, - "reason": "Chunked-prefill cache handling is not the same as the torch.compile attention-kernel branching issue." + "reason": "Generation kwargs handling after sync_gpus is not the same bug as the janus image-generation test failure." }, { "left": "issue:44038", "right": "issue:45310", "accept": false, - "reason": "Both involve Qwen3 VL/MoE models, but they report different versions and distinct from_pretrained failures." + "reason": "Both mention Qwen MoE, but one is a Qwen3-VL issue and the other is a Qwen3.5 from_pretrained regression." + }, + { + "left": "issue:43673", + "right": "issue:44188", + "accept": false, + "reason": "Chunked prefill cache missing and torch.compile attention-kernel divergence are different generation/runtime problems." }, { "left": "issue:42175", "right": "issue:45712", "accept": false, - "reason": "Missing tensorflow in the torch extra and leftover dummy PT classes are separate packaging problems." + "reason": "Dependency/backend packaging is unrelated to leftover dummy class cleanup." }, { "left": "issue:43526", "right": "issue:45561", "accept": false, - "reason": "A BeitImageProcessorFast label bug is unrelated to the xdist captured_info.txt race." + "reason": "Beit label reduction is a model-specific preprocessing bug, not the xdist file-race issue." }, { - "left": "issue:43504", + "left": "issue:44496", "right": "issue:45561", "accept": false, - "reason": "Legacy-field model loading and a pytest-xdist file race are not the same issue." + "reason": "Unrecognized model config loading and captured_info.txt race are unrelated." }, { - "left": "issue:44496", + "left": "issue:43504", "right": "issue:45561", "accept": false, - "reason": "An unrecognized-model config error is unrelated to the testing-utils race condition." + "reason": "Legacy field loading for Beit semantic segmentation is unrelated to the xdist testing-utils race." }, { "left": "issue:43377", "right": "issue:44242", "accept": false, - "reason": "Missing padding-mask support in MIMI encoding is different from the load-balancing-loss gating bug." + "reason": "MIMI padding-mask mismatch and MoE router-loss omission are different model-behavior bugs." }, { "left": "issue:42175", "right": "issue:44933", "accept": false, - "reason": "Backend dependency resolution and a missing image_utils import are unrelated." + "reason": "Backend packaging and a nonexistent image_utils import are unrelated." }, { - "left": "issue:42222", - "right": "issue:45200", + "left": "issue:42898", + "right": "issue:44568", "accept": false, - "reason": "Broken vitpose models and Gemma 4 mm_token_type_ids defaulting are different multimodal bugs." + "reason": "Both are tokenizer regressions in v5, but one is clean-up spacing behavior and the other is special-token insertion; not the same bug." }, { - "left": "issue:42898", - "right": "issue:44568", + "left": "issue:42222", + "right": "issue:45200", "accept": false, - "reason": "Both are tokenizer regressions in v5, but one is clean_up_tokenization_spaces behavior and the other is add_special_tokens BOS/EOS handling." + "reason": "VitPose breakage and Gemma 4 mm_token_type_ids defaults affect different models and code paths." }, { "left": "issue:43976", "right": "issue:44933", "accept": false, - "reason": "Python version compatibility and a missing import are unrelated." + "reason": "Python-version compatibility and a missing image_utils import are unrelated." }, { "left": "issue:30990", "right": "issue:35141", "accept": false, - "reason": "Sentence-transformer loading hangs and embedding reinitialization in post_init are different problems." + "reason": "Sentence-transformers loading hang and token-embedding resizing/post_init reinit are different bugs." }, { "left": "issue:43479", "right": "issue:44869", "accept": false, - "reason": "Default multimodal config initialization and Whisper timestamp decoding crash are unrelated." - }, - { - "left": "issue:43479", - "right": "issue:44079", - "accept": false, - "reason": "Config defaulting for multimodal submodules does not match ModelOutput key assignment logic." + "reason": "Phi-4 multimodal config defaults and Whisper timestamp decoding are unrelated." }, { "left": "issue:43278", "right": "issue:45137", "accept": false, - "reason": "A dtype mismatch in evaluation is unrelated to the DeepSpeed deque pop error." + "reason": "Embedding dtype drift in eval and a ZeRO3 deque error are different problems." }, { - "left": "issue:44623", - "right": "issue:45310", + "left": "issue:43479", + "right": "issue:44079", "accept": false, - "reason": "Missing files on processor.save_pretrained and Qwen3.5 MoE from_pretrained failure are different load/save bugs." + "reason": "Multimodal config initialization and ModelOutput key assignment are unrelated." }, { - "left": "issue:42898", - "right": "issue:45812", + "left": "issue:44623", + "right": "issue:45310", "accept": false, - "reason": "Both are tokenizer regressions, but they affect different behaviors and model families, so they are not the same concrete bug." + "reason": "Missing processor save files and Qwen3.5 MoE from_pretrained failure are different operations." }, { - "left": "issue:44188", - "right": "issue:44373", + "left": "issue:30333", + "right": "issue:33290", "accept": false, - "reason": "A torch.compile attention-kernel divergence is unrelated to a docstring typo." + "reason": "MLflow reporting on failed training jobs and DeepSpeed Adafactor OOM are not the same bug." }, { - "left": "issue:30333", - "right": "issue:33290", + "left": "issue:42898", + "right": "issue:45812", "accept": false, - "reason": "MLflow reporting on failed training jobs and AdaFactor OOM in DeepSpeed are separate training issues." + "reason": "Both are v5 tokenizer regressions, but clean_up_tokenization_spaces and Granite token IDs are distinct behaviors." }, { "left": "issue:43784", "right": "issue:43824", "accept": false, - "reason": "A sentence-transformers import NameError and a Qwen2.5-VL import error are different import failures." + "reason": "Sentence-transformers import NameError and Qwen2.5-VL import failure are unrelated import issues." }, { "left": "issue:44734", "right": "issue:45103", "accept": false, - "reason": "KV-cache continuation indexing in transformers serve is unrelated to the auto_docstring future-annotations crash." + "reason": "KV-cache continuation crash in serve and auto_docstring future-annotations crash are unrelated." }, { "left": "issue:43723", "right": "issue:44568", "accept": false, - "reason": "Tokenizer loading in v5 and BOS/EOS add_special_tokens behavior are different tokenizer regressions." + "reason": "AutoTokenizer loading regression and special-token insertion regression are different tokenizer failure modes." }, { "left": "issue:42898", - "right": "issue:45356", + "right": "issue:44779", "accept": false, - "reason": "Clean-up spacing behavior in v5 and Kimi-K2.5 codec handling are separate tokenizer issues." + "reason": "Both are tokenizer regressions, but one is a spacing cleanup change and the other is DeepSeek codec handling; not the same underlying defect." }, { "left": "issue:42898", - "right": "issue:44779", + "right": "issue:45356", "accept": false, - "reason": "These are both tokenizer regressions, but for different models and different failure modes." + "reason": "General v5 tokenization behavior change and Kimi-K2.5 codec-handling regression are separate tokenizer issues." }, { "left": "issue:43874", "right": "issue:45092", "accept": false, - "reason": "A missing image-patch count method and an InternVL2 meta-init incompatibility are not the same bug." - }, - { - "left": "issue:45405", - "right": "issue:45712", - "accept": false, - "reason": "A bumped minimum PEFT version and dummy PT class cleanup are unrelated." + "reason": "Missing image-patch counting and old InternVL2 meta-init incompatibility are different multimodal loading bugs." }, { "left": "issue:42898", "right": "issue:44448", "accept": false, - "reason": "A tokenizer behavior regression and a model output discrepancy for Pegasus are different issues." - }, - { - "left": "issue:44060", - "right": "issue:45125", - "accept": false, - "reason": "An incorrect tied-weights warning in Qwen3-Next is not the same as a missing tensor-parallel plan in Qwen3.5 MoE." + "reason": "Tokenizer clean-up behavior and Pegasus output drift are different regression classes." } ] }, @@ -12258,26 +12215,24 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:22355", "issue:28282", "issue:30333", - "issue:30990", "issue:34689", "issue:35141", "issue:36331", - "issue:38175", "issue:41628", "issue:42757", "issue:42831", - "issue:42907", "issue:43116", "issue:43232", "issue:43479", "issue:43644", "issue:43723", "issue:43761", + "issue:44060", "issue:44190", "issue:44206", "issue:44222", @@ -12298,18 +12253,21 @@ "issue:45071", "issue:45092", "issue:45103", + "issue:45125", "issue:45245", "issue:45310", "issue:45357", + "issue:45405", "issue:45406", "issue:45656", "issue:45712", "issue:45834", - "issue:46050", "issue:46082", "issue:46132" ], "soft_pairs": [ + "issue:45405|issue:45712", + "issue:44060|issue:45125", "issue:44295|issue:45656", "issue:44448|issue:46132", "issue:44933|issue:45712", @@ -12319,264 +12277,274 @@ "issue:43479|issue:43644", "issue:44190|issue:46082", "issue:44222|issue:44623", - "issue:30333|issue:36331", "issue:42831|issue:44623", "issue:30333|issue:34689", "issue:45245|issue:46132", - "issue:45071|issue:46082", + "issue:30333|issue:36331", "issue:22355|issue:28282", + "issue:45071|issue:46082", "issue:41628|issue:42757", - "issue:44206|issue:45103", "issue:28282|issue:30333", "issue:30333|issue:35141", + "issue:44206|issue:45103", "issue:44297|issue:45310", - "issue:43723|issue:44977", "issue:44222|issue:44484", + "issue:43723|issue:44977", "issue:43232|issue:45834", - "issue:43761|issue:46082", "issue:44263|issue:45092", - "issue:44483|issue:45406", + "issue:43761|issue:46082", "issue:44295|issue:44623", + "issue:44483|issue:45406", "issue:44373|issue:44485", "issue:44514|issue:45103", "issue:43723|issue:44871", "issue:45092|issue:45357", - "issue:44263|issue:44360", - "issue:30990|issue:38175", - "issue:42907|issue:46050" + "issue:44263|issue:44360" ], - "prepared_review_unit_hash": "5a8150cde9b810f48fd881f556beaf5d795db9dcb8a9bdef078c070f149a7558", + "prepared_review_unit_hash": "66754c136a053313fdfbab24b43d3358f4c5be3fb0d5addebfe2eb88b1feab01", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { - "node_count": 48, - "item_count": 48, + "node_count": 47, + "item_count": 47, "soft_pair_count": 34, - "serialized_chars": 37629, - "estimated_input_tokens": 9408, - "estimated_eval_tokens": 19072 + "serialized_chars": 37148, + "estimated_input_tokens": 9287, + "estimated_eval_tokens": 18830 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The items are a heterogeneous set of unrelated Transformers issues; no clear duplicate cluster emerges, and all soft candidate pairs should be rejected.", - "confidence": 0.24, - "canonical_issue_reason": "No real duplicate cluster is present; if a representative issue is needed, #44297 is the most concrete, narrowly scoped serialization bug among otherwise unrelated reports.", + "summary": "This cluster is highly heterogeneous: most items are superficial keyword matches around imports, configs, or save/load behavior, but they describe different code paths and failures. No soft pair looks like a true duplicate, so I rejected them all. There are no PRs in the set; issue 44623 is the clearest standalone representative of the cluster's serialization/save-pretrained theme.", + "confidence": 0.63, + "canonical_issue_reason": "Issue 44623 is the most concrete and self-contained bug report in the set: it names a specific API (`processor.save_pretrained(...)`) and a clear failure mode (missing files).", "canonical_pr_reason": null, - "best_issue_reason": "#44297 is the best triage candidate because it has a specific, reproducible save_pretrained symptom and a clear code path, making it more actionable than the other heterogeneous issues.", + "best_issue_reason": "Issue 44623 is the best standalone issue to anchor this cluster because it is actionable, specific, and broadly representative of the save/load serialization problems that several nearby items loosely resemble.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:45405", + "right": "issue:45712", + "accept": false, + "reason": "Unrelated: one is a PEFT version bump, the other is leftover dummy classes leaking into exports/check_repo." + }, + { + "left": "issue:44060", + "right": "issue:45125", + "accept": false, + "reason": "Both mention Qwen3 MoE, but one is a tied-weights warning and the other is missing `_tp_plan`; different bugs." + }, { "left": "issue:44295", "right": "issue:45656", "accept": false, - "reason": "Different bugs: buffer registration/access error versus optimizer stepping twice under deepspeed." + "reason": "Different subsystems: `position_ids` buffer access vs. a deepspeed double optimizer-step report." }, { "left": "issue:44448", "right": "issue:46132", "accept": false, - "reason": "Both touch model behavior, but one is a Pegasus output change and the other is an AttentionInterface registration side effect." + "reason": "Different issues: model output drift across versions vs. `AttentionInterface.register` changing function behavior." }, { "left": "issue:44933", "right": "issue:45712", "accept": false, - "reason": "Both are import/export related, but one is a missing image_utils import and the other is leftover dummy PT classes leaking into dir()." + "reason": "Both touch import/export surfaces, but one is a missing image_utils import and the other is dummy class cleanup." }, { "left": "issue:44222", "right": "issue:44297", "accept": false, - "reason": "Both involve save_pretrained, but one is FP8 MoE model saving and the other is tokenizer metadata mismatch." + "reason": "Both involve `save_pretrained`, but one is FP8 MoE model saving and the other is tokenizer class metadata; not the same bug." }, { "left": "issue:44297", "right": "issue:45656", "accept": false, - "reason": "Tokenizer serialization bug is unrelated to a deepspeed optimizer double-step issue." + "reason": "Tokenizer save metadata mismatch is unrelated to a deepspeed optimizer-step problem." }, { "left": "issue:43116", "right": "issue:44190", "accept": false, - "reason": "Example-script failures in different workflows: multi-label classification output versus local dataset loading." + "reason": "Both concern example scripts, but one is multi-label classification output and the other is local dataset loading." }, { "left": "issue:43479", "right": "issue:43644", "accept": false, - "reason": "Config default initialization bug is unrelated to non-persistent buffer corruption." + "reason": "Different bugs: multimodal config defaults vs. non-persistent buffers being filled with junk." }, { "left": "issue:44190", "right": "issue:46082", "accept": false, - "reason": "Local dataset loading issue is unrelated to LlamaConfig head_dim validation." + "reason": "Unrelated: dataset loading in an example script vs. LlamaConfig head_dim validation." }, { "left": "issue:44222", "right": "issue:44623", "accept": false, - "reason": "Different save-pretrained problems affecting different objects: FP8 MoE model versus processor artifact files." - }, - { - "left": "issue:30333", - "right": "issue:36331", - "accept": false, - "reason": "Both are training-related, but MLflow reporting on failure is separate from a compute_loss signature break." + "reason": "Same general save-pretrained area, but one is FP8 MoE model saving and the other is processor file omission." }, { "left": "issue:42831", "right": "issue:44623", "accept": false, - "reason": "Accuracy regression in FineGrainedFP8 is unrelated to missing processor save files." + "reason": "Accuracy regression in FineGrainedFP8 is unrelated to missing processor files during save_pretrained." }, { "left": "issue:30333", "right": "issue:34689", "accept": false, - "reason": "Training-job reporting and a Llama 3.2 model-loading regression are different code paths." + "reason": "Different failures: MLflow reporting on failed training vs. model loading regression for Llama 3.2 Vision." }, { "left": "issue:45245", "right": "issue:46132", "accept": false, - "reason": "Category-count runtime error is unrelated to AttentionInterface registration behavior." + "reason": "Categorical-cardinality runtime error is unrelated to attention registration behavior." }, { - "left": "issue:45071", - "right": "issue:46082", + "left": "issue:30333", + "right": "issue:36331", "accept": false, - "reason": "PretrainedConfig type-checking break is not the same as LlamaConfig head_dim rejection." + "reason": "MLflow reporting bug is unrelated to the trainer `compute_loss` signature change." }, { "left": "issue:22355", "right": "issue:28282", "accept": false, - "reason": "Both are import errors, but one is a missing transformers.onnx module and the other is missing PyTorch dependency detection." + "reason": "Both are import errors, but one is missing `transformers.onnx` and the other is PyTorch dependency detection." }, { - "left": "issue:41628", - "right": "issue:42757", + "left": "issue:45071", + "right": "issue:46082", "accept": false, - "reason": "Different missing symbols from different packages; not the same underlying failure." + "reason": "Type-checking breakage in `PretrainedConfig` is unrelated to LlamaConfig head_dim rejection." }, { - "left": "issue:44206", - "right": "issue:45103", + "left": "issue:41628", + "right": "issue:42757", "accept": false, - "reason": "Feature-extractor argument crash and auto-docstring annotation parsing crash are unrelated." + "reason": "Both are import errors, but they involve different missing symbols and different packages." }, { "left": "issue:28282", "right": "issue:30333", "accept": false, - "reason": "ImportError for PyTorch dependency is unrelated to MLflow reporting on failed training jobs." + "reason": "PyTorch import detection and MLflow reporting are unrelated." }, { "left": "issue:30333", "right": "issue:35141", "accept": false, - "reason": "Training reporting bug is unrelated to embedding reinitialization after resize_token_embeddings." + "reason": "Failed-job reporting has nothing to do with embedding resizing/reinitialization." }, { - "left": "issue:44297", - "right": "issue:45310", + "left": "issue:44206", + "right": "issue:45103", "accept": false, - "reason": "Tokenizer_class mismatch in save_pretrained is not the same as Qwen3.5 MoE from_pretrained failure." + "reason": "Different code paths: feature extractor argument mismatch vs. auto-docstring annotation handling." }, { - "left": "issue:43723", - "right": "issue:44977", + "left": "issue:44297", + "right": "issue:45310", "accept": false, - "reason": "Tokenizer loading regression and Qwen3.5 flash-attention generation bug are different problems." + "reason": "Tokenizer save metadata mismatch is not the same as the Qwen3.5 MoE from_pretrained regression." }, { "left": "issue:44222", "right": "issue:44484", "accept": false, - "reason": "Both mention save_pretrained, but one is FP8 MoE saving and the other is shard-size default behavior." + "reason": "FP8 MoE save_pretrained bug is unrelated to max_shard_size default behavior." }, { - "left": "issue:43232", - "right": "issue:45834", + "left": "issue:43723", + "right": "issue:44977", "accept": false, - "reason": "Generation kwargs update after sync_gpus is unrelated to long OCR index errors." + "reason": "Tokenizer loading regression and flash-attention generation issues are different bugs." }, { - "left": "issue:43761", - "right": "issue:46082", + "left": "issue:43232", + "right": "issue:45834", "accept": false, - "reason": "CLIPVisionModel hidden_states regression is unrelated to LlamaConfig head_dim validation." + "reason": "Generation kwargs update after sync_gpus is unrelated to Kosmos2.5 long OCR index errors." }, { "left": "issue:44263", "right": "issue:45092", "accept": false, - "reason": "GlmMoeDsaIndexer torch.split issue is unrelated to remote-code checkpoint meta-init incompatibility." + "reason": "Torch.split return handling in a MoE indexer is unrelated to remote-code checkpoint meta-initialization." }, { - "left": "issue:44483", - "right": "issue:45406", + "left": "issue:43761", + "right": "issue:46082", "accept": false, - "reason": "API request rejection and Gemma4Processor crash are different service-level failures." + "reason": "Hidden-states regression in CLIPVisionModel is unrelated to LlamaConfig head_dim validation." }, { "left": "issue:44295", "right": "issue:44623", "accept": false, - "reason": "Position_ids buffer access error is unrelated to missing processor save artifacts." + "reason": "Reading `position_ids` after buffer registration is unrelated to processor save_pretrained file omission." + }, + { + "left": "issue:44483", + "right": "issue:45406", + "accept": false, + "reason": "Chat/completions request handling is unrelated to Gemma4Processor missing `_tokenizer`." }, { "left": "issue:44373", "right": "issue:44485", "accept": false, - "reason": "Wrong docstring for position_ids is not the same as the GLM-5 RoPE implementation discussion." + "reason": "Wrong docstring for `position_ids` is a documentation issue; GLM-5 RoPE is an implementation discussion." }, { "left": "issue:44514", "right": "issue:45103", "accept": false, - "reason": "Chat-template batching crash and auto-docstring annotation crash are unrelated." + "reason": "Processor batch-padding crash is unrelated to auto-docstring annotation processing." }, { "left": "issue:43723", "right": "issue:44871", "accept": false, - "reason": "Tokenizer loading regression is unrelated to eos_token_id configuration mismatch." + "reason": "Tokenizer loading regression and eos_token_id inconsistency are separate issues." }, { "left": "issue:45092", "right": "issue:45357", "accept": false, - "reason": "Old InternVL2 meta-init incompatibility is unrelated to Qwen3.5 save_pretrained visual-key regression." + "reason": "Both involve model loading/saving, but they affect different models and different serialization problems." }, { - "left": "issue:44263", - "right": "issue:44360", + "left": "issue:45405", + "right": "issue:45712", "accept": false, - "reason": "Different GLM-5 DSA topics: a torch.split bug versus a missing ReLU discussion." + "reason": "PEFT version pinning is unrelated to dummy class cleanup/export leakage." }, { - "left": "issue:30990", - "right": "issue:38175", + "left": "issue:45656", + "right": "issue:45834", "accept": false, - "reason": "Sentence Transformers loading hang and SigLIP2 zero-probability outputs are unrelated." + "reason": "Double optimizer-step in deepspeed is unrelated to Kosmos2.5 OCR index errors." }, { - "left": "issue:42907", - "right": "issue:46050", + "left": "issue:44263", + "right": "issue:44360", "accept": false, - "reason": "Dequantized model save failure is unrelated to sinq quantization breakage after save/load." + "reason": "Both mention DSA indexer, but one is about torch.split return values and the other about a missing ReLU; not the same bug." } ] }, @@ -12598,12 +12566,13 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:22355", "issue:28218", "issue:30990", "issue:33357", + "issue:38175", "issue:39401", "issue:41628", "issue:42371", @@ -12635,10 +12604,8 @@ "issue:44568", "issue:44671", "issue:44704", - "issue:44743", "issue:44829", "issue:44913", - "issue:44945", "issue:44991", "issue:45092", "issue:45278", @@ -12647,248 +12614,245 @@ "issue:45593", "issue:45753", "issue:46002", + "issue:46050", "issue:46132" ], "soft_pairs": [ + "issue:30990|issue:38175", + "issue:42907|issue:46050", "issue:43723|issue:44991", "issue:44829|issue:46002", - "issue:43723|issue:44442", "issue:44261|issue:45092", + "issue:43723|issue:44442", + "issue:41628|issue:43824", "issue:42831|issue:45310", "issue:43479|issue:44913", - "issue:41628|issue:43824", "issue:42831|issue:44038", "issue:44263|issue:44373", "issue:39401|issue:44568", "issue:42757|issue:45278", - "issue:43232|issue:45593", "issue:42886|issue:42994", + "issue:43232|issue:45593", "issue:42831|issue:45753", "issue:42886|issue:43066", "issue:22355|issue:28218", "issue:43756|issue:44060", "issue:44671|issue:46132", "issue:43122|issue:44521", - "issue:44117|issue:44704", "issue:43576|issue:43784", + "issue:44117|issue:44704", "issue:43646|issue:46002", "issue:30990|issue:33357", "issue:42371|issue:44263", "issue:44295|issue:44297", - "issue:44704|issue:45290", - "issue:42907|issue:44945", - "issue:41628|issue:45278", - "issue:43232|issue:44743" + "issue:44704|issue:45290" ], - "prepared_review_unit_hash": "54b43756e2184666db45bf5017d7e95f09833010e9cdac1f4901bb6c68b5db90", + "prepared_review_unit_hash": "28f145cd17438926d9ae0188f8bb266d2cb1c875672396b3e34a1efb099d6ebe", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 29, - "serialized_chars": 35956, - "estimated_input_tokens": 8989, - "estimated_eval_tokens": 18234 + "soft_pair_count": 28, + "serialized_chars": 35659, + "estimated_input_tokens": 8915, + "estimated_eval_tokens": 18086 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is mostly a grab bag of unrelated transformer regressions. The only recurring theme is tokenizer/import breakage in v5, but the soft pairs still point to different concrete failures, so I would not merge any of them.", - "confidence": 0.9, - "canonical_issue_reason": "Issue 43723 is the broadest tokenizer-loading regression in v5 and is the closest hub for the tokenizer-related reports, but the overall set is too heterogeneous for a true duplicate canonical.", + "summary": "Mostly unrelated issues with only one credible duplicate pair in the tokenizer-loading regression area. Most other soft matches are superficial (same broad subsystem, same model family, or generic failure type) but do not look like the same underlying bug.", + "confidence": 0.76, + "canonical_issue_reason": "issue:43723 is the broadest representative of the only credible duplicate subcluster: a v5 AutoTokenizer loading regression that also covers the specific tokenizer-load failure in issue:44991.", "canonical_pr_reason": null, - "best_issue_reason": "43723 is the most representative issue for the tokenizer-loading regression subset because it targets the generic AutoTokenizer.from_pretrained failure in v5.", + "best_issue_reason": "issue:43723 is the strongest umbrella issue for the tokenizer-loading regression theme; it is more general than the specific model report in issue:44991 and best fits the duplicate cluster if one is chosen.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:30990", + "right": "issue:38175", + "accept": false, + "reason": "Different symptoms and code paths: loading hangs in Sentence Transformers vs zero probabilities in SigLIP2 inference." + }, + { + "left": "issue:42907", + "right": "issue:46050", + "accept": false, + "reason": "Both involve quantized-model saving, but the models and failure modes differ (dequantized Ministrals/Devstrals vs sinq save_pretrained/from_pretrained breakage)." + }, { "left": "issue:43723", "right": "issue:44991", - "accept": false, - "reason": "Both are tokenizer-loading complaints, but one is a generic v5 AutoTokenizer regression and the other is a model-specific failure for EMBEDDIA/est-roberta; not enough evidence of the same bug." + "accept": true, + "reason": "Both describe a v5 AutoTokenizer.from_pretrained/tokenizer-loading regression; 44991 looks like a specific model instance of the broader failure in 43723." }, { "left": "issue:44829", "right": "issue:46002", "accept": false, - "reason": "Different problem domains: flash_attention_3 training degradation vs NaNs after checkout/init in classification heads." + "reason": "Both mention bad training/NaNs, but one is tied to flash_attention_3 in sequence classification and the other to checkout/init NaNs in classification heads; not the same bug." + }, + { + "left": "issue:44261", + "right": "issue:45092", + "accept": false, + "reason": "Different root causes: missing rms_norm_eps in MLA layernorm vs remote-code/meta-initialization incompatibility for InternVL2." }, { "left": "issue:43723", "right": "issue:44442", "accept": false, - "reason": "Shared surface area around AutoTokenizer, but one is a general v5 loading regression and the other is a specific FastSpeech2ConformerTokenizer export/loading failure." + "reason": "Both are tokenizer-loading failures, but the titles only show a generic v5 regression versus a specific FastSpeech2ConformerTokenizer load issue; not enough to treat as the same bug." }, { - "left": "issue:44261", - "right": "issue:45092", + "left": "issue:41628", + "right": "issue:43824", "accept": false, - "reason": "MLA layernorm precision/config issue is unrelated to InternVL2 remote-code meta-initialization incompatibility." + "reason": "Both are import errors, but they concern different missing symbols/classes and likely different export paths." }, { "left": "issue:42831", "right": "issue:45310", "accept": false, - "reason": "FineGrainedFP8 accuracy regression and Qwen3.5-Moe from_pretrained error are distinct failures." + "reason": "Different issues: FineGrainedFP8 accuracy vs a Qwen3.5 MoE from_pretrained error." }, { "left": "issue:43479", "right": "issue:44913", "accept": false, - "reason": "Different configs and symptoms: Phi4Multimodal default-init bug vs GPTNeoX rotary_pct not persisting on reload." - }, - { - "left": "issue:41628", - "right": "issue:43824", - "accept": false, - "reason": "Both are import errors, but they concern different missing symbols and likely different registration/export paths." + "reason": "Both are config/default handling bugs, but they affect different models and different config fields/behaviors." }, { "left": "issue:42831", "right": "issue:44038", "accept": false, - "reason": "FineGrainedFP8 accuracy problems are not the same as Qwen3/VL-Moe load errors." + "reason": "Not the same problem: one is an FP8 accuracy issue, the other a Qwen3-VL-Moe bug report." }, { "left": "issue:44263", "right": "issue:44373", "accept": false, - "reason": "The first is a code bug in torch.split handling; the second is just a wrong docstring." + "reason": "One is a runtime tensor split issue; the other is just a docstring problem." }, { "left": "issue:39401", "right": "issue:44568", "accept": false, - "reason": "Qwen3 offset_mapping correctness and mdeberta add_special_tokens BOS/EOS omission are different tokenizer behaviors." + "reason": "Both are tokenizer behavior bugs, but one is wrong offset_mapping and the other is missing BOS/EOS insertion; different concrete defects." }, { "left": "issue:42757", "right": "issue:45278", "accept": false, - "reason": "Missing is_offline_mode from huggingface_hub is a specific dependency import issue; 45278 is a broad collection of import errors after upgrade." + "reason": "45278 is a broad import-error regression, but 42757 is specifically about is_offline_mode; too generic to call the same bug." }, { - "left": "issue:43232", - "right": "issue:45593", + "left": "issue:42886", + "right": "issue:42994", "accept": false, - "reason": "Generation state handling after sync_gpus is unrelated to D-FINE auxiliary-loss behavior when denoising is off." + "reason": "Offline tokenizer cache loading and quantized model saving are unrelated." }, { - "left": "issue:42886", - "right": "issue:42994", + "left": "issue:43232", + "right": "issue:45593", "accept": false, - "reason": "Offline tokenizer cache loading and quantized model saving are separate code paths and symptoms." + "reason": "Generation kwarg syncing and D-FINE auxiliary losses are unrelated subsystems." }, { "left": "issue:42831", "right": "issue:45753", "accept": false, - "reason": "FP8 accuracy regression does not match a Qwen3_5 infinite-loop bug on a specific image." + "reason": "A numerical accuracy issue is not the same as an infinite-loop bug on a specific image." }, { "left": "issue:42886", "right": "issue:43066", "accept": false, - "reason": "Offline cache loading failure and wrong tokenizer decoder type in v5 are different tokenizer subsystems." + "reason": "Offline cache loading failure and wrong tokenizer decoder type are different tokenizer bugs." }, { "left": "issue:22355", "right": "issue:28218", "accept": false, - "reason": "Missing transformers.onnx is an import/package issue; added-token spacing is a tokenizer behavior bug." + "reason": "Missing transformers.onnx import and extra tokenizer space after added token are unrelated." }, { "left": "issue:43756", "right": "issue:44060", "accept": false, - "reason": "Smollm3 RoPE-layer dropping and Qwen3-Next tied-weights warning are unrelated model-architecture issues." + "reason": "Different model-specific architecture/config problems with no shared concrete code path." }, { "left": "issue:44671", "right": "issue:46132", "accept": false, - "reason": "CamemBERT MLM prediction regression is not the same as AttentionInterface.register changing callback behavior." + "reason": "CamemBERT MLM predictions vs AttentionInterface.register behavior are unrelated." }, { "left": "issue:43122", "right": "issue:44521", "accept": false, - "reason": "Both involve tokenization, but one is a general tokenization drift across versions while the other is multimodal assistant_mask generation." + "reason": "Different tokenizer/chat-template problems: tokenization drift across versions vs multimodal assistant mask generation." }, { - "left": "issue:44117", - "right": "issue:44704", + "left": "issue:43576", + "right": "issue:43784", "accept": false, - "reason": "TOKENIZER_MAPPING_NAMES None handling and AutoProcessor kwargs propagation are separate loader plumbing bugs." + "reason": "A broken CLI command and an import NameError in sentence-transformers are not the same issue." }, { - "left": "issue:43576", - "right": "issue:43784", + "left": "issue:44117", + "right": "issue:44704", "accept": false, - "reason": "Broken transformers env command and a sentence-transformers import NameError are unrelated failures." + "reason": "Both are from_pretrained-related, but one is a tokenizer-mapping None bug and the other is AutoProcessor kwarg forwarding; different code paths." }, { "left": "issue:43646", "right": "issue:46002", "accept": false, - "reason": "Custom model initialization breakage is not the same as NaNs appearing in classification heads after checkout/init." + "reason": "Custom model initialization breakage is not the same as NaNs in classification heads after init." }, { "left": "issue:30990", "right": "issue:33357", "accept": false, - "reason": "Sentence Transformers loading stalls and a MacOS bus error on CLIP are different runtime failures." + "reason": "Sentence Transformers loading stall and a MacOS bus error in CLIP inference are different failures." }, { "left": "issue:42371", "right": "issue:44263", "accept": false, - "reason": "TF32 API guidance and a torch.split indexing bug do not describe the same issue." + "reason": "TF32 API guidance and a torch.split return-value issue are unrelated." }, { "left": "issue:44295", "right": "issue:44297", "accept": false, - "reason": "Registering position_ids as a buffer causing read errors is unrelated to tokenizer_class metadata mismatch on save." + "reason": "Reading position_ids after buffer registration and tokenizer save_pretrained metadata mismatch are unrelated." }, { "left": "issue:44704", "right": "issue:45290", "accept": false, - "reason": "Passing kwargs to cached_file and crashing on tool-call assistant messages are different apply_chat_template/processor bugs." - }, - { - "left": "issue:42907", - "right": "issue:44945", - "accept": false, - "reason": "Saving dequantized models and incorrect output under pipeline parallelism are unrelated model-save vs inference-parallelism issues." - }, - { - "left": "issue:41628", - "right": "issue:45278", - "accept": false, - "reason": "AutoImageProcessor import failure is one symbol missing; 45278 reports many import errors after upgrade, so they are not the same concrete bug." - }, - { - "left": "issue:43232", - "right": "issue:44743", - "accept": false, - "reason": "Generation kwargs update after sync_gpus and Qwen3.5 recurrent-state reset are different generation-path bugs." + "reason": "AutoProcessor kwarg forwarding and chat-template crashes on tool-call assistant messages are different bugs." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The single accepted duplicate pair is plausibly the same v5 AutoTokenizer/tokenizer-loading regression, and the other soft-edge rejections are appropriately cautious given only title-level evidence. No pair appears overstated or clearly non-mergeable." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -12903,7 +12867,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:22355", "issue:28218", @@ -12911,22 +12875,23 @@ "issue:30990", "issue:36296", "issue:39401", - "issue:42175", - "issue:42673", + "issue:41628", "issue:42757", "issue:42907", "issue:43116", "issue:43122", + "issue:43232", "issue:43278", "issue:43408", "issue:43452", "issue:43475", - "issue:43493", "issue:43784", "issue:43824", + "issue:43906", "issue:43937", "issue:43976", "issue:44038", + "issue:44188", "issue:44222", "issue:44261", "issue:44295", @@ -12939,31 +12904,34 @@ "issue:44514", "issue:44521", "issue:44625", + "issue:44743", "issue:44779", "issue:44829", - "issue:44938", "issue:44945", "issue:44964", "issue:44977", - "issue:45072", "issue:45200", "issue:45216", + "issue:45278", "issue:45446", "issue:45478", - "issue:45600", - "issue:45753" + "issue:45600" ], "soft_pairs": [ - "issue:43122|issue:44514", + "issue:44188|issue:44373", + "issue:42907|issue:44945", + "issue:41628|issue:45278", + "issue:43232|issue:44743", + "issue:43784|issue:45600", "issue:43976|issue:44945", "issue:39401|issue:44488", - "issue:43784|issue:45600", "issue:44261|issue:44373", + "issue:43122|issue:44514", "issue:43408|issue:43475", "issue:42907|issue:43937", "issue:39401|issue:44521", - "issue:43116|issue:45200", "issue:44625|issue:44829", + "issue:43116|issue:45200", "issue:42907|issue:44964", "issue:44360|issue:44485", "issue:44038|issue:44297", @@ -12972,229 +12940,236 @@ "issue:43122|issue:44779", "issue:42907|issue:43452", "issue:36296|issue:43116", - "issue:44038|issue:44222", "issue:43824|issue:44351", + "issue:44038|issue:44222", + "issue:43122|issue:43906", "issue:45216|issue:45478", "issue:42757|issue:44351", "issue:43784|issue:45446", "issue:43278|issue:44945", "issue:22355|issue:29159", - "issue:43122|issue:44977", - "issue:42175|issue:44938", - "issue:43493|issue:45753", - "issue:42673|issue:45072" + "issue:43122|issue:44977" ], - "prepared_review_unit_hash": "992c2b8cd9aa81120e9c54b8b8ec04b9391b15c5d66fa0c264532c80ba2bd6ea", + "prepared_review_unit_hash": "f58cb17fb0986388ea2df0d280e6b69fb4806c75568c9e675322a80eea4ad18f", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 47, "item_count": 47, - "soft_pair_count": 29, - "serialized_chars": 35357, - "estimated_input_tokens": 8840, - "estimated_eval_tokens": 17936 + "soft_pair_count": 31, + "serialized_chars": 35997, + "estimated_input_tokens": 9000, + "estimated_eval_tokens": 18256 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly unrelated issues across tokenization, model loading, and backend regressions. The Qwen3.5 save/load reports are thematically close, but #45216 and #45478 are not strong enough evidence of the same underlying bug to merge as duplicates.", - "confidence": 0.63, - "canonical_issue_reason": "Issue #45216 is the broadest and clearest representative of the Qwen3.5 5.4.0 save_pretrained serialization regression, but it should not absorb the separate from_pretrained error in #45478 without stronger body-level evidence of a shared root cause.", + "summary": "No clear duplicate cluster here: the issues span unrelated tokenizer, import, model-loading, generation, and training problems, so no soft-edge pair is strong enough to merge.", + "confidence": 0.93, + "canonical_issue_reason": "No single canonical issue stands out; the set is heterogeneous and the titles point to different bugs rather than one underlying defect.", "canonical_pr_reason": null, - "best_issue_reason": "#45216 is the best anchor for the Qwen3.5 save/load regression theme because it describes the core checkpoint corruption symptom most generally.", + "best_issue_reason": "45216 is the most concrete regression report, but it is only a representative example\u2014not a duplicate anchor for the rest of the set.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43122", - "right": "issue:44514", + "left": "issue:44188", + "right": "issue:44373", "accept": false, - "reason": "Both involve tokenizer/chat-template behavior, but one is a tokenizer regression and the other is a batched apply_chat_template crash; different symptoms and code paths." + "reason": "Different problems: torch.compile attention-kernel branching vs a docstring typo for position_ids." }, { - "left": "issue:43976", + "left": "issue:42907", "right": "issue:44945", "accept": false, - "reason": "A Python version compatibility issue and an incorrect output under pipeline parallelism are unrelated bugs." + "reason": "Unrelated: saving a dequantized model vs incorrect output under pipeline parallelism." }, { - "left": "issue:39401", - "right": "issue:44488", + "left": "issue:41628", + "right": "issue:45278", + "accept": false, + "reason": "One is a single AutoImageProcessor import failure; the other is a broad upgrade-related import-breakage report." + }, + { + "left": "issue:43232", + "right": "issue:44743", "accept": false, - "reason": "Wrong offset_mapping for Qwen3 tokenizer and failure to load a specific model are different problems; only the model family overlaps." + "reason": "Both are generation-related, but they describe different bugs and code paths." }, { "left": "issue:43784", "right": "issue:45600", "accept": false, - "reason": "Both are import/load failures, but one is a missing nn symbol in sentence-transformers integration and the other is stale auto_mappings references." + "reason": "Importing sentence-transformers vs CI break from removed Sam3LiteText config references are not the same bug." + }, + { + "left": "issue:43976", + "right": "issue:44945", + "accept": false, + "reason": "Python-version compatibility regression vs pipeline-parallel output corruption." + }, + { + "left": "issue:39401", + "right": "issue:44488", + "accept": false, + "reason": "Different tokenizer failures: offset_mapping mismatch vs a model load failure." }, { "left": "issue:44261", "right": "issue:44373", "accept": false, - "reason": "A numerical precision/config issue in MLA and a wrong docstring for position_ids are unrelated." + "reason": "Numerical precision/config issue in MLA layer vs a docstring issue." + }, + { + "left": "issue:43122", + "right": "issue:44514", + "accept": false, + "reason": "Tokenizer-version regression vs batched chat-template crash; different failure modes." }, { "left": "issue:43408", "right": "issue:43475", "accept": false, - "reason": "Both are SAM 3 related, but one is a model-type warning and the other is a missing attribute on a vision encoder output." + "reason": "Same model family, but one is a config/model-type warning and the other is an attribute error." }, { "left": "issue:42907", "right": "issue:43937", "accept": false, - "reason": "Saving dequantized models and invalid GenerationConfig are distinct code paths and symptoms." + "reason": "Saving dequantized models is unrelated to invalid GenerationConfig." }, { "left": "issue:39401", "right": "issue:44521", "accept": false, - "reason": "Both touch tokenizer/multimodal processing, but wrong offset mapping and all-zero assistant masks are separate bugs." + "reason": "Offset-mapping bug vs assistant_mask generation bug; different tokenizer paths." }, { - "left": "issue:43116", - "right": "issue:45200", + "left": "issue:44625", + "right": "issue:44829", "accept": false, - "reason": "A classification example returning empty results and a Gemma 4 token-type-id requirement are not the same underlying issue." + "reason": "num_labels propagation in Qwen3.5 is unrelated to flash_attention_3 training degeneration." }, { - "left": "issue:44625", - "right": "issue:44829", + "left": "issue:43116", + "right": "issue:45200", "accept": false, - "reason": "num_labels propagation and flash_attention_3 degenerate training are unrelated model configuration/performance bugs." + "reason": "Example-script multi-label output bug vs Gemma 4 multimodal token-type defaults." }, { "left": "issue:42907", "right": "issue:44964", "accept": false, - "reason": "Saving dequantized models and loading a multimodal Phi-4 model are different problems." + "reason": "Model save/dequantization issue vs a specific multimodal model load failure." }, { "left": "issue:44360", "right": "issue:44485", "accept": false, - "reason": "DSA indexer activation logic and GLM-5 RoPE implementation are unrelated." + "reason": "DSA ReLU discussion vs GLM-5 RoPE implementation; no shared underlying defect." }, { "left": "issue:44038", "right": "issue:44297", "accept": false, - "reason": "A Qwen3-VL-Moe loading issue and tokenizer_class mismatch on save_pretrained are different regressions." + "reason": "Qwen3-VL-Moe load bug vs tokenizer save metadata mismatch." }, { "left": "issue:28218", "right": "issue:30990", "accept": false, - "reason": "Tokenizer adding an extra space and Sentence Transformers getting stuck loading do not describe the same bug." + "reason": "Tokenizer spacing bug vs Sentence Transformers loading hang; unrelated." }, { "left": "issue:44038", "right": "issue:44295", "accept": false, - "reason": "Qwen3-VL-Moe loading and reading position_ids after buffer registration are unrelated." + "reason": "Model-load issue vs position_ids buffer access error." }, { "left": "issue:43122", "right": "issue:44779", "accept": false, - "reason": "Both are tokenizer regressions, but one is version-difference behavior and the other is Deepseek incorrect results; different models and failure modes." + "reason": "Both mention tokenization regressions, but they concern different models and symptoms." }, { "left": "issue:42907", "right": "issue:43452", "accept": false, - "reason": "Saving dequantized models and gguf_file breaking AutoTokenizer/AutoModel loading are distinct issues." + "reason": "Dequantized save failure vs gguf_file handling for from_pretrained; different code paths." }, { "left": "issue:36296", "right": "issue:43116", "accept": false, - "reason": "Tensor parallel training and a multi-label classification example returning empty results are unrelated." + "reason": "Tensor-parallel training bug vs example-script classification output bug." + }, + { + "left": "issue:43824", + "right": "issue:44351", + "accept": false, + "reason": "Different missing imports: Qwen2_5_VLForConditionalGeneration vs HybridCache." }, { "left": "issue:44038", "right": "issue:44222", "accept": false, - "reason": "Qwen3-VL-Moe loading and FP8 save_pretrained for moe are both MoE-related but not the same code-path failure." + "reason": "Qwen3-VL-Moe model loading issue vs FP8 save_pretrained bug; not the same bug." }, { - "left": "issue:43824", - "right": "issue:44351", + "left": "issue:43122", + "right": "issue:43906", "accept": false, - "reason": "Both are import errors, but they involve different missing exports and different fixes." + "reason": "Tokenizer regression vs an isolated reproduction of a different issue; no concrete overlap." }, { "left": "issue:45216", "right": "issue:45478", "accept": false, - "reason": "The titles point to a related Qwen3.5 save/load theme, but one is a save_pretrained checkpoint corruption report and the other is a from_pretrained load error for Qwen3.5 MoE; that's not enough to prove the same bug." + "reason": "Related Qwen3.5 regression theme, but save_pretrained checkpoint corruption and from_pretrained load error are not clearly the same code-path bug." }, { "left": "issue:42757", "right": "issue:44351", "accept": false, - "reason": "Missing is_offline_mode from huggingface_hub and missing HybridCache from transformers are separate import/export issues." + "reason": "ImportError from huggingface_hub vs ImportError from transformers; different missing symbols." }, { "left": "issue:43784", "right": "issue:45446", "accept": false, - "reason": "Importing sentence-transformers with latest transformers and a PyTorch version check for AuxRequest are unrelated." + "reason": "Sentence-transformers import NameError vs incorrect PyTorch version gating for AuxRequest." }, { "left": "issue:43278", "right": "issue:44945", "accept": false, - "reason": "Embedding dtype changing between training and evaluate is not the same as incorrect output under pipeline parallelism." + "reason": "Dtype drift in evaluation vs incorrect LLM output under pipeline parallelism." }, { "left": "issue:22355", "right": "issue:29159", "accept": false, - "reason": "No module named transformers.onnx and slow/fast tokenizer inconsistency are different historical bugs." - }, - { - "left": "issue:43122", - "right": "issue:44977", - "accept": false, - "reason": "Tokenizer version-difference behavior and Qwen3.5 flash-attention generation problems are unrelated." - }, - { - "left": "issue:42175", - "right": "issue:44938", - "accept": false, - "reason": "Missing TensorFlow backend in an install extra and Python 3.14 loading failure are different packaging/runtime issues." - }, - { - "left": "issue:43493", - "right": "issue:45753", - "accept": false, - "reason": "SigLIP2 HF/JAX discrepancy and Qwen3_5 infinite loop on a specific image are separate model bugs." + "reason": "onnx module import failure vs slow/fast tokenizer inconsistency; unrelated." }, { - "left": "issue:42673", - "right": "issue:45072", + "left": "issue:44261", + "right": "issue:44485", "accept": false, - "reason": "VRAM leak in Qwen3ForCausalLM multithreaded loading and dtype mismatches in bfloat16 inference are unrelated." + "reason": "Layer norm epsilon mismatch vs RoPE implementation discussion; different model components." } ] }, - "evaluator_result": { - "accept": false, - "feedback": "The overall summary is fine, but the accepted edge between issue:45216 and issue:45478 is too speculative for the packet. The titles only show a Qwen3.5 / 5.4.0 save_pretrained checkpoint corruption report and a separate from_pretrained load error for Qwen3.5 MoE; that is a plausible theme match, but not enough evidence to call them the same bugfix. A more conservative verdict would keep this pair as non-duplicate unless the bodies show a shared serialization root cause." - }, - "evaluator_used": true, - "retried": true, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null @@ -13210,13 +13185,14 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:22355", "issue:29127", "issue:33453", "issue:38617", "issue:39401", + "issue:42175", "issue:42222", "issue:42371", "issue:42673", @@ -13241,29 +13217,32 @@ "issue:44117", "issue:44291", "issue:44380", - "issue:44466", "issue:44485", "issue:44704", "issue:44779", "issue:44936", + "issue:44938", "issue:44977", "issue:45071", - "issue:45081", + "issue:45072", "issue:45083", "issue:45278", "issue:45357", - "issue:45405", "issue:45446", "issue:45478", "issue:45563", "issue:45588", + "issue:45753", "issue:46002", "issue:46077" ], "soft_pairs": [ - "issue:43992|issue:44704", - "issue:43066|issue:44779", + "issue:42175|issue:44938", + "issue:43493|issue:45753", + "issue:42673|issue:45072", "issue:38617|issue:45278", + "issue:43066|issue:44779", + "issue:43992|issue:44704", "issue:22355|issue:29127", "issue:43611|issue:46002", "issue:43937|issue:44485", @@ -13284,215 +13263,212 @@ "issue:43827|issue:45446", "issue:39401|issue:44779", "issue:42673|issue:43906", - "issue:43937|issue:44977", "issue:44291|issue:45071", - "issue:43450|issue:43986", - "issue:44466|issue:46002", - "issue:45405|issue:45446", - "issue:44117|issue:45081" + "issue:43937|issue:44977", + "issue:43450|issue:43986" ], - "prepared_review_unit_hash": "9262a5943d5f2df4cf9b9ca845cc446d74839acbbc5c6c595f35b0e2af74a07b", + "prepared_review_unit_hash": "f85ba557decb255e5a12f13ab1f4a3b9ee72857ea3d85c59135be4c6a99a3451", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { - "node_count": 47, - "item_count": 47, + "node_count": 48, + "item_count": 48, "soft_pair_count": 29, - "serialized_chars": 35667, - "estimated_input_tokens": 8917, - "estimated_eval_tokens": 18090 + "serialized_chars": 36035, + "estimated_input_tokens": 9009, + "estimated_eval_tokens": 18274 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These issues are largely unrelated regressions across different models, APIs, and failure modes. None of the soft pairs look like the same underlying bug or change, so I would not merge any of them as duplicates.", - "confidence": 0.93, - "canonical_issue_reason": "issue:45278 is the broadest representative item in the set: it describes multiple import errors after upgrading to 5.5.0, which makes it the most central umbrella issue among these otherwise distinct reports.", + "summary": "This cluster is a loose semantic bucket of mostly unrelated Transformers v5 regressions, model-specific bugs, and a few packaging/docs/deprecation issues; none of the suggested soft pairs look like true duplicates.", + "confidence": 0.19, + "canonical_issue_reason": "issue:45278 is the best umbrella representative because it captures the broad post-upgrade breakage theme that recurs across several reports, even though the cluster is too heterogeneous for a true canonical duplicate.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the best single issue to anchor the cluster because it captures a broad upgrade regression and is more representative than the model-specific or narrowly scoped reports.", + "best_issue_reason": "issue:45278 has the widest scope and strongest tie to the recurring v5 import/regression pattern, so it is the most suitable representative issue.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43992", - "right": "issue:44704", + "left": "issue:42175", + "right": "issue:44938", "accept": false, - "reason": "Different code paths: UMT5Encoder weight loading vs AutoProcessor forwarding kwargs to cached_file." + "reason": "Different failures: missing TensorFlow backend from a torch-only install vs Python 3.14 import/load failure." }, { - "left": "issue:43066", - "right": "issue:44779", + "left": "issue:43493", + "right": "issue:45753", + "accept": false, + "reason": "Both are Qwen3.5-related, but one is a SigLIP2 implementation discrepancy and the other is an infinite-loop generation bug on a specific image." + }, + { + "left": "issue:42673", + "right": "issue:45072", "accept": false, - "reason": "Both tokenizer-related, but one is wrong decoder type and the other is incorrect Deepseek tokenization results; not the same bug." + "reason": "VRAM leak in Qwen3ForCausalLM multi-threaded dataloader use is unrelated to dtype mismatches in CI inference." }, { "left": "issue:38617", "right": "issue:45278", "accept": false, - "reason": "One is a specific missing import, the other is a broad set of import errors after upgrade; related theme but not the same underlying defect." + "reason": "One is an import failure for a missing symbol; the other is a broad upgrade report about many import errors, not the same underlying bug." + }, + { + "left": "issue:43066", + "right": "issue:44779", + "accept": false, + "reason": "Wrong tokenizer decoder type in v5 is a different tokenizer bug than Deepseek producing incorrect results." + }, + { + "left": "issue:43992", + "right": "issue:44704", + "accept": false, + "reason": "Missing embed_tokens.weight in UMT5Encoder loading is unrelated to AutoProcessor not forwarding kwargs to cached_file." }, { "left": "issue:22355", "right": "issue:29127", "accept": false, - "reason": "Completely different problems: missing transformers.onnx module vs a confusing layoutlmv3 error message." + "reason": "Module import failure for transformers.onnx and a LayoutLMv3 error-message clarity issue are unrelated." }, { "left": "issue:43611", "right": "issue:46002", "accept": false, - "reason": "Loading with base_model_prefix broke, but the other report is NaNs in classification heads after checkout/init; unrelated failure modes." + "reason": "base_model_prefix loading breakage and NaNs in classification heads after checkout/init are different code paths and symptoms." }, { "left": "issue:43937", "right": "issue:44485", "accept": false, - "reason": "Both mention GLM-5, but one is invalid GenerationConfig and the other is RoPE implementation discussion; different bugs." + "reason": "Invalid GenerationConfig for GLM-5 is not the same as a RoPE implementation discussion." }, { "left": "issue:43976", "right": "issue:45446", "accept": false, - "reason": "Python version compatibility regression vs an incorrect PyTorch version check in flex_attention; unrelated." + "reason": "Python version compatibility for Transformers v5.1.0 is unrelated to a PyTorch version check bug in flex_attention." }, { "left": "issue:42222", "right": "issue:43441", "accept": false, - "reason": "VitPose model breakage and Ministral FlashAttention failure are different model-specific issues." + "reason": "VitPose model breakage and Ministral-3 FlashAttention failure are distinct model-specific regressions." }, { "left": "issue:43116", "right": "issue:43493", "accept": false, - "reason": "Example-script multi-label classification behavior is unrelated to SigLIP2 implementation discrepancy." + "reason": "Empty results in the example classification script is unrelated to a SigLIP2 implementation discrepancy." }, { "left": "issue:42371", "right": "issue:43874", "accept": false, - "reason": "TF32 settings and a missing image-processor method are unrelated." + "reason": "TF32 settings warning and a missing image-patch helper in GLM46V are different issues." }, { "left": "issue:44075", "right": "issue:44936", "accept": false, - "reason": "Optimizer argument handling and trainer.evaluate() after train are different trainer/optimizer issues." + "reason": "Optimizer SGD args ignored is unrelated to trainer.evaluate() failing after train()." }, { "left": "issue:43064", "right": "issue:43673", "accept": false, - "reason": "Distributed optimizer-state corruption and missing GenerationMixin cache are unrelated code paths." + "reason": "FSDP2/PEFT optimizer-state corruption is a different bug from missing GenerationMixin cache during chunked_prefill." }, { "left": "issue:45357", "right": "issue:45478", "accept": false, - "reason": "Both concern Qwen3.5, but save_pretrained key serialization and from_pretrained loading errors are different bugs." + "reason": "Both involve Qwen3.5, but one is a save_pretrained key regression and the other is a from_pretrained load error; not the same fix." }, { "left": "issue:44038", "right": "issue:45478", "accept": false, - "reason": "Same general model family, but Qwen3-VL-Moe vs Qwen3.5 MoE from_pretrained are not the same failure." + "reason": "Qwen3-VL-Moe and Qwen3.5-Moe are different model families and symptoms, so this is not one underlying bug." }, { "left": "issue:43116", "right": "issue:43825", "accept": false, - "reason": "Classification example output bug vs pipeline translation-task messaging are unrelated." + "reason": "Example-script multi-label behavior and pipeline() translation support/error messaging are unrelated." }, { "left": "issue:45083", "right": "issue:45446", "accept": false, - "reason": "A feature-extraction helper issue and a PyTorch version check bug are unrelated." + "reason": "A Qwen3_omni_moe helper-length bug is unrelated to the flex_attention import/version check issue." }, { "left": "issue:43937", "right": "issue:45563", "accept": false, - "reason": "GenerationConfig invalidity and a stale warning for num_return_sequences are different issues." + "reason": "Invalid GenerationConfig and a stale warning for num_return_sequences are not the same defect." }, { "left": "issue:44380", "right": "issue:46077", "accept": false, - "reason": "Attention-scaling ignored in GPT2 backend vs Gemma4 bidirectional mask construction are different model/backend bugs." + "reason": "GPT2 attention scaling under SDPA/FlashAttention is unrelated to Gemma4 building causal masks when bidirectional attention is requested." }, { "left": "issue:33453", "right": "issue:39401", "accept": false, - "reason": "Both tokenizer-related regressions, but generic loading regression vs Qwen3 offset_mapping bug are not the same defect." + "reason": "Tokenizer loading regression and Qwen3 offset_mapping errors are different tokenizer problems with different failure modes." }, { "left": "issue:44117", "right": "issue:45588", "accept": false, - "reason": "Tokenizer mapping None handling and flash_attention crashing on s_aux=None are unrelated." + "reason": "TOKENIZER_MAPPING_NAMES returning None and a flash_attention crash on s_aux=None are unrelated." }, { "left": "issue:43827", "right": "issue:45446", "accept": false, - "reason": "Documentation references to pipeline() vs a runtime version check bug have no shared underlying code path." + "reason": "Docs still referencing pipeline() after v5 removals is unrelated to an AuxRequest import version check bug." }, { "left": "issue:39401", "right": "issue:44779", "accept": false, - "reason": "Different model-specific tokenizer regressions: Qwen3 offset mapping vs Deepseek incorrect results." + "reason": "Wrong Qwen3 offset_mapping and incorrect Deepseek tokenizer results are separate tokenizer regressions." }, { "left": "issue:42673", "right": "issue:43906", "accept": false, - "reason": "VRAM leak in Qwen3ForCausalLM threads is not the same as a reproduction of issue 38071." - }, - { - "left": "issue:43937", - "right": "issue:44977", - "accept": false, - "reason": "Different GLM/Qwen generation failures with different symptoms and likely different causes." + "reason": "A VRAM leak in multi-threaded Qwen3ForCausalLM use is not the same as an isolated reproduction of another issue." }, { "left": "issue:44291", "right": "issue:45071", "accept": false, - "reason": "init_empty_weights argument incompatibility is unrelated to PretrainedConfig type-checking breakage." + "reason": "Unexpected _is_hf_initialized argument during init_empty_weights is unrelated to PretrainedConfig type-checking breakage." }, { - "left": "issue:43450", - "right": "issue:43986", - "accept": false, - "reason": "Batched video processor shape bug vs missing torchvision crash when loading via AutoProcessor are distinct issues." - }, - { - "left": "issue:44466", - "right": "issue:46002", - "accept": false, - "reason": "Serialization of tied lm_head weights and NaNs in classification heads are unrelated." - }, - { - "left": "issue:45405", - "right": "issue:45446", + "left": "issue:43937", + "right": "issue:44977", "accept": false, - "reason": "A PEFT minimum-version bump issue is unrelated to the flex_attention import version check." + "reason": "GLM-5 GenerationConfig invalidity and Qwen3.5 flash-attention generation problems are different model/runtime failures." }, { - "left": "issue:44117", - "right": "issue:45081", + "left": "issue:43450", + "right": "issue:43986", "accept": false, - "reason": "Tokenizer mapping fallback handling and a Mistral regex patch crash are different tokenizer bugs." + "reason": "Video processor batch-shape bug and missing-torchvision AutoProcessor crash are related to video processing but not the same code-path problem." } ] }, @@ -13514,7 +13490,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:38617", "issue:39401", @@ -13532,46 +13508,49 @@ "issue:43122", "issue:43408", "issue:43421", - "issue:43441", "issue:43577", "issue:43582", "issue:43673", "issue:43742", - "issue:43874", "issue:43937", "issue:44075", + "issue:44117", "issue:44220", "issue:44261", - "issue:44263", - "issue:44360", "issue:44410", + "issue:44466", "issue:44483", "issue:44484", - "issue:44485", "issue:44493", "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", - "issue:46172", + "issue:46002", "issue:46178" ], "soft_pairs": [ + "issue:44466|issue:46002", + "issue:45405|issue:45446", + "issue:44117|issue:45081", "issue:45341|issue:45561", "issue:42222|issue:46178", "issue:38617|issue:41628", "issue:44410|issue:45310", - "issue:39401|issue:43421", "issue:44829|issue:45216", + "issue:39401|issue:43421", "issue:42617|issue:45341", "issue:44484|issue:45310", "issue:42673|issue:43582", @@ -13579,260 +13558,229 @@ "issue:43408|issue:43742", "issue:42371|issue:44261", "issue:44933|issue:45278", - "issue:44483|issue:45464", "issue:38617|issue:44220", - "issue:43937|issue:44496", "issue:42222|issue:45542", + "issue:43937|issue:44496", + "issue:44483|issue:45464", "issue:43066|issue:43122", "issue:42175|issue:42222", "issue:42371|issue:42831", "issue:44075|issue:45656", - "issue:43673|issue:45341", "issue:44410|issue:45478", + "issue:43673|issue:45341", "issue:43012|issue:43577", "issue:44484|issue:45478", "issue:43097|issue:44493", - "issue:41628|issue:45071", - "issue:43874|issue:44261", - "issue:44263|issue:44485", - "issue:45071|issue:45542", - "issue:44263|issue:46172", - "issue:44360|issue:46172", - "issue:43012|issue:43408", - "issue:43441|issue:44829" + "issue:41628|issue:45071" ], - "prepared_review_unit_hash": "573ac12730a34a75c005a551453139f4b133089737cba965ec9930cc7ce31a15", + "prepared_review_unit_hash": "8d3f62a26dbbbd1800fb448b123f42a482ab4b82b8109daa179b0053f966a952", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 34, - "serialized_chars": 37402, - "estimated_input_tokens": 9351, - "estimated_eval_tokens": 18958 + "soft_pair_count": 30, + "serialized_chars": 36435, + "estimated_input_tokens": 9109, + "estimated_eval_tokens": 18474 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is heterogeneous: most items are distinct import, tokenizer, model-loading, backend, or training bugs rather than true duplicates. None of the soft pairs look like the same concrete issue, so all are rejected.", - "confidence": 0.8, - "canonical_issue_reason": "issue:45278 is the broadest umbrella in the set ('Many import errors after update from 4.57.0 to 5.5.0') and is the closest representative of the import-breakage subset, though the cluster overall is not a single duplicate group.", + "summary": "This cluster is highly heterogeneous: most items are unrelated bug reports, with only a small import-regression subgroup. None of the soft pairs look like the same concrete bug/change, and there are no PRs in the set.", + "confidence": 0.79, + "canonical_issue_reason": "issue:45278 is the broadest umbrella report about import failures after upgrading, so it is the best anchor for the small import-regression subgroup.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the most representative high-level regression report and the best anchor if one issue must be chosen from this mixed set.", + "best_issue_reason": "issue:45278 is the most representative issue in this mixed set; it is broader than the other import-related reports and closer to a possible cluster summary.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44466", + "right": "issue:46002", + "accept": false, + "reason": "Both mention model weights/training behavior, but one is a serialization/tied-weights issue and the other is NaNs in classification heads; different bugs." + }, + { + "left": "issue:45405", + "right": "issue:45446", + "accept": false, + "reason": "Unrelated topics: PEFT version pinning vs a PyTorch version-check bug in flex_attention." + }, + { + "left": "issue:44117", + "right": "issue:45081", + "accept": false, + "reason": "Both are tokenizer-related, but one is a mapping lookup bug and the other is a Mistral regex crash; different code paths." + }, { "left": "issue:45341", "right": "issue:45561", "accept": false, - "reason": "Both mention testing_utils, but one is a vague bug report and the other is a specific xdist race on captured_info.txt; different failures." + "reason": "The second is a pytest-xdist race in captured_info.txt; the first is only a vague testing_utils bug and is not clearly the same issue." }, { "left": "issue:42222", "right": "issue:46178", "accept": false, - "reason": "Different subsystems: vitpose model breakage vs backend-mapping error for tensorflow_text." + "reason": "VitPose model breakage and a tensorflow_text backend lookup error are different failures." }, { "left": "issue:38617", "right": "issue:41628", "accept": false, - "reason": "Both are import errors, but for different missing symbols and code paths." + "reason": "Both are import errors, but for different missing symbols and likely different fixes." }, { "left": "issue:44410", "right": "issue:45310", "accept": false, - "reason": "Different Qwen issues: missing layer projections vs a Qwen3.5 MoE from_pretrained error." + "reason": "Different model families and symptoms: missing Qwen3Next projections vs Qwen3.5-MoE from_pretrained failure." }, { - "left": "issue:39401", - "right": "issue:43421", + "left": "issue:44829", + "right": "issue:45216", "accept": false, - "reason": "Both are tokenizer-related, but wrong offset_mapping and runtime post-processor updates are different problems." + "reason": "One is an FA3 training-degeneration issue; the other is a save_pretrained regression for Qwen3.5 checkpoints." }, { - "left": "issue:44829", - "right": "issue:45216", + "left": "issue:39401", + "right": "issue:43421", "accept": false, - "reason": "FlashAttention-3 degenerate training and Qwen3.5 save_pretrained checkpoint corruption are unrelated regressions." + "reason": "Both involve tokenizers, but offset_mapping errors and runtime post-processor updates are distinct bugs." }, { "left": "issue:42617", "right": "issue:45341", "accept": false, - "reason": "A script failure and a testing_utils bug are unrelated." + "reason": "A 3d_parallel.py runtime problem is unrelated to a small testing_utils bug." }, { "left": "issue:44484", "right": "issue:45310", "accept": false, - "reason": "Shard-size behavior in save_pretrained is unrelated to the Qwen3.5 from_pretrained regression." + "reason": "max_shard_size behavior in save_pretrained is unrelated to a Qwen3.5-MoE from_pretrained error." }, { "left": "issue:42673", "right": "issue:43582", "accept": false, - "reason": "VRAM leakage in multi-threaded loading and an Apple Silicon TypeError are distinct issues." + "reason": "A VRAM leak in multi-threaded dataloading and an Apple Silicon TypeError are different issues." }, { "left": "issue:42490", "right": "issue:42673", "accept": false, - "reason": "Trailing-slash path warning vs VRAM leak under multiple dataloader threads are different bugs." + "reason": "Import warning on local model paths and a Qwen3ForCausalLM VRAM leak are unrelated." }, { "left": "issue:43408", "right": "issue:43742", "accept": false, - "reason": "Model-type mismatch warning for sam3_tracker is unrelated to the MobileLLM key error." + "reason": "Model-type warning for sam3 variants is not the same as a key error loading facebook/MobileLLM-125M." }, { "left": "issue:42371", "right": "issue:44261", "accept": false, - "reason": "TF32 settings warning and MLA rms_norm_eps precision error are different problems." + "reason": "TF32 configuration guidance and an MLA rms_norm_eps precision bug are unrelated." }, { "left": "issue:44933", "right": "issue:45278", "accept": false, - "reason": "Both are import-related, but missing image_utils import and broad 5.5.0 import errors are not the same concrete failure." + "reason": "A missing image_utils import may be related to import regressions, but it is not the same concrete bug as the broad upgrade-related report." }, { - "left": "issue:44483", - "right": "issue:45464", + "left": "issue:38617", + "right": "issue:44220", "accept": false, - "reason": "Different API failures: generic chat/completions rejection vs Qwen3.5 streaming inference failure." + "reason": "A missing configuration import and an fbank feature-extraction issue are different code paths." }, { - "left": "issue:38617", - "right": "issue:44220", + "left": "issue:42222", + "right": "issue:45542", "accept": false, - "reason": "ImportError for layer_type_validation is unrelated to _torch_extract_fbank_features()." + "reason": "VitPose model breakage is unrelated to a missing TensorFlow backend when only tensorboard is installed." }, { "left": "issue:43937", "right": "issue:44496", "accept": false, - "reason": "Invalid GenerationConfig for GLM-5 is different from unrecognized model config.json." + "reason": "GenerationConfig validation for GLM-5 and unrecognized-model loading for Olmo-Hybrid are distinct failures." }, { - "left": "issue:42222", - "right": "issue:45542", + "left": "issue:44483", + "right": "issue:45464", "accept": false, - "reason": "vitpose model breakage and missing TensorFlow backend are unrelated." + "reason": "Both mention chat/completions failures, but one is a generic request rejection and the other is a streaming inference symptom on a specific model; not clearly the same bug." }, { "left": "issue:43066", "right": "issue:43122", "accept": false, - "reason": "Tokenizer decoder type mismatch and changed tokenization output are distinct regressions." + "reason": "Tokenizer decoder-type mismatch and version-to-version tokenization differences are related only at a high level, not the same concrete issue." }, { "left": "issue:42175", "right": "issue:42222", "accept": false, - "reason": "TensorFlow extra/backend packaging issue vs vitpose model breakage." + "reason": "Missing TensorFlow in a torch-only install and broken VitPose models are unrelated." }, { "left": "issue:42371", "right": "issue:42831", "accept": false, - "reason": "TF32 API warning is unrelated to FineGrainedFP8 accuracy." + "reason": "TF32 behavior controls and FineGrainedFP8 accuracy problems are different topics." }, { "left": "issue:44075", "right": "issue:45656", "accept": false, - "reason": "Optimizer SGD args ignored and optimizer step called twice under deepspeed are different optimizer bugs." + "reason": "SGD arguments not being used and an optimizer step firing twice under deepspeed are separate optimizer bugs." }, { - "left": "issue:43673", - "right": "issue:45341", + "left": "issue:44410", + "right": "issue:45478", "accept": false, - "reason": "Generation cache missing in v5 RC is unrelated to the testing_utils bug." + "reason": "Missing Qwen3Next projections and Qwen3.5-MoE from_pretrained failures do not look like the same defect." }, { - "left": "issue:44410", - "right": "issue:45478", + "left": "issue:43673", + "right": "issue:45341", "accept": false, - "reason": "Missing projections and Qwen3.5 from_pretrained error are different code-path failures." + "reason": "Generation cache behavior during chunked_prefill is unrelated to a testing_utils bug." }, { "left": "issue:43012", "right": "issue:43577", "accept": false, - "reason": "bfloat16 precision warning and BLIP2 dtype propagation bug are different dtype issues." + "reason": "A bfloat16 precision warning and Blip2 dtype remaining float32 are different dtype-related symptoms." }, { "left": "issue:44484", "right": "issue:45478", "accept": false, - "reason": "Shard-size question and Qwen3.5 from_pretrained regression are unrelated." + "reason": "save_pretrained shard sizing and Qwen3.5-MoE loading failures are unrelated." }, { "left": "issue:43097", "right": "issue:44493", "accept": false, - "reason": "Removed tie_embeddings_and_encoder_decoder API and unexpected key with position id are separate regressions." + "reason": "A removed config attribute and unexpected position-id keys are different regression surfaces." }, { "left": "issue:41628", "right": "issue:45071", "accept": false, - "reason": "AutoImageProcessor ImportError and PreTrainedConfig type-checking breakage are unrelated." - }, - { - "left": "issue:43874", - "right": "issue:44261", - "accept": false, - "reason": "Missing image patch-count helper and MLA eps precision bug are different issues." - }, - { - "left": "issue:44263", - "right": "issue:44485", - "accept": false, - "reason": "torch.split return handling in an indexer and GLM-5 RoPE implementation are unrelated." - }, - { - "left": "issue:45071", - "right": "issue:45542", - "accept": false, - "reason": "Type-checking breakage is unrelated to the missing TensorFlow backend error." - }, - { - "left": "issue:44263", - "right": "issue:46172", - "accept": false, - "reason": "DSA indexer split handling and deepseek-v4 transpose/dtype issue are unrelated." - }, - { - "left": "issue:44360", - "right": "issue:46172", - "accept": false, - "reason": "DSA indexer lacking ReLU and deepseek-v4 comb transpose bug are different problems." - }, - { - "left": "issue:43012", - "right": "issue:43408", - "accept": false, - "reason": "bfloat16 warning and sam3 model-type mismatch are different model-loading problems." - }, - { - "left": "issue:43441", - "right": "issue:44829", - "accept": false, - "reason": "FlashAttention failure in Ministral-3 and flash_attention_3 training degeneration are unrelated." + "reason": "An AutoImageProcessor import error and a PreTrainedConfig type-checking regression are unrelated." } ] }, @@ -13854,23 +13802,22 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:38617", "issue:42757", + "issue:43012", "issue:43064", "issue:43066", "issue:43097", - "issue:43208", "issue:43335", "issue:43408", + "issue:43441", "issue:43452", "issue:43502", "issue:43531", - "issue:43550", "issue:43673", "issue:43824", - "issue:43825", "issue:43873", "issue:43874", "issue:43906", @@ -13884,13 +13831,13 @@ "issue:44263", "issue:44315", "issue:44351", + "issue:44360", "issue:44368", "issue:44410", "issue:44484", "issue:44485", - "issue:44655", "issue:44704", - "issue:44938", + "issue:44829", "issue:44987", "issue:45003", "issue:45071", @@ -13899,13 +13846,20 @@ "issue:45372", "issue:45375", "issue:45440", + "issue:45542", "issue:45588", "issue:46050", "issue:46123", - "issue:46172", - "issue:46178" + "issue:46172" ], "soft_pairs": [ + "issue:43874|issue:44261", + "issue:44263|issue:44485", + "issue:45071|issue:45542", + "issue:44360|issue:46172", + "issue:44263|issue:46172", + "issue:43012|issue:43408", + "issue:43441|issue:44829", "issue:43931|issue:44410", "issue:43931|issue:44038", "issue:43335|issue:45071", @@ -13917,8 +13871,8 @@ "issue:43408|issue:44368", "issue:43986|issue:44484", "issue:43874|issue:44263", - "issue:43986|issue:45372", "issue:45440|issue:46172", + "issue:43986|issue:45372", "issue:43531|issue:45341", "issue:38617|issue:42757", "issue:44261|issue:44485", @@ -13930,242 +13884,256 @@ "issue:38617|issue:44351", "issue:44038|issue:44410", "issue:43502|issue:43992", - "issue:44704|issue:45103", "issue:43097|issue:43873", + "issue:44704|issue:45103", "issue:43986|issue:44117", "issue:43824|issue:43986", - "issue:43066|issue:43906", - "issue:44938|issue:46178", - "issue:43208|issue:43550", - "issue:43992|issue:44484", - "issue:43825|issue:44655" + "issue:43066|issue:43906" ], - "prepared_review_unit_hash": "dccbd5bd37c7d5b432acbef53af0a81bca7ef2d960739c78fbd39d4bd2d5fc0c", + "prepared_review_unit_hash": "8856ca51782a93d16b788a20366e7fd4a77e4eaad7781c66ba11d500ed3d64db", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 33, - "serialized_chars": 37511, - "estimated_input_tokens": 9378, - "estimated_eval_tokens": 19012 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 36, + "serialized_chars": 37926, + "estimated_input_tokens": 9482, + "estimated_eval_tokens": 19220 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is a grab bag of mostly unrelated Transformers regression reports, many centered on v5 migration breakages. None of the soft pairs look like the same underlying bug or change, so all are rejected as duplicates.", - "confidence": 0.91, - "canonical_issue_reason": "Issue 43097 is the broadest, clearest v5 regression report in the set and reads like a representative umbrella complaint about a breaking API removal; the other issues are separate bugs in different code paths.", + "summary": "These items do not form a real duplicate cluster; they cover many unrelated Transformers bugs and regressions. I found no PRs to compare, and I would not merge any of the soft pairs based on the available evidence.", + "confidence": 0.97, + "canonical_issue_reason": "No single canonical issue exists here: the set spans unrelated problems across imports, model loading, quantization, configuration, tokenizers, and generation.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43097 is the best single representative of the cluster\u2019s general v5-breaking-change theme, but it should not be treated as a duplicate target for the other reports.", + "best_issue_reason": "issue:43502 is the strongest standalone bug report: it is a clear, reproducible user-facing loading-path regression with broad impact.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43874", + "right": "issue:44261", + "accept": false, + "reason": "Different bugs: missing image-processor method vs MLA layernorm config precision handling." + }, + { + "left": "issue:44263", + "right": "issue:44485", + "accept": false, + "reason": "Different code paths: GlmMoeDsaIndexer split behavior vs GLM-5 RoPE implementation." + }, + { + "left": "issue:45071", + "right": "issue:45542", + "accept": false, + "reason": "Unrelated: PretrainedConfig type-checking regression vs backend detection when only tensorboard is installed." + }, + { + "left": "issue:44360", + "right": "issue:46172", + "accept": false, + "reason": "Different DeepSeek/GLM internals: DSA ReLU discussion vs deepseek-v4 transpose issue." + }, + { + "left": "issue:44263", + "right": "issue:46172", + "accept": false, + "reason": "Different bugs in different model internals; no shared failing code path." + }, + { + "left": "issue:43012", + "right": "issue:43408", + "accept": false, + "reason": "Different symptoms and subsystems: bfloat16 compile warning vs model-type mismatch warning." + }, + { + "left": "issue:43441", + "right": "issue:44829", + "accept": false, + "reason": "Both mention FlashAttention, but they are different failures on different models and code paths." + }, { "left": "issue:43931", "right": "issue:44410", "accept": false, - "reason": "Both are Qwen-related loading/model-structure bugs, but they describe different failures: weight-shape mismatch vs missing projections in a different architecture." + "reason": "Different model-loading problems: weight shape mismatch vs missing projections in a different architecture." }, { "left": "issue:43931", "right": "issue:44038", "accept": false, - "reason": "Same broad model family, but the reported failures are distinct Qwen-VL issues with different symptoms and likely different code paths." + "reason": "Different Qwen/VL issues with different failure modes; not the same bug." }, { "left": "issue:43335", "right": "issue:45071", "accept": false, - "reason": "SwitchTransformers sparse-layer construction and PreTrainedConfig type checking are unrelated bugs." + "reason": "Unrelated: SwitchTransformers sparse-layer construction vs PretrainedConfig type-checking." }, { "left": "issue:43673", "right": "issue:46123", "accept": false, - "reason": "Chunked prefill cache handling and MaskGenerationPipeline final-batch handling are different generation/pipeline defects." + "reason": "Different generation bugs: missing cache during chunked prefill vs final partial batch handling." }, { "left": "issue:43097", "right": "issue:43452", "accept": false, - "reason": "Both are v5 breakage reports, but one is about a removed config helper and the other about tokenizer/model loading for gguf_file; not the same bug." + "reason": "Different problems: removed tie_embeddings behavior vs gguf_file breaking model/tokenizer loading." }, { "left": "issue:45003", "right": "issue:45341", "accept": false, - "reason": "Unsafe sys.modules access and a testing_utils bug are unrelated." + "reason": "Different areas: unsafe sys.modules access vs a testing_utils bug." }, { "left": "issue:43986", "right": "issue:45341", "accept": false, - "reason": "Video-model loading without torchvision and a testing utility issue do not share the same failure path." + "reason": "Different issues: missing torchvision handling in AutoProcessor vs testing_utils." }, { "left": "issue:44117", "right": "issue:44987", "accept": false, - "reason": "TOKENIZER_MAPPING_NAMES returning None and a model-loading failure for physical-intelligence/fast are not the same underlying defect." + "reason": "Different failures: tokenizer mapping assumptions vs a specific model-loading regression in 5.1.0." }, { "left": "issue:43408", "right": "issue:44368", "accept": false, - "reason": "These are different warning/regression reports involving different model families and different config fields." + "reason": "Both are warnings, but they concern different warnings and different configuration fields." }, { "left": "issue:43986", "right": "issue:44484", "accept": false, - "reason": "AutoProcessor/torchvision loading crash is unrelated to save_pretrained shard-size behavior." + "reason": "Unrelated: video-model loading without torchvision vs max_shard_size question." }, { "left": "issue:43874", "right": "issue:44263", "accept": false, - "reason": "Different GLM bugs in different components: image processor missing a method versus torch.split return handling." + "reason": "Different GLM bugs: missing image-processor method vs torch.split return handling." }, { - "left": "issue:43986", - "right": "issue:45372", + "left": "issue:45440", + "right": "issue:46172", "accept": false, - "reason": "Missing torchvision and missing ReasoningEffort are separate import/dependency problems." + "reason": "Different DeepSeek model discrepancies; not the same concrete defect." }, { - "left": "issue:45440", - "right": "issue:46172", + "left": "issue:43986", + "right": "issue:45372", "accept": false, - "reason": "Both are DeepSeek-family issues, but one is an implementation divergence and the other is a specific tensor transpose expression; not clearly the same bug." + "reason": "Different import/loading failures affecting different dependencies and model paths." }, { "left": "issue:43531", "right": "issue:45341", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior and a testing_utils bug are unrelated." + "reason": "Different areas: Qwen3-MoE sliding_window behavior vs testing_utils." }, { "left": "issue:38617", "right": "issue:42757", "accept": false, - "reason": "Both are import errors, but they involve different missing symbols from different modules and different breakages." + "reason": "Both are ImportErrors, but for different missing symbols from different modules." }, { "left": "issue:44261", "right": "issue:44485", "accept": false, - "reason": "MLA layer-norm epsilon precision and GLM RoPE implementation are different numerical/modeling issues." + "reason": "Different model internals and unrelated fixes: rms_norm_eps precision issue vs GLM-5 RoPE implementation." }, { "left": "issue:43064", "right": "issue:44315", "accept": false, - "reason": "Trainer/FSDP2 optimizer-state corruption and Liger Kernel not being applied are separate training-path bugs." + "reason": "Different training issues: FSDP2/PEFT optimizer-state bug vs Liger Kernel not applied with model_init." }, { "left": "issue:43097", "right": "issue:46050", "accept": false, - "reason": "A removed tie_embeddings_and_encoder_decoder API and a quantized-model save/load regression are different failure modes." + "reason": "Different failures: removed embedding-tie config warning vs sinq quantization save/load breakage." }, { "left": "issue:43097", "right": "issue:45588", "accept": false, - "reason": "A v5 API removal and a flash-attention sinkless-model crash do not describe the same code-path problem." + "reason": "Different subsystems: tie_embeddings deprecation/removal vs flash_attention sinkless-model crash." }, { "left": "issue:44062", "right": "issue:44117", "accept": false, - "reason": "AddedToken keyword duplication and tokenizer mapping None are tokenizer-related but distinct defects." + "reason": "Tokenizer construction error vs tokenizer mapping None; not the same bug." }, { "left": "issue:44410", "right": "issue:45375", "accept": false, - "reason": "Different Qwen config/model bugs: missing projections versus a missing vision config field." + "reason": "Different Qwen-family configuration bugs with different missing fields/projections." }, { "left": "issue:38617", "right": "issue:44351", "accept": false, - "reason": "Different missing imports from different namespaces; these are not the same underlying regression." + "reason": "Different missing imports from different modules and different upstream API breakages." }, { "left": "issue:44038", "right": "issue:44410", "accept": false, - "reason": "Both involve Qwen models, but one is a VL-MoE bug and the other is a missing-projections issue in a different model variant." + "reason": "Different Qwen model families and different failure modes; not mergeable as one fix." }, { "left": "issue:43502", "right": "issue:43992", "accept": false, - "reason": "Local_files_only network leakage and UMT5Encoder weight loading are separate from_pretrained issues with different causes." + "reason": "Different loading regressions: local_files_only network requests vs missing embed_tokens.weight for UMT5." }, { - "left": "issue:44704", - "right": "issue:45103", + "left": "issue:43097", + "right": "issue:43873", "accept": false, - "reason": "AutoProcessor kwargs propagation and auto_docstring annotation handling are unrelated." + "reason": "Different issues: tie_embeddings removal vs quantization/offloading behavior." }, { - "left": "issue:43097", - "right": "issue:43873", + "left": "issue:44704", + "right": "issue:45103", "accept": false, - "reason": "A removed v5 API and quantization offloading behavior are different classes of bugs." + "reason": "Different code paths: AutoProcessor kwargs forwarding vs auto_docstring annotation processing." }, { "left": "issue:43986", "right": "issue:44117", "accept": false, - "reason": "Video-model loading without torchvision and tokenizer mapping assumptions are separate loading paths." + "reason": "Different failures in processor loading vs tokenizer mapping resolution." }, { "left": "issue:43824", "right": "issue:43986", "accept": false, - "reason": "Different processor/model import failures for different model families." + "reason": "Different problems: missing Qwen2.5-VL export vs AutoProcessor crashing without torchvision." }, { "left": "issue:43066", "right": "issue:43906", "accept": false, - "reason": "Wrong tokenizer decoder type and an isolated reproduction issue are not the same bug." - }, - { - "left": "issue:44938", - "right": "issue:46178", - "accept": false, - "reason": "Python 3.14 import/load failure and an unsupported tensorflow_text backend error are unrelated environment problems." - }, - { - "left": "issue:43208", - "right": "issue:43550", - "accept": false, - "reason": "xLSTM training blockers and Bamba torch.compile/SDPA failure are different model/backend bugs." - }, - { - "left": "issue:43992", - "right": "issue:44484", - "accept": false, - "reason": "Missing embed_tokens.weight and default max_shard_size are unrelated save/load behaviors." - }, - { - "left": "issue:43825", - "right": "issue:44655", - "accept": false, - "reason": "Pipeline translation error messaging and pipeline save_pretrained support are different pipeline features." + "reason": "Insufficient evidence of the same bug; one is a tokenizer-decoder mismatch, the other is only a reproduction of another issue." } ] }, @@ -14187,18 +14155,15 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ "issue:36683", "issue:38617", "issue:42490", "issue:42757", - "issue:42898", "issue:42907", - "issue:42994", "issue:43012", "issue:43064", - "issue:43066", "issue:43208", "issue:43299", "issue:43352", @@ -14212,9 +14177,10 @@ "issue:43761", "issue:43792", "issue:43824", + "issue:43825", "issue:43867", - "issue:43901", "issue:43976", + "issue:43992", "issue:44038", "issue:44162", "issue:44222", @@ -14222,13 +14188,14 @@ "issue:44368", "issue:44380", "issue:44483", + "issue:44484", "issue:44485", "issue:44514", "issue:44655", "issue:44683", + "issue:44938", "issue:45276", "issue:45290", - "issue:45381", "issue:45478", "issue:45479", "issue:45698", @@ -14236,269 +14203,257 @@ "issue:46077", "issue:46123", "issue:46132", - "issue:46172" + "issue:46172", + "issue:46178" ], "soft_pairs": [ + "issue:44938|issue:46178", + "issue:43208|issue:43550", + "issue:43992|issue:44484", "issue:43012|issue:43550", + "issue:43825|issue:44655", "issue:43012|issue:44368", - "issue:42907|issue:45753", "issue:42907|issue:44655", + "issue:42907|issue:45753", "issue:43352|issue:44380", "issue:44162|issue:46172", "issue:43352|issue:43976", - "issue:43792|issue:46123", - "issue:44380|issue:45479", "issue:44380|issue:46132", + "issue:44380|issue:45479", + "issue:43792|issue:46123", "issue:43064|issue:44380", "issue:44483|issue:44514", "issue:44222|issue:45478", "issue:36683|issue:43582", - "issue:43012|issue:44683", "issue:43208|issue:43526", - "issue:42490|issue:43012", - "issue:43618|issue:43761", + "issue:43012|issue:44683", "issue:42757|issue:43824", + "issue:43618|issue:43761", + "issue:42490|issue:43012", "issue:45698|issue:46172", "issue:43618|issue:44380", "issue:38617|issue:43502", "issue:44038|issue:44230", "issue:44483|issue:45290", - "issue:44483|issue:45381", "issue:43756|issue:44485", "issue:43299|issue:43867", "issue:36683|issue:43475", - "issue:45276|issue:46077", - "issue:43901|issue:44655", - "issue:42994|issue:44655", - "issue:42898|issue:43066", - "issue:43299|issue:45753" + "issue:45276|issue:46077" ], - "prepared_review_unit_hash": "e67c0f3c353fb1e5b67f8b538fe2638ad28ae3f7bfffc7ab2a237dfa5afb3179", + "prepared_review_unit_hash": "8295e67fced754fd2c585756d9070e3809e35a4ca0076292b8be1cc2bcf847e3", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 33, - "serialized_chars": 37291, - "estimated_input_tokens": 9323, - "estimated_eval_tokens": 18902 + "soft_pair_count": 32, + "serialized_chars": 37020, + "estimated_input_tokens": 9255, + "estimated_eval_tokens": 18766 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These items are not a true duplicate cluster; they span unrelated regressions across model loading, saving, compilation, tokenization, and API behavior. No soft edge looks safe to merge, so the best outcome is to keep them separate and use one broad issue only as a loose cluster anchor.", - "confidence": 0.37, - "canonical_issue_reason": "issue:44483 is the broadest, highest-impact regression in the set and the most plausible cluster anchor by title and severity; the rest are mostly model-specific or orthogonal failures.", + "summary": "This cluster is not a duplicate set: it mixes unrelated import errors, model-specific regressions, attention/backends bugs, save/load issues, and API/pipeline behavior changes. The soft edges are mostly superficial keyword similarity rather than the same underlying bug.", + "confidence": 0.94, + "canonical_issue_reason": "No single canonical issue fits this cluster; the items are too heterogeneous, and the proposed soft matches are only broad topic overlaps.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44483 is the best single representative issue if one must choose one, but it should not be treated as a duplicate magnet for the other items.", + "best_issue_reason": "No issue is a strong global representative for deduping because none covers the others' concrete failure modes.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44938", + "right": "issue:46178", + "accept": false, + "reason": "Different failure classes: Python 3.14 import/load breakage vs an invalid backend mapping for tensorflow_text." + }, + { + "left": "issue:43208", + "right": "issue:43550", + "accept": false, + "reason": "Different models and different bugs: xLSTM training blockers vs Bamba torch.compile/SDPA failure." + }, + { + "left": "issue:43992", + "right": "issue:44484", + "accept": false, + "reason": "Load-state missing weight vs save_pretrained shard-size behavior; not the same underlying issue." + }, { "left": "issue:43012", "right": "issue:43550", "accept": false, - "reason": "Different failures: a PyTorch precision warning during compile versus a Bamba SDPA torch.compile error." + "reason": "A PyTorch warning on bfloat16 compilation is not the same as a hard compile/SDPA failure." + }, + { + "left": "issue:43825", + "right": "issue:44655", + "accept": false, + "reason": "Pipeline error-message regression vs inability to save pipeline objects are different code paths." }, { "left": "issue:43012", "right": "issue:44368", "accept": false, - "reason": "Unrelated problems: bfloat16 compile warning versus a config warning about tie_word_embeddings in Qwen3.5 fine-tuning." + "reason": "Both are warnings, but they stem from unrelated causes and model/config paths." }, { "left": "issue:42907", - "right": "issue:45753", + "right": "issue:44655", "accept": false, - "reason": "Both involve model saving/loading, but one is dequantized Ministral/Devstral save failure and the other is an image-specific infinite-loop inference bug." + "reason": "Saving dequantized model variants is distinct from saving Pipeline objects." }, { "left": "issue:42907", - "right": "issue:44655", + "right": "issue:45753", "accept": false, - "reason": "Saving a dequantized model is not the same as saving Pipeline objects; different code paths and failure modes." + "reason": "Dequantized save failure and an image-specific infinite loop are unrelated bugs." }, { "left": "issue:43352", "right": "issue:44380", "accept": false, - "reason": "Flash Attention support error for NemotronH versus GPT2 attention scaling being ignored under SDPA/FlashAttention are distinct bugs." + "reason": "Different attention issues on different models; one is backend support, the other ignores a scaling config." }, { "left": "issue:44162", "right": "issue:46172", "accept": false, - "reason": "ESM2 breakage is a model-loading/runtime issue, while deepseek-v4 hits a specific tensor transpose bug." + "reason": "Completely different model-specific regressions." }, { "left": "issue:43352", "right": "issue:43976", "accept": false, - "reason": "Nemotron Flash Attention support and Python version compatibility are unrelated." + "reason": "Model/backend support bug is unrelated to a Python-version compatibility problem." }, { - "left": "issue:43792", - "right": "issue:46123", + "left": "issue:44380", + "right": "issue:46132", "accept": false, - "reason": "Whisper inference failure is unrelated to MaskGenerationPipeline dropping the final partial batch." + "reason": "Attention scaling ignored and register-changing behavior are distinct attention subsystem bugs." }, { "left": "issue:44380", "right": "issue:45479", "accept": false, - "reason": "Attention scaling being ignored is different from a degenerate zero-loss bug in sequence classification." + "reason": "Attention scaling regression is unrelated to the zero-loss classification bug." }, { - "left": "issue:44380", - "right": "issue:46132", + "left": "issue:43792", + "right": "issue:46123", "accept": false, - "reason": "GPT2 backend-specific attention scaling is unrelated to AttentionInterface.register changing callback behavior." + "reason": "Whisper model runtime failure and MaskGenerationPipeline batching logic are unrelated." }, { "left": "issue:43064", "right": "issue:44380", "accept": false, - "reason": "Trainer/FSDP2 optimizer-state corruption is a distributed training bug, not an attention-backend config regression." + "reason": "Trainer/FSDP/PEFT optimizer-state corruption is not the same as an attention backend config bug." }, { "left": "issue:44483", "right": "issue:44514", "accept": false, - "reason": "Chat/completions request rejection is unrelated to Qwen2_5_VLProcessor crashing on batched chat templates." + "reason": "Both involve chat-style APIs, but one is a server endpoint acceptance issue and the other is a processor/template crash." }, { "left": "issue:44222", "right": "issue:45478", "accept": false, - "reason": "Both mention FP8/quantization and MoE, but one is save_pretrained failure and the other is from_pretrained loading error." + "reason": "Saving FP8 MoE models and loading Qwen3.5 MoE under v5.4 are different save/load paths." }, { "left": "issue:36683", "right": "issue:43582", "accept": false, - "reason": "Gemma3Config missing vocab_size and Apple Silicon caching_allocator_warmup TypeError are unrelated." + "reason": "Gemma3 config attribute error and AppleSilicon allocator TypeError are unrelated." }, { - "left": "issue:43012", - "right": "issue:44683", + "left": "issue:43208", + "right": "issue:43526", "accept": false, - "reason": "A warning during bfloat16 compile is not the same as flex_attention failing on torch >= 2.9." + "reason": "xLSTM training bugs and BeitImageProcessorFast label reduction bug are unrelated." }, { - "left": "issue:43208", - "right": "issue:43526", + "left": "issue:43012", + "right": "issue:44683", "accept": false, - "reason": "xLSTM training bugs and BeitImageProcessorFast reduce_labels truncation are different subsystems and bugs." + "reason": "A warning during compilation is not the same as a compiled flex_attention failure on newer torch." }, { - "left": "issue:42490", - "right": "issue:43012", + "left": "issue:42757", + "right": "issue:43824", "accept": false, - "reason": "Path-trailing-slash import warning differs completely from a compile-time PyTorch precision warning." + "reason": "Both are import errors, but they concern different symbols and different root causes." }, { "left": "issue:43618", "right": "issue:43761", "accept": false, - "reason": "CLIP attentions being unassigned and CLIPVisionModel returning hidden_states=None are separate v5 regressions." + "reason": "Both are CLIP regressions, but they affect different outputs and code paths; not the same bug." }, { - "left": "issue:42757", - "right": "issue:43824", + "left": "issue:42490", + "right": "issue:43012", "accept": false, - "reason": "Missing is_offline_mode and missing Qwen2_5_VLForConditionalGeneration are different import errors from different symbols." + "reason": "Local-path slash warning is unrelated to a bfloat16 compilation warning." }, { "left": "issue:45698", "right": "issue:46172", "accept": false, - "reason": "A custom-module reload bug after save_pretrained is unrelated to a low-level tensor transpose bug in deepseek-v4." + "reason": "Custom-module deserialization after save_pretrained is unrelated to a DeepSeek tensor transpose/dtype bug." }, { "left": "issue:43618", "right": "issue:44380", "accept": false, - "reason": "CLIP output attentions regression and GPT2 attention scaling behavior are distinct model/backend issues." + "reason": "CLIP attentions regression and GPT2 attention scaling regression are different issues." }, { "left": "issue:38617", "right": "issue:43502", "accept": false, - "reason": "Missing layer_type_validation import and local_files_only still making API requests are unrelated import/network bugs." + "reason": "Importing a removed utility and local_files_only still triggering network calls are unrelated." }, { "left": "issue:44038", "right": "issue:44230", "accept": false, - "reason": "Both involve Qwen3-VL-Moe, but one is a generic transformers loading bug and the other is FP8 inference support." + "reason": "Same broad Qwen/MoE family, but one is a loading regression and the other is FP8 inference support." }, { "left": "issue:44483", "right": "issue:45290", "accept": false, - "reason": "Chat/completions request handling is unrelated to apply_chat_template crashing on assistant tool-call messages." - }, - { - "left": "issue:44483", - "right": "issue:45381", - "accept": false, - "reason": "API request acceptance and Qwen2.5-VL video vision_position_ids are different failure modes in different code paths." + "reason": "Both are chat/template-related, but they hit different APIs and failure modes." }, { "left": "issue:43756", "right": "issue:44485", "accept": false, - "reason": "Smollm3 RoPE layer dropping and GLM-5 RoPE implementation discussion are not the same concrete bug." + "reason": "Both mention RoPE, but they describe different model implementations and different bugs." }, { "left": "issue:43299", "right": "issue:43867", "accept": false, - "reason": "Qwen3VL-Moe loading breakage and state_dict sorting load errors are different model-loading problems." - }, - { - "left": "issue:36683", - "right": "issue:43475", - "accept": false, - "reason": "Gemma3Config vocab_size AttributeError and SAM 3 Video missing fpn_position_embeddings are unrelated missing-attribute bugs." + "reason": "Qwen3-VL-Moe load regression and sorted-state_dict load error are not the same underlying defect." }, { "left": "issue:45276", "right": "issue:46077", "accept": false, - "reason": "Gemma4 token embedding resize behavior and bidirectional attention mask construction are different bugs in different parts of the model." - }, - { - "left": "issue:43901", - "right": "issue:44655", - "accept": false, - "reason": "Deprecated docs wording for return_all_scores is unrelated to pipeline save_pretrained failure." - }, - { - "left": "issue:42994", - "right": "issue:44655", - "accept": false, - "reason": "Quantized model saving failure and pipeline serialization failure are different save_pretrained bugs." - }, - { - "left": "issue:42898", - "right": "issue:43066", - "accept": false, - "reason": "Tokenizer clean_up_tokenization_spaces behavior changes and wrong decoder type are unrelated v5 issues." - }, - { - "left": "issue:43299", - "right": "issue:45753", - "accept": false, - "reason": "Qwen3.5-VL/Moe loading failure and a specific-image infinite loop are different bugs with different triggers." + "reason": "Gemma4 embedding resize behavior and Gemma4 bidirectional-attention mask construction are separate bugs." } ] }, @@ -14520,25 +14475,26 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ - "issue:28282", - "issue:33453", "issue:36010", - "issue:36296", "issue:36683", "issue:41669", "issue:42490", "issue:42757", "issue:42890", + "issue:42898", + "issue:42994", "issue:43010", "issue:43064", + "issue:43066", + "issue:43299", "issue:43352", "issue:43525", - "issue:43575", "issue:43611", "issue:43618", "issue:43867", + "issue:43901", "issue:43931", "issue:43937", "issue:43976", @@ -14548,14 +14504,11 @@ "issue:44242", "issue:44246", "issue:44355", - "issue:44360", "issue:44380", - "issue:44484", "issue:44492", "issue:44625", "issue:44655", "issue:44855", - "issue:44857", "issue:44938", "issue:45071", "issue:45216", @@ -14563,20 +14516,25 @@ "issue:45310", "issue:45357", "issue:45375", - "issue:45440", "issue:45478", "issue:45561", "issue:45593", + "issue:45753", "issue:45850", "issue:46077", - "issue:46082" + "issue:46082", + "issue:46202" ], "soft_pairs": [ + "issue:42994|issue:44655", + "issue:43901|issue:44655", + "issue:42898|issue:43066", + "issue:43299|issue:45753", "issue:36010|issue:42757", "issue:44077|issue:44380", "issue:36683|issue:44077", - "issue:43352|issue:43937", "issue:43611|issue:44655", + "issue:43352|issue:43937", "issue:43867|issue:45216", "issue:44625|issue:46077", "issue:43976|issue:44938", @@ -14589,6 +14547,7 @@ "issue:43064|issue:44492", "issue:43010|issue:45278", "issue:43992|issue:45310", + "issue:43867|issue:46202", "issue:44355|issue:44855", "issue:43867|issue:45375", "issue:41669|issue:44246", @@ -14600,245 +14559,240 @@ "issue:42490|issue:44075", "issue:43010|issue:43976", "issue:43618|issue:44077", - "issue:43992|issue:45478", - "issue:36296|issue:43575", - "issue:28282|issue:33453", - "issue:43867|issue:44484", - "issue:43618|issue:44857", - "issue:44360|issue:45440" + "issue:43992|issue:45478" ], - "prepared_review_unit_hash": "c90995dda5f7afcae37de3aa51afdba66abafbd636ca643fc106dcf81c6114df", + "prepared_review_unit_hash": "17ba71d62e04ccdf19cbe2eeb7179dbefef7cd6be0a73b1093b14a2dc9a314f0", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { - "node_count": 48, - "item_count": 48, + "node_count": 47, + "item_count": 47, "soft_pair_count": 34, - "serialized_chars": 37386, - "estimated_input_tokens": 9347, - "estimated_eval_tokens": 18950 + "serialized_chars": 36810, + "estimated_input_tokens": 9203, + "estimated_eval_tokens": 18662 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is very heterogeneous: it mixes unrelated import errors, model/config regressions, save/load bugs, training issues, and test/performance complaints. None of the soft edges look like true duplicates of the same underlying bug, so I would not merge any of them.", + "summary": "These are mostly unrelated Transformers regression reports that only share broad surface themes like imports, saving/loading, or config changes. No soft pair looks like the same underlying bug/change, so I would not merge any of them as duplicates.", "confidence": 0.93, - "canonical_issue_reason": "If forced to pick one issue, issue 36010 is the cleanest concrete bug report: a specific import failure with a clear missing symbol traceback. It is only a weak canonical choice because the surrounding items are mostly unrelated.", + "canonical_issue_reason": "issue:45278 is the broadest umbrella symptom in the set (\u201cmany import errors after update\u201d), so it is the most representative issue, though the cluster is heterogeneous and not a true duplicate set.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 36010 is the best representative issue for triage clarity, but not because it matches the rest of the cluster; it is simply the most specific and actionable report among a mixed set.", + "best_issue_reason": "issue:45278 is the best single representative of the cluster because it captures the broad v5 import-regression theme better than the more model-specific reports.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:42994", + "right": "issue:44655", + "accept": false, + "reason": "Both mention save_pretrained, but one is quantized model saving and the other is saving Pipeline objects; different code paths." + }, + { + "left": "issue:43901", + "right": "issue:44655", + "accept": false, + "reason": "Docs/runtime mismatch about return_all_scores vs pipeline save_pretrained failure; not the same bug." + }, + { + "left": "issue:42898", + "right": "issue:43066", + "accept": false, + "reason": "Both are tokenizer/config behavior changes, but they concern different settings and symptoms." + }, + { + "left": "issue:43299", + "right": "issue:45753", + "accept": false, + "reason": "Different model families and failures: load-time MoE breakage vs an infinite loop on a specific image." + }, { "left": "issue:36010", "right": "issue:42757", "accept": false, - "reason": "Both are import-name errors, but they involve different missing symbols from different packages and likely different fixes." + "reason": "Both are import errors, but for different symbols from different packages and different root causes." }, { "left": "issue:44077", "right": "issue:44380", "accept": false, - "reason": "One is about optimizer arguments not being used; the other is about attention scaling being ignored in SDPA/FlashAttention. Different code paths." + "reason": "PatchTSMixer optional post_init vs GPT2 attention scaling under SDPA/FlashAttention are unrelated bugs." }, { "left": "issue:36683", "right": "issue:44077", "accept": false, - "reason": "Gemma3 config missing vocab_size is unrelated to SGD optimizer args not being used." + "reason": "Gemma3 config missing vocab_size is unrelated to PatchTSMixer post_init handling." }, { - "left": "issue:43352", - "right": "issue:43937", + "left": "issue:43611", + "right": "issue:44655", "accept": false, - "reason": "FlashAttention unsupported for NemotronHForCausalLM is unrelated to GLM-5 generation config validation." + "reason": "base_model_prefix loading regression and pipeline save_pretrained are different code paths." }, { - "left": "issue:43611", - "right": "issue:44655", + "left": "issue:43352", + "right": "issue:43937", "accept": false, - "reason": "base_model_prefix loading regression and Pipeline save_pretrained failure are different save/load behaviors with different failure modes." + "reason": "Nemotron FlashAttention support and invalid GenerationConfig for GLM-5 are unrelated issues." }, { "left": "issue:43867", "right": "issue:45216", "accept": false, - "reason": "State-dict ordering load error is not the same bug as Qwen3.5 checkpoint saving regression." + "reason": "Both are Qwen3.5-related, but one is state_dict ordering/load failure and the other is incorrect saved checkpoint content." }, { "left": "issue:44625", "right": "issue:46077", "accept": false, - "reason": "num_labels propagation in Qwen3.5 is unrelated to Gemma4 attention mask construction." + "reason": "num_labels propagation and Gemma4 bidirectional attention masks are different config bugs." }, { "left": "issue:43976", "right": "issue:44938", "accept": false, - "reason": "Both mention Python versions, but one is a 5.1.0 compatibility issue and the other is a Python 3.14 import failure with a different cause." + "reason": "Both are Python-version breakages, but they involve different versions and different causes." }, { "left": "issue:46077", "right": "issue:46082", "accept": false, - "reason": "Gemma4 bidirectional attention masking and LlamaConfig head_dim validation are separate configuration bugs." + "reason": "Both are config issues, but one is attention masking and the other is head_dim validation; not the same fix." }, { "left": "issue:43352", "right": "issue:45593", "accept": false, - "reason": "Unsupported FlashAttention for Nemotron and D-FINE auxiliary-loss behavior are unrelated model issues." + "reason": "Nemotron FlashAttention support and D-FINE auxiliary-loss behavior are unrelated." }, { "left": "issue:36683", "right": "issue:43525", "accept": false, - "reason": "Missing vocab_size in Gemma3Config and missing pad_token_id in Llama4Config are similar symptom types but different configs and fields." + "reason": "Gemma3 missing vocab_size vs Llama4 missing pad_token_id are different model-specific config gaps." }, { "left": "issue:43618", "right": "issue:45216", "accept": false, - "reason": "CLIPOutput attentions assignment and Qwen3.5 save_pretrained regression are distinct subsystems." + "reason": "CLIPOutput attentions regression is unrelated to Qwen3.5 save_pretrained checkpoint corruption." }, { "left": "issue:36683", "right": "issue:44242", "accept": false, - "reason": "A missing Gemma3 config attribute is not the same as load balancing loss omitted when output_router_logits=False." + "reason": "Gemma3 vocab_size and load balancing loss omission are unrelated bugs." }, { "left": "issue:43352", "right": "issue:43931", "accept": false, - "reason": "Nemotron FlashAttention support and Qwen3-VL weight-shape mismatch are different model-loading problems." + "reason": "FlashAttention support for Nemotron and Qwen3-VL weight-shape mismatch are different failures." }, { "left": "issue:43064", "right": "issue:44492", "accept": false, - "reason": "FSDP2 optimizer-state corruption is unrelated to a typo in cache strategy docs/code." + "reason": "FSDP2/PEFT optimizer-state corruption is unrelated to a typo in cache strategy names." }, { "left": "issue:43010", "right": "issue:45278", "accept": false, - "reason": "Cache update no_grad behavior and broad import errors after upgrade are not the same issue." + "reason": "Both are broad v5 regressions, but one is cache update decoration and the other is import errors; not the same concrete bug." }, { "left": "issue:43992", "right": "issue:45310", "accept": false, - "reason": "UMT5Encoder missing embed_tokens.weight is unrelated to Qwen3.5 MoE from_pretrained errors." + "reason": "UMT5Encoder missing embed_tokens.weight and Qwen3.5 MoE from_pretrained failure are different model/load bugs." + }, + { + "left": "issue:43867", + "right": "issue:46202", + "accept": false, + "reason": "State_dict-sorted load failure and Gemma pipeline roundtrip failure are unrelated." }, { "left": "issue:44355", "right": "issue:44855", "accept": false, - "reason": "Both are import-related, but one concerns compiled Python files and the other is a Python 3.13 IndentationError from a torch.jit.script decorator/comment parsing issue." + "reason": "Compiled-file import errors and Python 3.13 @torch.jit.script parsing/IndentationError have different causes." }, { "left": "issue:43867", "right": "issue:45375", "accept": false, - "reason": "State-dict sorting load error and missing deepstack_visual_indexes are different Qwen3.5 failure modes." + "reason": "Qwen3.5 state_dict loading and missing deepstack_visual_indexes are different config/save issues." }, { "left": "issue:41669", "right": "issue:44246", "accept": false, - "reason": "Both touch import time, but one is about removing import * usage and the other is about slow imports; not the same bug." + "reason": "Import-time slowdown from removing star imports and a general 'import transformers takes long' report are not the same underlying bug." }, { "left": "issue:36683", "right": "issue:43064", "accept": false, - "reason": "Gemma3 config missing vocab_size and optimizer-state corruption under FSDP2 are unrelated." + "reason": "Gemma3 config field absence and Trainer optimizer-state corruption are unrelated." }, { "left": "issue:44938", "right": "issue:45071", "accept": false, - "reason": "Python 3.14 load failure and PretrainedConfig type-checking breakage are different regression reports." + "reason": "Python 3.14 load failure and PretrainedConfig type-checking regression are different breakages." }, { "left": "issue:42890", "right": "issue:45561", "accept": false, - "reason": "Missing set_seed in SamHQ tests and xdist race on captured_info.txt are separate test-flakiness issues." + "reason": "Flaky integration tests from missing set_seed and xdist file races are different testing problems." }, { "left": "issue:43010", "right": "issue:45850", "accept": false, - "reason": "A specific cache/no_grad bug is not the same as a broad 'too many models broken' complaint." + "reason": "A specific no_grad decoration request is not the same as a broad complaint that 'too many models' break." }, { "left": "issue:43867", "right": "issue:45357", "accept": false, - "reason": "Sorted state-dict loading error and incorrect visual encoder keys in save_pretrained are different save/load regressions." + "reason": "Qwen3.5 checkpoint load/save failure and incorrect visual encoder keys on save_pretrained are related only by model family, not by bug." }, { "left": "issue:42490", "right": "issue:44075", "accept": false, - "reason": "Local-path slash import warning is unrelated to SGD args not being used." + "reason": "Trailing-slash local model import warning and unused SGD args are unrelated." }, { "left": "issue:43010", "right": "issue:43976", "accept": false, - "reason": "Cache update decoration and Python-version compatibility are unrelated." + "reason": "Cache update no_grad and Python 3.9/3.10 compatibility are unrelated." }, { "left": "issue:43618", "right": "issue:44077", "accept": false, - "reason": "CLIPOutput attentions missing and optimizer argument handling are different code paths." + "reason": "CLIP attentions assignment regression and PatchTSMixer post_init handling are unrelated." }, { "left": "issue:43992", "right": "issue:45478", "accept": false, - "reason": "Missing embed_tokens.weight in UMT5Encoder is unrelated to Qwen3.5 MoE from_pretrained errors." - }, - { - "left": "issue:36296", - "right": "issue:43575", - "accept": false, - "reason": "Tensor-parallel training bug and Qwen2-57B-A14B-Instruct OOM are related only at a very broad level; they are different failures." - }, - { - "left": "issue:28282", - "right": "issue:33453", - "accept": false, - "reason": "AutoModel missing PyTorch and tokenizer-loading regression are unrelated import/loading issues." - }, - { - "left": "issue:43867", - "right": "issue:44484", - "accept": false, - "reason": "Model loading error from sorted state_dict and a question about max_shard_size are not duplicates." - }, - { - "left": "issue:43618", - "right": "issue:44857", - "accept": false, - "reason": "Missing CLIPOutput attentions and an AMP/CUDA crash in LwDetrImageLoss are unrelated bugs." - }, - { - "left": "issue:44360", - "right": "issue:45440", - "accept": false, - "reason": "DSA indexer ReLU discussion and DeepseekV3MoE implementation divergence do not describe the same underlying problem." + "reason": "UMT5Encoder missing embeddings and Qwen3.5 MoE from_pretrained failures are different model-specific bugs." } ] }, @@ -14860,16 +14814,15 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ + "issue:28282", "issue:30333", "issue:30990", "issue:31795", "issue:33453", "issue:34689", "issue:36296", - "issue:38617", - "issue:41628", "issue:42548", "issue:42757", "issue:42831", @@ -14879,6 +14832,7 @@ "issue:43232", "issue:43299", "issue:43502", + "issue:43575", "issue:43576", "issue:43618", "issue:43723", @@ -14898,6 +14852,7 @@ "issue:44556", "issue:44655", "issue:44749", + "issue:44857", "issue:44961", "issue:44964", "issue:44977", @@ -14905,13 +14860,16 @@ "issue:45125", "issue:45341", "issue:45375", - "issue:45468", + "issue:45440", "issue:45478", "issue:45600", - "issue:46132", - "issue:46178" + "issue:46132" ], "soft_pairs": [ + "issue:36296|issue:43575", + "issue:28282|issue:33453", + "issue:43618|issue:44857", + "issue:44360|issue:45440", "issue:43618|issue:44977", "issue:42890|issue:44964", "issue:43502|issue:44062", @@ -14937,241 +14895,242 @@ "issue:43502|issue:44961", "issue:44315|issue:44360", "issue:43827|issue:44961", - "issue:30333|issue:36296", "issue:44355|issue:45071", + "issue:30333|issue:36296", "issue:44355|issue:44655", "issue:33453|issue:34689", "issue:42757|issue:43576", "issue:44222|issue:44230", "issue:43576|issue:45071", "issue:33453|issue:36296", - "issue:43576|issue:43824", - "issue:31795|issue:38617", - "issue:44961|issue:45468", - "issue:41628|issue:42548", - "issue:38617|issue:43576", - "issue:44355|issue:46178" + "issue:43576|issue:43824" ], - "prepared_review_unit_hash": "6996115dfa2504d97f548376f92dc036288768318c2f4004e795050628e5cd43", + "prepared_review_unit_hash": "99993f86265dd9860150b26618c7ab2ba71d939eebe48c19d04bb38ac3fdfcc0", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 39, - "serialized_chars": 38792, - "estimated_input_tokens": 9698, - "estimated_eval_tokens": 19652 + "soft_pair_count": 38, + "serialized_chars": 38489, + "estimated_input_tokens": 9623, + "estimated_eval_tokens": 19502 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is a loose mix of Transformers v5 regression reports, import/load failures, and a few unrelated docs/test/model-specific bugs. I do not see any strong duplicate pairs; all soft edges look like separate underlying issues.", - "confidence": 0.42, - "canonical_issue_reason": "Issue 44556 is the broadest, most representative loading-regression report in the set: a v4.57-to-v5.x checkpoint reload breakage. It fits the common compatibility-break theme better than the narrower import, model-specific, test, or docs issues.", + "summary": "These items are mostly unrelated issues across imports, loading, tests, docs, FP8, and tensor-parallel behavior. The Qwen3.5 MoE reports (issue:45125 and issue:45478) look plausibly related at a high level, but the evidence here is not strong enough to treat them as the same bug or as one mergeable fix.", + "confidence": 0.78, + "canonical_issue_reason": "issue:45125 is the best anchor because it describes a concrete tensor-parallel failure with `_tp_plan`, making it the most specific and actionable Qwen3.5 MoE-related report in the set.", "canonical_pr_reason": null, - "best_issue_reason": "44556 is the best single issue to anchor this cluster because it captures the general v5 upgrade/loading incompatibility pattern without being tied to one niche model or auxiliary symptom.", + "best_issue_reason": "issue:45125 is the strongest representative issue overall: it is concrete, reproducible, and specific enough to serve as the anchor for the nearby Qwen3.5 MoE loading reports, even though that connection is only plausible rather than duplicate-level.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:36296", + "right": "issue:43575", + "accept": false, + "reason": "Both involve tensor parallelism, but one is a generic training bug and the other is a model-load OOM; not the same concrete defect." + }, + { + "left": "issue:28282", + "right": "issue:33453", + "accept": false, + "reason": "Different failure classes: missing PyTorch import vs tokenizer loading regression." + }, + { + "left": "issue:43618", + "right": "issue:44857", + "accept": false, + "reason": "Unrelated model output attribute issue vs AMP/CUDA crash in a different loss path." + }, + { + "left": "issue:44360", + "right": "issue:45440", + "accept": false, + "reason": "Different code paths and symptoms; DSA indexer discussion is unrelated to DeepSeekV3MoE divergence." + }, { "left": "issue:43618", "right": "issue:44977", "accept": false, - "reason": "Different model-level bugs: CLIP attentions assignment vs Qwen3.5 flash-attention generation." + "reason": "CLIPOutput attentions assignment and Qwen3.5 flash-attention generation are distinct problems." }, { "left": "issue:42890", "right": "issue:44964", "accept": false, - "reason": "Both involve loading, but one is a SAM test flake and the other is a Phi-4 multimodal model-load failure; different code paths." + "reason": "Test seeding flakiness is unrelated to loading a specific multimodal model." }, { "left": "issue:43502", "right": "issue:44062", "accept": false, - "reason": "Unrelated failures: local_files_only still making requests vs AddedToken keyword duplication." + "reason": "local_files_only network leak and AddedToken keyword collision are different bugs." }, { "left": "issue:42890", "right": "issue:44112", "accept": false, - "reason": "A seeding-related SAM CI flake is not the same as a GraniteSpeech stale device override failure." + "reason": "Both are test failures, but on different models and causes; not the same bug." }, { "left": "issue:42890", "right": "issue:45600", "accept": false, - "reason": "Different areas: SAM integration test flakiness vs broken auto_mappings references." + "reason": "Different CI/test issues with different affected files and root causes." }, { "left": "issue:43576", "right": "issue:46132", "accept": false, - "reason": "Different subsystems: v5 env CLI behavior vs AttentionInterface.register changing callbacks." + "reason": "A broken env command is unrelated to AttentionInterface.register behavior changes." }, { "left": "issue:43723", "right": "issue:44556", "accept": false, - "reason": "Both are loading regressions, but one is tokenizer loading and the other is checkpoint reload compatibility; not the same bug." + "reason": "Both are loading regressions after v5 upgrades, but one is tokenizer-specific and the other is checkpoint reload; not concrete duplicates." }, { "left": "issue:44387", "right": "issue:44556", "accept": false, - "reason": "Int4 memory/OOM regression is a different issue from checkpoint reload failure." + "reason": "Int4 CUDA memory OOM and checkpoint reload failure are separate issues." }, { "left": "issue:42890", "right": "issue:45341", "accept": false, - "reason": "Both touch tests, but this is SAM test seeding flakiness vs a generic testing_utils bug." + "reason": "Test seeding flakiness and a small testing_utils bug are not the same underlying defect." }, { "left": "issue:44222", "right": "issue:45125", "accept": false, - "reason": "Serialization bug in FP8 save_pretrained is not the same as missing tensor-parallel plan metadata." + "reason": "FP8 save_pretrained/moe support and missing _tp_plan for tensor parallelism are different code paths." }, { "left": "issue:43010", "right": "issue:43065", "accept": false, - "reason": "No common underlying bug: no_grad decoration for cache updates vs dummy Conv2d in Sam3PixelDecoder." + "reason": "Cache update no_grad decoration and a dummy Conv2d in Sam3PixelDecoder are unrelated." }, { "left": "issue:42548", "right": "issue:44351", "accept": false, - "reason": "Different missing imports: PreTrainedModel vs HybridCache." + "reason": "Both are import errors, but for different symbols and likely different missing exports." }, { "left": "issue:44355", "right": "issue:44749", "accept": false, - "reason": "Compiled-file errors and a Chinese report about preprocessing slowdown are unrelated." + "reason": "Compiled Python file errors and slower filtering after upgrade are unrelated." }, { "left": "issue:43502", "right": "issue:44485", "accept": false, - "reason": "Network requests despite local_files_only is unrelated to GLM-5 RoPE implementation." + "reason": "local_files_only network behavior and GLM-5 RoPE implementation are different defects." }, { "left": "issue:45125", "right": "issue:45478", "accept": false, - "reason": "Tensor-parallel plan metadata and Qwen3.5 Moe loading failure are related only by model family, not the same concrete bug." + "reason": "Both are Qwen3.5 MoE / v5.4.0 regressions, but one is a specific tensor-parallel `_tp_plan` failure and the other is a broader `from_pretrained` error; related in theme, not strong enough to treat as the same bug." }, { "left": "issue:30333", "right": "issue:33453", "accept": false, - "reason": "MLFlow failure reporting and tokenizer loading regression are unrelated." + "reason": "MLflow reporting on failed training jobs is unrelated to tokenizer loading regression." }, { "left": "issue:43010", "right": "issue:43232", "accept": false, - "reason": "Both generation-adjacent, but one is a no_grad decoration request and the other is a sync_gpus generation state bug." + "reason": "Generation kwargs sync behavior is a different code path from cache/layer no_grad decoration." }, { "left": "issue:45125", "right": "issue:45375", "accept": false, - "reason": "Missing _tp_plan and missing deepstack_visual_indexes are separate model config issues." + "reason": "Same model family, but one is tensor-parallel loading while the other is a missing config field; not the same bug." }, { "left": "issue:30990", "right": "issue:31795", "accept": false, - "reason": "A loading hang in Sentence Transformers is not the same as a forward-docs clarification issue." + "reason": "Sentence Transformers loading hang and forward() doc confusion are unrelated." }, { "left": "issue:43502", "right": "issue:44222", "accept": false, - "reason": "local_files_only network leakage and FP8 save_pretrained moe are different bugs." + "reason": "Network request leakage and FP8 moe save_pretrained behavior are not the same issue." }, { "left": "issue:43299", "right": "issue:44556", "accept": false, - "reason": "Both are version-related loading regressions, but they affect different model families and failure modes." + "reason": "Both are v5 loading regressions, but one is specific to Qwen3VL MoE while the other is generic checkpoint reload." }, { "left": "issue:42831", "right": "issue:43874", "accept": false, - "reason": "FP8 accuracy regression is unrelated to the GLM46V image-patch counting AttributeError." - }, - { - "left": "issue:43502", - "right": "issue:44961", - "accept": false, - "reason": "local_files_only behavior and the racoon issue are unrelated." - }, - { - "left": "issue:44315", - "right": "issue:44360", - "accept": false, - "reason": "Liger Kernel application under model_init is unrelated to the DSA indexer ReLU discussion." + "reason": "FP8 accuracy concerns and missing image processor method are unrelated." }, { - "left": "issue:43827", - "right": "issue:44961", + "left": "issue:44355", + "right": "issue:45071", "accept": false, - "reason": "Docs still referencing pipeline() after removals is unrelated to racoon." + "reason": "Compiled-file execution errors and PretrainedConfig type checking are different defects." }, { "left": "issue:30333", "right": "issue:36296", "accept": false, - "reason": "MLFlow reporting on failed training jobs is unrelated to tensor-parallel training." - }, - { - "left": "issue:44355", - "right": "issue:45071", - "accept": false, - "reason": "Compiled Python file errors are not the same as PretrainedConfig type-checking breakage." + "reason": "MLflow job status reporting and tensor-parallel training bug are unrelated." }, { "left": "issue:44355", "right": "issue:44655", "accept": false, - "reason": "Compiled-file errors and Pipeline save_pretrained failure are different problems." + "reason": "Compiled Python errors and Pipeline.save_pretrained issues are different problems." }, { "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." + "reason": "Tokenizer loading regression and Llama model loading breakage are not the same concrete bug." }, { "left": "issue:42757", "right": "issue:43576", "accept": false, - "reason": "Missing is_offline_mode import and broken transformers env command are unrelated." + "reason": "huggingface_hub import breakage and transformers env command breakage are unrelated." }, { "left": "issue:44222", "right": "issue:44230", "accept": false, - "reason": "FP8 save_pretrained moe vs FP8 inference support for Qwen3.5 VL are distinct issues." + "reason": "Both concern FP8/moe, but one is save_pretrained and the other is inference support; not the same bug." }, { "left": "issue:43576", "right": "issue:45071", "accept": false, - "reason": "Broken env CLI and PretrainedConfig type checking are unrelated." + "reason": "env command breakage and PretrainedConfig type-checking regression are unrelated." }, { "left": "issue:33453", @@ -15183,43 +15142,16 @@ "left": "issue:43576", "right": "issue:43824", "accept": false, - "reason": "CLI env command issues are unrelated to the Qwen2.5 VL import error." - }, - { - "left": "issue:31795", - "right": "issue:38617", - "accept": false, - "reason": "Documentation confusion and an ImportError for layer_type_validation are unrelated." - }, - { - "left": "issue:44961", - "right": "issue:45468", - "accept": false, - "reason": "racoon is not related to Gemma-4 audio positional encoding." - }, - { - "left": "issue:41628", - "right": "issue:42548", - "accept": false, - "reason": "AutoImageProcessor import failure and PreTrainedModel import failure are different symbols and fixes." - }, - { - "left": "issue:38617", - "right": "issue:43576", - "accept": false, - "reason": "ImportError for layer_type_validation is unrelated to the transformers env command regression." - }, - { - "left": "issue:44355", - "right": "issue:46178", - "accept": false, - "reason": "Compiled-file errors are unrelated to the tensorflow_text backend mapping ValueError." + "reason": "Broken env command is unrelated to the missing Qwen2_5_VLForConditionalGeneration export." } ] }, - "evaluator_result": null, - "evaluator_used": false, - "retried": false, + "evaluator_result": { + "accept": false, + "feedback": "The overall clustering is mostly conservative, but the positive soft-edge verdict for issue:45125 vs issue:45478 overstates the packet evidence. From the packet we only know one is a specific tensor-parallel `_tp_plan` failure and the other is a broader Qwen3.5 MoE `from_pretrained` error; that is enough for a plausible connection, not a strong duplicate conclusion or a clear single-bug merge. The summary and canonical reasons should be softened accordingly." + }, + "evaluator_used": true, + "retried": true, "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null @@ -15235,11 +15167,15 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ + "issue:31795", "issue:36296", + "issue:38617", + "issue:41628", "issue:41669", "issue:42371", + "issue:42548", "issue:42890", "issue:43352", "issue:43408", @@ -15248,27 +15184,23 @@ "issue:43572", "issue:43576", "issue:43673", - "issue:43827", "issue:43901", "issue:43976", "issue:44038", - "issue:44077", "issue:44230", "issue:44246", "issue:44273", "issue:44295", "issue:44297", "issue:44315", - "issue:44351", + "issue:44355", "issue:44393", "issue:44485", "issue:44492", "issue:44556", "issue:44623", "issue:44704", - "issue:44861", "issue:44908", - "issue:44945", "issue:44961", "issue:45003", "issue:45071", @@ -15276,17 +15208,22 @@ "issue:45125", "issue:45230", "issue:45278", - "issue:45341", "issue:45362", - "issue:45478", + "issue:45468", "issue:45542", "issue:45753", "issue:45850", "issue:46095", "issue:46143", - "issue:46144" + "issue:46144", + "issue:46178" ], "soft_pairs": [ + "issue:31795|issue:38617", + "issue:41628|issue:42548", + "issue:44961|issue:45468", + "issue:38617|issue:43576", + "issue:44355|issue:46178", "issue:46143|issue:46144", "issue:44908|issue:44961", "issue:44485|issue:44961", @@ -15301,9 +15238,9 @@ "issue:44393|issue:45071", "issue:44230|issue:46095", "issue:44393|issue:45753", - "issue:41669|issue:43673", - "issue:43525|issue:45850", "issue:43576|issue:44556", + "issue:43525|issue:45850", + "issue:41669|issue:43673", "issue:44556|issue:45092", "issue:43572|issue:45850", "issue:44492|issue:45850", @@ -15311,291 +15248,265 @@ "issue:45278|issue:45850", "issue:44246|issue:44273", "issue:42890|issue:44908", - "issue:44704|issue:44908", "issue:43408|issue:44315", + "issue:44704|issue:44908", "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:43976|issue:45850", - "issue:44393|issue:45478", - "issue:44077|issue:44861", - "issue:43827|issue:44908", - "issue:41669|issue:44908" + "issue:44908|issue:45071" ], - "prepared_review_unit_hash": "aa1aee864624b8b3559eba34a87729c8a81a1ff9a19a098123ba0a032d89d730", + "prepared_review_unit_hash": "7057b1948095f019f5ec7802f7d57c6da9942d2516422bb56b09e1742a6cb247", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 40, - "serialized_chars": 38998, - "estimated_input_tokens": 9750, - "estimated_eval_tokens": 19756 + "soft_pair_count": 37, + "serialized_chars": 38128, + "estimated_input_tokens": 9532, + "estimated_eval_tokens": 19320 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is noisy and mostly contains unrelated issues; the only clearly related subtheme is import/lazy-loading performance regressions, but the soft edges are too weak to merge. I did not find any PRs in the input.", - "confidence": 0.58, - "canonical_issue_reason": "issue:44246 is the broadest, most representative report of the import/performance subtheme and has the clearest user-facing framing; it reads like the umbrella issue for the cluster.", + "summary": "This cluster is a loose collection of Transformers regressions and model-specific bugs, not a set of true duplicates. The closest shared theme is broad v5 breakage, so the most representative issue is a generic umbrella report rather than a precise defect.", + "confidence": 0.88, + "canonical_issue_reason": "issue:45850 is the broadest umbrella among the set (\u201cSince 5.0 version it breaks too many models\u201d), so it best represents the overall v5-regression theme even though it is very generic.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44246 is the best single representative issue because it captures the main recurring symptom in this set: slow or problematic imports around lazy loading.", + "best_issue_reason": "issue:45850 is the best single representative for the cluster because it captures the widest scope of the repeated \u201cv5 breaks things\u201d reports.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:31795", + "right": "issue:38617", + "accept": false, + "reason": "Documentation confusion about forward arguments is unrelated to an ImportError for layer_type_validation." + }, + { + "left": "issue:41628", + "right": "issue:42548", + "accept": false, + "reason": "Both are import failures, but for different missing symbols and likely different root causes." + }, + { + "left": "issue:44961", + "right": "issue:45468", + "accept": false, + "reason": "The titles are unrelated; one is a nonsense/uninformative issue and the other is a Gemma-4 audio positional-encoding bug." + }, + { + "left": "issue:38617", + "right": "issue:43576", + "accept": false, + "reason": "A missing import name and a broken CLI command in v5 are different problems." + }, + { + "left": "issue:44355", + "right": "issue:46178", + "accept": false, + "reason": "Compiled Python file errors and a tensorflow_text backend mapping error are not the same bug." + }, { "left": "issue:46143", "right": "issue:46144", "accept": false, - "reason": "Same RoFormer area, but one is kwargs propagation and the other is attention-interface usage; related but not the same bug." + "reason": "Both concern RoFormer, but one is kwargs propagation and the other is attention-interface usage; different code paths." }, { "left": "issue:44908", "right": "issue:44961", "accept": false, - "reason": "Scheduler kwargs vs an unrelated placeholder issue title; no shared underlying defect." + "reason": "A scheduler kwarg bug and an unrelated nonspecific issue do not match." }, { "left": "issue:44485", "right": "issue:44961", "accept": false, - "reason": "RoPE implementation discussion is unrelated to the placeholder issue." + "reason": "RoPE implementation discussion is unrelated to the racoon issue." }, { "left": "issue:43673", "right": "issue:44492", "accept": false, - "reason": "Chunked prefill cache regression and a cache-strategy typo are different cache problems." + "reason": "Cache missing in chunked prefill is not the same as a typo in cache strategy docs/code." }, { "left": "issue:36296", "right": "issue:43901", "accept": false, - "reason": "Tensor parallel training and TextClassificationPipeline docs are unrelated." + "reason": "Tensor parallel training bugs and text-classification pipeline docs mentioning return_all_scores are unrelated." }, { "left": "issue:36296", "right": "issue:43526", "accept": false, - "reason": "Tensor parallel training and BeitImageProcessorFast label reduction are unrelated defects." + "reason": "Tensor parallel training and BeitImageProcessorFast label reduction are different subsystems and failures." }, { "left": "issue:45362", "right": "issue:45850", "accept": false, - "reason": "Both mention model breakage, but one is a specific Qwen3.5 chat crash and the other is a broad complaint." + "reason": "A specific Qwen3.5-35B chat crash is not the same concrete bug as the generic \u201cv5 breaks too many models\u201d report." }, { "left": "issue:44623", "right": "issue:45230", "accept": false, - "reason": "Processor save_pretrained missing files is not the same as a generic bug report." + "reason": "Missing files on processor.save_pretrained and a vague bug report are not the same issue." }, { "left": "issue:44273", "right": "issue:45542", "accept": false, - "reason": "Lazy loading issues and a TensorFlow backend import error are different failure modes." + "reason": "Lazy loading malfunction and undefined tf backend from tensorboard-only installs are different bugs." }, { "left": "issue:44038", "right": "issue:45125", "accept": false, - "reason": "Qwen3-VL-Moe support bug and missing _tp_plan for tensor parallelism are distinct model issues." + "reason": "A Qwen3-VL-Moe bug and missing _tp_plan for tensor parallelism are related only by model family, not by the same defect." }, { "left": "issue:44273", "right": "issue:45003", "accept": false, - "reason": "Both touch import mechanics, but sys.modules access and lazy loading are not clearly the same bug." + "reason": "Lazy loading problems and unsafe sys.modules access may overlap conceptually, but they are not the same concrete failure." }, { "left": "issue:44393", "right": "issue:45071", "accept": false, - "reason": "Qwen3-VL 2D bbox errors and PretrainedConfig type checking breakage are unrelated." + "reason": "Qwen3-VL bounding-box output errors are unrelated to PretrainedConfig type-checking regressions." }, { "left": "issue:44230", "right": "issue:46095", "accept": false, - "reason": "FP8 inference support and a weight conversion-script question are not the same change or bug." + "reason": "FP8 inference support for Qwen3-VL/qwen3.5 moe is unrelated to a DeepSeek weight-conversion question." }, { "left": "issue:44393", "right": "issue:45753", "accept": false, - "reason": "Both involve Qwen3-VL models, but one is bbox output and the other is an infinite-loop image case." + "reason": "Both involve Qwen3-VL variants, but one is 2D bbox output and the other is an infinite loop on a specific image; different symptoms and fixes." }, { - "left": "issue:41669", - "right": "issue:43673", + "left": "issue:43576", + "right": "issue:44556", "accept": false, - "reason": "Import-star performance regression and chunked-prefill cache regression are different code-path problems." + "reason": "A broken env command and checkpoint reload incompatibility after upgrade are different version-5 regressions." }, { "left": "issue:43525", "right": "issue:45850", "accept": false, - "reason": "A missing pad_token_id attribute and a broad v5 breakage complaint are not the same issue." + "reason": "Missing pad_token_id in Llama4Config is a specific config bug, not the same as the broad model-breakage umbrella." }, { - "left": "issue:43576", - "right": "issue:44556", + "left": "issue:41669", + "right": "issue:43673", "accept": false, - "reason": "Broken env command and checkpoint reload incompatibility are different upgrade regressions." + "reason": "Removing import * for performance and missing GenerationMixin cache in chunked_prefill are unrelated." }, { "left": "issue:44556", "right": "issue:45092", "accept": false, - "reason": "Both are upgrade-related, but one is generic reload failure and the other is InternVL2 meta-init incompatibility." + "reason": "Both are v5 incompatibilities, but one is checkpoint reload breakage and the other is remote-code/meta-init incompatibility for a specific model family." }, { "left": "issue:43572", "right": "issue:45850", "accept": false, - "reason": "Missing pad_token_idx in StableLmConfig is unrelated to the broad breakage report." + "reason": "StableLmConfig missing pad_token_idx is a specific configuration regression, not the generic v5-breakage report." }, { "left": "issue:44492", "right": "issue:45850", "accept": false, - "reason": "Cache-strategy typo is a narrow docs/code typo, not the same as a broad compatibility complaint." + "reason": "A typo in cache strategies is not the same defect as broad model breakage after v5." }, { "left": "issue:42371", "right": "issue:44492", "accept": false, - "reason": "TF32 settings guidance and cache-strategy typo are unrelated." + "reason": "TF32 API settings guidance and a cache-strategy typo are unrelated." }, { "left": "issue:45278", "right": "issue:45850", "accept": false, - "reason": "Many import errors after upgrade and a vague 'breaks too many models' complaint are too broad to call the same bug." + "reason": "Many import errors after upgrade and generic model breakage are both broad v5 regressions, but not the same underlying bug." }, { "left": "issue:44246", "right": "issue:44273", "accept": false, - "reason": "Both are import/lazy-loading themed, but one is slow import performance and the other is a broader lazy-loading failure; not clearly the same underlying defect." + "reason": "Import performance spikes and lazy-loading failure are related to loading, but not the same concrete issue." }, { "left": "issue:42890", "right": "issue:44908", "accept": false, - "reason": "Missing set_seed in SAM HQ tests and scheduler kwargs are unrelated." + "reason": "Missing set_seed in integration tests and inverse_sqrt scheduler kwargs handling are unrelated." }, { - "left": "issue:44704", - "right": "issue:44908", + "left": "issue:43408", + "right": "issue:44315", "accept": false, - "reason": "AutoProcessor kwargs passing and scheduler kwargs are different APIs and bugs." + "reason": "A sam3_video/sam3_tracker model-type warning and Liger Kernel not applied with model_init are different problems." }, { - "left": "issue:43408", - "right": "issue:44315", + "left": "issue:44704", + "right": "issue:44908", "accept": false, - "reason": "SAM3 model-type warning and Liger Kernel application via model_init are unrelated." + "reason": "AutoProcessor kwargs not passed to cached_file and scheduler kwargs being ignored are separate kwargs bugs in different components." }, { "left": "issue:43976", "right": "issue:44393", "accept": false, - "reason": "Python-version compatibility and Qwen3-VL bbox errors are unrelated." + "reason": "Python version compatibility issues and Qwen3-VL bbox hallucination/error are unrelated." }, { "left": "issue:43352", "right": "issue:44393", "accept": false, - "reason": "Flash Attention support for NemotronH and Qwen3-VL bbox errors are unrelated." + "reason": "Flash Attention 2 support for NemotronHForCausalLM is unrelated to Qwen3-VL bbox output errors." }, { "left": "issue:44297", "right": "issue:45230", "accept": false, - "reason": "Tokenizer class mismatch on save_pretrained is not the same as a generic bug report." + "reason": "Tokenizer save_pretrained mismatch and a generic bug report are not the same defect." }, { "left": "issue:43576", "right": "issue:44908", "accept": false, - "reason": "Broken env command and scheduler kwargs are unrelated." + "reason": "Broken env command and scheduler kwargs handling are unrelated version-5 regressions." }, { "left": "issue:44295", "right": "issue:45230", "accept": false, - "reason": "position_ids buffer access error is not the same as a generic bug report." + "reason": "Reading position_ids after buffer registration is unrelated to a generic bug report." }, { "left": "issue:44908", "right": "issue:45071", "accept": false, - "reason": "Scheduler kwargs handling and PretrainedConfig type checking are unrelated." - }, - { - "left": "issue:41669", - "right": "issue:44351", - "accept": false, - "reason": "Import-star performance and a HybridCache import error are not the same concrete bug." - }, - { - "left": "issue:41669", - "right": "issue:45341", - "accept": false, - "reason": "Import performance regression and a testing_utils typo are unrelated." - }, - { - "left": "issue:44492", - "right": "issue:44945", - "accept": false, - "reason": "Cache strategy typo and incorrect pipeline-parallel output are different bugs." - }, - { - "left": "issue:43976", - "right": "issue:45850", - "accept": false, - "reason": "Python-version incompatibility and broad model breakage are too different to merge." - }, - { - "left": "issue:44393", - "right": "issue:45478", - "accept": false, - "reason": "Different Qwen3.5 model failures with different symptoms and likely different code paths." - }, - { - "left": "issue:44077", - "right": "issue:44861", - "accept": false, - "reason": "Optional post_init policy and tied-weight-key crash are unrelated." - }, - { - "left": "issue:43827", - "right": "issue:44908", - "accept": false, - "reason": "Docs still mentioning pipeline() and scheduler kwargs are unrelated." - }, - { - "left": "issue:41669", - "right": "issue:44908", - "accept": false, - "reason": "Import-star slowdown and inverse_sqrt scheduler kwargs are unrelated." + "reason": "Scheduler kwargs being ignored and PretrainedConfig type-checking regressions are different code paths and symptoms." } ] }, @@ -15617,20 +15528,16 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ - "issue:30333", "issue:31515", "issue:31795", "issue:33453", "issue:34689", - "issue:36296", - "issue:37428", - "issue:38617", + "issue:41628", "issue:41669", "issue:42371", "issue:42913", - "issue:42936", "issue:43066", "issue:43298", "issue:43502", @@ -15641,13 +15548,16 @@ "issue:43606", "issue:43618", "issue:43704", - "issue:43717", - "issue:44230", + "issue:43827", + "issue:43976", + "issue:44077", "issue:44261", "issue:44263", "issue:44273", "issue:44315", + "issue:44351", "issue:44360", + "issue:44393", "issue:44485", "issue:44492", "issue:44623", @@ -15655,6 +15565,7 @@ "issue:44829", "issue:44861", "issue:44908", + "issue:44945", "issue:44998", "issue:45092", "issue:45230", @@ -15662,13 +15573,21 @@ "issue:45310", "issue:45341", "issue:45468", + "issue:45478", "issue:45850", "issue:46018", "issue:46095", - "issue:46144", "issue:46172" ], "soft_pairs": [ + "issue:41669|issue:44351", + "issue:41669|issue:45341", + "issue:44492|issue:44945", + "issue:43976|issue:45850", + "issue:44393|issue:45478", + "issue:44077|issue:44861", + "issue:43827|issue:44908", + "issue:41628|issue:41669", "issue:31795|issue:33453", "issue:44315|issue:44829", "issue:43576|issue:44273", @@ -15681,7 +15600,7 @@ "issue:43519|issue:44908", "issue:41669|issue:43704", "issue:31795|issue:34689", - "issue:31795|issue:37428", + "issue:31515|issue:31795", "issue:44315|issue:45092", "issue:43704|issue:44485", "issue:44485|issue:45468", @@ -15696,105 +15615,143 @@ "issue:42913|issue:43066", "issue:44908|issue:44998", "issue:44492|issue:44998", - "issue:44861|issue:45290", "issue:43618|issue:44998", + "issue:44861|issue:45290", "issue:44998|issue:45850", "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", - "issue:43717|issue:46144", - "issue:42936|issue:46018" + "issue:43572|issue:44861" ], - "prepared_review_unit_hash": "f72ddff805dccf4641ee58a32d7a817595d4739fc79e571f5f1a3438292d9ddd", + "prepared_review_unit_hash": "2bb45afb0272c6ab006ec22648266b5b07d655d5e724c370deb7ab88122a18bb", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 43, - "serialized_chars": 39838, - "estimated_input_tokens": 9960, - "estimated_eval_tokens": 20176 + "soft_pair_count": 41, + "serialized_chars": 39192, + "estimated_input_tokens": 9798, + "estimated_eval_tokens": 19852 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is dominated by Transformer v5 regression reports, especially model/tokenizer loading and configuration/API breakages. The broad umbrella issue about v5 breaking many models is the best representative; none of the soft pairs look like the same concrete bug/change.", - "confidence": 0.77, - "canonical_issue_reason": "issue:45850 is the broadest and most cluster-representative report: it explicitly frames a v5-wide breakage affecting many models, which matches the surrounding loading/config/import regression issues.", + "summary": "These items are mostly unrelated bug reports that only share broad keywords like loading, tokenizer, v5, or import. I would not merge any of the soft pairs as duplicates.", + "confidence": 0.93, + "canonical_issue_reason": "issue:41669 is the most concrete and broadly representative report in this set, but the set does not actually form a single duplicate cluster.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45850 best captures the overall theme of the cluster as a general v5 regression umbrella rather than a narrow model-specific bug.", + "best_issue_reason": "issue:41669 is the best issue to anchor on if one must choose, because it is a specific, actionable bug report with the strongest superficial overlap to other import-related reports.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:41669", + "right": "issue:44351", + "accept": false, + "reason": "Both mention imports, but one is about model import-star usage/performance and the other is a missing top-level symbol; different bugs and fixes." + }, + { + "left": "issue:41669", + "right": "issue:45341", + "accept": false, + "reason": "Unrelated: one is a library import/packaging concern, the other is a testing utility bug." + }, + { + "left": "issue:44492", + "right": "issue:44945", + "accept": false, + "reason": "Cache-strategy typo and pipeline-parallelism output error are not the same code-path or bug." + }, + { + "left": "issue:43976", + "right": "issue:45850", + "accept": false, + "reason": "One is a Python-version compatibility issue; the other is a broad complaint about many model regressions. Too generic to be the same bug." + }, + { + "left": "issue:44393", + "right": "issue:45478", + "accept": false, + "reason": "Both are Qwen-related, but they describe different model behaviors and likely different failure points." + }, + { + "left": "issue:44077", + "right": "issue:44861", + "accept": false, + "reason": "Optional post-init validation and tied-weight-key attribute handling are separate implementation issues." + }, + { + "left": "issue:43827", + "right": "issue:44908", + "accept": false, + "reason": "Documentation referencing removed pipeline APIs is unrelated to a scheduler kwarg bug." + }, + { + "left": "issue:41628", + "right": "issue:41669", + "accept": false, + "reason": "Both involve imports, but one is a missing exported class and the other is a model import-star refactor/performance issue." + }, { "left": "issue:31795", "right": "issue:33453", "accept": false, - "reason": "Both touch model/tokenizer docs vs tokenizer loading regressions, but one is a documentation confusion issue and the other is a runtime loading regression; not the same underlying bug." + "reason": "One is forward-API documentation confusion; the other is a tokenizer loading regression." }, { "left": "issue:44315", "right": "issue:44829", "accept": false, - "reason": "Liger kernel application via model_init is unrelated to flash_attention_3 causing degenerate training; different code paths and failure modes." + "reason": "Liger kernel application under model_init and flash-attention training degeneration are different training paths and failure modes." }, { "left": "issue:43576", "right": "issue:44273", "accept": false, - "reason": "Broken `transformers env` CLI and lazy loading malfunction are separate features with no shared concrete bug." + "reason": "Broken env command and lazy loading failure are unrelated CLI/runtime issues." }, { "left": "issue:44360", "right": "issue:45468", "accept": false, - "reason": "DSA indexer ReLU concern and Gemma-4 audio positional encoding are different model internals; no shared fix target." + "reason": "Different model components and different bugs; no shared concrete code-path." }, { "left": "issue:44655", "right": "issue:44861", "accept": false, - "reason": "Pipeline `save_pretrained` failure and `_get_tied_weight_keys` crashing on list input are separate save/load helper bugs." + "reason": "Saving pipeline objects and tied-weight-key attribute crashes are separate save/serialization problems." }, { "left": "issue:45230", "right": "issue:45310", "accept": false, - "reason": "Generic bug report and Qwen3.5 MoE `from_pretrained` error are too vague vs specific to be the same issue." + "reason": "One is a placeholder bug report, the other is a specific from_pretrained failure for Qwen3.5 MoE." }, { "left": "issue:44273", "right": "issue:44908", "accept": false, - "reason": "Lazy loading failure and inverse_sqrt scheduler kwargs being ignored are unrelated subsystems." + "reason": "Lazy loading behavior and inverse_sqrt scheduler kwargs are unrelated." }, { "left": "issue:46018", "right": "issue:46172", "accept": false, - "reason": "DeepSeek-V4 gating logic and a tensor transpose bug in `comb.to(dtype)` are different implementation defects." + "reason": "Shared-expert gating and a tensor transpose bug in deepseek-v4 are different defects." }, { "left": "issue:43519", "right": "issue:44485", "accept": false, - "reason": "Qwen3VL timestamp calculation and GLM-5 RoPE implementation are separate model-specific math bugs." + "reason": "Timestamp calculation in Qwen3VL processor and GLM-5 RoPE implementation are different model-specific bugs." }, { "left": "issue:43519", @@ -15806,199 +15763,139 @@ "left": "issue:41669", "right": "issue:43704", "accept": false, - "reason": "Import-star performance issue and Qwen3ForCausalLM VRAM leak are different problems despite both being runtime regressions." + "reason": "Import-star cleanup/performance and VRAM leak in multi-threaded dataloading are unrelated." }, { "left": "issue:31795", "right": "issue:34689", "accept": false, - "reason": "Documentation confusion around inputs/past_key_values is not the same as a Llama 3.2 model loading regression." + "reason": "Documentation confusion for forward inputs is not the same as a model-loading regression for Llama 3.2 Vision." }, { - "left": "issue:31795", - "right": "issue:37428", + "left": "issue:31515", + "right": "issue:31795", "accept": false, - "reason": "Forward-argument docs and a flash-attention import error are unrelated." + "reason": "Checkpoint loading speed and forward-method documentation are unrelated issues." }, { "left": "issue:44315", "right": "issue:45092", "accept": false, - "reason": "Applying Liger Kernel in model_init and meta-initialization incompatibility for old InternVL2 checkpoints are different integration bugs." + "reason": "Both mention model initialization, but they concern different models and different failure mechanisms." }, { "left": "issue:43704", "right": "issue:44485", "accept": false, - "reason": "VRAM leakage across dataloader threads is unrelated to RoPE implementation correctness." + "reason": "A VRAM leak under dataloader threads and a RoPE implementation issue are not the same bug." }, { "left": "issue:44485", "right": "issue:45468", "accept": false, - "reason": "GLM-5 RoPE math and Gemma-4 audio positional encoding are different model-specific position-encoding issues." + "reason": "Distinct model internals and distinct reported symptoms; no shared fix path." }, { "left": "issue:43298", "right": "issue:46095", "accept": false, - "reason": "Continuous batching not supporting audio models and a DeepSeek-V4 weight conversion question are not the same bug." + "reason": "Continuous batching audio support and a weight conversion question are not duplicate bug reports." }, { "left": "issue:42371", "right": "issue:43704", "accept": false, - "reason": "TF32 API guidance and a VRAM leak do not share the same concrete code path." + "reason": "TF32 settings guidance and a VRAM leak are unrelated." }, { "left": "issue:43502", "right": "issue:43519", "accept": false, - "reason": "Accidental API requests despite `local_files_only=True` and incorrect Qwen3VL timestamp computation are unrelated." + "reason": "Remote-file API calls despite local_files_only and Qwen3VL timestamp math are different subsystems." }, { "left": "issue:43519", "right": "issue:44623", "accept": false, - "reason": "Timestamp calculation bug and missing files from `processor.save_pretrained(...)` are separate processor issues." + "reason": "Processor timestamp calculation and processor.save_pretrained file omission are different bugs." }, { "left": "issue:43519", "right": "issue:43704", "accept": false, - "reason": "Qwen3VL timestamp math and Qwen3ForCausalLM thread-related VRAM leak are different bugs." + "reason": "No shared code-path: processor timestamp logic vs multi-thread VRAM leak." }, { "left": "issue:43606", "right": "issue:45468", "accept": false, - "reason": "CPU offload device mismatch for bark-small and Gemma-4 audio positional encoding are both audio-related but not the same failure." + "reason": "CPU offload device mismatch and Gemma audio positional encoding are unrelated." }, { "left": "issue:44263", "right": "issue:45468", "accept": false, - "reason": "`torch.split` return handling in GlmMoeDsaIndexer is unrelated to Gemma-4 audio positional encoding." + "reason": "A torch.split return-value bug in one indexer and Gemma audio encoding are not the same issue." }, { "left": "issue:44261", "right": "issue:45468", "accept": false, - "reason": "MLA layernorm epsilon precision issue and Gemma-4 audio positional encoding are distinct model math bugs." + "reason": "RMS norm epsilon precision discussion and Gemma audio positional encoding are different technical problems." }, { "left": "issue:42913", "right": "issue:43066", "accept": false, - "reason": "Tokenizer behavior change from v4 to v5 and wrong tokenizer decoder type in v5 are both tokenizer-related but not clearly the same concrete defect." + "reason": "Both are tokenizer-related v5 complaints, but one is generic behavior change and the other is a specific decoder-type bug; not enough to treat as the same underlying issue." }, { "left": "issue:44908", "right": "issue:44998", "accept": false, - "reason": "Scheduler kwargs ignored and a non-technical issue ('Unemployment') are obviously unrelated." + "reason": "Scheduler kwarg handling and an unrelated placeholder issue are not duplicates." }, { "left": "issue:44492", "right": "issue:44998", "accept": false, - "reason": "Cache strategies typo and a non-technical issue are unrelated." + "reason": "A typo report and an irrelevant placeholder issue share no bug content." }, { - "left": "issue:44861", - "right": "issue:45290", + "left": "issue:43618", + "right": "issue:44998", "accept": false, - "reason": "Tied-weight key handling and chat template crashes with tool calls are different code paths." + "reason": "CLIP attentions assignment regression and an irrelevant placeholder issue are unrelated." }, { - "left": "issue:43618", - "right": "issue:44998", + "left": "issue:44861", + "right": "issue:45290", "accept": false, - "reason": "CLIPOutput attentions regression and a non-technical issue are unrelated." + "reason": "Tied-weight key handling and chat-template tool-call crashes are different code paths." }, { "left": "issue:44998", "right": "issue:45850", "accept": false, - "reason": "A non-technical issue cannot be merged with a broad v5 regression tracker." + "reason": "A placeholder issue cannot be merged with a broad regression complaint; no concrete overlap." }, { "left": "issue:44998", "right": "issue:45341", "accept": false, - "reason": "A non-technical issue and a small testing_utils bug are unrelated." + "reason": "Placeholder issue and testing_utils bug are unrelated." }, { "left": "issue:43525", "right": "issue:44861", "accept": false, - "reason": "Missing `pad_token_id` on `Llama4Config` and tied-weight key crash are different attribute/utility problems." + "reason": "Missing pad_token_id on a config and an AttributeError in tied-weight key processing are different bugs." }, { "left": "issue:43572", "right": "issue:44861", "accept": false, - "reason": "Missing `pad_token_idx` in `StableLmConfig` is a config-API regression, not the tied-weight list handling crash." - }, - { - "left": "issue:31515", - "right": "issue:38617", - "accept": false, - "reason": "Slow checkpoint loading and missing `layer_type_validation` import are both loading-related in a broad sense, but not the same bug or fix." - }, - { - "left": "issue:44230", - "right": "issue:44623", - "accept": false, - "reason": "FP8 support request for Qwen3-VL/MoE and missing files on processor save are unrelated." - }, - { - "left": "issue:30333", - "right": "issue:31515", - "accept": false, - "reason": "MLFlow reporting on failed training jobs and slow checkpoint loading are completely different concerns." - }, - { - "left": "issue:31515", - "right": "issue:36296", - "accept": false, - "reason": "Slow `from_pretrained` checkpoint loading and tensor parallel training bugs are different subsystems and failure modes." - }, - { - "left": "issue:31515", - "right": "issue:31795", - "accept": false, - "reason": "Checkpoint load slowness and forward doc confusion are not the same issue." - }, - { - "left": "issue:44230", - "right": "issue:45310", - "accept": false, - "reason": "FP8 support request and Qwen3.5 MoE `from_pretrained` error are not the same bug." - }, - { - "left": "issue:31515", - "right": "issue:33453", - "accept": false, - "reason": "Slow checkpoint loading and tokenizer loading regression are both load-time issues, but they are not the same concrete defect." - }, - { - "left": "issue:43298", - "right": "issue:44230", - "accept": false, - "reason": "Continuous batching audio-model support and FP8 inference support are different feature gaps." - }, - { - "left": "issue:43717", - "right": "issue:46144", - "accept": false, - "reason": "Mamba init-weights usage and RoFormer attention interface usage are unrelated architecture implementation issues." - }, - { - "left": "issue:42936", - "right": "issue:46018", - "accept": false, - "reason": "Mask2Former ignore_value misuse and DeepSeek-V4 gating logic are distinct model bugs." + "reason": "Missing pad_token_idx after v5 update and tied-weight-key crash are not the same failure." } ] }, @@ -16020,17 +15917,37 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-428", + "cluster_id": "cluster-10000-429", "nodes": [ + "issue:30333", + "issue:31515", + "issue:33453", + "issue:36296", "issue:37934", + "issue:38617", "issue:42936", "issue:43240", + "issue:43298", "issue:43668", + "issue:43717", "issue:43813", "issue:44031", + "issue:44230", + "issue:44623", + "issue:45310", + "issue:46018", "issue:46144" ], "soft_pairs": [ + "issue:31515|issue:38617", + "issue:44230|issue:44623", + "issue:30333|issue:31515", + "issue:31515|issue:36296", + "issue:44230|issue:45310", + "issue:31515|issue:33453", + "issue:43298|issue:44230", + "issue:43717|issue:46144", + "issue:42936|issue:46018", "issue:43668|issue:44031", "issue:42936|issue:43240", "issue:43240|issue:46144", @@ -16042,94 +15959,148 @@ "issue:37934|issue:43668", "issue:42936|issue:43668" ], - "prepared_review_unit_hash": "ac5bc3e5a5b27972796756213c96bec1d52767ac4a255a2677055e4dd84054da", + "prepared_review_unit_hash": "86ac08ff22400010fe54bc67682f9a4d8ba89ecf1cd77ff6bdbfc96eae6008a8", "component_budget": { - "node_count": 428, - "item_count": 428, - "soft_pair_count": 1582, - "serialized_chars": 818962, - "estimated_input_tokens": 204741, - "estimated_eval_tokens": 409738 + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 }, "budget": { - "node_count": 7, - "item_count": 7, - "soft_pair_count": 10, - "serialized_chars": 6938, - "estimated_input_tokens": 1735, - "estimated_eval_tokens": 3726 + "node_count": 18, + "item_count": 18, + "soft_pair_count": 19, + "serialized_chars": 15703, + "estimated_input_tokens": 3926, + "estimated_eval_tokens": 8108 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These issues are only loosely similar at the wording level; they cover unrelated bugs across norms, loss plumbing, configuration typing, typo fixes, tokenizer warnings, and model attention implementation. I would not merge any of them as duplicates.", - "confidence": 0.97, - "canonical_issue_reason": "No clear canonical issue: the cluster is a set of distinct bug reports affecting different models and code paths, with no shared targets or concrete overlap.", + "summary": "This cluster looks over-grouped: the issues span unrelated models, configs, tokenizer warnings, training/runtime behavior, and one-off typos. None of the soft pairs appear to describe the same underlying bug or change.", + "confidence": 0.96, + "canonical_issue_reason": "Issue 31515 is the most connected hub in the soft-similarity graph, but the cluster is heterogeneous, so it is only a weak representative and not a true duplicate canonical.", "canonical_pr_reason": null, - "best_issue_reason": "None of the issues stands out as the obvious duplicate hub; if forced, issue 43240 is the most broadly phrased, but it is still a distinct loss-passing bug rather than a representative superset.", + "best_issue_reason": "Issue 31515 is the closest to a cluster seed because it links to several other items by similarity, but its checkpoint-loading slowdown is still unrelated to the rest.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:31515", + "right": "issue:38617", + "accept": false, + "reason": "Checkpoint loading slowness vs an ImportError in configuration_utils: different failure modes and code paths." + }, + { + "left": "issue:44230", + "right": "issue:44623", + "accept": false, + "reason": "FP8 inference support for Qwen models vs missing files on processor.save_pretrained; not the same bug." + }, + { + "left": "issue:30333", + "right": "issue:31515", + "accept": false, + "reason": "MLflow status reporting on failed training vs from_pretrained checkpoint load speed." + }, + { + "left": "issue:31515", + "right": "issue:36296", + "accept": false, + "reason": "Checkpoint loading performance vs tensor-parallel training bug." + }, + { + "left": "issue:44230", + "right": "issue:45310", + "accept": false, + "reason": "Both mention Qwen3.5, but one is FP8 support and the other is a from_pretrained error; different concrete issues." + }, + { + "left": "issue:31515", + "right": "issue:33453", + "accept": false, + "reason": "Checkpoint loading slowdown vs tokenizer loading regression; not duplicates." + }, + { + "left": "issue:43298", + "right": "issue:44230", + "accept": false, + "reason": "Continuous batching support for audio models vs FP8 Qwen3-VL/Qwen3.5 support." + }, + { + "left": "issue:43717", + "right": "issue:46144", + "accept": false, + "reason": "Mamba init_weights behavior vs RoFormer attention interface usage; unrelated model implementation problems." + }, + { + "left": "issue:42936", + "right": "issue:46018", + "accept": false, + "reason": "Mask2Former ignore_value handling vs DeepSeek-V4 shared expert gating." + }, { "left": "issue:43668", "right": "issue:44031", "accept": false, - "reason": "One is a ModernBERT type-hint bug; the other is a tokenizer regex warning regression. Different subsystems and failure modes." + "reason": "ModernBERT config type hint issue vs tokenizer regex warning after upgrade; different artifacts." }, { "left": "issue:42936", "right": "issue:43240", "accept": false, - "reason": "Mask2Former ignore_value handling and loss-kwargs forwarding are unrelated implementation bugs, even though both touch training code." + "reason": "Both touch loss-related code, but one is ignore_value handling and the other is kwargs propagation; not the same bug." }, { "left": "issue:43240", "right": "issue:46144", "accept": false, - "reason": "Loss kwargs propagation and RoFormer attention interface usage affect different model paths and do not describe the same change." + "reason": "Loss kwargs forwarding vs RoFormer attention interface implementation." }, { "left": "issue:42936", "right": "issue:44031", "accept": false, - "reason": "Mask2Former ignore_value and tokenizer regex warnings are unrelated; no shared code path or fix." + "reason": "Mask2Former loss parameter handling vs tokenizer warning regression." }, { "left": "issue:42936", "right": "issue:46144", "accept": false, - "reason": "A segmentation loss-parameter bug is not the same as a RoFormer attention-interface bug." + "reason": "Different model subsystems and different bugs." }, { "left": "issue:42936", "right": "issue:43813", "accept": false, - "reason": "Ignore_value usage and a typo in a quantization attribute are different classes of issues with no concrete overlap." + "reason": "Mask2Former ignore_value handling vs a quantization typo; no underlying overlap." }, { "left": "issue:43240", "right": "issue:43668", "accept": false, - "reason": "Passing kwargs to loss calculation is unrelated to a ModernBERT config annotation problem." + "reason": "Loss kwargs not passed vs incorrect type hint; unrelated." }, { "left": "issue:43668", "right": "issue:43813", "accept": false, - "reason": "Both are small fixes, but they target different files and bugs: type hint vs typo." + "reason": "ModernBERT type hint mismatch vs typo in a quantization symbol." }, { "left": "issue:37934", "right": "issue:43668", "accept": false, - "reason": "Llama4TextL2Norm/RMS norm question is unrelated to ModernBERT norm_eps typing." + "reason": "Question about Llama4TextL2Norm being RMSNorm vs a ModernBERT config type-hint issue." }, { "left": "issue:42936", "right": "issue:43668", "accept": false, - "reason": "Different models and different bug types; no same underlying defect." + "reason": "Mask2Former ignore_value bug vs ModernBERT norm_eps annotation issue." } ] }, @@ -16162,12 +16133,12 @@ "issue:10519|issue:11005", "issue:11005|issue:11307" ], - "prepared_review_unit_hash": "de98ab6a0b469a88cefd82b7f8dbe4a49599f62e96fd510d40ae0cf65a31b8ab", + "prepared_review_unit_hash": "77810f68ceb91c8ccda0611d3fef63af16ec9cc6c4a8989715764263c21c4d6c", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 2875, + "serialized_chars": 2876, "estimated_input_tokens": 719, "estimated_eval_tokens": 1694 }, @@ -16175,7 +16146,7 @@ "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 2875, + "serialized_chars": 2876, "estimated_input_tokens": 719, "estimated_eval_tokens": 1694 }, @@ -16184,7 +16155,7 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These three issues are about different feature requests in different areas: token truncation behavior, learning-rate scheduling, and Wav2Vec2 word boundary offsets. I do not see any duplicates or a single coherent canonical issue here.", + "summary": "These three issues are unrelated feature requests/questions in different areas (token truncation, learning-rate scheduling, and Wav2Vec2 word timestamps). They should not be deduplicated.", "confidence": 0.98, "canonical_issue_reason": null, "canonical_pr_reason": null, @@ -16195,19 +16166,19 @@ "left": "issue:10519", "right": "issue:11307", "accept": false, - "reason": "One is a tokenizer truncation option request; the other asks for word start/end timestamps in Wav2Vec2. Different API areas and different underlying problems." + "reason": "Different features and domains: truncation direction vs. word-level timing offsets in Wav2Vec2." }, { "left": "issue:10519", "right": "issue:11005", "accept": false, - "reason": "Token truncation behavior and ReduceLROnPlateau-like scheduler functionality are unrelated feature requests with no shared code-path or concrete bug." + "reason": "No common underlying bug/change; one is about tokenizer truncation behavior, the other about scheduler functionality." }, { "left": "issue:11005", "right": "issue:11307", "accept": false, - "reason": "A learning-rate scheduler feature request is unrelated to extracting time offsets from Wav2Vec2 word boundaries." + "reason": "Unrelated topics: ReduceLROnPlateau-like scheduler behavior versus extracting timestamps for words." } ] }, @@ -16239,12 +16210,12 @@ "issue:13244|issue:16618", "issue:15980|issue:16618" ], - "prepared_review_unit_hash": "5f276f9695cd09466d7695025896d5ce7e5e6173ce00f8622c4a3c02ca35051e", + "prepared_review_unit_hash": "7c9e70f935bf4a9797a6c6ed144ea0a77edeb22d04c6511badbba524da29b174", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 2479, + "serialized_chars": 2478, "estimated_input_tokens": 620, "estimated_eval_tokens": 1496 }, @@ -16252,7 +16223,7 @@ "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 2479, + "serialized_chars": 2478, "estimated_input_tokens": 620, "estimated_eval_tokens": 1496 }, @@ -16261,24 +16232,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The cluster is not a true duplicate set. Issue 13244 is about Tapas tokenization matching TensorFlow code, while 15980 is about a bad login-related error for private model downloads, and 16618 is a separate model-loading failure for bert-base-uncased. The soft-similarity signals are too broad to treat any pair as the same underlying bug.", - "confidence": 0.91, - "canonical_issue_reason": "No single canonical issue is strongly supported; if one must be chosen, #16618 is the broadest model-loading report, but it does not match the others closely enough to serve as a true duplicate anchor.", + "summary": "These three issues do not look like true duplicates: one is about Tapas tokenization mismatch, one about private-model auth/error messaging, and one about a generic model-load failure. The cluster appears to be soft-similarity only, not the same underlying bug.", + "confidence": 0.82, + "canonical_issue_reason": "Issue #16618 is the broadest and most central of the three, describing a model-loading failure, while the other two are narrower and about different topics.", "canonical_pr_reason": null, - "best_issue_reason": "#16618 is the most central and broadly phrased model-loading issue in the set, but it still appears distinct from both the Tapas tokenization bug and the private-model login/error-message issue.", + "best_issue_reason": "#16618 is the best representative issue for this cluster because it is the clearest user-facing loading problem and the most likely anchor for related reports; the others are not close enough to be merged into it as duplicates.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:13244", "right": "issue:16618", "accept": false, - "reason": "Tapas tokenization vs. bert-base-uncased loading are different code paths and different failure modes; only a vague NLP/model similarity is shared." + "reason": "Tapas tokenization behavior is a different problem domain from failing to load bert-base-uncased; no evidence they describe the same code-path bug." }, { "left": "issue:15980", "right": "issue:16618", "accept": false, - "reason": "Both concern model download/load failures, but one is specifically about private models without login and the other is a public model load failure; not the same concrete bug." + "reason": "Private-model download/auth error messaging is distinct from a generic model-load failure for bert-base-uncased; they do not clearly share the same underlying defect." } ] }, @@ -16308,12 +16279,12 @@ "soft_pairs": [ "issue:26350|issue:33260" ], - "prepared_review_unit_hash": "ab1a4f331af7c6d6534f6bdcd7a616d0221a85181649e4f63ca332c1dcb19f4c", + "prepared_review_unit_hash": "9b5cf9cbed794be0e538a6f10d2c87400a8b27f56725d3b8c675024e26732112", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1589, + "serialized_chars": 1590, "estimated_input_tokens": 398, "estimated_eval_tokens": 1052 }, @@ -16321,7 +16292,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1589, + "serialized_chars": 1590, "estimated_input_tokens": 398, "estimated_eval_tokens": 1052 }, @@ -16330,18 +16301,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are two separate community contribution tracking issues for different features: Flash Attention 2 support vs GGUF support. They share a broad theme of expanding architecture support, but they do not describe the same underlying change or bug.", - "confidence": 0.98, + "summary": "These are two separate community feature requests: one for Flash Attention 2 support across more architectures, and one for GGUF support across more architectures. The shared wording is generic, but the underlying changes are different and there is no evidence they describe the same bug or code change.", + "confidence": 0.96, "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Issue 26350 is the stronger representative issue overall because it has substantially higher discussion activity and appears more central within this cluster, but it is not a duplicate of 33260.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:26350", "right": "issue:33260", "accept": false, - "reason": "Reject: the issues target different features and code paths. Flash Attention 2 support and GGUF support are unrelated contributions beyond both being architecture-expansion requests." + "reason": "Different feature areas (Flash Attention 2 vs GGUF) and different implementation targets; similar phrasing about \"more architectures\" is too broad to treat as the same underlying issue." } ] }, @@ -16389,12 +16360,12 @@ "issue:43834|issue:44365", "issue:44365|issue:44370" ], - "prepared_review_unit_hash": "bc60e30a09a96aef241cce34c5e31df766a9e0cf2372eae5fc8422a29172b3e7", + "prepared_review_unit_hash": "d6eeee5d7913169dd58013da80c0f86b6c6c8cd697d89bbb7532a5efa2d1de59", "component_budget": { "node_count": 6, "item_count": 6, "soft_pair_count": 15, - "serialized_chars": 8794, + "serialized_chars": 8793, "estimated_input_tokens": 2199, "estimated_eval_tokens": 4654 }, @@ -16402,7 +16373,7 @@ "node_count": 6, "item_count": 6, "soft_pair_count": 15, - "serialized_chars": 8794, + "serialized_chars": 8793, "estimated_input_tokens": 2199, "estimated_eval_tokens": 4654 }, @@ -16411,109 +16382,112 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are all documentation translation requests, but the explicitly named issues are for different languages, and the generic placeholder-title issues do not provide enough evidence to treat them as the same underlying request. No PRs are present.", - "confidence": 0.86, - "canonical_issue_reason": "No single canonical duplicate stands out: the named issues are language-specific requests, and the placeholder-title issues are too underspecified to safely collapse into one canonical issue.", + "summary": "This cluster mixes three language-specific i18n doc translation issues (Turkish, Spanish, Romanian) with three near-identical generic template issues. The generic placeholder issues are duplicates of each other; the language-specific issues are not duplicates because they target different translations.", + "confidence": 0.96, + "canonical_issue_reason": "issue:43834 is the earliest generic placeholder issue and matches the same template wording as the other two placeholder issues, making it the best duplicate anchor.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43834 is the closest representative only because it is the broad template-style translation issue, but it still should not subsume the language-specific requests.", + "best_issue_reason": "issue:43834 is the best representative of the duplicate template issues because it is the earliest and most canonical-looking copy of the generic i18n translation request.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:27088", "right": "issue:44370", "accept": false, - "reason": "Turkish docs translation vs generic placeholder translation; no evidence they are the same request." + "reason": "Different target language (Turkish vs placeholder); same i18n theme but not the same underlying issue." }, { "left": "issue:27088", "right": "issue:44365", "accept": false, - "reason": "Turkish docs translation vs generic placeholder translation; different underlying request is more likely." + "reason": "Different target language (Turkish vs placeholder); not the same concrete request." }, { "left": "issue:27088", "right": "issue:43834", "accept": false, - "reason": "Named Turkish translation request vs underspecified template issue; not enough to merge." + "reason": "Concrete Turkish translation request versus generic template issue; not duplicates." }, { "left": "issue:27088", "right": "issue:38435", "accept": false, - "reason": "Different target languages: Turkish vs Romanian." + "reason": "Different target languages (Turkish vs Romanian), so these are separate translation requests." }, { "left": "issue:27088", "right": "issue:28936", "accept": false, - "reason": "Different target languages: Turkish vs Spanish." + "reason": "Different target languages (Turkish vs Spanish); related topic but distinct issues." }, { "left": "issue:28936", "right": "issue:43834", "accept": false, - "reason": "Spanish translation request vs generic placeholder issue; no concrete same-bug evidence." + "reason": "Concrete Spanish translation request versus generic template issue; not the same underlying issue." }, { "left": "issue:28936", "right": "issue:44365", "accept": false, - "reason": "Spanish translation request vs generic placeholder issue; insufficient evidence of a single underlying issue." + "reason": "Concrete Spanish translation request versus generic template issue; not duplicates." }, { "left": "issue:28936", "right": "issue:38435", "accept": false, - "reason": "Different target languages: Spanish vs Romanian." + "reason": "Different target languages (Spanish vs Romanian), so they should stay separate." }, { "left": "issue:28936", "right": "issue:44370", "accept": false, - "reason": "Spanish translation request vs generic placeholder issue; do not merge on broad similarity alone." + "reason": "Concrete Spanish translation request versus generic template issue; not the same request." }, { "left": "issue:38435", "right": "issue:44370", "accept": false, - "reason": "Romanian translation request vs generic placeholder issue; not enough evidence they are the same request." + "reason": "Concrete Romanian translation request versus generic template issue; not duplicates." }, { "left": "issue:38435", "right": "issue:44365", "accept": false, - "reason": "Romanian translation request vs generic placeholder issue; no explicit link or shared target." + "reason": "Concrete Romanian translation request versus generic template issue; not the same underlying issue." }, { "left": "issue:38435", "right": "issue:43834", "accept": false, - "reason": "Romanian translation request vs underspecified template issue; too little evidence to merge." + "reason": "Concrete Romanian translation request versus generic template issue; not duplicates." }, { "left": "issue:43834", "right": "issue:44370", - "accept": false, - "reason": "Both are template-style titles, but the bodies/targets are not shown; strict triage should not assume they are duplicates." + "accept": true, + "reason": "Both are the same generic placeholder i18n translation issue with identical wording and no language-specific content." }, { "left": "issue:43834", "right": "issue:44365", - "accept": false, - "reason": "Identical placeholder title is not enough to prove the same underlying translation request." + "accept": true, + "reason": "Both are the same generic placeholder i18n translation issue; no substantive difference is visible." }, { "left": "issue:44365", "right": "issue:44370", - "accept": false, - "reason": "Both are generic placeholder translation issues, but there is no concrete evidence they target the same language or work item." + "accept": true, + "reason": "Both are identical generic placeholder issues for translating docs; effectively duplicates." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: the Turkish, Spanish, and Romanian issues are distinct by title, and the three placeholder issues are the closest match cluster with 43834 as the earliest. The soft-edge verdicts are conservative overall." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -16585,12 +16559,12 @@ "issue:43837|issue:45177", "issue:45322|issue:46133" ], - "prepared_review_unit_hash": "4e38cc7d50b7e00681e72aebc9f2c16725af0212e2f2882789aa0f22d9e6203c", + "prepared_review_unit_hash": "1f542d67541bf73d6ab8ceae795d1f53a11b8d5fa6881cad85e1d6806318bebd", "component_budget": { "node_count": 16, "item_count": 16, "soft_pair_count": 36, - "serialized_chars": 21657, + "serialized_chars": 21660, "estimated_input_tokens": 5415, "estimated_eval_tokens": 11086 }, @@ -16598,7 +16572,7 @@ "node_count": 16, "item_count": 16, "soft_pair_count": 36, - "serialized_chars": 21657, + "serialized_chars": 21660, "estimated_input_tokens": 5415, "estimated_eval_tokens": 11086 }, @@ -16607,228 +16581,222 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is a loose topical group of unrelated model-addition requests. They all resemble \u201cplease add support for model X,\u201d but they are not duplicates of the same underlying issue. No PRs are present.", - "confidence": 0.95, - "canonical_issue_reason": "issue:43671 is the broadest and most central representative of the cluster\u2019s generic model-support requests, but it is not a true duplicate of the others.", + "summary": "These are all distinct model-request issues that share only a broad \"add support\" theme; I do not see true duplicates or a single underlying bug/change cluster.", + "confidence": 0.98, + "canonical_issue_reason": "No single canonical issue: each item requests a different model family, architecture, or modality, so the similarity is only topical.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43671 is the best single representative because it is an open, discussion-backed model support request and sits near the center of the similarity graph.", + "best_issue_reason": "issue:46133 is the most detailed and recent request, so it is the best representative of the theme, but it still is not a duplicate hub.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:36817", "right": "issue:41211", "accept": false, - "reason": "Different requested models (EuroBert vs DEIMv2); only the generic add-support framing overlaps." + "reason": "EuroBert config support and DEIMv2 are unrelated model requests; only the generic \"add model\" pattern matches." }, { "left": "issue:36817", "right": "issue:43671", "accept": false, - "reason": "EuroBert config support and Qwen3-TTS support are unrelated model additions." + "reason": "EuroBert config support and Qwen3-TTS are different model families and modalities, not the same change." }, { "left": "issue:36817", "right": "issue:36879", "accept": false, - "reason": "EuroBert vs RF-DETR are different architectures and different feature requests." + "reason": "EuroBert and RF-DETR are separate model additions with no shared code-path bug." }, { "left": "issue:36879", "right": "issue:41211", "accept": false, - "reason": "RF-DETR and DEIMv2 are distinct model integrations, not the same bug/change." + "reason": "RF-DETR and DEIMv2 are different model requests, not one duplicated implementation task." }, { "left": "issue:36879", "right": "issue:43909", "accept": false, - "reason": "RF-DETR detection support and LFM2.5 Audio support are different domains." + "reason": "RF-DETR and LFM2.5 Audio target different model domains and would not be merged as one PR." }, { "left": "issue:36879", "right": "issue:44121", "accept": false, - "reason": "RF-DETR and OpenAI weight-sparse transformer are unrelated model requests." + "reason": "RF-DETR and the weight-sparse transformer request are unrelated architectures and use cases." }, { "left": "issue:36879", "right": "issue:43837", "accept": false, - "reason": "RF-DETR and Qwen3-ASR are different models with different code paths." + "reason": "RF-DETR and Qwen3-ASR are separate model support requests, not the same underlying change." }, { "left": "issue:36879", "right": "issue:43671", "accept": false, - "reason": "RF-DETR and Qwen3-TTS are unrelated additions despite both being model support requests." + "reason": "RF-DETR (vision detection) and Qwen3-TTS (speech) are clearly different requests." }, { "left": "issue:37015", "right": "issue:43837", "accept": false, - "reason": "NeoBERT and Qwen3-ASR are unrelated model additions." + "reason": "NeoBERT and Qwen3-ASR are unrelated model additions with different code paths." }, { "left": "issue:37015", "right": "issue:44121", "accept": false, - "reason": "NeoBERT support and weight-sparse transformer support do not describe the same change." + "reason": "NeoBERT and the sparse transformer request are different model families and concerns." }, { "left": "issue:37015", "right": "issue:43909", "accept": false, - "reason": "NeoBERT and LFM2.5 Audio are distinct model requests." + "reason": "NeoBERT and LFM2.5 Audio are distinct model support requests, not duplicates." }, { "left": "issue:36879", "right": "issue:37015", "accept": false, - "reason": "RF-DETR and NeoBERT are different model integrations." + "reason": "RF-DETR and NeoBERT are separate model additions with no shared concrete bug." }, { "left": "issue:37015", "right": "issue:42503", "accept": false, - "reason": "NeoBERT and ModernVBERT are different BERT-family requests, not the same model." + "reason": "NeoBERT and ModernVBERT are different model families; the overlap is only that both are BERT-like." }, { "left": "issue:41115", "right": "issue:43837", "accept": false, - "reason": "MiniCPM3 architecture support and Qwen3-ASR support are unrelated." + "reason": "MiniCPM3 and Qwen3-ASR are different model requests and not the same fix." }, { "left": "issue:41115", "right": "issue:44121", "accept": false, - "reason": "MiniCPM3 and the weight-sparse transformer request target different code paths." + "reason": "MiniCPM3 support and the sparse transformer request are unrelated changes." }, { "left": "issue:41115", "right": "issue:42503", "accept": false, - "reason": "MiniCPM3 and ModernVBERT are separate model additions." + "reason": "MiniCPM3 and ModernVBERT are distinct model-addition issues, not duplicates." }, { "left": "issue:41115", "right": "issue:45027", "accept": false, - "reason": "MiniCPM3 and Voxtral TTS are different model families and tasks." + "reason": "MiniCPM3 and Voxtral-4B-TTS are different model families and modalities." }, { "left": "issue:41211", "right": "issue:43671", "accept": false, - "reason": "DEIMv2 and Qwen3-TTS are unrelated model requests." + "reason": "DEIMv2 and Qwen3-TTS are unrelated model requests, sharing only a general support theme." }, { "left": "issue:42503", "right": "issue:43837", "accept": false, - "reason": "ModernVBERT and Qwen3-ASR are different model additions." + "reason": "ModernVBERT and Qwen3-ASR are different model support requests." }, { "left": "issue:42503", "right": "issue:43671", "accept": false, - "reason": "ModernVBERT and Qwen3-TTS are different models with different support needs." + "reason": "ModernVBERT and Qwen3-TTS are distinct model requests with different modalities." }, { "left": "issue:42503", "right": "issue:42738", "accept": false, - "reason": "ModernVBERT and BERT-like models with RoPE are related only broadly, not the same concrete change." + "reason": "ModernVBERT models and BERT-like models with RoPE are related in theme but not the same concrete request." }, { "left": "issue:42738", "right": "issue:45027", "accept": false, - "reason": "RoPE support for BERT-like models and Voxtral TTS support are unrelated changes." + "reason": "BERT-like models with RoPE and Voxtral TTS are unrelated model additions." }, { "left": "issue:43671", "right": "issue:43837", "accept": false, - "reason": "Qwen3-TTS and Qwen3-ASR are related product lines but different modalities and implementations." + "reason": "Qwen3-TTS and Qwen3-ASR are sibling requests but target different speech tasks and should not be merged." }, { "left": "issue:43671", - "right": "issue:45027", + "right": "issue:43909", "accept": false, - "reason": "Qwen3-TTS and Voxtral TTS are distinct TTS model support requests." + "reason": "Qwen3-TTS and LFM2.5 Audio are different audio model requests, not one duplicated change." }, { "left": "issue:43671", - "right": "issue:45177", + "right": "issue:44121", "accept": false, - "reason": "Qwen3-TTS and DeepSeek-OCR2 are different model additions." + "reason": "Qwen3-TTS and the sparse transformer request address different model types and code paths." }, { "left": "issue:43671", - "right": "issue:44121", + "right": "issue:45027", "accept": false, - "reason": "Qwen3-TTS support and weight-sparse transformer support are not the same underlying change." + "reason": "Qwen3-TTS and Voxtral-4B-TTS are separate TTS model support requests, not the same artifact." }, { "left": "issue:43671", - "right": "issue:43909", + "right": "issue:45177", "accept": false, - "reason": "Qwen3-TTS and LFM2.5 Audio are different audio-model requests." + "reason": "Qwen3-TTS and DeepSeek-OCR2 are unrelated model families and modalities." }, { "left": "issue:43837", "right": "issue:43909", "accept": false, - "reason": "Qwen3-ASR and LFM2.5 Audio are separate audio model integrations." - }, - { - "left": "issue:43837", - "right": "issue:45322", - "accept": false, - "reason": "Qwen3-ASR and EUPE are unrelated model requests." + "reason": "Qwen3-ASR and LFM2.5 Audio are different audio-model requests, not duplicates." }, { "left": "issue:43837", "right": "issue:44121", "accept": false, - "reason": "Qwen3-ASR support and weight-sparse transformer support are different changes." + "reason": "Qwen3-ASR and the sparse transformer request are unrelated changes." }, { - "left": "issue:43909", - "right": "issue:44205", + "left": "issue:43837", + "right": "issue:45027", "accept": false, - "reason": "LFM2.5 Audio and SAM3-LiteText are different model families and tasks." + "reason": "Qwen3-ASR and Voxtral-4B-TTS are different speech tasks and model families." }, { - "left": "issue:44121", - "right": "issue:45322", + "left": "issue:43837", + "right": "issue:45177", "accept": false, - "reason": "Weight-sparse transformer support and EUPE support are unrelated model requests." + "reason": "Qwen3-ASR and DeepSeek-OCR2 are distinct model support requests." }, { "left": "issue:43837", - "right": "issue:45027", + "right": "issue:45322", "accept": false, - "reason": "Qwen3-ASR and Voxtral TTS are different speech-model additions." + "reason": "Qwen3-ASR and EUPE are separate model requests with no shared concrete implementation target." }, { - "left": "issue:37015", - "right": "issue:45027", + "left": "issue:43909", + "right": "issue:44205", "accept": false, - "reason": "NeoBERT and Voxtral TTS are unrelated model requests." + "reason": "LFM2.5 Audio and SAM3-LiteText are different modality/model requests." }, { - "left": "issue:43837", - "right": "issue:45177", + "left": "issue:44121", + "right": "issue:45322", "accept": false, - "reason": "Qwen3-ASR and DeepSeek-OCR2 are different model additions." + "reason": "The sparse transformer request and EUPE are unrelated model additions, not one code change." }, { "left": "issue:45322", "right": "issue:46133", "accept": false, - "reason": "EUPE and TIPSv2 are distinct vision-language model requests." + "reason": "EUPE and TIPSv2 are distinct model requests from different authors and use cases." } ] }, @@ -16858,7 +16826,7 @@ "soft_pairs": [ "issue:41084|issue:43037" ], - "prepared_review_unit_hash": "37fca706d0e8b45ecbafe199df80c911dc3460adad84ad37fb0efcb1f4c24703", + "prepared_review_unit_hash": "010669a4ae6d9023b2f4a7a6a74aa588703e224df6a09cb9cf0c44e8f740e483", "component_budget": { "node_count": 2, "item_count": 2, @@ -16880,18 +16848,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two issues are unrelated: one is a block decoding setting change, the other is a request for DeepSeek v3.2 support. They should not be treated as duplicates or one cluster representative.", - "confidence": 0.98, + "summary": "The two issues are not duplicates: #41084 is about Set Block Decoding, while #43037 is a request for DeepSeek v3.2 support. They describe different features/problems with no shared targets or code paths.", + "confidence": 0.97, "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "No single best issue for a duplicate cluster; the issues are unrelated and cover different user needs.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:41084", "right": "issue:43037", "accept": false, - "reason": "Different underlying requests: 'Set Block Decoding' is a decoding/configuration feature, while 'DeepSeek v3.2 support' is model support. No shared code-path or concrete bug overlap is evident." + "reason": "Different topics and likely different code paths: block decoding behavior vs model compatibility/support. The weak textual similarity is not enough to indicate the same underlying bug or change." } ] }, @@ -16921,12 +16889,12 @@ "soft_pairs": [ "issue:43598|issue:43600" ], - "prepared_review_unit_hash": "7a2f54d8b939df308495286e3bd634788e7888f6f2d004c7ba890ac0cf813ddd", + "prepared_review_unit_hash": "12e6cf905b6acf7c69e02097a412edd9acd245f67f3d2b6d03b2323e4de88cc0", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1583, + "serialized_chars": 1584, "estimated_input_tokens": 396, "estimated_eval_tokens": 1048 }, @@ -16934,7 +16902,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1583, + "serialized_chars": 1584, "estimated_input_tokens": 396, "estimated_eval_tokens": 1048 }, @@ -16943,18 +16911,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two issues are loosely related through Trainer/custom-trainer behavior, but they describe different problems: #43598 is about `remove_unused_column` customization, while #43600 is about FLOPS estimation for custom trainers. They should not be treated as duplicates.", - "confidence": 0.96, + "summary": "These two closed issues are related only at a broad Trainer/customization level, but they describe different problems and fixes: one is about `remove_unused_column` behavior, the other about FLOPS estimation for custom trainers. They should not be treated as duplicates.", + "confidence": 0.89, "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "No issue is a clear canonical duplicate representative because the two reports target different Trainer code paths; if forced, #43598 is the more self-contained feature request, but it does not subsume #43600.", + "best_issue_reason": "issue:43598 is the more concrete and self-contained Trainer customization request, but it does not cover the FLOPS-estimation problem in issue:43600.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43598", "right": "issue:43600", "accept": false, - "reason": "Different underlying concerns: one changes column-removal behavior for customizability, the other changes FLOPS estimation for custom trainers. Shared Trainer context is too broad to merge them." + "reason": "Different underlying bugs: `remove_unused_column` customizability in Trainer versus accounting for custom trainers in FLOPS estimation. Same general subsystem, but not the same change or code path." } ] }, @@ -16984,7 +16952,7 @@ "soft_pairs": [ "issue:43684|issue:44405" ], - "prepared_review_unit_hash": "fdfd7cfed96e347f416dae52fae993f9a95da4f7b861acd420c98dca7a9a6a59", + "prepared_review_unit_hash": "9549391a400f2e89dfea51e0e9ba4ff1f33b00543dcfaa4aae5efa1af718f3cd", "component_budget": { "node_count": 2, "item_count": 2, @@ -17006,18 +16974,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are separate feature requests for different model families and different auto-model heads, so they should not be clustered as duplicates.", - "confidence": 0.95, - "canonical_issue_reason": null, + "summary": "These are two closed enhancement requests for different Qwen variants and different model heads; they do not look like duplicate reports of the same underlying bug/change.", + "confidence": 0.97, + "canonical_issue_reason": "No canonical duplicate: issue 43684 is about registering Qwen3-Omni with AutoModel/AutoModelForConditionalGeneration, while issue 44405 is about adding AutoModelForSequenceClassification support for Qwen3.5 (Qwen3_5Config).", "canonical_pr_reason": null, - "best_issue_reason": "No single best canonical issue: #43684 asks for Qwen3-Omni registration in AutoModel/AutoModelForConditionalGeneration, while #44405 asks for AutoModelForSequenceClassification support for Qwen3.5 (Qwen3_5Config). They target different code paths and tasks.", + "best_issue_reason": "If a representative issue is needed, 43684 is the broader library-registration request, but it still does not cover the distinct sequence-classification support asked for in 44405.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43684", "right": "issue:44405", "accept": false, - "reason": "Different model variants and different auto-class heads; this is not the same underlying bug or change." + "reason": "Different model families and different task heads; this is a soft similarity only, not the same underlying bug/change." } ] }, @@ -17054,12 +17022,12 @@ "issue:43845|issue:43859", "issue:43846|issue:43859" ], - "prepared_review_unit_hash": "0019635b2842297879147a3e434944583c548a51a1067d55309375c16fdce949", + "prepared_review_unit_hash": "a440aaab826acf4ff33297c9c812c136713014c7245bbea0d81dce2219bbfb3d", "component_budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 4261, + "serialized_chars": 4264, "estimated_input_tokens": 1066, "estimated_eval_tokens": 2388 }, @@ -17067,7 +17035,7 @@ "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 4261, + "serialized_chars": 4264, "estimated_input_tokens": 1066, "estimated_eval_tokens": 2388 }, @@ -17076,55 +17044,58 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The cluster is too underspecified to confidently treat these as duplicates. The three \"huggingface\" issues may be related to each other by title, but there is no body or target evidence showing the same underlying bug, and \"Fett\" looks unrelated.", - "confidence": 0.31, - "canonical_issue_reason": "Issue 43845 is the earliest of the repeated \"huggingface\" titles and is the most plausible anchor if this cluster were later confirmed to be duplicates.", + "summary": "Three issues titled \"huggingface \" look like the same duplicate report; the \"Fett\" issue appears unrelated. I\u2019d keep the earliest huggingface issue as canonical.", + "confidence": 0.72, + "canonical_issue_reason": "Issue 43845 is the earliest of the near-identical \"huggingface \" reports, so it is the best canonical representative among the likely duplicates.", "canonical_pr_reason": null, - "best_issue_reason": "43845 is the best issue candidate only because it is the earliest repeated title; however, the evidence is too weak to call it a true canonical duplicate target.", + "best_issue_reason": "Issue 43845 is the best cluster anchor because it matches the repeated huggingface title pattern and is the earliest of that group.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43835", "right": "issue:43845", "accept": false, - "reason": "Different titles and no body/target evidence tying \"Fett\" to the \"huggingface\" reports." + "reason": "Different titles and no supporting description or targets; no evidence they are the same underlying issue." }, { "left": "issue:43835", "right": "issue:43846", "accept": false, - "reason": "Different titles and no evidence of the same underlying problem." + "reason": "Different titles and no supporting description or targets; too little evidence to treat as duplicates." }, { "left": "issue:43835", "right": "issue:43859", "accept": false, - "reason": "Different titles and no evidence these describe the same bug." + "reason": "Different titles and no supporting description or targets; not enough to connect them as the same issue." }, { "left": "issue:43845", "right": "issue:43846", - "accept": false, - "reason": "Same short title, but there is no issue-body or target detail confirming the same underlying report." + "accept": true, + "reason": "Exact same title pattern and nearly identical metadata, with no sign of a different underlying problem." }, { "left": "issue:43845", "right": "issue:43859", - "accept": false, - "reason": "Matching title alone is not enough here; the issues are too underspecified to merge as duplicates." + "accept": true, + "reason": "Same title pattern and very similar duplicate-looking reports; no evidence of a distinct issue." }, { "left": "issue:43846", "right": "issue:43859", - "accept": false, - "reason": "Matching title alone is insufficient to confirm the same bug." + "accept": true, + "reason": "Same title pattern and very similar duplicate-looking reports; no evidence of a distinct issue." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "The anchor choice is grounded: 43845 is the earliest of the three near-identical \"huggingface \" issues. The rejection of 43835 as unrelated is conservative and supported by the title mismatch. The soft-edge accepts are also reasonably cautious given the matching titles and soft-similarity evidence, so I don't see an overstatement that would require rejection." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -17158,7 +17129,7 @@ "issue:44572|issue:44937", "issue:44573|issue:44937" ], - "prepared_review_unit_hash": "984722bb2ca964ae12be9c7c15283bde548d490db181ca44dadf228f9221149c", + "prepared_review_unit_hash": "bc490bef964e203c83282dcb8bfae6ac9d8cf26112d00e39c2dd0cd6335186a5", "component_budget": { "node_count": 5, "item_count": 5, @@ -17180,66 +17151,66 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "All items are low-signal and look like unrelated spam/placeholder issues rather than duplicates of one concrete bug or change. No soft pair should be merged.", - "confidence": 0.96, - "canonical_issue_reason": "issue:44418 is the only item with a somewhat descriptive title, but it still lacks concrete problem details and does not match the others as the same underlying report.", + "summary": "This cluster is dominated by low-signal/spam issues with unrelated titles; there is no clear shared bug or change to unify.", + "confidence": 0.92, + "canonical_issue_reason": "Issue #44418 is the only one with a somewhat descriptive, non-spam title, so it is the least ambiguous representative of the cluster.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44418 is the most informative representative by title alone, but it is still not a strong canonical candidate for a duplicate cluster.", + "best_issue_reason": "#44418 is the best issue representative because it is the most readable and specific title, even though it still looks generic and low-value.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44371", "right": "issue:44572", "accept": false, - "reason": "Both are placeholder '' issues with no substantive bug description; no evidence they report the same problem." + "reason": "Both are titled '', but there is no evidence they describe the same underlying bug or request beyond identical spam labeling." }, { "left": "issue:44371", "right": "issue:44573", "accept": false, - "reason": "Same as above: generic spam-like placeholders, not a concrete shared issue." + "reason": "Identical spam titles are not enough to treat them as the same issue; no shared details or target are provided." }, { "left": "issue:44371", "right": "issue:44418", "accept": false, - "reason": "A spam placeholder and a vague documentation suggestion are not enough to establish the same underlying issue." + "reason": "One is spam and the other is a generic documentation suggestion; they do not look like the same issue." }, { "left": "issue:44371", "right": "issue:44937", "accept": false, - "reason": "The titles are unrelated and there is no shared code-path or explicit linkage." + "reason": "'Check out \"Google LLC\"' is unrelated to the spam placeholder title and gives no basis for duplication." }, { "left": "issue:44418", "right": "issue:44572", "accept": false, - "reason": "Different vague topics with no concrete symptoms, targets, or evidence of duplication." + "reason": "A documentation enhancement request is not the same underlying item as a spam placeholder issue." }, { "left": "issue:44418", "right": "issue:44573", "accept": false, - "reason": "The documentation suggestion does not look like the same report as the spam placeholder issue." + "reason": "Generic documentation feedback and spam placeholder content do not indicate the same bug or change." }, { "left": "issue:44572", "right": "issue:44573", "accept": false, - "reason": "Both are spam-like placeholders, but there is no basis to conclude they describe the same underlying bug or change." + "reason": "Although both are spam-titled, there is no concrete evidence they refer to the same report or change." }, { "left": "issue:44572", "right": "issue:44937", "accept": false, - "reason": "Unrelated titles and no shared issue details indicate different topics." + "reason": "Spam placeholder and 'Check out \"Google LLC\"' are unrelated; no shared code-path or request is visible." }, { "left": "issue:44573", "right": "issue:44937", "accept": false, - "reason": "No concrete overlap beyond being low-information closed issues." + "reason": "The titles do not match in subject matter, and there is no supporting detail to justify a duplicate merge." } ] }, @@ -17269,12 +17240,12 @@ "soft_pairs": [ "issue:45145|issue:45151" ], - "prepared_review_unit_hash": "95571c546c479d44e639775f5e05db2caaffbfbaa98a0f38754315bf85ed912f", + "prepared_review_unit_hash": "a10feab0ec3d1a67b9ba5c56a695376c0afd547f73d2c65a399523973c3fdd3f", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1646, + "serialized_chars": 1645, "estimated_input_tokens": 412, "estimated_eval_tokens": 1080 }, @@ -17282,7 +17253,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1646, + "serialized_chars": 1645, "estimated_input_tokens": 412, "estimated_eval_tokens": 1080 }, @@ -17291,24 +17262,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two closed issues are highly similar and likely duplicate the same report: identical titles, very similar body lengths, close timestamps, and a soft-similarity signal. #45145 is the better canonical issue because it was created first and already has an inbound reference.", - "confidence": 0.87, - "canonical_issue_reason": "#45145 is the best canonical anchor: it appeared first and already has an inbound reference, while the paired issue is highly similar.", + "summary": "The two closed issues are very likely duplicates or closely related: they have the exact same title and moderate textual similarity, but the evidence stops short of proving they are exact duplicates. #45145 remains the best canonical issue because it has the inbound reference.", + "confidence": 0.86, + "canonical_issue_reason": "#45145 is the better canonical issue because it has the same title as #45151 and already has an inbound reference, so it is the more natural anchor for the cluster.", "canonical_pr_reason": null, - "best_issue_reason": "#45145 is the strongest representative of the cluster due to its earlier creation time and existing inbound reference, with no evidence that it is a different report.", + "best_issue_reason": "#45145 is the best issue overall for the cluster because it is the most referenced instance of the same titled report and is a reasonable canonical representative.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45145", "right": "issue:45151", "accept": true, - "reason": "The pair looks like the same underlying issue: identical titles, very close body sizes/timestamps, and a similarity signal. The evidence is suggestive rather than definitive, but sufficient to treat them as duplicates." + "reason": "These look like a likely duplicate/closely related issue pair: the titles match exactly and the body similarity is moderate, but the available evidence does not conclusively establish perfect duplication." } ] }, "evaluator_result": { "accept": false, - "feedback": "The pair looks plausibly duplicate, but the analyst overstates the evidence by calling it a definite \"true duplicate pair.\" The packet only supports identical titles, similar body length, close timestamps, and a soft-similarity signal; there are no explicit links or stronger deterministic indicators. The summary is mostly grounded, but the soft-edge verdict should be more conservative." + "feedback": "The packet supports that the issues have the same title and a soft-similarity signal, but it does not establish that they are exact duplicates or that the text is highly overlapping beyond the similarity metric. The canonical choice based on the inbound reference is reasonable, but the summary and soft-edge language overstate the evidence. Please downgrade the verdict to a more conservative formulation (e.g., likely duplicate / closely related)." }, "evaluator_used": true, "retried": true, @@ -17389,40 +17360,40 @@ "soft_pairs": [ "issue:45672|issue:45674" ], - "prepared_review_unit_hash": "4d665438b390f53ff0576751f55adfa4c00a49f651492b172f1ded1b3a6aa3ad", + "prepared_review_unit_hash": "c447b4349d721d84f02dec5299d3b357e15038f781560b4e91162f632061bfce", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1668, - "estimated_input_tokens": 417, - "estimated_eval_tokens": 1090 + "serialized_chars": 1669, + "estimated_input_tokens": 418, + "estimated_eval_tokens": 1092 }, "budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1668, - "estimated_input_tokens": 417, - "estimated_eval_tokens": 1090 + "serialized_chars": 1669, + "estimated_input_tokens": 418, + "estimated_eval_tokens": 1092 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open issues report different 4-bit inference failures in different parts of the stack: one in Gemma4 audio module dtype handling, the other in BitsAndBytesConfig module-exclusion logic. They are related by quantized inference, but not the same underlying bug.", - "confidence": 0.92, - "canonical_issue_reason": "Issue #45674 is the better representative because it describes a clear, config-driven regression with a concrete failure mode and reproduction path.", + "summary": "These are two separate 4-bit inference regressions: one in Gemma4 audio-module dtype handling (torch.finfo on uint8 weights), and one in BitsAndBytesConfig skip-module defaults affecting lm_head exclusion. They should not be merged as duplicates.", + "confidence": 0.97, + "canonical_issue_reason": "No canonical duplicate: 45672 is a Gemma4 audio-module uint8/torch.finfo failure, while 45674 is a BitsAndBytesConfig skip_modules/lm_head assertion regression.", "canonical_pr_reason": null, - "best_issue_reason": "Issue #45674 is the strongest single issue in the cluster: it is specific, actionable, and centers on a concrete 4-bit inference regression.", + "best_issue_reason": "Neither issue fully represents the other; 45674 is the broader configuration regression, but it should not absorb 45672.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45672", "right": "issue:45674", "accept": false, - "reason": "Different failures and code paths: #45672 is a Gemma4 audio-module uint8/torch.finfo TypeError, while #45674 is a BitsAndBytesConfig lm_int8_skip_modules regression that clears the default lm_head exclusion and triggers an AssertionError. They should not be merged as duplicates." + "reason": "Different bugs and code paths: Gemma4 audio-module finfo/uint8 handling vs BitsAndBytesConfig clearing the default lm_head exclusion. Shared 4-bit inference context is too broad to treat as one fix." } ] }, @@ -17452,7 +17423,7 @@ "soft_pairs": [ "issue:45762|issue:45763" ], - "prepared_review_unit_hash": "8e9a399efd21ef390332339b6077c3df032430369ead22e53e32172cc706f7f3", + "prepared_review_unit_hash": "50f64a7c4a18e923f16dc354cafee6fb7e1946f5be38162119d9226d64fee02d", "component_budget": { "node_count": 2, "item_count": 2, @@ -17474,8 +17445,8 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two closed issues look unrelated: both are bare personal-name/date entries with no body, no links, and no shared bug or feature context. This is not a duplicate cluster.", - "confidence": 0.96, + "summary": "The two issues are unrelated closed items with only name/date-like titles; there is no evidence they describe the same bug or request.", + "confidence": 0.98, "canonical_issue_reason": null, "canonical_pr_reason": null, "best_issue_reason": null, @@ -17485,7 +17456,7 @@ "left": "issue:45762", "right": "issue:45763", "accept": false, - "reason": "Titles are different personal-name/date strings and there is no issue body or linked context showing the same underlying problem." + "reason": "Similar surface structure in the titles, but they refer to different people and dates and contain no shared bug/report context; not the same underlying issue." } ] }, @@ -17515,40 +17486,40 @@ "soft_pairs": [ "issue:45764|issue:45765" ], - "prepared_review_unit_hash": "d486228ace9611605118b53c09e6d7daa7b5bbfffc48772f0b28c8fd96ac8230", + "prepared_review_unit_hash": "66ff4ecda68211c661ff54be8e5e511735db1f9db61c8ca9885393c707a1e022", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1481, - "estimated_input_tokens": 371, - "estimated_eval_tokens": 998 + "serialized_chars": 1480, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 }, "budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1481, - "estimated_input_tokens": 371, - "estimated_eval_tokens": 998 + "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 closed issues are unrelated personal-name/date entries with no description, references, or shared technical context. There is no evidence they describe the same bug, request, or change.", - "confidence": 0.99, + "summary": "The two issues are both empty, closed, and only share a weak name/date pattern; there is no evidence they describe the same bug or request.", + "confidence": 0.98, "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "Neither issue is a good canonical representative: both have no body, no references, and look like unrelated low-signal entries rather than a real duplicate cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45764", "right": "issue:45765", "accept": false, - "reason": "The titles are different names and dates, and both issues lack body text or linking evidence; they do not appear to be the same underlying report." + "reason": "Only soft text similarity is present; the titles are different names with different dates and there is no shared problem statement or linkage indicating the same underlying issue." } ] }, @@ -17588,12 +17559,12 @@ "issue:45871|issue:45873", "issue:45872|issue:45873" ], - "prepared_review_unit_hash": "fe5b78ddf4fbb5ce8d6ec645192f544204d79042420d1536212cef440886aee4", + "prepared_review_unit_hash": "1b1c0988e3e8bb2e6f2cb1b792d5f8eef001797f065277a9940f230e10b2f459", "component_budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 8, - "serialized_chars": 5726, + "serialized_chars": 5728, "estimated_input_tokens": 1432, "estimated_eval_tokens": 3120 }, @@ -17601,7 +17572,7 @@ "node_count": 5, "item_count": 5, "soft_pair_count": 8, - "serialized_chars": 5726, + "serialized_chars": 5728, "estimated_input_tokens": 1432, "estimated_eval_tokens": 3120 }, @@ -17610,69 +17581,69 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two high-confidence duplicate candidates appear: 45870/45871 and 45872/45873. 45869 looks like a separate dataset-promo issue. The evidence supports duplicate pairing mainly from identical titles and identical body lengths, but the packet does not expose body text, so the certainty should stay slightly qualified.", - "confidence": 0.89, - "canonical_issue_reason": "Issue 45870 is a reasonable canonical issue for the first duplicate pair because it is the earlier of the two identical-title reports and has slightly more discussion activity.", + "summary": "The cluster is not a single duplicate set: it contains two exact duplicate issue pairs (45870/45871 and 45872/45873) plus one separate dataset-related issue (45869). There is no one global canonical issue for all five items.", + "confidence": 0.96, + "canonical_issue_reason": "No single canonical issue for the whole cluster; it splits into two unrelated exact-duplicate pairs, with 45870/45871 and 45872/45873 each representing separate underlying issues.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45870 is the best overall issue representative for this cluster because it is the earliest clear duplicate candidate and has the most activity among the example-prediction pair.", + "best_issue_reason": "No single best issue across the full cluster; if forced to pick within the duplicate pairs, the earliest and slightly more active copy in 45870/45871 is the strongest representative for that pair.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45869", "right": "issue:45870", "accept": false, - "reason": "Different titles and different apparent topic: dataset promo versus example prediction thread." + "reason": "Different artifact: dataset listing vs example issue; only broad financial theme overlaps." }, { "left": "issue:45869", "right": "issue:45871", "accept": false, - "reason": "Different titles and different apparent topic: dataset promo versus example prediction thread." + "reason": "Different artifact: dataset listing vs example issue; only broad financial theme overlaps." }, { "left": "issue:45870", "right": "issue:45871", "accept": true, - "reason": "Same title, same body length, and close timestamps; strong duplicate signal." + "reason": "Exact duplicate: same title and matching body length/topic." }, { "left": "issue:45870", "right": "issue:45872", "accept": false, - "reason": "Related financial/DataForge wording, but the titles describe different requests." + "reason": "Related finance/DataForge wording, but different underlying request: example prediction vs scraping-service topic." }, { "left": "issue:45870", "right": "issue:45873", "accept": false, - "reason": "Related financial/DataForge wording, but the titles describe different requests." + "reason": "Related finance/DataForge wording, but different underlying request: example prediction vs scraping-service topic." }, { "left": "issue:45871", "right": "issue:45872", "accept": false, - "reason": "Different titles and different request shape: example prediction versus scraping-service topic." + "reason": "Related finance/DataForge wording, but different underlying request: example prediction vs scraping-service topic." }, { "left": "issue:45871", "right": "issue:45873", "accept": false, - "reason": "Different titles and different request shape: example prediction versus scraping-service topic." + "reason": "Related finance/DataForge wording, but different underlying request: example prediction vs scraping-service topic." }, { "left": "issue:45872", "right": "issue:45873", "accept": true, - "reason": "Same title, same body length, and close timestamps; strong duplicate signal." + "reason": "Exact duplicate: same title and matching body length/topic." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The grouping is directionally plausible, but several claims overstate the evidence available in the packet. The packet only provides titles, body lengths, and timestamps; it does not expose body text, so statements like \u201cexact duplicate,\u201d \u201cmatching body length/content pattern,\u201d and \u201cexact same title\u201d are only partly grounded. In particular, calling 45870/45871 and 45872/45873 definite duplicates is stronger than the evidence supports; \u2018likely duplicate\u2019 or \u2018high-confidence duplicate candidate\u2019 would be safer. The summary also says \u2018Two clear duplicate pairs appear,\u2019 which is more certain than the packet justifies. The 45869 separation is conservative and grounded." + "accept": true, + "feedback": "Grounded and conservative overall. The summary correctly identifies two exact-duplicate pairs (45870/45871 and 45872/45873) and treats 45869 as separate. The soft-edge false verdicts are appropriately cautious, and there is no evidence of overclaiming beyond what the packet supports." }, "evaluator_used": true, - "retried": true, + "retried": false, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -17715,8 +17686,8 @@ "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:43995|pull_request:45213", "pull_request:44827|pull_request:45170", "pull_request:44827|pull_request:46048", "pull_request:44827|pull_request:45655", @@ -17724,7 +17695,7 @@ "pull_request:43823|pull_request:45213", "pull_request:43251|pull_request:43254" ], - "prepared_review_unit_hash": "12ddc956583868684b2c7dcc90306d3dbae282d1d3d967612f01c080cd619b0d", + "prepared_review_unit_hash": "c9abc291c4e2dad75880798294a9aeb51e022dfa5bb47b37d6d430113a8bb9a9", "component_budget": { "node_count": 13, "item_count": 13, @@ -17746,126 +17717,126 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Most items are unrelated PRs across different models/features. The only clear duplicate pair is the two `fixed_cross_entropy` PRs, which patch the same function for the same issue.", - "confidence": 0.96, + "summary": "The cluster is mostly heterogeneous and does not form one duplicate set. The only true duplicate-like pair is the two `fixed_cross_entropy` PRs (#43251 and #43254), which patch the same loss helper for the same underlying kwargs-handling bug. All other pairs are unrelated by code path despite broad topical overlap.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #43251 is the best canonical PR for the duplicate pair because it directly targets issue #43240 and presents the more complete, issue-linked fix for `fixed_cross_entropy`.", + "canonical_pr_reason": "PR #43251 is the best canonical PR because it directly fixes the tracked `cross_entropy` kwargs bug in `loss_utils.py` with an explicit issue link, and PR #43254 is just a narrower variant of the same fix.", "best_issue_reason": null, - "best_pr_reason": "PR #43251 is the strongest representative change in this set: it has an explicit issue target, a focused code-path fix, and matches the concrete bug described in the diff. ", + "best_pr_reason": "PR #43251 is the strongest representative of the only real duplicate cluster in this set: it addresses the same `fixed_cross_entropy` bug as #43254 and has the clearest issue linkage and implementation.", "soft_edge_verdicts": [ { "left": "pull_request:39895", "right": "pull_request:43424", "accept": false, - "reason": "Different features: new VideoPrism model package/docs vs an Executorch dynamic-shapes test. No shared code-path or mergeable overlap." + "reason": "VideoPrism model integration vs executorch dynamic-shape export test; different subsystems and no shared bug/change." }, { "left": "pull_request:41855", "right": "pull_request:43823", "accept": false, - "reason": "Unrelated tokenizer API additions for Mistral common backend vs adding the MobileLLM model." + "reason": "Mistral tokenizer helper methods vs adding MobileLLM model support; unrelated changes." }, { "left": "pull_request:41855", "right": "pull_request:43424", "accept": false, - "reason": "Tokenizer method addition vs Executorch export test; same broad repo area only, not the same bug/change." + "reason": "Tokenizer API additions and an executorch export test are not the same underlying change." }, { "left": "pull_request:42668", "right": "pull_request:43823", "accept": false, - "reason": "Processor auto-loading robustness changes vs a new model implementation; too different to be duplicates." + "reason": "Processor auto-loading robustness vs new MobileLLM model support; broad overlap in modeling infra but not the same fix." }, { "left": "pull_request:43251", "right": "pull_request:43823", "accept": false, - "reason": "Loss-function kwargs fix vs adding MobileLLM; no shared underlying bug." + "reason": "Loss-function kwargs bugfix vs MobileLLM model addition; no common code-path problem." }, { "left": "pull_request:43251", "right": "pull_request:44827", "accept": false, - "reason": "`cross_entropy` kwargs support fix is unrelated to Mistral4 test/model adjustments." + "reason": "Both touch different areas of training/testing; the loss-helper fix and Mistral4 test changes are not mergeable as one bug fix." }, { "left": "pull_request:43424", "right": "pull_request:44827", "accept": false, - "reason": "Executorch dynamic-shapes export test and Mistral4 test fixes address different concerns." + "reason": "Executorch dynamic-shape export test vs Mistral4 test fixes; different concrete issues." }, { "left": "pull_request:43424", "right": "pull_request:43823", "accept": false, - "reason": "Dynamic-shapes export coverage vs MobileLLM model addition are unrelated." + "reason": "Executorch exportability test and MobileLLM model addition are unrelated." }, { "left": "pull_request:43823", "right": "pull_request:45655", "accept": false, - "reason": "New MobileLLM model vs config-resolution order fix; different code paths and intents." + "reason": "Adding MobileLLM vs config-resolution ordering fix; no shared underlying defect." }, { "left": "pull_request:43823", "right": "pull_request:43995", "accept": false, - "reason": "MobileLLM model addition vs Falcon output-collection refactor; not the same change." + "reason": "MobileLLM model addition vs Falcon output-collection refactor; different code paths and goals." }, { "left": "pull_request:43995", - "right": "pull_request:45213", + "right": "pull_request:44827", "accept": false, - "reason": "Falcon forward-signature refactor vs a model-creation skill draft; no overlap in the concrete bug/change." + "reason": "Falcon refactor and Mistral4 test fix are separate model-specific changes." }, { "left": "pull_request:43995", - "right": "pull_request:44827", + "right": "pull_request:45213", "accept": false, - "reason": "Falcon interface refactor and Mistral4 fixes are distinct model-specific changes." + "reason": "Falcon model refactor vs model-creation skill/docs PR; unrelated." }, { "left": "pull_request:44827", "right": "pull_request:45170", "accept": false, - "reason": "Mistral4 test/model fixes vs CLIP-like `layrnorm` rename correction; separate bugs." + "reason": "Mistral4 test fixes vs CLIP-family weight-renaming cleanup; different model families and bugs." }, { "left": "pull_request:44827", "right": "pull_request:46048", "accept": false, - "reason": "Mistral4 fixes vs adding a TDT loss kernel; unrelated subsystems." + "reason": "Mistral4 tests vs TDT loss kernel integration; unrelated functionality." }, { "left": "pull_request:44827", "right": "pull_request:45655", "accept": false, - "reason": "Mistral4 test/model fixes are unrelated to class config resolution order." + "reason": "Mistral4 test fixes and config-resolution ordering fix are not the same code-path issue." }, { "left": "pull_request:44827", "right": "pull_request:45213", "accept": false, - "reason": "Model/test fixes vs a draft model-creation skill; not a duplicate change." + "reason": "A model test fix and a model-creation skill/docs PR are clearly unrelated." }, { "left": "pull_request:43823", "right": "pull_request:45213", "accept": false, - "reason": "New MobileLLM model addition vs model-creation skill draft; one is implementation, the other is tooling/docs." + "reason": "New MobileLLM model code vs a model-creation skill/draft PR; not the same underlying change." }, { "left": "pull_request:43251", "right": "pull_request:43254", "accept": true, - "reason": "Both PRs modify `fixed_cross_entropy` in `loss_utils.py` to pass through the same supported `cross_entropy` kwargs for the same issue #43240; they are the same underlying fix." + "reason": "Both modify `src/transformers/loss/loss_utils.py` to pass extra `cross_entropy` kwargs and address the same `fixed_cross_entropy` bug, so they could plausibly be merged into one PR." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative. The only accepted pair, PR #43251 and PR #43254, is well supported: both change `src/transformers/loss/loss_utils.py`, both target issue #43240, and both pass supported `cross_entropy` kwargs through the same helper. The other soft-edge verdicts are appropriately negative and do not overstate duplicate evidence." + "feedback": "The evaluation is grounded in the packet and stays conservative. The only clearly mergeable duplicate pair is PR #43251/#43254: both edit `src/transformers/loss/loss_utils.py`, both target issue 43240, and both implement the same `fixed_cross_entropy` kwargs bugfix. The remaining pairs are reasonably judged unrelated despite superficial topic overlap." }, "evaluator_used": true, "retried": false, @@ -17892,7 +17863,7 @@ "soft_pairs": [ "pull_request:40546|pull_request:42781" ], - "prepared_review_unit_hash": "c8fac57a1efdc76eb99f3247e320e4de735b1669ab9873136dc753462f6519cb", + "prepared_review_unit_hash": "aec7bfddbca0e814bbf51260271bc4632f757cf152f6ab510e7e6ca051c78664", "component_budget": { "node_count": 2, "item_count": 2, @@ -17914,18 +17885,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are related VibeVoice PRs, but they are not duplicates: one adds the base VibeVoice implementation, while the other adds a separate realtime/acoustic-tokenizer extension on top of that family.", - "confidence": 0.89, + "summary": "Both PRs work on VibeVoice, but they are not the same change: #40546 is the core VibeVoice implementation, while #42781 is a draft for VibeVoice Realtime plus the acoustic tokenizer and additional generation/feature-extraction plumbing. They overlap in shared model files, but the concrete scope differs enough that they should not be merged as duplicates.", + "confidence": 0.9, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #40546 is the better canonical representative because it is the original non-draft VibeVoice implementation and covers the core model integration; #42781 is a later, narrower realtime-focused extension with additional tokenizer/generation work.", + "canonical_pr_reason": "#40546 is the best canonical PR because it is the original, non-draft VibeVoice implementation and provides the core model/docs/auto-registry changes that the later work builds on.", "best_issue_reason": null, - "best_pr_reason": "PR #40546 is the strongest overall representative of the cluster since it is broader, more mature, and closer to the primary VibeVoice landing; #42781 is a distinct follow-on change rather than the same PR.", + "best_pr_reason": "#40546 is the better global representative: it is broader, more complete, and non-draft, whereas #42781 is a narrower realtime follow-up with extra tokenizer and generation changes.", "soft_edge_verdicts": [ { "left": "pull_request:40546", "right": "pull_request:42781", "accept": false, - "reason": "They share the VibeVoice subsystem, but #42781 is a separate realtime/acoustic-tokenizer addition rather than the same concrete code-path fix or the same mergeable change as #40546." + "reason": "Shared VibeVoice files alone are not enough: #40546 implements the base model, while #42781 adds realtime support and an acoustic tokenizer, so they target different concrete functionality and could not be cleanly merged into one PR." } ] }, @@ -17955,7 +17926,7 @@ "soft_pairs": [ "pull_request:40755|pull_request:41224" ], - "prepared_review_unit_hash": "d9b138efd317c52cd54378377030619618781764c8a96cefa0be603ff7f02336", + "prepared_review_unit_hash": "40dfb802ec76acaff4be9386ef635883d9cd98a1573a0add6f664ec8c9dd3dad", "component_budget": { "node_count": 2, "item_count": 2, @@ -17977,18 +17948,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two PRs are unrelated: one adds TimesFM covariate forecasting, the other adds DINOv3 image-classification support. They do not fix the same code path or represent one mergeable change.", - "confidence": 0.99, + "summary": "The two PRs are unrelated feature additions: TimesFM covariate forecasting versus DINOv3 image-classification support. They do not appear to fix the same bug or implement the same change, so this cluster should not be merged.", + "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR for the cluster; the PRs implement distinct features in different model families and are not duplicates.", + "canonical_pr_reason": "No canonical PR: the PRs target different model families, different code paths, and different user-facing features.", "best_issue_reason": null, - "best_pr_reason": "No single best PR as a cluster representative because the items are heterogeneous and should not be grouped as one change.", + "best_pr_reason": "PR #41224 is the more self-contained and better-reviewed change, but it is not a duplicate of #40755.", "soft_edge_verdicts": [ { "left": "pull_request:40755", "right": "pull_request:41224", "accept": false, - "reason": "Different models, different features, and different files/code paths; they are not the same underlying bug or change." + "reason": "Different features in different subsystems: TimesFM covariate forecasting versus DINOv3 image classification. They do not share the same underlying bug or change and could not plausibly be merged into one PR." } ] }, @@ -18083,12 +18054,12 @@ "pull_request:41797|pull_request:45186", "pull_request:45186|pull_request:45630" ], - "prepared_review_unit_hash": "682fdc1f74e4375464101dcc610536d03253489e616cf8791c6b0e4f6779ec6d", + "prepared_review_unit_hash": "890774250e31b9e74bcfb49a34e99daa4d87826b1a46009ed9015f796742dc1a", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 10435, + "serialized_chars": 10436, "estimated_input_tokens": 2609, "estimated_eval_tokens": 5474 }, @@ -18096,7 +18067,7 @@ "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 10435, + "serialized_chars": 10436, "estimated_input_tokens": 2609, "estimated_eval_tokens": 5474 }, @@ -18105,24 +18076,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are three separate model-addition PRs (DeepSeek OCR, Isaac, Kimi2-6). They share common integration scaffolding, but each targets a different model and codepath, so they are not duplicates.", - "confidence": 0.98, + "summary": "These are three separate model-addition PRs for different architectures (DeepSeek OCR, Isaac, and Kimi2-6). They share repository scaffolding, but not the same model or concrete code-path change, so they should not be merged as duplicates.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": null, + "canonical_pr_reason": "No canonical PR: each PR adds a different model family and touches distinct model implementations, configs, and tests.", "best_issue_reason": null, - "best_pr_reason": "Kimi2-6 is the broadest and most mature-looking integration here, with the highest review activity and the largest set of model/auto-registration changes, but it is still a distinct PR rather than a duplicate of the others.", + "best_pr_reason": "PR 45630 is the strongest standalone candidate by activity and breadth, but it is still not a duplicate of the others.", "soft_edge_verdicts": [ { "left": "pull_request:41797", "right": "pull_request:45186", "accept": false, - "reason": "Different models and implementations: DeepSeek OCR vs Isaac. The overlap is only in generic model-registration/docs boilerplate, not the same underlying change." + "reason": "Different additions: DeepSeek OCR vs Isaac. Shared auto-registry/docs scaffolding is expected for new-model PRs, but the model code, files, and purpose are unrelated." }, { "left": "pull_request:45186", "right": "pull_request:45630", "accept": false, - "reason": "Different model families and concrete integrations: Isaac vs Kimi2-6. Shared auto-mapping/docs scaffolding is too broad to treat as the same PR." + "reason": "Different model families: Isaac vs Kimi2-6. Overlap is limited to generic framework registration and docs; they do not fix the same code-path problem." } ] }, @@ -18152,7 +18123,7 @@ "soft_pairs": [ "pull_request:42975|pull_request:42976" ], - "prepared_review_unit_hash": "08e51c95551a9519460377214bcdc8027bc0d4af16c3ae606be57ab1ad7fe9d9", + "prepared_review_unit_hash": "f32dc76a2fc3cf1effd70d8a7abde57d60dafea87f8690eaf059b22edd1f3e23", "component_budget": { "node_count": 2, "item_count": 2, @@ -18174,18 +18145,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both items are broad GitHub Actions upgrade PRs, but they target different action families and different concerns: Node 24 compatibility vs latest-version bumps for docker/build-push-action. They are related in scope yet not the same concrete change, so they should not be deduplicated.", + "summary": "Two open PRs that both update GitHub Actions versions, but they target different action families and different workflow sets. They overlap only at a broad maintenance level, not the same concrete change.", "confidence": 0.95, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 42975 is the better representative because its title and edits are more specifically about the compatibility-driven workflow action upgrade theme, which is the closer cluster anchor here.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "PR 42975 is the strongest single representative of the cluster because it touches many workflow actions in a clearly defined compatibility upgrade, while 42976 is a separate version-bump effort focused on docker build actions.", + "best_pr_reason": "PR 42975 is the more representative GitHub Actions maintenance PR because its scope is clearly centered on Node 24-compatible core actions across many workflows, while 42976 is a separate update focused mainly on docker/build-push-action and other latest-version bumps.", "soft_edge_verdicts": [ { "left": "pull_request:42975", "right": "pull_request:42976", "accept": false, - "reason": "Related workflow maintenance, but they update different actions for different purposes and would not naturally be merged into one concrete fix." + "reason": "Reject: both are workflow dependency upgrades, but they touch different actions and different code paths (core workflow actions vs docker build actions). The overlap is too broad to treat as the same underlying change." } ] }, @@ -18224,12 +18195,12 @@ "pull_request:43451|pull_request:45490", "pull_request:45490|pull_request:46162" ], - "prepared_review_unit_hash": "9a01b9fe7c7b4db8bb3d75736c2724a48e77859d31b1b6f644b71f629161cb22", + "prepared_review_unit_hash": "f3ef85915c8a699c1f27337dcab06a0b20115d7c7688e00a857e071d47ce971e", "component_budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 7, - "serialized_chars": 16554, + "serialized_chars": 16553, "estimated_input_tokens": 4139, "estimated_eval_tokens": 8534 }, @@ -18237,7 +18208,7 @@ "node_count": 5, "item_count": 5, "soft_pair_count": 7, - "serialized_chars": 16554, + "serialized_chars": 16553, "estimated_input_tokens": 4139, "estimated_eval_tokens": 8534 }, @@ -18246,54 +18217,54 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are all separate additions or test-only changes across different models and code paths; the shared files are mostly boilerplate model-registration/docs touchpoints, not evidence of duplicate underlying work.", - "confidence": 0.97, + "summary": "This cluster is heterogeneous: four independent model-addition PRs (ViT NEPA, Molmo, Molmo2, CTSM) plus one small test-only XPU expectation PR. They target different models and code paths, so there is no duplicate/canonical change here.", + "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43451 is the most substantial and actively discussed item in the cluster, but it is not a duplicate of the others; it is just the best representative if one must be chosen.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "PR 43451 has the broadest scope and highest review activity, making it the strongest standalone representative of the cluster, though not a duplicate target.", + "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "pull_request:42978", "right": "pull_request:43448", "accept": false, - "reason": "Different model additions: ViT NEPA vs Molmo. Overlap is limited to shared registration/docs scaffolding, not the same code-path change." + "reason": "Different model integrations: ViT NEPA vs Molmo. Shared docs/auto-registration files are expected for new-model PRs and do not indicate the same underlying change." }, { "left": "pull_request:42978", "right": "pull_request:43451", "accept": false, - "reason": "Different model families and implementations: ViT NEPA vs Molmo2. Shared auto/docs edits are incidental boilerplate." + "reason": "Different model additions: ViT NEPA vs Molmo2. The overlap is only in generic registration/docs files, not a shared bug or code-path fix." }, { "left": "pull_request:42978", "right": "pull_request:45490", "accept": false, - "reason": "Completely different domains: a vision model addition vs a time-series model addition. No same bug or mergeable single change." + "reason": "ViT NEPA and CTSM are unrelated model implementations. Similar auto/docs updates are boilerplate for adding a model, not duplicate work." }, { "left": "pull_request:43448", "right": "pull_request:43451", "accept": false, - "reason": "Molmo and Molmo2 are related names but are distinct model releases with separate configs, processors, and tests; not the same underlying change." + "reason": "Molmo and Molmo2 are separate model families with distinct files and functionality. They are not the same concrete feature or fix." }, { "left": "pull_request:43448", "right": "pull_request:45490", "accept": false, - "reason": "Molmo model addition vs CTSM model addition; only broad model-registry files overlap, which is not enough to treat them as duplicates." + "reason": "Molmo vs CTSM are unrelated model additions; shared framework registration files are too broad to merge as duplicates." }, { "left": "pull_request:43451", "right": "pull_request:45490", "accept": false, - "reason": "Molmo2 and CTSM are unrelated model additions touching different architectures and files; shared auto-registration edits are superficial." + "reason": "Molmo2 and CTSM implement different models and code paths. This is not the same underlying change despite similar integration patterns." }, { "left": "pull_request:45490", "right": "pull_request:46162", "accept": false, - "reason": "CTSM model integration vs test annotation changes for Florence2/LFM2-VL. The latter is test maintenance, not the same code-path fix or feature." + "reason": "CTSM is a model-addition PR, while 46162 is a narrow test-only change adding XPU expectations. Different scope and code path, so not duplicates." } ] }, @@ -18328,12 +18299,12 @@ "pull_request:43665|pull_request:46102", "pull_request:43665|pull_request:44815" ], - "prepared_review_unit_hash": "4155d50ded71537fe1e003f7367ed45759fc4545aef5582129c953827f68724f", + "prepared_review_unit_hash": "fa2328e4fdf4fd6d7845b67a52189f5928e7386b7763836d3bfaaf8ab88b51fd", "component_budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 4, - "serialized_chars": 9391, + "serialized_chars": 9390, "estimated_input_tokens": 2348, "estimated_eval_tokens": 4952 }, @@ -18341,7 +18312,7 @@ "node_count": 4, "item_count": 4, "soft_pair_count": 4, - "serialized_chars": 9391, + "serialized_chars": 9390, "estimated_input_tokens": 2348, "estimated_eval_tokens": 4952 }, @@ -18350,36 +18321,36 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are not duplicates: the PRs target unrelated areas (Whisper decoding, CLIP/ViT test edits, FP8 dequantization, and FSDP tied-weights handling). The only commonality is generic \"fix\" wording and test touchpoints in some diffs.", + "summary": "These PRs are not duplicates: they cover unrelated areas (Whisper decoding/tests, CLIP/ViT test placeholders, FP8 dequantization, and FSDP tied-weights). The one soft-similarity edge is not strong enough to merge into a single change.", "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "pull_request:46102 is the clearest focused bug fix with a concrete code path (FSDP tied weights / model loading), but it is not a duplicate of the others.", + "canonical_pr_reason": "PR 44815 is the strongest standalone candidate: it has a coherent code-path fix in model loading / FP8 quantization with supporting tests. The others are either test-only or address different subsystems.", "best_issue_reason": null, - "best_pr_reason": "pull_request:46102 is the strongest standalone PR: specific title, cohesive FSDP scope, and a focused fix path compared with the more generic or test-heavy alternatives.", + "best_pr_reason": "PR 44815 is the best representative of the cluster because it is an actual functional fix rather than a test-only edit, and it has the clearest end-to-end bug/fix relationship.", "soft_edge_verdicts": [ { "left": "pull_request:43291", "right": "pull_request:43665", "accept": false, - "reason": "Different subsystems and problems: Whisper tokenizer decoding vs CLIP/ViT test edits. Superficial \"fix\" similarity only." + "reason": "Both are test-related, but they target different models and different changes (Whisper tokenizer behavior vs. CLIP/ViT test edits). Not the same underlying bug or mergeable into one PR." }, { "left": "pull_request:43291", "right": "pull_request:44815", "accept": false, - "reason": "Whisper timestamp decoding and FP8 dequant/model-loading changes are unrelated code paths; no same underlying bug." + "reason": "Whisper decoding/tokenization changes are unrelated to FP8 dequantization and model loading logic." }, { "left": "pull_request:43665", "right": "pull_request:46102", "accept": false, - "reason": "Test-file edits for vision models are not the same issue as FSDP tied-weights/model-loading changes." + "reason": "CLIP/ViT test placeholders are unrelated to the FSDP tied-weights fix; they do not share a concrete code-path problem." }, { "left": "pull_request:43665", "right": "pull_request:44815", "accept": false, - "reason": "These touch unrelated areas (vision tests vs FP8 quantization/loading). Shared generic wording is insufficient." + "reason": "Despite superficial similarity as fixes, one is only test edits while the other is a quantization/model-loading bug fix; not the same change." } ] }, @@ -18416,73 +18387,73 @@ "pull_request:45932|pull_request:46100", "pull_request:46100|pull_request:46114" ], - "prepared_review_unit_hash": "7877d7166add60e71b11c9f8b09302c913da14e5c60f60271fa9f28e0c9320be", + "prepared_review_unit_hash": "3a40b3ef80670fd1722af77b2fea6ae70a362aeb7c8b30aa851aab8de93b1361", "component_budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 5, - "serialized_chars": 11341, - "estimated_input_tokens": 2836, - "estimated_eval_tokens": 5928 + "serialized_chars": 11339, + "estimated_input_tokens": 2835, + "estimated_eval_tokens": 5926 }, "budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 5, - "serialized_chars": 11341, - "estimated_input_tokens": 2836, - "estimated_eval_tokens": 5928 + "serialized_chars": 11339, + "estimated_input_tokens": 2835, + "estimated_eval_tokens": 5926 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is mostly synthetic or test-only PRs. PR 45932 is the only substantive implementation change and is the best representative. The one true duplicate pair is 46100 and 46114, which have identical ViT test edits; the other soft-similarity pairs do not look like the same underlying change.", - "confidence": 0.82, + "summary": "Only the two ViT test-migration PRs are true duplicates; the other soft links are superficial filename overlaps or unrelated CI/test scaffolding changes.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45932 is the best canonical PR because it contains the real multi-file implementation/config/CI change, while the others are either synthetic test PRs or unrelated workflow/test edits.", + "canonical_pr_reason": "PR #46100 is the cleanest representative of the duplicated ViT test-migration change; #46114 appears to be the forked copy with the same patch.", "best_issue_reason": null, - "best_pr_reason": "PR 45932 is the clearest representative of the cluster\u2019s substantive change set and is more useful as the cluster anchor than the synthetic duplicates.", + "best_pr_reason": "PR #46100 is the best global PR candidate because it is the canonical version of the only real duplicate pair and has the clearest title for the shared change.", "soft_edge_verdicts": [ { "left": "pull_request:43488", "right": "pull_request:46114", "accept": false, - "reason": "Both touch ViT tests, but 43488 also changes setup/dependency files and has a different purpose; the diffs are not the same underlying change." + "reason": "Both touch tests/models/vit/test_modeling_vit.py, but #43488 is a repo-bot/version/dependency stub and #46114 is a test-migration/OTEL PR; they are not the same underlying change." }, { "left": "pull_request:43488", "right": "pull_request:43532", "accept": false, - "reason": "Shared test-file overlap is too weak: 43488 is setup/version/dependency-oriented, while 43532 is workflow/testing-utils oriented." + "reason": "Shared ViT test file is incidental; #43488 is setup/version/dependency plumbing while #43532 is workflow/notification/testing-utils changes. Different PR goals and code paths." }, { "left": "pull_request:43532", "right": "pull_request:46114", "accept": false, - "reason": "43532 changes workflows and testing utilities, whereas 46114 is a forked ViT test-migration PR; they are not the same code change." + "reason": "Both mention ViT tests only tangentially; #43532 centers on CI workflows and utilities, while #46114 is a forked test-migration PR. Not the same fix/change." }, { "left": "pull_request:45932", "right": "pull_request:46100", "accept": false, - "reason": "These are different changes: 45932 updates model/config/CI code across many files, while 46100 only injects failing assertions into tests/models/vit/test_modeling_vit.py." + "reason": "Despite the similarity signal, #45932 is a broad Grafana/testing/integration PR across many models and workflows, while #46100 is a tiny ViT test assertion change. Not mergeable as one PR." }, { "left": "pull_request:46100", "right": "pull_request:46114", "accept": true, - "reason": "These appear to be the same synthetic ViT test PR: same file, same inserted assertions, and matching diff preview, so they could plausibly be merged as one PR." + "reason": "These are effectively identical: same file, same added failing assertions, and the titles indicate the same test-migration intent. They look like forked duplicates of one underlying change." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The summary is not fully grounded in the packet. Most notably, the packet marks pull_request:45932 | pull_request:46100 as deterministic_accept=true, but the analyst says that pair is not the same underlying change and instead calls 46100 | 46114 the only true duplicate pair. That directly conflicts with the provided pair evidence. Also, the claim that 46100 and 46114 are the same synthetic PR is stronger than the packet supports, since their evidence is only soft_similarity, not deterministic acceptance. The representative choice of 45932 is fine, but the soft-edge verdicts and duplicate-pair summary need to be more conservative." + "accept": true, + "feedback": "The duplicate judgement for 46100/46114 is grounded by the identical diff preview and titles. The other soft-edge rejections are conservative and supported by the packet: they share at most a filename or broad testing/CI context, but not the same underlying bugfix or a mergeable single PR change. The summary stays within the evidence." }, "evaluator_used": true, - "retried": true, + "retried": false, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -18506,7 +18477,7 @@ "soft_pairs": [ "pull_request:43612|pull_request:43613" ], - "prepared_review_unit_hash": "b99469c6ee2b9bb25e897c96d8d68749c688fae68bad626cfd307cd1df2a7d67", + "prepared_review_unit_hash": "b52d527be0d0325bb742fec92c54ab31c42561426b3e40306685bf584ea3ca7a", "component_budget": { "node_count": 2, "item_count": 2, @@ -18528,18 +18499,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two feature PRs with overlapping scaffolding, but they implement different pipelines and different underlying segmentation tasks; they should not be merged as duplicates.", - "confidence": 0.94, + "summary": "Two separate feature PRs: one adds Promptable Concept Segmentation, the other adds Promptable Visual Segmentation. They share framework/docs scaffolding but target different pipelines, models, and tests, so they are not duplicates.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical duplicate PR: 43612 adds Promptable Concept Segmentation, while 43613 adds Promptable Visual Segmentation; they target different code paths and model integrations.", + "canonical_pr_reason": "No single canonical PR for a duplicate set here; these are distinct pipeline additions rather than two implementations of the same change.", "best_issue_reason": null, - "best_pr_reason": "PR 43613 is the broader of the two feature additions and touches more model/test integration, so it is the better representative if one must be chosen, though it is still not a duplicate of 43612.", + "best_pr_reason": "If a representative is needed, #43613 is slightly broader/more integrated, but it is still a separate feature from #43612 rather than a duplicate counterpart.", "soft_edge_verdicts": [ { - "left": "pull_request:43612", - "right": "pull_request:43613", + "left": "Add Promptable Concept Segmentation pipeline", + "right": "Add Promptable Visual Segmentation pipeline", "accept": false, - "reason": "Different pipelines/features (concept segmentation vs visual segmentation) with different model and test coverage; shared docs/boilerplate files are not enough to treat them as the same change." + "reason": "Different underlying tasks and code paths: concept segmentation vs visual segmentation use different model integrations and tests, so shared docs/pipeline plumbing does not make them the same change." } ] }, @@ -18569,7 +18540,7 @@ "soft_pairs": [ "pull_request:43651|pull_request:43663" ], - "prepared_review_unit_hash": "cdc471dec3cf0047c73971c6e64d50ff26d19b9750dadea2aade31cc0ada433d", + "prepared_review_unit_hash": "7e149a7f484b9678838fb92c4c141f85dd32c0c30dc4ec4083a4cf7df4dd60ef", "component_budget": { "node_count": 2, "item_count": 2, @@ -18591,18 +18562,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open Trainer PRs touch the same file but implement different extension points: one changes gradient-accumulation loss scaling, the other refactors signature-column filtering for custom trainers. They are not the same underlying change.", - "confidence": 0.95, + "summary": "Two open PRs touch `trainer.py` and both add override points for custom trainers, but they address different behaviors: gradient-accumulation loss scaling vs. signature-column filtering. They are not the same underlying change.", + "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43651 is the more concrete standalone fix: it changes loss scaling behavior in training_step and adds a supporting property. PR 43663 is a separate refactor for column-filtering extensibility.", + "canonical_pr_reason": "No canonical PR: PR #43651 changes training loss scaling logic, while PR #43663 changes dataloader column filtering/signature inspection; they are unrelated extension points.", "best_issue_reason": null, - "best_pr_reason": "PR 43651 is the better representative because it has a narrowly defined behavior change and clearer bug-fix intent than the column-filtering refactor in 43663.", + "best_pr_reason": "PR #43651 is the more self-contained trainer behavior change, but the cluster does not have a single best representative because the PRs solve different problems.", "soft_edge_verdicts": [ { "left": "pull_request:43651", "right": "pull_request:43663", "accept": false, - "reason": "Different code paths and goals: 43651 adjusts gradient accumulation loss normalization, while 43663 adds an overrideable helper for signature-column filtering. Shared file alone is not enough to treat them as duplicates." + "reason": "Different code paths and goals: #43651 adds `_loss_is_scaled_for_ga` for gradient accumulation loss normalization, while #43663 adds `_get_signature_columns` for column filtering. Same file, but not the same fix." } ] }, @@ -18632,7 +18603,7 @@ "soft_pairs": [ "pull_request:43656|pull_request:43842" ], - "prepared_review_unit_hash": "5963cc1b90f71e31551fbf24df588b6326f9a971b0e7be3981afc138a5c72c8d", + "prepared_review_unit_hash": "07657b337baabeb8089f43a15e3470e19ca7706371ab31be477f23bd9ccb2324", "component_budget": { "node_count": 2, "item_count": 2, @@ -18654,18 +18625,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open PRs touch the same file and the same general TypeAdapter annotation problem in `src/transformers/cli/serve.py`, but they use different fixes and appear to target different concrete failure modes, so they should not be collapsed as duplicates.", - "confidence": 0.78, + "summary": "Both PRs touch the same CLI file and both mention a TypeAdapter NameError, but they address different fixes: one is broader annotation/postponement cleanup, the other is a targeted pydantic-absent runtime import issue. I would not merge them as duplicates.", + "confidence": 0.83, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #43656 is the stronger canonical representative: it has the explicit issue link, more discussion/review activity, and a broader runtime-safe typing cleanup in the CLI serve code path.", + "canonical_pr_reason": "PR #43842 is the more precise fix: it directly addresses the TypeAdapter NameError when pydantic is not installed, with a minimal change in the exact validation path.", "best_issue_reason": null, - "best_pr_reason": "PR #43842 is the more narrowly targeted fix for the specific pydantic-absent `TypeAdapter` NameError, but it is less established than #43656 and appears to be an alternate implementation rather than the same change.", + "best_pr_reason": "PR #43842 is the best standalone PR because it targets a concrete runtime failure with a narrow, plausible merge surface and clear dependency-related behavior.", "soft_edge_verdicts": [ { "left": "pull_request:43656", "right": "pull_request:43842", "accept": false, - "reason": "Both are in `cli/serve.py` and mention `TypeAdapter`, but the diffs show different remedies (`from __future__ import annotations`/typing cleanup vs `TYPE_CHECKING` import plus quoted annotation) and different issue targets, so they do not look like the same concrete PR change." + "reason": "They share a file and a loosely related NameError theme, but the fixes are not the same code-path problem: #43656 is broader typing/annotations cleanup, while #43842 specifically handles TypeAdapter when pydantic is absent." } ] }, @@ -18814,8 +18785,8 @@ "pull_request:44098|pull_request:44101", "pull_request:44059|pull_request:44722", "pull_request:44018|pull_request:44071", - "pull_request:44017|pull_request:44161", "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:43997|pull_request:44073", @@ -18857,148 +18828,148 @@ "pull_request:44044|pull_request:44129", "pull_request:44044|pull_request:44154" ], - "prepared_review_unit_hash": "75773f077841fe924b1af82b6bb723107ba20ff9dcaef128f3441637aeaa8bdc", + "prepared_review_unit_hash": "1674e09279a5d1448f9588266b336f51a49ca32e467ce8b2c3ac64291350709e", "component_budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 78, - "serialized_chars": 84901, - "estimated_input_tokens": 21226, - "estimated_eval_tokens": 42708 + "serialized_chars": 84893, + "estimated_input_tokens": 21224, + "estimated_eval_tokens": 42704 }, "budget": { "node_count": 27, "item_count": 27, "soft_pair_count": 72, - "serialized_chars": 75096, - "estimated_input_tokens": 18774, - "estimated_eval_tokens": 37804 + "serialized_chars": 75089, + "estimated_input_tokens": 18773, + "estimated_eval_tokens": 37802 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is dominated by model-specific output-tracing refactors. The only clear duplicate groups are the GPT-Neo pair and the GPT-J family (including the later GPT-J/CodeGen follow-up); the rest are same-theme but different model/code paths.", - "confidence": 0.84, + "summary": "This cluster is mostly a theme cluster of output-tracing refactors across many unrelated models, not one single duplicate chain. Only the same-model GPT-Neo and GPT-J pairs look like true overlaps; the rest are separate model-specific refactors that should stay distinct.", + "confidence": 0.83, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44722 is the strongest representative of the GPT-J output-tracing refactor cluster: it is the latest and most complete decorator-based migration on the same code path, with the clearest overlap to the earlier GPT-J PRs.", + "canonical_pr_reason": "No canonical issue is present. As a representative PR, 44066 is the strongest anchor because it has an explicit issue link, covers the core GPT-J/CodeGen output-tracing refactor, and overlaps with later GPT-J follow-ups.", "best_issue_reason": null, - "best_pr_reason": "PR 44722 best represents the duplicate cluster because it most completely captures the shared GPT-J output-tracing change and also subsumes the related CodeGen work.", + "best_pr_reason": "44066 is the best representative for the cluster\u2019s central refactor theme: it is broad, explicit about the tracking issue, and closest to the repeated GPT-J/CodeGen duplicate stream.", "soft_edge_verdicts": [ { "left": "pull_request:43996", "right": "pull_request:44085", "accept": false, - "reason": "Different model families and code paths; same output-tracing theme is too broad." + "reason": "Different model families (FNet/CVT vs GPT-J) with only a shared refactor theme." }, { "left": "pull_request:43996", "right": "pull_request:44044", "accept": false, - "reason": "Unrelated models (FNet/CVT vs DeBERTa); not the same underlying change." + "reason": "Different model families and different code paths; same broad output-tracing motif is not enough." }, { "left": "pull_request:44066", "right": "pull_request:44085", "accept": true, - "reason": "Both are GPT-J output-tracing refactors on the same model code path; the later PR is a broader variant, but the underlying change matches." + "reason": "Both target GPT-J output tracing in the same code path and are plausibly mergeable into one PR." }, { "left": "pull_request:44007", "right": "pull_request:44072", "accept": false, - "reason": "Different vision models and different implementations; only the refactor pattern is shared." + "reason": "ResNet/RT-DETR ResNet vs EfficientNet are separate model implementations, not the same change." }, { "left": "pull_request:44072", "right": "pull_request:44722", "accept": false, - "reason": "EfficientNet and GPT-J/CodeGen are unrelated; same refactor style does not make them duplicates." + "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; different code paths and model families." + "reason": "GPT-J/CodeGen vs EfficientNet are different models and different fixes." }, { "left": "pull_request:44013", "right": "pull_request:44044", "accept": false, - "reason": "MobileNetV2 and DeBERTa are unrelated models." + "reason": "MobileNetV2 vs DeBERTa-V2 are unrelated model-specific refactors." }, { "left": "pull_request:44066", "right": "pull_request:44086", "accept": false, - "reason": "GPT-J/CodeGen vs MGP-STR; not the same bug/change." + "reason": "GPT-J/CodeGen vs MGP-STR are unrelated implementations." }, { "left": "pull_request:44066", "right": "pull_request:44071", "accept": false, - "reason": "GPT-J/CodeGen and MPT are different model implementations." + "reason": "GPT-J/CodeGen and MPT are different model code paths." }, { "left": "pull_request:44018", "right": "pull_request:44068", "accept": true, - "reason": "Same GPT-Neo output-tracing migration on the same model family and code path." + "reason": "Both refactor GPT-Neo output tracing in the same file and appear to be the same underlying change." }, { "left": "pull_request:44066", "right": "pull_request:44068", "accept": false, - "reason": "GPT-J/CodeGen and GPT-Neo are unrelated model code paths." + "reason": "GPT-J/CodeGen and GPT-Neo are different model families." }, { "left": "pull_request:44018", "right": "pull_request:44066", "accept": false, - "reason": "Different model families (GPT-Neo vs GPT-J/CodeGen); same issue target is not enough." + "reason": "GPT-Neo and GPT-J/CodeGen are separate model implementations." }, { "left": "pull_request:44019", "right": "pull_request:44722", "accept": false, - "reason": "ResNet and GPT-J/CodeGen are unrelated; no shared concrete bug/change." + "reason": "ResNet vs GPT-J/CodeGen are unrelated." }, { "left": "pull_request:44086", "right": "pull_request:44722", "accept": false, - "reason": "MGP-STR and GPT-J/CodeGen are unrelated code paths." + "reason": "MGP-STR vs GPT-J/CodeGen are unrelated model changes." }, { "left": "pull_request:44019", "right": "pull_request:44085", "accept": false, - "reason": "ResNet and GPT-J are unrelated model implementations." + "reason": "ResNet and GPT-J are different code paths." }, { "left": "pull_request:44018", "right": "pull_request:44019", "accept": false, - "reason": "GPT-Neo and ResNet are unrelated; only the refactor theme overlaps." + "reason": "GPT-Neo and ResNet are different models; shared refactor pattern is not duplicate evidence." }, { "left": "pull_request:44019", "right": "pull_request:44071", "accept": false, - "reason": "ResNet and MPT are unrelated models and code paths." + "reason": "ResNet vs MPT are unrelated model-specific changes." }, { "left": "pull_request:44068", "right": "pull_request:44116", "accept": false, - "reason": "GPT-Neo and Flaubert are unrelated model families." + "reason": "GPT-Neo and Flaubert are unrelated implementations." }, { "left": "pull_request:44068", "right": "pull_request:44722", "accept": false, - "reason": "GPT-Neo and GPT-J/CodeGen are different model families and refactors." + "reason": "GPT-Neo vs GPT-J/CodeGen are different model families." }, { "left": "pull_request:44018", @@ -19010,217 +18981,247 @@ "left": "pull_request:44071", "right": "pull_request:44722", "accept": false, - "reason": "MPT and GPT-J/CodeGen are unrelated model implementations." + "reason": "MPT and GPT-J/CodeGen are different models." }, { "left": "pull_request:44018", "right": "pull_request:44086", "accept": false, - "reason": "GPT-Neo and MGP-STR are unrelated; same output-tracing pattern is too broad." + "reason": "GPT-Neo vs MGP-STR are unrelated model changes." }, { "left": "pull_request:44018", "right": "pull_request:44085", "accept": false, - "reason": "GPT-Neo and GPT-J are different model code paths." + "reason": "GPT-Neo vs GPT-J are different code paths." }, { "left": "pull_request:44068", "right": "pull_request:44086", "accept": false, - "reason": "GPT-Neo and MGP-STR are unrelated." + "reason": "GPT-Neo vs MGP-STR are unrelated." }, { - "left": "pull_request:44071", - "right": "pull_request:44086", + "left": "pull_request:44098", + "right": "pull_request:44101", "accept": false, - "reason": "MPT and MGP-STR are unrelated model refactors." + "reason": "ViLT and XLM are distinct model families." }, { "left": "pull_request:44059", - "right": "pull_request:44086", + "right": "pull_request:44722", "accept": false, - "reason": "GPT2 and MGP-STR are unrelated code paths." + "reason": "GPT-2 and GPT-J/CodeGen are separate implementations." }, { - "left": "pull_request:44085", - "right": "pull_request:44086", + "left": "pull_request:44018", + "right": "pull_request:44071", "accept": false, - "reason": "GPT-J and MGP-STR are unrelated models." + "reason": "GPT-Neo and MPT are different models." }, { - "left": "pull_request:44098", - "right": "pull_request:44101", + "left": "pull_request:44017", + "right": "pull_request:44722", "accept": false, - "reason": "ViLT and Flaubert/XLM are unrelated model families." + "reason": "SegFormer and GPT-J/CodeGen are unrelated." }, { - "left": "pull_request:44059", - "right": "pull_request:44722", + "left": "pull_request:44017", + "right": "pull_request:44161", "accept": false, - "reason": "GPT2 and GPT-J/CodeGen are different model implementations." + "reason": "SegFormer and LongT5 are unrelated model-specific refactors." }, { - "left": "pull_request:44018", + "left": "pull_request:44017", + "right": "pull_request:44073", + "accept": false, + "reason": "SegFormer and VisualBERT are different code paths." + }, + { + "left": "pull_request:44068", "right": "pull_request:44071", "accept": false, - "reason": "GPT-Neo and MPT are unrelated code paths." + "reason": "GPT-Neo and MPT are different models." }, { - "left": "pull_request:44059", - "right": "pull_request:44068", + "left": "pull_request:43997", + "right": "pull_request:44073", "accept": false, - "reason": "GPT2 and GPT-Neo are different model families." + "reason": "RegNet and VisualBERT are unrelated." }, { "left": "pull_request:44071", - "right": "pull_request:44085", + "right": "pull_request:44076", "accept": false, - "reason": "MPT and GPT-J are unrelated models." + "reason": "MPT and ImageGPT are separate model implementations." }, { - "left": "pull_request:44059", - "right": "pull_request:44071", + "left": "pull_request:44074", + "right": "pull_request:44101", "accept": false, - "reason": "GPT2 and MPT are unrelated code paths." + "reason": "TextNet and XLM are unrelated models." }, { - "left": "pull_request:44073", + "left": "pull_request:44056", "right": "pull_request:44161", "accept": false, - "reason": "VisualBERT and LongT5 are unrelated models." + "reason": "MPNet and LongT5 are unrelated code paths." }, { - "left": "pull_request:44018", - "right": "pull_request:44059", + "left": "pull_request:43997", + "right": "pull_request:44018", "accept": false, - "reason": "GPT-Neo and GPT2 are different model implementations." + "reason": "RegNet and GPT-Neo are different model families." }, { - "left": "pull_request:44101", + "left": "pull_request:43997", "right": "pull_request:44161", "accept": false, - "reason": "Flaubert/XLM and LongT5 are unrelated code paths." + "reason": "RegNet and LongT5 are unrelated." }, { - "left": "pull_request:43997", - "right": "pull_request:44017", + "left": "pull_request:44074", + "right": "pull_request:44161", + "accept": false, + "reason": "TextNet and LongT5 are unrelated model changes." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44161", "accept": false, - "reason": "RegNet and SegFormer are different vision models." + "reason": "GPT-Neo and LongT5 are unrelated." }, { "left": "pull_request:43997", - "right": "pull_request:44056", + "right": "pull_request:44071", "accept": false, - "reason": "RegNet and MPNet are unrelated models." + "reason": "RegNet and MPT are different code paths." }, { - "left": "pull_request:44071", - "right": "pull_request:44076", + "left": "pull_request:44010", + "right": "pull_request:44071", "accept": false, - "reason": "MPT and ImageGPT are unrelated model implementations." + "reason": "SqueezeBERT and MPT are unrelated models." }, { - "left": "pull_request:44074", - "right": "pull_request:44101", + "left": "pull_request:44010", + "right": "pull_request:44073", + "accept": false, + "reason": "SqueezeBERT and VisualBERT are separate implementations." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44129", "accept": false, - "reason": "TextNet and Flaubert/XLM are unrelated code paths." + "reason": "GPT-Neo and SpeechT5 are unrelated model-specific refactors." }, { "left": "pull_request:44056", "right": "pull_request:44161", "accept": false, - "reason": "MPNet and LongT5 are unrelated models." + "reason": "MPNet and LongT5 are unrelated." }, { "left": "pull_request:43997", "right": "pull_request:44018", "accept": false, - "reason": "RegNet and GPT-Neo are unrelated model families." + "reason": "RegNet and GPT-Neo are different model families." }, { "left": "pull_request:43997", "right": "pull_request:44161", "accept": false, - "reason": "RegNet and LongT5 are unrelated code paths." + "reason": "RegNet and LongT5 are unrelated." }, { "left": "pull_request:44074", "right": "pull_request:44161", "accept": false, - "reason": "TextNet and LongT5 are unrelated models." + "reason": "TextNet and LongT5 do not share the same code-path change." }, { "left": "pull_request:44018", "right": "pull_request:44161", "accept": false, - "reason": "GPT-Neo and LongT5 are unrelated code paths." + "reason": "GPT-Neo and LongT5 are unrelated model changes." }, { "left": "pull_request:43997", "right": "pull_request:44071", "accept": false, - "reason": "RegNet and MPT are unrelated models." + "reason": "RegNet and MPT are unrelated." }, { "left": "pull_request:44010", "right": "pull_request:44071", "accept": false, - "reason": "SqueezeBert and MPT are unrelated model implementations." + "reason": "SqueezeBERT and MPT are different models." }, { "left": "pull_request:44010", "right": "pull_request:44073", "accept": false, - "reason": "SqueezeBert and VisualBERT are different models." + "reason": "SqueezeBERT and VisualBERT are unrelated." }, { - "left": "pull_request:44018", + "left": "pull_request:44010", "right": "pull_request:44044", "accept": false, - "reason": "GPT-Neo and DeBERTa are unrelated code paths." + "reason": "SqueezeBERT and DeBERTa-V2 are unrelated." }, { "left": "pull_request:44044", "right": "pull_request:44074", "accept": false, - "reason": "DeBERTa and TextNet are unrelated models." + "reason": "DeBERTa-V2 and TextNet are different model implementations." }, { "left": "pull_request:44066", "right": "pull_request:44722", "accept": true, - "reason": "Same GPT-J/CodeGen output-tracing refactor on overlapping code paths; the later PR looks like a broader rework of the same change." + "reason": "Same GPT-J output-tracing refactor on the same concrete code path; these could plausibly be one PR." }, { "left": "pull_request:44085", "right": "pull_request:44722", "accept": true, - "reason": "Both target the GPT-J output-tracing migration on the same underlying code path, with the later PR expanding the refactor." + "reason": "Both touch GPT-J output tracing in the same file and look like overlapping refactor variants." }, { "left": "pull_request:44085", "right": "pull_request:44129", "accept": false, - "reason": "GPT-J and SpeechT5 are unrelated models." + "reason": "GPT-J vs SpeechT5 are unrelated model code paths." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44007", + "accept": false, + "reason": "FNet/CVT and RegNet/ResNet are different models; same architectural theme is insufficient." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44129", + "accept": false, + "reason": "FNet/CVT and SpeechT5 are unrelated." }, { "left": "pull_request:44044", "right": "pull_request:44129", "accept": false, - "reason": "DeBERTa and SpeechT5 are unrelated code paths." + "reason": "DeBERTa-V2 and SpeechT5 are unrelated model-specific changes." }, { "left": "pull_request:44044", "right": "pull_request:44154", "accept": false, - "reason": "DeBERTa and VITS are unrelated model implementations." + "reason": "DeBERTa-V2 and VITS are different code paths and model families." } ] }, "evaluator_result": { "accept": true, - "feedback": "The cluster summary is conservative and grounded in the packet. The accepted soft edges are limited to the clearly mergeable GPT-Neo and GPT-J/CodeGen follow-up chains, and the rejected edges avoid overgeneralizing across unrelated model families/code paths." + "feedback": "The evaluation is grounded in the packet and stays conservative on soft-edge calls. The accepted pairs are plausible same-code-path overlaps (GPT-Neo and GPT-J/CodeGen), and the rejected pairs correctly separate different model families and unrelated fixes. The canonical/representative PR choice is also reasonable given the explicit issue link and breadth of 44066." }, "evaluator_used": true, "retried": false, @@ -19258,20 +19259,20 @@ "pull_request:43997|pull_request:44010", "pull_request:44010|pull_request:44129" ], - "prepared_review_unit_hash": "247ede06c9acf6503c18e57190c12d34cbd51f224c2527df5a6b22a969a1bc22", + "prepared_review_unit_hash": "136ed919d772830ba6c128a5b872bfc04b3dca0a8fc1df190421eb966601441d", "component_budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 78, - "serialized_chars": 84901, - "estimated_input_tokens": 21226, - "estimated_eval_tokens": 42708 + "serialized_chars": 84893, + "estimated_input_tokens": 21224, + "estimated_eval_tokens": 42704 }, "budget": { "node_count": 8, "item_count": 8, "soft_pair_count": 6, - "serialized_chars": 17126, + "serialized_chars": 17125, "estimated_input_tokens": 4282, "estimated_eval_tokens": 8820 }, @@ -19280,48 +19281,48 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These PRs share a broad theme of migrating model implementations to standardized output tracing/capture hooks, but they are model-specific refactors rather than duplicates of the same concrete code path. I would keep one representative PR for the cluster theme, but reject all soft pair merges.", - "confidence": 0.88, + "summary": "These PRs all refactor model-specific output tracing toward the same library-wide decorator pattern, but they are separate per-model changes and not true duplicates of one another.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "44073 is a good canonical PR for the cluster because it clearly represents the recurring standardized-output refactor pattern (adding can_return_tuple/capture_outputs and model-specific output hooks) without being dominated by an unrelated issue target.", + "canonical_pr_reason": "No single PR is the obvious duplicate canonical: each PR targets a different model file and code path. If one representative must be chosen, PR 44129 is the strongest anchor because it has an explicit issue target and a concrete SpeechT5 refactor.", "best_issue_reason": null, - "best_pr_reason": "44129 is the strongest standalone PR in the set because it has an explicit issue target and a concrete model-specific output-tracing refactor, making it the most actionable single change even though it is not a duplicate of the others.", + "best_pr_reason": "PR 44129 is the best representative because it is the most concretely scoped, has an explicit linked issue, and clearly describes the standardized output capture refactor for one model.", "soft_edge_verdicts": [ { "left": "pull_request:44024", "right": "pull_request:44076", "accept": false, - "reason": "Both are output-tracing refactors, but one is FocalNet and the other is ImageGPT; they touch different model code paths and are not the same fix." + "reason": "Same broad migration theme, but FocalNet and ImageGPT are different model implementations with separate forward paths; not the same underlying change." }, { "left": "pull_request:44073", "right": "pull_request:44074", "accept": false, - "reason": "VisualBert vs TextNet are separate implementations; this is the same general migration style, not one mergeable duplicate PR." + "reason": "Both are output-tracing refactors, but they touch different models (VisualBert vs TextNet) and distinct code paths, so they are not mergeable as one PR." }, { "left": "pull_request:44056", "right": "pull_request:44073", "accept": false, - "reason": "MPNet and VisualBert both adopt capture_outputs, but they are distinct model-specific changes with different hooks and forward paths." + "reason": "MPNet and VisualBert are unrelated model-specific refactors; shared decorator usage alone is too broad to treat as the same change." }, { "left": "pull_request:44056", "right": "pull_request:44074", "accept": false, - "reason": "These are parallel refactors in different models, not the same underlying bug or change." + "reason": "Different models and different forward/tracing implementations; this is the same migration pattern, not the same bug or fix." }, { "left": "pull_request:43997", "right": "pull_request:44010", "accept": false, - "reason": "RegNet and SqueezeBert are unrelated model code paths; similarity is only the shared output-tracing migration pattern." + "reason": "RegNet and SqueezeBert changes are model-specific output-tracing migrations, not the same concrete code-path problem." }, { "left": "pull_request:44010", "right": "pull_request:44129", "accept": false, - "reason": "SqueezeBert and SpeechT5 are different model implementations, and the explicit issue target on SpeechT5 does not make these the same PR." + "reason": "SqueezeBert and SpeechT5 affect different architectures and output flows; they share a refactor goal but not a single duplicate fix." } ] }, @@ -19407,334 +19408,304 @@ "pull_request:44002|pull_request:46106", "pull_request:43998|pull_request:46106" ], - "prepared_review_unit_hash": "6181569103897973301d948050265797e80e0ed8571c1a212309bf20cf1128a2", + "prepared_review_unit_hash": "8b96f7a3020a11410d6ab5619e79c193b8a56cdbf2e84b0cb7d2a2d1309733e2", "component_budget": { "node_count": 14, "item_count": 14, "soft_pair_count": 45, - "serialized_chars": 43785, - "estimated_input_tokens": 10947, - "estimated_eval_tokens": 22150 + "serialized_chars": 43771, + "estimated_input_tokens": 10943, + "estimated_eval_tokens": 22142 }, "budget": { "node_count": 14, "item_count": 14, "soft_pair_count": 45, - "serialized_chars": 43785, - "estimated_input_tokens": 10947, - "estimated_eval_tokens": 22150 + "serialized_chars": 43771, + "estimated_input_tokens": 10943, + "estimated_eval_tokens": 22142 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are mostly independent, model-specific output-tracing refactors that share a naming pattern but not the same concrete change. The only unrelated item is the docs toctree fix. I found no duplicate-worthy pairings here under a strict PR policy.", - "confidence": 0.9, + "summary": "This is a loose similarity cluster of parallel \"refactor output tracing\" PRs across different model implementations, plus one unrelated docs toctree edit. They share a pattern and vocabulary, but not the same concrete change or code path, so there is no true duplicate PR set here.", + "confidence": 0.95, "canonical_issue_reason": null, - "canonical_pr_reason": "#44003 is the broadest and most representative output-tracing refactor in the set, touching two related model implementations and the shared output-capturing plumbing.", + "canonical_pr_reason": "No single canonical PR: the PRs are independent, model-specific output-tracing refactors rather than duplicate fixes for one shared code path.", "best_issue_reason": null, - "best_pr_reason": "#44003 is the strongest cluster representative: it is a substantive code change, spans multiple related files, and best matches the cluster\u2019s core theme of output-tracing refactoring.", + "best_pr_reason": "44003 is the broadest representative of the pattern, but it still only covers Mamba/Falcon-Mamba and is not a mergeable duplicate of the other PRs.", "soft_edge_verdicts": [ { "left": "pull_request:43998", "right": "pull_request:44002", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "Same refactor theme, but different model files and code paths; not the same underlying change." }, { "left": "pull_request:43998", "right": "pull_request:44000", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "Both are output-tracing refactors, but they target unrelated model implementations." }, { "left": "pull_request:43998", "right": "pull_request:44001", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "Different models with separate forward paths; too broad a similarity to count as a duplicate." }, { "left": "pull_request:43998", "right": "pull_request:44003", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." - }, - { - "left": "pull_request:43998", - "right": "pull_request:44004", - "accept": false, - "reason": "Different code paths and files; both mention output tracing, but they are separate model changes." + "reason": "Timm backbone vs Mamba/Falcon-Mamba are unrelated code paths, so these are not mergeable as one PR." }, { "left": "pull_request:43998", "right": "pull_request:44029", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." - }, - { - "left": "pull_request:43998", - "right": "pull_request:46106", - "accept": false, - "reason": "Unrelated docs toctree change, not an output-tracing refactor." + "reason": "Same naming pattern, but separate model code and different behavior; not a duplicate fix." }, { "left": "pull_request:43999", "right": "pull_request:44001", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "MobileNetV1 and UnivNet are unrelated model implementations; this is only a shared refactor style." }, { "left": "pull_request:43999", "right": "pull_request:44002", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "They both modernize output handling, but in different models with different forward logic." }, { "left": "pull_request:43999", "right": "pull_request:44025", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "Different model families and files; not the same concrete bug or change." }, { "left": "pull_request:43999", "right": "pull_request:44026", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "Same broad output-tracing cleanup, but the code paths are distinct encoder-decoder vs MobileNetV1." }, { "left": "pull_request:43999", "right": "pull_request:44027", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "These touch unrelated models; similarity is only at the refactor pattern level." }, { "left": "pull_request:44000", "right": "pull_request:44001", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "Vision-text dual encoder and UnivNet are separate implementations; not one shared fix." }, { "left": "pull_request:44000", "right": "pull_request:44002", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "Same refactor theme, but different model classes and output paths." }, { "left": "pull_request:44000", "right": "pull_request:44003", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." - }, - { - "left": "pull_request:44000", - "right": "pull_request:44004", - "accept": false, - "reason": "Different code paths and files; both mention output tracing, but they are separate model changes." + "reason": "Different subsystems and model families; not plausibly merged into one PR." }, { "left": "pull_request:44000", "right": "pull_request:44025", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "Both are output-tracing refactors, but for unrelated model code paths." }, { "left": "pull_request:44001", "right": "pull_request:44002", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "UnivNet and UperNet are unrelated models; only the refactor pattern matches." }, { "left": "pull_request:44001", "right": "pull_request:44003", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." - }, - { - "left": "pull_request:44001", - "right": "pull_request:44004", - "accept": false, - "reason": "Different code paths and files; both mention output tracing, but they are separate model changes." + "reason": "Different model stacks and forward implementations; not a duplicate." }, { "left": "pull_request:44001", "right": "pull_request:44025", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." - }, - { - "left": "pull_request:44001", - "right": "pull_request:46106", - "accept": false, - "reason": "Unrelated docs toctree change, not an output-tracing refactor." - }, - { - "left": "pull_request:44002", - "right": "pull_request:44003", - "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." - }, - { - "left": "pull_request:44002", - "right": "pull_request:44004", - "accept": false, - "reason": "Different code paths and files; both mention output tracing, but they are separate model changes." + "reason": "These are separate model-specific refactors, not the same underlying change." }, { "left": "pull_request:44002", "right": "pull_request:44029", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "UperNet and RWKV are unrelated code paths; similarity is only conceptual." }, { "left": "pull_request:44002", - "right": "pull_request:46106", - "accept": false, - "reason": "Unrelated docs toctree change, not an output-tracing refactor." - }, - { - "left": "pull_request:44003", - "right": "pull_request:44004", + "right": "pull_request:44003", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "Different model families and files; not the same fix." }, { "left": "pull_request:44003", "right": "pull_request:44028", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "Mamba/Falcon-Mamba and SuperPoint are unrelated code paths, so this is not a duplicate." }, { "left": "pull_request:44003", - "right": "pull_request:44030", + "right": "pull_request:44004", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "Both refactor outputs, but CodeGen and Mamba address different model internals and cannot be one PR." }, { "left": "pull_request:43998", "right": "pull_request:44004", "accept": false, - "reason": "Different code paths and files; both mention output tracing, but they are separate model changes." + "reason": "Timm backbone and CodeGen are unrelated models; not the same concrete change." }, { "left": "pull_request:44001", "right": "pull_request:44004", "accept": false, - "reason": "Different code paths and files; both mention output tracing, but they are separate model changes." + "reason": "UnivNet and CodeGen have different forward logic and output semantics." }, { "left": "pull_request:44002", "right": "pull_request:44004", "accept": false, - "reason": "Different code paths and files; both mention output tracing, but they are separate model changes." + "reason": "UperNet segmentation and CodeGen are unrelated implementations; not a duplicate." }, { "left": "pull_request:44000", "right": "pull_request:44004", "accept": false, - "reason": "Different code paths and files; both mention output tracing, but they are separate model changes." + "reason": "Vision-text dual encoder and CodeGen are separate code paths; only the refactor style is shared." }, { "left": "pull_request:44025", "right": "pull_request:44026", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "Depth Anything and Vision-Encoder-Decoder are different model families; same theme, different change." }, { "left": "pull_request:44025", "right": "pull_request:44027", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "Different encoder-decoder models with distinct forward paths; not mergeable as one fix." }, { "left": "pull_request:44025", "right": "pull_request:44028", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "Depth Anything and SuperPoint are unrelated model implementations." }, { "left": "pull_request:44025", "right": "pull_request:44029", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "Different models and output structures; only the refactor motif matches." }, { "left": "pull_request:44025", "right": "pull_request:44030", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "Depth Anything and DPR are separate code paths, so this is not a duplicate PR." }, { "left": "pull_request:44026", - "right": "pull_request:44027", + "right": "pull_request:44029", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "Vision-Encoder-Decoder and RWKV are unrelated models; not the same underlying change." }, { "left": "pull_request:44026", - "right": "pull_request:44028", + "right": "pull_request:44027", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "Both are model refactors, but for different encoder-decoder stacks and code paths." }, { "left": "pull_request:44026", - "right": "pull_request:44029", + "right": "pull_request:44028", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "Different model families and forward methods; not a duplicate." }, { "left": "pull_request:44026", "right": "pull_request:44030", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." - }, - { - "left": "pull_request:44026", - "right": "pull_request:46106", - "accept": false, - "reason": "Unrelated docs toctree change, not an output-tracing refactor." + "reason": "Vision-Encoder-Decoder and DPR do not share the same code path or fix." }, { "left": "pull_request:44027", "right": "pull_request:44028", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "Speech-Encoder-Decoder and SuperPoint are unrelated implementations; similarity is only superficial." }, { "left": "pull_request:44027", "right": "pull_request:44029", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "Different model stacks; not the same concrete bug or change." }, { "left": "pull_request:44027", "right": "pull_request:44030", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." - }, - { - "left": "pull_request:44027", - "right": "pull_request:46106", - "accept": false, - "reason": "Unrelated docs toctree change, not an output-tracing refactor." + "reason": "Speech-Encoder-Decoder and DPR are separate code paths, so not a duplicate." }, { "left": "pull_request:44028", "right": "pull_request:44029", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "SuperPoint and RWKV are unrelated models; this is only a shared refactor pattern." }, { "left": "pull_request:44028", "right": "pull_request:44030", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "Different model domains and forward logic; not mergeable as one PR." }, { "left": "pull_request:44029", "right": "pull_request:44030", "accept": false, - "reason": "Different model families and files; same refactor theme but not the same concrete change." + "reason": "RWKV and DPR are distinct model implementations, not the same underlying fix." + }, + { + "left": "pull_request:44027", + "right": "pull_request:46106", + "accept": false, + "reason": "Model output-tracing refactor vs docs toctree edit; completely different change." + }, + { + "left": "pull_request:44026", + "right": "pull_request:46106", + "accept": false, + "reason": "A docs navigation tweak is unrelated to encoder-decoder output tracing." + }, + { + "left": "pull_request:44001", + "right": "pull_request:46106", + "accept": false, + "reason": "UnivNet model refactor and docs toctree change are unrelated." + }, + { + "left": "pull_request:44002", + "right": "pull_request:46106", + "accept": false, + "reason": "UperNet output tracing and docs navigation changes are not the same issue." + }, + { + "left": "pull_request:43998", + "right": "pull_request:46106", + "accept": false, + "reason": "Timm backbone refactor vs docs toctree edit; no shared underlying change." } ] }, @@ -19767,52 +19738,52 @@ "pull_request:44662|pull_request:45075", "pull_request:45075|pull_request:45401" ], - "prepared_review_unit_hash": "7625955c16f8b35bb35b75d769b140bf1fb46062d2064b99f7419714bcd66749", + "prepared_review_unit_hash": "9ce3da2c82805116caba8aeb7667de2017c21ecf7fa607735fe439e7600f1810", "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": 10914, + "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": 10914, + "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-addition PRs for unrelated models; the overlap is mostly boilerplate docs, auto-registry wiring, and tests, not a shared bug or the same change.", + "summary": "All three pull requests are separate model-onboarding changes for different architectures (PenguinVL, DeepSeek-OCR-2, and Voxtral TTS). They share framework boilerplate and auto-registration updates, but they do not fix the same code-path problem and should not be merged as duplicates.", "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": null, + "canonical_pr_reason": "No canonical PR: these are distinct model-addition PRs for different models, with different configs, model files, processors, and tests.", "best_issue_reason": null, - "best_pr_reason": "PR 45075 is the strongest representative if one must be picked: it is a substantial, non-draft model integration with high review activity and broad implementation coverage, but it is still not a duplicate of the others.", + "best_pr_reason": "PR #45075 is the strongest representative only in the sense of being the most complete model onboarding patch (includes conversion script, image processing variants, and broad integration work), but it is not a duplicate of the others.", "soft_edge_verdicts": [ { "left": "pull_request:44662", "right": "pull_request:45401", "accept": false, - "reason": "Different model integrations (PenguinVL vs Voxtral TTS); shared files are only generic auto-registry/docs plumbing, not the same underlying code-path change." + "reason": "Different models and different functionality: PenguinVL implementation vs Voxtral TTS support. Shared auto-registration/docs scaffolding is generic boilerplate, not the same underlying change." }, { "left": "pull_request:44662", "right": "pull_request:45075", "accept": false, - "reason": "Both add separate vision-language models, but they target different models and implementations; shared files are generic registration/docs changes, so this is not a duplicate PR." + "reason": "Both are model additions, but for unrelated models (PenguinVL vs DeepSeek-OCR-2) with different model code, processors, and tests; not the same bug or change." }, { "left": "pull_request:45075", "right": "pull_request:45401", "accept": false, - "reason": "DeepSeek-OCR-2 and Voxtral TTS are unrelated model additions with distinct architecture and code paths; overlap is limited to standard Transformers integration scaffolding." + "reason": "DeepSeek-OCR-2 and Voxtral TTS are distinct model ports with different code paths and file sets. Overlap in shared Transformers registry files is expected and not sufficient for duplication." } ] }, @@ -19842,12 +19813,12 @@ "soft_pairs": [ "pull_request:44979|pull_request:45363" ], - "prepared_review_unit_hash": "596f4bbf30794e0eb641bf5f03fcdd76a6804a515b83d58d1708bb3a3ade686a", + "prepared_review_unit_hash": "ddb908bc2c2ad10573767698cff54a4cc09e4bfeab13b0514437cdbbc937f8e1", "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 }, @@ -19855,7 +19826,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4407, + "serialized_chars": 4408, "estimated_input_tokens": 1102, "estimated_eval_tokens": 2460 }, @@ -19864,18 +19835,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are related to kernel/module fusion, but they target different abstractions and code paths: one introduces a generic Module Fusion API, while the other adds n-to-1 fusion through KernelConfig and integration hooks. They are not duplicates.", - "confidence": 0.86, + "summary": "These are related fusion-feature PRs, but they target different layers of the stack: one adds a generic module-fusion API, while the other wires KernelConfig-driven n-to-1 kernel fusion into model loading/integration code. They are not the same underlying change and would not plausibly be merged into one PR as duplicates.", + "confidence": 0.88, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #44979 is the cleaner core API proposal: it adds a new `module_fusion.py` module plus tests, centered on the fusion abstraction itself. It is more canonical for the general feature area than the more specialized kernel-config integration PR.", + "canonical_pr_reason": "PR #45363 is the broader, more user-facing feature work: it threads KernelConfig-based fusion through loading/integration paths and adds an example, making it the better representative PR for this cluster.", "best_issue_reason": null, - "best_pr_reason": "PR #45363 is the most complete user-facing implementation in this cluster: it wires fusion into `modeling_utils`, `integrations`, and `KernelConfig`, and includes a runnable example. It is the strongest standalone PR, though it addresses a different mechanism than #44979.", + "best_pr_reason": "PR #45363 is the strongest standalone PR in the cluster because it covers the end-to-end kernel-fusion flow, not just the lower-level fusion primitive.", "soft_edge_verdicts": [ { "left": "pull_request:44979", "right": "pull_request:45363", "accept": false, - "reason": "They both concern fusion, but #44979 is a generic module fusion API while #45363 implements n-to-1 kernel fusion via `KernelConfig` and integration plumbing. Different concrete mechanisms and merge targets." + "reason": "Related fusion infrastructure, but not the same concrete change: #44979 introduces a generic module fusion API, while #45363 implements KernelConfig-based n-to-1 kernel fusion and model integration. Different code paths and different deliverables." } ] }, @@ -19905,7 +19876,7 @@ "soft_pairs": [ "pull_request:45086|pull_request:45317" ], - "prepared_review_unit_hash": "7f07bf70f36bbd57c88a72d1d42bacce5b6a391334cfcd97cf2c3b03a1ee0798", + "prepared_review_unit_hash": "0318b8c1f01b668dbf8de1b6494e3f882a32eee2de79063bfd6c92196d92ff02", "component_budget": { "node_count": 2, "item_count": 2, @@ -19927,18 +19898,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs fix the same _patch_mistral_regex AttributeError by switching from backend_tokenizer.pre_tokenizer to tokenizer.pre_tokenizer; 45317 is the more complete later patch with tests.", - "confidence": 0.99, + "summary": "Both pull requests fix the same concrete Mistral regex patching AttributeError in the same code path, and the later PR 45317 appears to be the more complete version with tests.", + "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "pull_request:45317 is the stronger canonical PR: it targets the same bug as 45086, adds tests, and appears to be the fuller implementation of the same fix.", + "canonical_pr_reason": "PR 45317 is the better canonical PR because it implements the same fix as 45086 and adds test coverage in the same area.", "best_issue_reason": null, - "best_pr_reason": "pull_request:45317 is the best representative PR because it covers the same concrete code-path bug and includes test coverage, making it the most complete version of the fix.", + "best_pr_reason": "PR 45317 is the strongest representative of the cluster since it contains the same code fix plus validation tests.", "soft_edge_verdicts": [ { "left": "pull_request:45086", "right": "pull_request:45317", "accept": true, - "reason": "Same underlying AttributeError fix in the same file and code path; the diff is effectively the same change, with 45317 adding tests." + "reason": "Same underlying bug and same file-level fix: both replace backend_tokenizer.pre_tokenizer access with tokenizer.pre_tokenizer to avoid the AttributeError in _patch_mistral_regex; the later PR adds tests and looks like the merged-into-one version." } ] }, @@ -19968,7 +19939,7 @@ "soft_pairs": [ "pull_request:45115|pull_request:45569" ], - "prepared_review_unit_hash": "aedcce9b4cec296758b56f74354b0392bf5007111dadac7f3e7377e232196dc6", + "prepared_review_unit_hash": "a0d32dbf900967b20dd8a2eb632d3209833b81316aed3f16ba8f00e1ef6ea8d1", "component_budget": { "node_count": 2, "item_count": 2, @@ -19990,18 +19961,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two PRs touch Nemotron H files, but they are different changes: one is a base-model refactor/conversion-mapping update, the other is a broader split into NemotronH dense/sparse models with docs and tests. They should not be treated as duplicates.", - "confidence": 0.82, + "summary": "Two related NemotronH pull requests, but they address different changes: one is a conversion/refactor PR for NemotronH-to-GraniteMoeHybrid style mapping, while the other splits NemotronH into dense and sparse model variants with docs/tests updates.", + "confidence": 0.9, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45569 is the better canonical PR because it is the broader, more complete implementation of the Nemotron H model split (dense/sparse wrappers, docs, auto mappings, tests), while PR 45115 is a narrower refactor focused on inheritance and conversion mapping.", + "canonical_pr_reason": "PR 45569 is the better canonical PR because it is the broader, more complete architecture change and includes the user-facing docs/test surface; PR 45115 is a narrower conversion-mapping refactor.", "best_issue_reason": null, - "best_pr_reason": "PR 45569 is the strongest representative of the cluster: it contains the main user-facing model restructuring and supporting documentation/tests. PR 45115 is a separate, narrower code-path refactor and not a duplicate.", + "best_pr_reason": "PR 45569 best represents the cluster since it introduces the new dense/sparse NemotronH model family and associated documentation, which is the larger end-state change in this set.", "soft_edge_verdicts": [ { "left": "pull_request:45115", "right": "pull_request:45569", "accept": false, - "reason": "They overlap on Nemotron H base files, but the concrete changes differ: 45115 is a refactor/conversion-mapping and inheritance update, while 45569 adds dense/sparse model variants, docs, auto mappings, and tests. Not the same underlying fix and not a single PR candidate." + "reason": "They share NemotronH files, but the concrete changes differ: 45115 updates checkpoint conversion and internal inheritance/mapping, while 45569 introduces separate dense/sparse model packages, docs, and tests. These are distinct code paths and not the same fix." } ] }, @@ -20031,7 +20002,7 @@ "soft_pairs": [ "pull_request:45332|pull_request:45333" ], - "prepared_review_unit_hash": "71fc5528e0b8f779659676eed86bec33dfa58af2ac4ef81de8bf0c7448f04f9a", + "prepared_review_unit_hash": "b84a21632379376bce376ce6126e669c3411561e3490420576a181c29c99c5c8", "component_budget": { "node_count": 2, "item_count": 2, @@ -20053,18 +20024,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two related but distinct feature PRs: one introduces heterogeneous per-layer config plumbing, the other adds broader heterogeneous model/runtime support on top. They share infrastructure files but are not the same concrete change, so they should not be merged as duplicates.", - "confidence": 0.92, + "summary": "Two related but distinct feature PRs: one adds heterogeneous per-layer config support, the other adds heterogeneous modeling/runtime support that consumes that config. They overlap in files and theme, but they are not duplicates of the same change.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45332 is the broader umbrella change and the better representative of the cluster: it extends the feature into cache, masking, and model code paths, whereas #45333 is limited to per-layer config plumbing.", + "canonical_pr_reason": "PR #45332 is the broader, more end-to-end change: it adds heterogeneous model/runtime support across cache, masking, modeling, and GPT-OSS code paths, building on the config primitives. It is the better representative of the feature cluster.", "best_issue_reason": null, - "best_pr_reason": "PR #45332 is the strongest single PR to represent this cluster because it covers the larger end-to-end heterogeneous model support effort and contains the most complete implementation surface.", + "best_pr_reason": "PR #45332 is the stronger anchor for the cluster because it exercises the new heterogeneous config in concrete model execution paths and spans the larger user-facing change set.", "soft_edge_verdicts": [ { "left": "pull_request:45332", "right": "pull_request:45333", "accept": false, - "reason": "Related feature work, but not the same underlying change. #45333 adds per-layer config support; #45332 adds model/runtime support that builds on heterogeneous config. They could land in sequence, not as one duplicate PR." + "reason": "Related feature work, but not the same underlying change. #45333 introduces per-layer heterogeneous config plumbing; #45332 adds heterogeneous modeling/runtime support that consumes such configs. They touch the same subsystem, but they would not be duplicates or a single fix for one concrete code-path bug." } ] }, @@ -20094,12 +20065,12 @@ "soft_pairs": [ "pull_request:45415|pull_request:45425" ], - "prepared_review_unit_hash": "b22e43170fd6bbee7deecd104c7ab5a6d10424e633b1442eb78c052cb1776955", + "prepared_review_unit_hash": "cf1f79e3ab618fd6f9e346372674f383ad58c36bb39b1e0283e58d96130fc486", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5513, + "serialized_chars": 5514, "estimated_input_tokens": 1379, "estimated_eval_tokens": 3014 }, @@ -20107,7 +20078,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5513, + "serialized_chars": 5514, "estimated_input_tokens": 1379, "estimated_eval_tokens": 3014 }, @@ -20116,18 +20087,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs are typing-focused, but they are different changes: #45415 is a broad type-checking sweep across many modules plus pyproject config, while #45425 adds specific typing helpers/protocols for modeling_utils/PEFT-related code. The overlap is incidental, not the same underlying fix.", + "summary": "These are both typing-related PRs, but they target different changes: one is a broad type-checking sweep across many transformer files, while the other adds specific typing helpers/protocols for modeling-related code. They do not look like the same underlying fix.", "confidence": 0.91, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45425 is the more self-contained, focused typing change; PR #45415 is a much broader repo-wide type-checking sweep.", + "canonical_pr_reason": "No single canonical PR: 45415 is a broad type-checking cleanup, while 45425 is a focused typing-helper/refactor PR; they are related but not duplicates.", "best_issue_reason": null, - "best_pr_reason": "PR #45425 is the best representative of the cluster because it makes a concrete typing-infrastructure change in a narrower code path, whereas #45415 is a large mixed typing cleanup.", + "best_pr_reason": "45425 is the more self-contained and concrete PR, with a narrower code change centered on new typing protocols and helpers.", "soft_edge_verdicts": [ { "left": "pull_request:45415", "right": "pull_request:45425", "accept": false, - "reason": "Shared files are incidental; #45415 is a broad type-checking sweep, while #45425 adds specific typing protocols/helpers for different code paths. They are not the same concrete change and would not plausibly merge into one PR." + "reason": "Both are typing work, but the scopes differ materially: 45415 is a broad mypy/type-checking sweep across many files, whereas 45425 adds targeted typing abstractions and support in modeling_utils/peft. They do not fix the same concrete problem and would not reasonably merge into one duplicate PR." } ] }, @@ -20161,52 +20132,52 @@ "pull_request:46109|pull_request:46151", "pull_request:46135|pull_request:46151" ], - "prepared_review_unit_hash": "00963de295bad7b69ebeffc1381f45996e149fc4a321a2c49074ac12e1f8d83d", + "prepared_review_unit_hash": "fe9c0b0fd9318120df780bce51a1aa4c2753f406d4fcee51f397fb7b1d11d3cb", "component_budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 3, - "serialized_chars": 9913, - "estimated_input_tokens": 2479, - "estimated_eval_tokens": 5214 + "serialized_chars": 9912, + "estimated_input_tokens": 2478, + "estimated_eval_tokens": 5212 }, "budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 3, - "serialized_chars": 9913, - "estimated_input_tokens": 2479, - "estimated_eval_tokens": 5214 + "serialized_chars": 9912, + "estimated_input_tokens": 2478, + "estimated_eval_tokens": 5212 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are not duplicates of one another: they cover different code paths and different kinds of changes (AltCLIP/ChineseCLIP model-parallel bugfixes, distributed trainer test parity tweaks, Kosmos2.5 integration-test expectations, and pipeline token-classification expectations).", - "confidence": 0.96, + "summary": "These are four unrelated open PRs: one model-parallel fix for AltCLIP/ChineseCLIP, one distributed trainer test generalization, one Kosmos2.5 XPU integration-test adjustment, and one token-classification pipeline expectation update. The soft similarity is only broad testing/accelerator overlap, not the same underlying change.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "No single canonical PR: the cluster mixes unrelated fixes, so there is no one artifact that subsumes the others.", + "canonical_pr_reason": "No true canonical duplicate exists in this cluster; PR 46151 is the cleanest representative only because it is the most self-contained test-expectation update, but it does not match the others\u2019 concrete change.", "best_issue_reason": null, - "best_pr_reason": "PR 45487 is the strongest standalone change because it fixes a concrete runtime bug in model code; the others are narrower test-expected-output adjustments in unrelated areas.", + "best_pr_reason": "PR 46151 is the most focused and understandable single change in the set, but it is not a duplicate of the others and should not be used to merge the cluster.", "soft_edge_verdicts": [ { "left": "pull_request:45487", "right": "pull_request:46151", "accept": false, - "reason": "Different features and code paths: AltCLIP/ChineseCLIP model-parallel device handling vs token-classification pipeline test expectations." + "reason": "Different targets and bugs: model-parallel token_type_ids/device handling in AltCLIP/ChineseCLIP vs token-classification pipeline test expectations." }, { "left": "pull_request:46109", "right": "pull_request:46151", "accept": false, - "reason": "Both are test-only, but they target different subsystems and issues: distributed trainer device-string parity vs pipeline token-classification expectations." + "reason": "Both touch tests, but one generalizes distributed trainer device assertions while the other adds pipeline token-classification expectations; not the same concrete change." }, { "left": "pull_request:46135", "right": "pull_request:46151", "accept": false, - "reason": "Kosmos2.5 integration-test expectations are unrelated to token-classification pipeline expectations; not the same underlying change." + "reason": "Both adjust accelerator-specific test expectations, but for different models and behaviors (Kosmos2.5 integration vs token classification pipeline); not mergeable as one PR." } ] }, @@ -20238,12 +20209,12 @@ "pull_request:45513|pull_request:46084", "pull_request:46084|pull_request:46098" ], - "prepared_review_unit_hash": "5a4046297a4240a7284b1773aaf360039955d995c9829af3ec0b8cc726524609", + "prepared_review_unit_hash": "7e593779429368ea08183ccdd6f6978b31c7cc2b25eb36fa4f337e24e44dfe61", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 7426, + "serialized_chars": 7427, "estimated_input_tokens": 1857, "estimated_eval_tokens": 3970 }, @@ -20251,7 +20222,7 @@ "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 7426, + "serialized_chars": 7427, "estimated_input_tokens": 1857, "estimated_eval_tokens": 3970 }, @@ -20260,30 +20231,30 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two PRs are about the same Mamba2 `use_cache`/`seq_len > 1` bug; the Qwen3.5 PR is a different model and code path. PR #46098 is the best representative because it is the most complete Mamba2 fix and explicitly targets the tracked issue.", - "confidence": 0.92, + "summary": "The cluster contains two unrelated PRs for cached-forward bugs: one in Qwen/Olmo hybrid attention and one in Mamba2. Only the two Mamba2 PRs appear to target the same underlying seq_len>1 cache bug; the Qwen/Olmo PR is separate.", + "confidence": 0.95, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #46098 is the cleanest representative of the duplicated Mamba2 bug fix: it explicitly targets issue #46032, covers the seq_len>1 cached path comprehensively, and includes tests/docs. PR #46084 is a narrower variant of the same fix, while #45513 is unrelated.", + "canonical_pr_reason": "PR 46098 is the best representative of the Mamba2 fix: it addresses the seq_len>1 use_cache bug directly, includes regression coverage, and documents the behavior change. PR 46084 is a narrower implementation-only slice of the same underlying fix.", "best_issue_reason": null, - "best_pr_reason": "PR #46098 is the best global PR candidate because it directly addresses the tracked Mamba2 cache bug with the broadest fix surface and validation, making it the most complete canonical change among the set.", + "best_pr_reason": "PR 46098 is the strongest global representative because its title and diff align most clearly with the full Mamba2 cached-forward bug, while 46084 looks like a partial/smaller patch to the same code path.", "soft_edge_verdicts": [ { "left": "pull_request:45513", "right": "pull_request:46084", "accept": false, - "reason": "Different models and bugs: Qwen3.5 linear-attention cached forward vs. Mamba2 `use_cache` handling. Similar symptom, but not the same concrete code-path change and not mergeable into one PR." + "reason": "Different models and different bugs: 45513 is about Qwen3.5/related hybrid cached multi-token forward behavior, while 46084 fixes Mamba2 use_cache when seq_len>1." }, { "left": "pull_request:46084", "right": "pull_request:46098", "accept": true, - "reason": "Same underlying Mamba2 `use_cache` with `seq_len > 1` bug on the same code path, with #46098 essentially extending/subsuming the narrower fix in #46084." + "reason": "Same underlying Mamba2 cache bug in the same code path (use_cache with seq_len>1); 46098 appears to be a fuller version with docs/tests around the same fix, so they could plausibly be merged into one PR." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet: 45513 is clearly a different Qwen3.5-related PR, while 46084 and 46098 share the same Mamba2 issue target and files. The soft-edge verdicts are conservative, and treating 46084 and 46098 as mergeable for the same bugfix is supported by the evidence." + "feedback": "The summary is grounded in the packet: PR 45513 is a separate model family and bug from the Mamba2 fixes, while 46084 and 46098 share the same issue target (46032), filenames, and seq_len>1 use_cache bug. The soft-edge verdicts are conservative enough, and the 46084/46098 pair looks mergeable into a single PR for the same bugfix." }, "evaluator_used": true, "retried": false, @@ -20310,7 +20281,7 @@ "soft_pairs": [ "pull_request:45548|pull_request:45662" ], - "prepared_review_unit_hash": "9555e949d36abd8cbf394499ae8b8d9b20a049de2a1d36b6be7fe651e85be000", + "prepared_review_unit_hash": "1d670eb6bd04fb8d8cc38bdcbbfa9e16321f3d257ee580ded6ea7fa2547a0921", "component_budget": { "node_count": 2, "item_count": 2, @@ -20332,18 +20303,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open PRs touch expert-parallel loading, but they fix different bugs: one is about preserving distributed_config / EP state when loading via accelerate+ZeRO-3, the other is about preventing expert weights from being overwritten by rank-0 broadcast under FSDP2.", - "confidence": 0.91, + "summary": "Both PRs concern expert-parallel loading paths, but they target different failure modes and distributed backends: one fixes EP + DeepSpeed ZeRO-3 loading via accelerate launch, the other fixes EP + FSDP2 where experts are overwritten by rank-0 broadcast. Related area, not the same underlying change.", + "confidence": 0.88, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45662 is the better cluster representative because it addresses a concrete EP/FSDP2 overwrite path with broader code impact; PR 45548 is a separate, narrower accelerate/ZeRO-3 configuration-loading fix.", + "canonical_pr_reason": "PR 45662 is the more concrete and self-contained fix: it addresses a specific expert-parallel parameter loading corruption path and touches the loader where the bug occurs.", "best_issue_reason": null, - "best_pr_reason": "PR 45662 is the strongest standalone PR in this set: it targets the actual expert-parameter overwrite failure mode across multiple loading modules, while 45548 is a smaller serialization/loading adjustment.", + "best_pr_reason": "PR 45662 is the better representative of the cluster because it fixes the more explicit code-path bug and has a clearer, narrower technical scope than the configuration/property tweak in 45548.", "soft_edge_verdicts": [ { "left": "pull_request:45548", "right": "pull_request:45662", "accept": false, - "reason": "Both are about expert parallelism, but the underlying bugs differ: 45548 fixes EP state/config handling during accelerate+ZeRO-3 loading, while 45662 fixes experts being overwritten by rank-0 broadcast in FSDP2. They would not be merged into one PR." + "reason": "They share the EP/distributed-loading theme, but the bugs differ: 45548 is about EP + DeepSpeed ZeRO-3/accelerate config handling, while 45662 is about EP + FSDP2 parameter overwrites during sharded loading. Not the same concrete fix and not safely mergeable into one PR." } ] }, @@ -20373,12 +20344,12 @@ "soft_pairs": [ "pull_request:45639|pull_request:45645" ], - "prepared_review_unit_hash": "cc6329d876355e0560bfba5d39a6ed1d4b8816e5eaac13c5a613de81142a9761", + "prepared_review_unit_hash": "ead192a85047a3a477fc0df20f2d0255c49773304ee9a686e495f2a787800c14", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4589, + "serialized_chars": 4590, "estimated_input_tokens": 1148, "estimated_eval_tokens": 2552 }, @@ -20386,7 +20357,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4589, + "serialized_chars": 4590, "estimated_input_tokens": 1148, "estimated_eval_tokens": 2552 }, @@ -20395,18 +20366,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both pull requests address the same xdist-related captured_info artifact collision problem; PR 45645 is the broader, more complete version that also updates CI log collection. PR 45639 looks like a narrower subset of the same fix.", - "confidence": 0.88, + "summary": "Both PRs target the same captured_info/xdist collision problem, but PR 45645 is the broader, more complete fix: it includes the xdist-safe testing_utils change plus CI workflow updates to preserve and print multiple captured_info files. PR 45639 is a narrower subset of that same change.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45645 is the better canonical candidate because it includes the core xdist-safe output-file change plus the CI workflow adjustment to collect multiple captured_info files, making it the more complete fix.", + "canonical_pr_reason": "PR 45645 is the best canonical PR because it covers the core xdist-safe artifact fix and the downstream CI/reporting changes needed to consume the new per-worker captured_info files.", "best_issue_reason": null, - "best_pr_reason": "PR 45645 is the best overall PR because it addresses the underlying collision bug and also preserves debug-log visibility in CI, whereas PR 45639 only covers the output-file side of the change.", + "best_pr_reason": "PR 45645 is the strongest representative of the cluster: same underlying bug, same shared testing_utils/test changes, and additional workflow handling that makes the fix complete.", "soft_edge_verdicts": [ { "left": "pull_request:45639", "right": "pull_request:45645", "accept": true, - "reason": "Both PRs target the same concrete bug: xdist collisions for captured_info artifacts in testing_utils. PR 45645 appears to supersede the narrower implementation in 45639 with the same core fix plus CI handling." + "reason": "They fix the same concrete captured_info xdist collision path; 45645 appears to incorporate 45639\u2019s core testing_utils/test changes and adds CI log aggregation, so they could plausibly be merged into one PR." } ] }, @@ -20509,12 +20480,12 @@ "pull_request:46073|pull_request:46196", "pull_request:46154|pull_request:46196" ], - "prepared_review_unit_hash": "c749d9042e9101fc8ed99af5adbaebb8183df06ea9e3584be5091188b08b45b5", + "prepared_review_unit_hash": "a788a403e1fccb6d7fbe8637de0167202813b8cfcfed3f459c0a402edd9c8e53", "component_budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 10494, + "serialized_chars": 10496, "estimated_input_tokens": 2624, "estimated_eval_tokens": 5504 }, @@ -20522,7 +20493,7 @@ "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 10494, + "serialized_chars": 10496, "estimated_input_tokens": 2624, "estimated_eval_tokens": 5504 }, @@ -20531,48 +20502,48 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs all add SDPA/attention-dispatch support, but each targets a different model family and code path, so they are related feature ports rather than duplicates.", - "confidence": 0.98, + "summary": "All four PRs are about adding SDPA/attention-dispatch support, but each targets a different model family and code path, so they are related theme-wise rather than duplicates.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "No single canonical PR: each change is model-specific (ShieldGemma2, CTRL, T5, SeamlessM4T/v2) and would not be merged into one concrete fix.", + "canonical_pr_reason": "No single canonical duplicate PR: these are separate model-specific implementations (ShieldGemma2, CTRL, T5, SeamlessM4T/v2) rather than one change that could be merged into a single PR.", "best_issue_reason": null, - "best_pr_reason": "PR 46196 is the broadest representative because it covers both SeamlessM4T and SeamlessM4T v2, but it is still not a duplicate of the other model-specific dispatch PRs.", + "best_pr_reason": "PR 46196 is the best representative of the cluster because it is the most complete model-family update, covering both SeamlessM4T and SeamlessM4T v2 plus tests.", "soft_edge_verdicts": [ { "left": "pull_request:46069", "right": "pull_request:46073", "accept": false, - "reason": "Same general SDPA theme, but ShieldGemma2 and CTRL are different model implementations with separate dispatch paths." + "reason": "Same general SDPA theme, but they modify different model implementations (ShieldGemma2 vs CTRL) and cannot plausibly be merged as one fix." }, { "left": "pull_request:46069", "right": "pull_request:46154", "accept": false, - "reason": "Both add attention-dispatch support, but ShieldGemma2 and T5 are unrelated code paths and not one concrete bug fix." + "reason": "Both add attention-dispatch support, but they target unrelated model code paths (ShieldGemma2 vs T5) with different implementation details." }, { "left": "pull_request:46069", "right": "pull_request:46196", "accept": false, - "reason": "ShieldGemma2 image-classification attention dispatch is distinct from SeamlessM4T/v2 seq2seq attention dispatch." + "reason": "These are separate model-family changes; ShieldGemma2 image-classification attention dispatch is not the same underlying change as SeamlessM4T/v2 seq2seq attention dispatch." }, { "left": "pull_request:46073", "right": "pull_request:46154", "accept": false, - "reason": "CTRL and T5 are separate model families; this is the same feature class, not the same underlying PR change." + "reason": "CTRL and T5 are different architectures and model files; this is a shared feature theme, not the same concrete bug or change." }, { "left": "pull_request:46073", "right": "pull_request:46196", "accept": false, - "reason": "CTRL SDPA dispatch and SeamlessM4T/v2 SDPA dispatch touch different architectures and cannot plausibly be one merged fix." + "reason": "Different model families and code paths; support for CTRL sdpa dispatch is not duplicate work with SeamlessM4T/v2 dispatch support." }, { "left": "pull_request:46154", "right": "pull_request:46196", "accept": false, - "reason": "T5 and SeamlessM4T/v2 both add SDPA support, but they are independent model-specific implementations, not duplicates." + "reason": "Both are sdpa-dispatch PRs, but they fix distinct model implementations (T5-related vs SeamlessM4T/v2), so they should stay separate." } ] }, diff --git a/analysis/current/manifest.json b/analysis/current/manifest.json index 0137c8cd77e1b39a0fa66fc4af898987a072cb81..52ebed96068edd3fcf9ef847b715881a6e6580a9 100644 --- a/analysis/current/manifest.json +++ b/analysis/current/manifest.json @@ -1,8 +1,8 @@ { - "analysis_id": "hybrid-model-20260525t120039z", + "analysis_id": "hybrid-model-20260525t180030z", "archived_artifacts": { - "hybrid": "snapshots/20260525T120039Z/analysis-runs/hybrid-model-20260525t120039z/analysis-report-hybrid.json", - "hybrid_reviews": "snapshots/20260525T120039Z/analysis-runs/hybrid-model-20260525t120039z/analysis-report-hybrid.llm-reviews.json" + "hybrid": "snapshots/20260525T180030Z/analysis-runs/hybrid-model-20260525t180030z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260525T180030Z/analysis-runs/hybrid-model-20260525t180030z/analysis-report-hybrid.llm-reviews.json" }, "artifacts": { "hybrid": "analysis/current/analysis-report-hybrid.json", @@ -10,9 +10,9 @@ }, "channel": "canonical", "model": null, - "published_at": "2026-05-25T12:15:45Z", + "published_at": "2026-05-25T18:21:08Z", "repo": "huggingface/transformers", "schema_version": 1, - "snapshot_id": "20260525T120039Z", + "snapshot_id": "20260525T180030Z", "variant": "hybrid" } diff --git a/snapshots/20260525T180030Z/analysis-runs/hybrid-model-20260525t180030z/analysis-report-hybrid.json b/snapshots/20260525T180030Z/analysis-runs/hybrid-model-20260525t180030z/analysis-report-hybrid.json new file mode 100644 index 0000000000000000000000000000000000000000..11a5cf3d08eeb5d2829a8b43995a965eb3eeedac --- /dev/null +++ b/snapshots/20260525T180030Z/analysis-runs/hybrid-model-20260525t180030z/analysis-report-hybrid.json @@ -0,0 +1,2388 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260525T180030Z", + "generated_at": "2026-05-25T18:21:06Z", + "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-46032-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #46032.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 46032, + "canonical_pr_number": 46084, + "issue_numbers": [ + 46032 + ], + "pr_numbers": [ + 46084, + 46098 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 46084, + "right_pr_number": 46098, + "code_similarity": 0.43, + "size_similarity": 0.5, + "file_overlap": 0.667, + "area_overlap": 0.226, + "patch_similarity": 0.339, + "shared_filenames": [ + "src/transformers/models/mamba2/modeling_mamba2.py", + "tests/models/mamba2/test_modeling_mamba2.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/mamba2/modeling_mamba2.py", + "left_ranges": [ + [ + 256, + 262 + ], + [ + 303, + 353 + ], + [ + 461, + 467 + ], + [ + 471, + 491 + ], + [ + 496, + 502 + ], + [ + 599, + 609 + ] + ], + "right_ranges": [ + [ + 255, + 373 + ], + [ + 481, + 495 + ] + ] + }, + { + "filename": "tests/models/mamba2/test_modeling_mamba2.py", + "left_ranges": [ + [ + 206, + 236 + ], + [ + 285, + 322 + ] + ], + "right_ranges": [ + [ + 476, + 542 + ] + ] + } + ] + } + ] + }, + { + "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-45081-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45081.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 45081, + "canonical_pr_number": 45317, + "issue_numbers": [ + 45081 + ], + "pr_numbers": [ + 45086, + 45317 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 45086, + "right_pr_number": 45317, + "code_similarity": 0.589, + "size_similarity": 0.34, + "file_overlap": 0.5, + "area_overlap": 1.0, + "patch_similarity": 0.136, + "shared_filenames": [ + "src/transformers/tokenization_utils_tokenizers.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/tokenization_utils_tokenizers.py", + "left_ranges": [ + [ + 1360, + 1370 + ], + [ + 1374, + 1380 + ] + ], + "right_ranges": [ + [ + 1360, + 1370 + ], + [ + 1374, + 1380 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45561-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45561.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 45561, + "canonical_pr_number": 45645, + "issue_numbers": [ + 45561 + ], + "pr_numbers": [ + 45639, + 45645 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 45639, + "right_pr_number": 45645, + "code_similarity": 0.532, + "size_similarity": 0.619, + "file_overlap": 0.5, + "area_overlap": 0.543, + "patch_similarity": 0.451, + "shared_filenames": [ + "src/transformers/testing_utils.py", + "tests/utils/test_testing_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/testing_utils.py", + "left_ranges": [ + [ + 3529, + 3536 + ], + [ + 3753, + 3787 + ] + ], + "right_ranges": [ + [ + 3525, + 3558 + ], + [ + 3782, + 3788 + ] + ] + }, + { + "filename": "tests/utils/test_testing_utils.py", + "left_ranges": [ + [ + 1, + 86 + ] + ], + "right_ranges": [ + [ + 1, + 114 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43698-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #43698.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 43698, + "canonical_pr_number": 43779, + "issue_numbers": [ + 43698 + ], + "pr_numbers": [ + 43779, + 43816 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 43779, + "right_pr_number": 43816, + "code_similarity": 0.418, + "size_similarity": 0.538, + "file_overlap": 1.0, + "area_overlap": 0.02, + "patch_similarity": 0.02, + "shared_filenames": [ + "src/transformers/integrations/integration_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/integrations/integration_utils.py", + "left_ranges": [ + [ + 2227, + 2241 + ], + [ + 2303, + 2309 + ] + ], + "right_ranges": [ + [ + 2278, + 2291 + ], + [ + 2309, + 2322 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43612-2", + "summary": "Cluster of 2 related pull requests linked by soft_similarity.", + "status": "open", + "confidence": 0.5, + "canonical_issue_number": null, + "canonical_pr_number": 43612, + "issue_numbers": [], + "pr_numbers": [ + 43612, + 43613 + ], + "evidence_types": [ + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 43612, + "right_pr_number": 43613, + "code_similarity": 0.6, + "size_similarity": 0.822, + "file_overlap": 0.333, + "area_overlap": 0.698, + "patch_similarity": 0.608, + "shared_filenames": [ + "docs/source/en/_toctree.yml", + "docs/source/en/main_classes/pipelines.md", + "docs/source/en/model_doc/auto.md", + "src/transformers/__init__.py", + "src/transformers/models/auto/modeling_auto.py", + "src/transformers/pipelines/__init__.py", + "utils/check_docstrings.py", + "utils/update_metadata.py" + ], + "shared_file_areas": [ + { + "filename": "docs/source/en/_toctree.yml", + "left_ranges": [ + [ + 335, + 342 + ] + ], + "right_ranges": [ + [ + 309, + 316 + ] + ] + }, + { + "filename": "docs/source/en/main_classes/pipelines.md", + "left_ranges": [ + [ + 473, + 484 + ] + ], + "right_ranges": [ + [ + 473, + 484 + ] + ] + }, + { + "filename": "docs/source/en/model_doc/auto.md", + "left_ranges": [ + [ + 113, + 122 + ] + ], + "right_ranges": [ + [ + 113, + 122 + ] + ] + }, + { + "filename": "src/transformers/__init__.py", + "left_ranges": [ + [ + 155, + 161 + ], + [ + 664, + 670 + ] + ], + "right_ranges": [ + [ + 155, + 161 + ], + [ + 664, + 670 + ] + ] + }, + { + "filename": "src/transformers/models/auto/modeling_auto.py", + "left_ranges": [ + [ + 1629, + 1642 + ], + [ + 1807, + 1816 + ], + [ + 1840, + 1849 + ], + [ + 2186, + 2192 + ], + [ + 2233, + 2239 + ] + ], + "right_ranges": [ + [ + 1629, + 1646 + ], + [ + 1811, + 1820 + ], + [ + 1844, + 1853 + ], + [ + 2190, + 2196 + ], + [ + 2237, + 2243 + ] + ] + }, + { + "filename": "src/transformers/pipelines/__init__.py", + "left_ranges": [ + [ + 71, + 77 + ], + [ + 108, + 114 + ], + [ + 300, + 311 + ], + [ + 446, + 453 + ] + ], + "right_ranges": [ + [ + 71, + 77 + ], + [ + 108, + 114 + ], + [ + 300, + 311 + ], + [ + 446, + 453 + ] + ] + }, + { + "filename": "utils/check_docstrings.py", + "left_ranges": [ + [ + 109, + 115 + ] + ], + "right_ranges": [ + [ + 109, + 115 + ] + ] + }, + { + "filename": "utils/update_metadata.py", + "left_ranges": [ + [ + 74, + 84 + ] + ], + "right_ranges": [ + [ + 74, + 84 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-46100-2", + "summary": "Cluster of 2 related pull requests linked by soft_similarity.", + "status": "open", + "confidence": 0.5, + "canonical_issue_number": null, + "canonical_pr_number": 46100, + "issue_numbers": [], + "pr_numbers": [ + 46100, + 46114 + ], + "evidence_types": [ + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 46100, + "right_pr_number": 46114, + "code_similarity": 1.0, + "size_similarity": 1.0, + "file_overlap": 1.0, + "area_overlap": 1.0, + "patch_similarity": 1.0, + "shared_filenames": [ + "tests/models/vit/test_modeling_vit.py" + ], + "shared_file_areas": [ + { + "filename": "tests/models/vit/test_modeling_vit.py", + "left_ranges": [ + [ + 216, + 226 + ] + ], + "right_ranges": [ + [ + 216, + 226 + ] + ] + } + ] + } + ] + }, + { + "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-43612-2", + "canonical_pr_number": 43612, + "duplicate_pr_numbers": [ + 43613 + ], + "target_issue_number": null, + "reason": "PRs in cluster-43612-2 are treated as duplicates because they share soft_similarity 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-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-46032-3", + "canonical_pr_number": 46084, + "duplicate_pr_numbers": [ + 46098 + ], + "target_issue_number": 46032, + "reason": "PRs in cluster-46032-3 are treated as duplicates because they converge on issue #46032 with closing_reference, shared_issue_target evidence." + }, + { + "cluster_id": "cluster-46100-2", + "canonical_pr_number": 46100, + "duplicate_pr_numbers": [ + 46114 + ], + "target_issue_number": null, + "reason": "PRs in cluster-46100-2 are treated as duplicates because they share 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/20260525T180030Z/analysis-runs/hybrid-model-20260525t180030z/analysis-report-hybrid.llm-reviews.json b/snapshots/20260525T180030Z/analysis-runs/hybrid-model-20260525t180030z/analysis-report-hybrid.llm-reviews.json new file mode 100644 index 0000000000000000000000000000000000000000..0af0b53cf6230bd84158947d14b7fc929002c777 --- /dev/null +++ b/snapshots/20260525T180030Z/analysis-runs/hybrid-model-20260525t180030z/analysis-report-hybrid.llm-reviews.json @@ -0,0 +1,20558 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260525T180030Z", + "generated_at": "2026-05-25T18:21:06Z", + "model": "gpt-5.4-mini?service_tier=flex", + "reviews": [ + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:24643", + "issue:30277", + "issue:34634", + "issue:34928", + "issue:35545", + "issue:36010", + "issue:36331", + "issue:39290", + "issue:41720", + "issue:41762", + "issue:42915", + "issue:43039", + "issue:43425", + "issue:43541", + "issue:43572", + "issue:43596", + "issue:43638", + "issue:43716", + "issue:43827", + "issue:43828", + "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", + "issue:46015", + "issue:46165" + ], + "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:45901|issue:46015", + "issue:44509|issue:44512", + "issue:35545|issue:36010", + "issue:44805|issue:45823", + "issue:44918|issue:46165", + "issue:43638|issue:44805", + "issue:43638|issue:46165", + "issue:43596|issue:44805", + "issue:44805|issue:45161", + "issue:44560|issue:46165", + "issue:43596|issue:46165", + "issue:44805|issue:44918", + "issue:43572|issue:46165", + "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:34928|issue:41720", + "issue:43828|issue:45161", + "issue:44918|issue:45161", + "issue:43828|issue:44292", + "issue:43716|issue:45685", + "issue:43541|issue:43716", + "issue:44292|issue:44918", + "issue:43716|issue:44292", + "issue:45507|issue:45685", + "issue:43039|issue:44918", + "issue:41762|issue:43638", + "issue:43827|issue:44512", + "issue:43716|issue:44560", + "issue:43828|issue:45685", + "issue:44918|issue:45685", + "issue:43039|issue:43828", + "issue:30277|issue:36331", + "issue:45237|issue:46015", + "issue:34928|issue:36010", + "issue:43039|issue:44805", + "issue:41762|issue:43596", + "issue:39290|issue:41720", + "issue:43901|issue:44512", + "issue:45237|issue:45901", + "issue:44841|issue:45823", + "issue:43039|issue:44560", + "issue:43975|issue:46015", + "issue:45812|issue:45920", + "issue:44863|issue:46015", + "issue:43866|issue:44863", + "issue:44292|issue:46015" + ], + "prepared_review_unit_hash": "45f778f6c20602229c81e49bdaa216b38bb28bfe3f6021cac25490939cfc798a", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 69, + "serialized_chars": 48405, + "estimated_input_tokens": 12102, + "estimated_eval_tokens": 24460 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most items are distinct bug reports, not duplicates. The only strong duplicate subclusters are the ZeRO-3 index-0 crashes on model loading, the Qwen3.5 MoE rotary-embedding/offload materialization bug, and the AutoTokenizer v5 regression affecting multiple model families. Similarity-only edges around docs, device mapping, or unrelated model errors should be rejected.", + "confidence": 0.88, + "canonical_issue_reason": "No single canonical issue spans the whole set; if forced to pick one representative for the strongest duplicate subcluster, issue:45920 is the best canonical because it is the broadest report of the AutoTokenizer v5 token-ID regression and subsumes the narrower Granite-only repro in 45812.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45920 is the best issue anchor overall because it is open, broad, and describes the shared tokenizer regression across several model families; it is more representative than narrower model-specific reproductions.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44322", + "right": "issue:45464", + "accept": false, + "reason": "Different failures: missing config attribute vs streaming chat/completions inference error." + }, + { + "left": "issue:45237", + "right": "issue:45685", + "accept": false, + "reason": "Unrelated hardware/runtime issues: AMD GPU failure vs MPS histogram op on Int." + }, + { + "left": "issue:43716", + "right": "issue:45237", + "accept": false, + "reason": "Different model/runtime paths: image-preprocessor dtype mismatch vs GPT-OSS AMD GPU failure." + }, + { + "left": "issue:43828", + "right": "issue:45237", + "accept": false, + "reason": "Both are runtime errors, but the code paths and root causes differ; this is not the same bug." + }, + { + "left": "issue:45237", + "right": "issue:45507", + "accept": false, + "reason": "Different model-specific failures: AMD GPU issue vs invalid-method call in GraniteMoEHybrid." + }, + { + "left": "issue:44292", + "right": "issue:45237", + "accept": false, + "reason": "Different repros and symptoms; Qwen NVFP4 failure is not the same as the AMD GPU crash." + }, + { + "left": "issue:30277", + "right": "issue:35545", + "accept": false, + "reason": "DeepSpeed collective mismatch and ONNX export error are unrelated bugs." + }, + { + "left": "issue:35545", + "right": "issue:42915", + "accept": false, + "reason": "Different subsystems and failures: ONNX export vs FineGrainedFP8 model load/runtime issue." + }, + { + "left": "issue:35545", + "right": "issue:41720", + "accept": false, + "reason": "Unrelated problems: ONNX export vs auto device-mapping CUDA assert." + }, + { + "left": "issue:45901", + "right": "issue:46015", + "accept": false, + "reason": "Table QA crash and outdated RAG docs are not the same underlying issue." + }, + { + "left": "issue:44509", + "right": "issue:44512", + "accept": false, + "reason": "Both are doc cleanups for v5 removals, but they cover different removed references and different pages." + }, + { + "left": "issue:35545", + "right": "issue:36010", + "accept": false, + "reason": "ONNX export error and GenerationMixin import error are unrelated." + }, + { + "left": "issue:44805", + "right": "issue:45823", + "accept": false, + "reason": "Different bug classes: mask/shape mismatch vs device-mapping mismatch." + }, + { + "left": "issue:44918", + "right": "issue:46165", + "accept": false, + "reason": "Different failures: TRL SFT input-embedding unpacking vs training-resume/trust-remote-code issue." + }, + { + "left": "issue:43638", + "right": "issue:44805", + "accept": false, + "reason": "Both mention indexing/shape errors, but the model and failure mode differ; not the same bug." + }, + { + "left": "issue:43638", + "right": "issue:46165", + "accept": false, + "reason": "ZeRO-3 Bert loading crash and training-resume issue are unrelated." + }, + { + "left": "issue:43596", + "right": "issue:44805", + "accept": false, + "reason": "Different errors: ZeRO-3 empty-tensor index crash vs attention mask shape mismatch." + }, + { + "left": "issue:44805", + "right": "issue:45161", + "accept": false, + "reason": "Mask shape mismatch is not the same as GPT-OSS tensor-parallel failure." + }, + { + "left": "issue:44560", + "right": "issue:46165", + "accept": false, + "reason": "Video StopIteration in Qwen3-vl-embedding is unrelated to resume-training behavior." + }, + { + "left": "issue:43596", + "right": "issue:46165", + "accept": false, + "reason": "ZeRO-3 Bert init crash and local-model resume issue are different." + }, + { + "left": "issue:44805", + "right": "issue:44918", + "accept": false, + "reason": "Both involve tensor shapes, but the trainer/input-embedding failure is a different code path." + }, + { + "left": "issue:43572", + "right": "issue:46165", + "accept": false, + "reason": "Missing pad_token_idx in config is unrelated to training resume with trust_remote_code." + }, + { + "left": "issue:34634", + "right": "issue:35545", + "accept": false, + "reason": "BarkProcessor voice_preset issue and ONNX export error are unrelated." + }, + { + "left": "issue:30277", + "right": "issue:43638", + "accept": false, + "reason": "Both involve DeepSpeed, but collective mismatch and ZeRO-3 index error are different bugs." + }, + { + "left": "issue:43596", + "right": "issue:43638", + "accept": true, + "reason": "Same underlying ZeRO-3 failure: index-0/out-of-bounds on empty tensors during BERT loading." + }, + { + "left": "issue:43039", + "right": "issue:45161", + "accept": false, + "reason": "Liger Kernel cross-entropy being called and GPT-OSS TP failure are unrelated." + }, + { + "left": "issue:43975", + "right": "issue:44457", + "accept": false, + "reason": "Detokenization bug and LoRA merge/save/reload inconsistency are different problems." + }, + { + "left": "issue:44292", + "right": "issue:44457", + "accept": false, + "reason": "Qwen NVFP4 runtime failure and LoRA merge inconsistency do not share the same root cause." + }, + { + "left": "issue:34928", + "right": "issue:44805", + "accept": false, + "reason": "Activation-checkpointing/FSDP recomputation mismatch is a different issue from the mask-shape IndexError." + }, + { + "left": "issue:24643", + "right": "issue:30277", + "accept": false, + "reason": "Both mention DeepSpeed, but the weight-dimension error and collective mismatch are different failures." + }, + { + "left": "issue:45859", + "right": "issue:45902", + "accept": true, + "reason": "Same Qwen3.5 MoE rotary-embedding/offload materialization bug; one report surfaces it as CPU-offload incompatibility, the other as uninitialized inv_freq after to_empty()." + }, + { + "left": "issue:43638", + "right": "issue:45161", + "accept": false, + "reason": "Bert ZeRO-3 index crash and GPT-OSS tensor-parallel failure are unrelated." + }, + { + "left": "issue:34928", + "right": "issue:36331", + "accept": false, + "reason": "Checkpointing/FSDP tensor-size mismatch and CustomTrainer signature mismatch are unrelated." + }, + { + "left": "issue:43596", + "right": "issue:45161", + "accept": false, + "reason": "ZeRO-3 Bert init crash and GPT-OSS TP failure are unrelated." + }, + { + "left": "issue:43716", + "right": "issue:45507", + "accept": false, + "reason": "Different models and symptoms: dtype mismatch in image preprocessing vs invalid method call." + }, + { + "left": "issue:39290", + "right": "issue:45081", + "accept": false, + "reason": "Gemma3/vLLM config attribute error and Mistral tokenizer regex patch crash are unrelated." + }, + { + "left": "issue:45823", + "right": "issue:45874", + "accept": false, + "reason": "Device-mapping mismatch and expensive reverse embedding lookup are different Gemma4 issues." + }, + { + "left": "issue:43425", + "right": "issue:44292", + "accept": false, + "reason": "Torch version incompatibility and Qwen NVFP4 runtime failure are unrelated." + }, + { + "left": "issue:43828", + "right": "issue:45685", + "accept": false, + "reason": "Autocast dtype mismatch and MPS histogram limitation are different bugs." + }, + { + "left": "issue:44918", + "right": "issue:45685", + "accept": false, + "reason": "TRL embedding unpacking failure and MPS histogram limitation are unrelated." + }, + { + "left": "issue:43039", + "right": "issue:43828", + "accept": false, + "reason": "Liger Kernel cross-entropy path and autocast dtype mismatch are different failures." + }, + { + "left": "issue:30277", + "right": "issue:36331", + "accept": false, + "reason": "DeepSpeed collective mismatch and compute_loss signature mismatch are unrelated." + }, + { + "left": "issue:45237", + "right": "issue:46015", + "accept": false, + "reason": "AMD GPU runtime failure and outdated RAG docs are not the same issue." + }, + { + "left": "issue:34928", + "right": "issue:36010", + "accept": false, + "reason": "FSDP activation-checkpointing bug and GenerationMixin import error are unrelated." + }, + { + "left": "issue:43039", + "right": "issue:44805", + "accept": false, + "reason": "Liger Kernel cross-entropy path and mask-shape IndexError do not match." + }, + { + "left": "issue:41762", + "right": "issue:43596", + "accept": true, + "reason": "Same ZeRO-3 empty-tensor crash pattern: index 0 out of bounds while initializing/loading models." + }, + { + "left": "issue:39290", + "right": "issue:41720", + "accept": false, + "reason": "Gemma3 sliding_window_pattern error and Qwen3 auto-device-map CUDA assert are unrelated." + }, + { + "left": "issue:43901", + "right": "issue:44512", + "accept": false, + "reason": "Different docs regressions: return_all_scores vs removed transformers run command." + }, + { + "left": "issue:45237", + "right": "issue:45901", + "accept": false, + "reason": "GPT-OSS AMD GPU runtime failure and table QA crash are unrelated." + }, + { + "left": "issue:44841", + "right": "issue:45823", + "accept": false, + "reason": "Processor failure for Voxtral and Gemma4 device-mapping mismatch are unrelated." + }, + { + "left": "issue:43039", + "right": "issue:44560", + "accept": false, + "reason": "Liger Kernel cross-entropy issue and Qwen3-vl StopIteration are unrelated." + }, + { + "left": "issue:43975", + "right": "issue:46015", + "accept": false, + "reason": "Detokenization bug and RAG docs cleanup are unrelated." + }, + { + "left": "issue:45812", + "right": "issue:45920", + "accept": true, + "reason": "Same AutoTokenizer v5 regression producing wrong token IDs; 45920 is the broader multi-model report and 45812 is a narrower Granite-only repro." + }, + { + "left": "issue:44863", + "right": "issue:46015", + "accept": false, + "reason": "NemotronH checkpoint loading failure and RAG docs issue are unrelated." + }, + { + "left": "issue:43866", + "right": "issue:44863", + "accept": false, + "reason": "Checkpoint corruption and checkpoint loading implementation failure are different problems." + }, + { + "left": "issue:44292", + "right": "issue:46015", + "accept": false, + "reason": "Qwen NVFP4 runtime failure and outdated RAG docs are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded and conservative overall. The three accepted duplicate edges are plausible same-bug pairs, and the rejected edges avoid overstating similarity across clearly different failures or docs-only issues. No mergeability problems apply here since these are issue pairs, not PR pairs." + }, + "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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:36010", + "issue:39186", + "issue:39290", + "issue:40990", + "issue:41093", + "issue:41762", + "issue:43054", + "issue:43296", + "issue:43366", + "issue:43404", + "issue:43425", + "issue:43531", + "issue:43541", + "issue:43572", + "issue:43596", + "issue:43638", + "issue:43645", + "issue:43716", + "issue:43792", + "issue:43828", + "issue:43854", + "issue:43866", + "issue:43975", + "issue:43994", + "issue:44291", + "issue:44292", + "issue:44387", + "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:39290|issue:43531", + "issue:43854|issue:43866", + "issue:43792|issue:45901", + "issue:41093|issue:43638", + "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:45464|issue:45685", + "issue:43404|issue:43866", + "issue:43541|issue:45685", + "issue:43541|issue:43828", + "issue:44841|issue:45084", + "issue:36010|issue:39290", + "issue:45800|issue:45823", + "issue:41093|issue:41762", + "issue:43296|issue:43366", + "issue:43572|issue:45070", + "issue:43541|issue:45161", + "issue:44387|issue:45005", + "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:45759|issue:45902", + "issue:45542|issue:45800", + "issue:39186|issue:44918", + "issue:43716|issue:44918", + "issue:40990|issue:44960", + "issue:45632|issue:45698", + "issue:43645|issue:45399", + "issue:43404|issue:45005" + ], + "prepared_review_unit_hash": "b0d0371cfe32d5bb7f87311ffb0714fc46cf47564eeeab639dbe5deb9fb7f59b", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 39, + "serialized_chars": 39129, + "estimated_input_tokens": 9783, + "estimated_eval_tokens": 19822 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous: many items are unrelated model-specific regressions, backend incompatibilities, or API edge cases. Only two soft pairs look like plausible duplicates: SigLIP2 inference/quality reports and `trust_remote_code` custom-module resolution problems.", + "confidence": 0.89, + "canonical_issue_reason": "No single canonical issue for the whole cluster; the items are largely unrelated, so only a couple of pairwise duplicates stand out.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45632 is the best representative issue here because it is a precise, actionable report about custom-module cache/path collision and has a close matching companion (issue:45698).", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:39290", + "right": "issue:43531", + "accept": false, + "reason": "Both mention `sliding_window`, but they affect different model families and failure modes; not clearly the same bug." + }, + { + "left": "issue:43854", + "right": "issue:43866", + "accept": false, + "reason": "Both are load-time failures, but one is a unit-test load issue and the other is a corrupted checkpoint report; different root causes." + }, + { + "left": "issue:43792", + "right": "issue:45901", + "accept": false, + "reason": "Unrelated models and subsystems: Whisper loading vs table-question-answering runtime crash." + }, + { + "left": "issue:41093", + "right": "issue:43638", + "accept": false, + "reason": "Both are index/shape errors, but one is a mask-length mismatch and the other is a ZeRO-3 BERT init failure." + }, + { + "left": "issue:43425", + "right": "issue:45070", + "accept": false, + "reason": "Both are version/regression complaints, but they target different incompatibilities and different code paths." + }, + { + "left": "issue:43596", + "right": "issue:45800", + "accept": false, + "reason": "Different failures: ZeRO-3 BERT loading vs a specific torch/transformers version incompatibility." + }, + { + "left": "issue:43975", + "right": "issue:45901", + "accept": false, + "reason": "Different functionality entirely: detokenization vs table QA task crashes." + }, + { + "left": "issue:43792", + "right": "issue:45070", + "accept": false, + "reason": "Whisper runtime failure is unrelated to the PretrainedConfig/pydantic regression." + }, + { + "left": "issue:45362", + "right": "issue:45464", + "accept": false, + "reason": "Both involve Qwen3.5 chat, but one is a transformers chat crash and the other is a streaming chat/completions API failure; too different to merge." + }, + { + "left": "issue:44292", + "right": "issue:45901", + "accept": false, + "reason": "Different models and symptoms; NVFP4 loading failure is not the same as table QA crashing." + }, + { + "left": "issue:39290", + "right": "issue:45823", + "accept": false, + "reason": "Both are model-specific regressions, but Gemma3 sliding-window config and Gemma4 device mismatch are distinct bugs." + }, + { + "left": "issue:45464", + "right": "issue:45685", + "accept": false, + "reason": "Qwen3.5 streaming API failure and MPS histogram-not-implemented error are unrelated." + }, + { + "left": "issue:43404", + "right": "issue:43866", + "accept": false, + "reason": "Mistral3 tied-weight bug and Ovis2 checkpoint corruption are different problems." + }, + { + "left": "issue:43541", + "right": "issue:45685", + "accept": false, + "reason": "Grouped_mm tracing failure and an MPS integer histogram limitation are different code paths." + }, + { + "left": "issue:43541", + "right": "issue:43828", + "accept": false, + "reason": "Both involve numeric/runtime issues, but grouped_mm tracing and autocast dtype mismatch are not the same bug." + }, + { + "left": "issue:44841", + "right": "issue:45084", + "accept": false, + "reason": "Processor failure for Voxtral and template-node compilation errors are unrelated." + }, + { + "left": "issue:36010", + "right": "issue:39290", + "accept": false, + "reason": "ImportError for `GenerationMixin` and Gemma3 sliding-window config are unrelated regressions." + }, + { + "left": "issue:45800", + "right": "issue:45823", + "accept": false, + "reason": "A torch/transformers version incompatibility is unrelated to a Gemma4 device-map forward mismatch." + }, + { + "left": "issue:41093", + "right": "issue:41762", + "accept": false, + "reason": "Both mention out-of-bounds/indexing, but one is a mask shape mismatch and the other is a ZeRO-3 load-time empty-tensor issue." + }, + { + "left": "issue:43296", + "right": "issue:43366", + "accept": false, + "reason": "PaddleOCR-VL loading in vLLM and GGUF gpt-oss support are different feature gaps." + }, + { + "left": "issue:43572", + "right": "issue:45070", + "accept": false, + "reason": "StableLmConfig `pad_token_idx` regression and PretrainedConfig pydantic field breakage are different configuration bugs." + }, + { + "left": "issue:43541", + "right": "issue:45161", + "accept": false, + "reason": "Both involve MoE/GPT-OSS-adjacent topics, but grouped_mm tracing and tensor-parallel support are not the same underlying issue." + }, + { + "left": "issue:44387", + "right": "issue:45005", + "accept": false, + "reason": "Int4 memory/OOM regression and tied-weights translation-model regression are unrelated." + }, + { + "left": "issue:43828", + "right": "issue:45464", + "accept": false, + "reason": "Autocast dtype mismatch in Phi-tiny-MoE is unrelated to Qwen3.5 streaming API failure." + }, + { + "left": "issue:44291", + "right": "issue:45070", + "accept": false, + "reason": "Both are v5 regressions, but one is `init_empty_weights` argument handling and the other is a pydantic field breakage." + }, + { + "left": "issue:43366", + "right": "issue:45464", + "accept": false, + "reason": "GGUF gpt-oss architecture support and Qwen3.5 streaming inference are unrelated." + }, + { + "left": "issue:45020", + "right": "issue:45800", + "accept": false, + "reason": "Remote-code model breakage and torch/transformers version incompatibility are different root causes." + }, + { + "left": "issue:43531", + "right": "issue:45070", + "accept": false, + "reason": "Sliding-window behavior on Qwen3-MoE is unrelated to the PretrainedConfig pydantic regression." + }, + { + "left": "issue:43541", + "right": "issue:44589", + "accept": false, + "reason": "Grouped_mm tracing failure and missing Float8 storage support are distinct runtime issues." + }, + { + "left": "issue:41093", + "right": "issue:43596", + "accept": false, + "reason": "Both are index-related, but they arise from different workflows and failure points." + }, + { + "left": "issue:43054", + "right": "issue:43994", + "accept": true, + "reason": "Both report SigLIP2 behaving incorrectly at inference/loading time; they likely stem from the same model implementation bug." + }, + { + "left": "issue:45759", + "right": "issue:45902", + "accept": false, + "reason": "Multimodal config unwrapping and rotary-embedding uninitialized-memory issues are different bugs." + }, + { + "left": "issue:45542", + "right": "issue:45800", + "accept": false, + "reason": "TensorBoard-without-TensorFlow backend error is unrelated to torch/transformers version incompatibility." + }, + { + "left": "issue:39186", + "right": "issue:44918", + "accept": false, + "reason": "FSDP weight-shape failure and Qwen3.5 embedding unpacking in TRL are different problems." + }, + { + "left": "issue:43716", + "right": "issue:44918", + "accept": false, + "reason": "Mistral3 image-preprocessor dtype mismatch and Qwen3.5 SFT embedding unpacking are unrelated." + }, + { + "left": "issue:40990", + "right": "issue:44960", + "accept": false, + "reason": "High perplexity on gpt-oss-20b and a GLM5 issue are not the same bug." + }, + { + "left": "issue:45632", + "right": "issue:45698", + "accept": true, + "reason": "Both describe `trust_remote_code`/custom-module resolution loading the wrong local module; same cache/path-selection bug." + }, + { + "left": "issue:43645", + "right": "issue:45399", + "accept": false, + "reason": "Custom-model Jupyter init breakage and flash-attn2 fallback gating are unrelated." + }, + { + "left": "issue:43404", + "right": "issue:45005", + "accept": false, + "reason": "Both concern tied weights, but they affect different model classes and likely different implementations." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: the cluster is mostly heterogeneous, and the two accepted soft pairs are the only ones that look plausibly duplicate based on the issue titles. The rejected pairs are phrased conservatively and do not overclaim identity. No mergeability problems 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": 3, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "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:44530", + "issue:44534", + "issue:44589", + "issue:44863", + "issue:44910", + "issue:44918", + "issue:44928", + "issue:44960", + "issue:45005", + "issue:45020", + "issue:45237", + "issue:45399", + "issue:45507", + "issue:45663", + "issue:45701", + "issue:45800", + "issue:45859", + "issue:45902" + ], + "soft_pairs": [ + "issue:42915|issue:45399", + "issue:44530|issue:45005", + "issue:43873|issue:45005", + "issue:44863|issue:45005", + "issue:44360|issue:44512", + "issue:44918|issue:45507", + "issue:44492|issue:44512", + "issue:43975|issue:44292", + "issue:44292|issue:45507", + "issue:43950|issue:44534", + "issue:43644|issue:43950", + "issue:39692|issue:43054", + "issue:43828|issue:44928", + "issue:36331|issue:41762", + "issue:41628|issue:45800", + "issue:43950|issue:45902", + "issue:43872|issue:44589", + "issue:43866|issue:44403", + "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:43975|issue:45237", + "issue:43643|issue:45020", + "issue:44403|issue:44488", + "issue:42947|issue:43856", + "issue:41762|issue:42915", + "issue:43881|issue:43883", + "issue:43782|issue:44960" + ], + "prepared_review_unit_hash": "fe6e7d225e607b85d1d877238cfb3a1ee69fc17f49b91c645b66b1c7df3cbdde", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37508, + "estimated_input_tokens": 9377, + "estimated_eval_tokens": 19010 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous, but there is a clear duplicate pocket around the Transformers 5.x non-persistent buffer regression. Most other pairs are different model-specific or API-specific bugs and should stay separate.", + "confidence": 0.84, + "canonical_issue_reason": "issue:43950 is the clearest, broadest statement of the shared regression: non-persistent buffers are corrupted during `from_pretrained()` in Transformers 5.x. It also naturally subsumes the later specific symptom in issue:45902 and the near-duplicate wording in issue:44534.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43950 best represents the duplicate set because it names the root regression directly and generalizes across the specific downstream symptoms reported later.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42915", + "right": "issue:45399", + "accept": false, + "reason": "Different failures: Qwen3Moe FP8 loading vs FlashAttention fallback gating." + }, + { + "left": "issue:44530", + "right": "issue:45005", + "accept": false, + "reason": "Qwen3.5 packed-sequence/cache crash is not the same bug as the tied-weights v5 regression." + }, + { + "left": "issue:43873", + "right": "issue:45005", + "accept": false, + "reason": "Quantization/offloading behavior is unrelated to tied-weights handling." + }, + { + "left": "issue:44863", + "right": "issue:45005", + "accept": false, + "reason": "NemotronH checkpoint loading failure is a different code path from tied-weights issues." + }, + { + "left": "issue:44360", + "right": "issue:44512", + "accept": false, + "reason": "DSA indexer/ReLU discussion is unrelated to a docs typo about the run command." + }, + { + "left": "issue:44918", + "right": "issue:45507", + "accept": false, + "reason": "TRL embedding unpacking and GraniteMoE invalid-method calls are different model/trainer bugs." + }, + { + "left": "issue:44492", + "right": "issue:44512", + "accept": false, + "reason": "Cache-strategy typo is not the same as removed-run-command documentation drift." + }, + { + "left": "issue:43975", + "right": "issue:44292", + "accept": false, + "reason": "DeepSeek detokenization regression and Qwen3 NVFP4 load failure are different bugs." + }, + { + "left": "issue:44292", + "right": "issue:45507", + "accept": false, + "reason": "Qwen3 NVFP4 load failure is unrelated to GraniteMoEHybrid's invalid method call." + }, + { + "left": "issue:43950", + "right": "issue:44534", + "accept": true, + "reason": "Same underlying non-persistent-buffer corruption regression in Transformers 5.x, phrased with different surface symptoms." + }, + { + "left": "issue:43644", + "right": "issue:43950", + "accept": false, + "reason": "`trust_remote_code` missing fields is a different regression than buffer corruption during load." + }, + { + "left": "issue:39692", + "right": "issue:43054", + "accept": false, + "reason": "Broken docs example and poor SigLIP2 text embeddings are different problems." + }, + { + "left": "issue:43828", + "right": "issue:44928", + "accept": false, + "reason": "Autocast dtype mismatch is a different failure from Qwen3.5 position-id/SDPA instability." + }, + { + "left": "issue:36331", + "right": "issue:41762", + "accept": false, + "reason": "Trainer API kwarg breakage is unrelated to Gemma3 ZeRO-3 loading." + }, + { + "left": "issue:41628", + "right": "issue:45800", + "accept": false, + "reason": "Importing `AutoImageProcessor` and a torch/transformers version incompatibility are not the same concrete bug." + }, + { + "left": "issue:43950", + "right": "issue:45902", + "accept": true, + "reason": "Issue:45902 is a concrete symptom of the same non-persistent-buffer/materialization corruption regression described in issue:43950." + }, + { + "left": "issue:43872", + "right": "issue:44589", + "accept": false, + "reason": "Bitsandbytes constructor mismatch and missing Float8 storage are separate quantization issues." + }, + { + "left": "issue:43866", + "right": "issue:44403", + "accept": false, + "reason": "A corrupted checkpoint and generic loading noise are not the same underlying bug." + }, + { + "left": "issue:43054", + "right": "issue:45701", + "accept": false, + "reason": "SigLIP2 embedding quality and version-dependent tokenization changes are different concerns." + }, + { + "left": "issue:41553", + "right": "issue:43883", + "accept": false, + "reason": "Bad AutoTokenizer error handling for Voxtral is unrelated to Molmo's missing tied-weights attribute." + }, + { + "left": "issue:38175", + "right": "issue:43054", + "accept": false, + "reason": "Both involve SigLIP2, but zero probabilities and lower text-embedding quality are not clearly the same concrete bug." + }, + { + "left": "issue:44910", + "right": "issue:45859", + "accept": false, + "reason": "FlashAttention packed-sequence crash on Qwen3.5 is distinct from CPU-offload incompatibility in rotary embedding." + }, + { + "left": "issue:45663", + "right": "issue:45902", + "accept": false, + "reason": "Gemma4 FSDP2 KeyError and Qwen3.5 buffer materialization corruption are unrelated." + }, + { + "left": "issue:41553", + "right": "issue:43881", + "accept": false, + "reason": "Voxtral tokenizer error messaging and glm-4v-9b load failure are different bugs." + }, + { + "left": "issue:42947", + "right": "issue:44387", + "accept": false, + "reason": "LoRA checkpointing ineffectiveness is not the same as int4 quantization memory growth/OOM." + }, + { + "left": "issue:43054", + "right": "issue:43493", + "accept": true, + "reason": "Both point at the same SigLIP2 HF-vs-JAX implementation discrepancy that degrades text-side behavior." + }, + { + "left": "issue:44403", + "right": "issue:44451", + "accept": false, + "reason": "Generic loading noise and inability to load a specific model are not the same defect." + }, + { + "left": "issue:43975", + "right": "issue:45237", + "accept": false, + "reason": "Detokenization regression and AMD GPU execution failure are unrelated." + }, + { + "left": "issue:43643", + "right": "issue:45020", + "accept": false, + "reason": "Missing fields from `AutoConfig` with `trust_remote_code` is only one possible symptom inside a broader remote-code complaint, not a clearly identical bug." + }, + { + "left": "issue:44403", + "right": "issue:44488", + "accept": false, + "reason": "These are different model-loading reports, not the same bug." + }, + { + "left": "issue:42947", + "right": "issue:43856", + "accept": false, + "reason": "PEFT gradient-checkpointing behavior and Qwen3 MoE memory usage are different training issues." + }, + { + "left": "issue:41762", + "right": "issue:42915", + "accept": false, + "reason": "Gemma3 ZeRO-3 load failure and Qwen3Moe FP8 failure are unrelated." + }, + { + "left": "issue:43881", + "right": "issue:43883", + "accept": false, + "reason": "Different models and different failure modes: glm-4v-9b load error vs Molmo tied-weights attribute error." + }, + { + "left": "issue:43782", + "right": "issue:44960", + "accept": false, + "reason": "Qwen3VL weight_only load failure and GLM5 are unrelated model-specific issues." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative overall. The only accepted duplicate pockets are the clearly related SigLIP2 pair and the Transformers v5 non-persistent-buffer regression cluster, which are both supported by the issue titles. The rest of the soft-edge rejections are appropriately cautious for a heterogeneous cluster." + }, + "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": 4, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "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:43824|issue:43872", + "issue:44991|issue:45399", + "issue:42491|issue:44368", + "issue:45020|issue:45823", + "issue:44661|issue:45020", + "issue:43828|issue:45823", + "issue:45081|issue:45399", + "issue:45020|issue:45356", + "issue:43742|issue:45399", + "issue:43404|issue:43950", + "issue:43827|issue:44509", + "issue:43638|issue:45823", + "issue:42915|issue:45020", + "issue:43257|issue:43866", + "issue:43872|issue:44291", + "issue:43792|issue:44220", + "issue:42915|issue:43872", + "issue:41553|issue:44991", + "issue:36331|issue:41093", + "issue:43257|issue:45305", + "issue:42947|issue:45923", + "issue:43940|issue:45313", + "issue:43854|issue:44863", + "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": "be43def021e578871f06c3fb7c8ac526b41bbc41750e98122562524d7c10ef52", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 38069, + "estimated_input_tokens": 9518, + "estimated_eval_tokens": 19292 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly unrelated issues; only a few soft pairs look like true duplicates, mainly exact-regression matches in tokenizer/docs/loading paths. No PRs are present.", + "confidence": 0.67, + "canonical_issue_reason": "issue:44291 is the clearest, most explicit reproduction of the shared `_is_hf_initialized` loading regression, and it lines up directly with the bitsandbytes-related duplicate.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44291 is the strongest issue anchor in this set because it describes a concrete, version-scoped code-path failure with a clear fix surface.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45685", + "right": "issue:45823", + "accept": false, + "reason": "Different failures: MPS integer histogram support vs device placement mismatch in Gemma4 PLE." + }, + { + "left": "issue:43824", + "right": "issue:43872", + "accept": false, + "reason": "Both are import/load failures, but they point to different model families and different failure modes." + }, + { + "left": "issue:44991", + "right": "issue:45399", + "accept": false, + "reason": "Tokenizer loading regression vs flash-attention fallback gating; unrelated code paths." + }, + { + "left": "issue:42491", + "right": "issue:44368", + "accept": false, + "reason": "Both mention Qwen/LoRA warnings, but one is a hard loading incompatibility and the other is a config warning." + }, + { + "left": "issue:45020", + "right": "issue:45823", + "accept": false, + "reason": "Remote-code regression and device-map mismatch are different bugs." + }, + { + "left": "issue:44661", + "right": "issue:45020", + "accept": false, + "reason": "Different issues: tokenizer mapping helper failure vs broad remote_code breakage." + }, + { + "left": "issue:43828", + "right": "issue:45823", + "accept": false, + "reason": "Autocast dtype mismatch is not the same as a device-map forward mismatch." + }, + { + "left": "issue:45081", + "right": "issue:45399", + "accept": false, + "reason": "Tokenizer regex crash vs flash-attn availability checks; not the same bug." + }, + { + "left": "issue:45020", + "right": "issue:45356", + "accept": false, + "reason": "Broad remote_code breakage and Kimi tokenizer regression are distinct." + }, + { + "left": "issue:43742", + "right": "issue:45399", + "accept": false, + "reason": "MobileLLM loading/key error and flash-attn fallback gating are unrelated." + }, + { + "left": "issue:43404", + "right": "issue:43950", + "accept": false, + "reason": "Weight tying bug and non-persistent buffer corruption are different loading regressions." + }, + { + "left": "issue:43827", + "right": "issue:44509", + "accept": true, + "reason": "Both are the same docs cleanup: stale v5 pipeline-task references that were removed." + }, + { + "left": "issue:43638", + "right": "issue:45823", + "accept": false, + "reason": "Zero-3 index error with a non-pretrained Bert model is unrelated to Gemma4 device placement." + }, + { + "left": "issue:42915", + "right": "issue:45020", + "accept": false, + "reason": "Qwen3 MoE weight conversion under deepspeed is not the same as general remote_code breakage." + }, + { + "left": "issue:43257", + "right": "issue:43866", + "accept": false, + "reason": "Weight loading under accelerate/deepspeed and a corrupted checkpoint are different problems." + }, + { + "left": "issue:43872", + "right": "issue:44291", + "accept": true, + "reason": "Same underlying `_is_hf_initialized`/tensor-construction TypeError during model loading; these can be fixed together." + }, + { + "left": "issue:43792", + "right": "issue:44220", + "accept": true, + "reason": "Both point to the Whisper feature-extraction path failing in the same audio preprocessing code." + }, + { + "left": "issue:42915", + "right": "issue:43872", + "accept": false, + "reason": "Qwen3 MoE weight conversion and bitsandbytes constructor incompatibility are unrelated." + }, + { + "left": "issue:41553", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer-loading complaints, but they affect different models and likely different causes." + }, + { + "left": "issue:36331", + "right": "issue:41093", + "accept": false, + "reason": "Trainer API kwarg mismatch and tensor mask shape mismatch are unrelated." + }, + { + "left": "issue:43257", + "right": "issue:45305", + "accept": false, + "reason": "DeepSpeed weight-loading failure and GAS gradient averaging regression are different code paths." + }, + { + "left": "issue:42947", + "right": "issue:45923", + "accept": false, + "reason": "Gradient checkpointing issue in PEFT LoRA is not the same as a missing supports_gradient_checkpointing flag on a remote-code model." + }, + { + "left": "issue:43940", + "right": "issue:45313", + "accept": false, + "reason": "Both involve Qwen + ZeRO-3 loading, but the model targets and failure descriptions are not concrete duplicates." + }, + { + "left": "issue:43854", + "right": "issue:44863", + "accept": false, + "reason": "Different model-loading failures with no clear shared code path." + }, + { + "left": "issue:44928", + "right": "issue:45588", + "accept": false, + "reason": "RLHF NaN/SDPA fallback issue is unrelated to a flash_attention.py crash on sink-less models." + }, + { + "left": "issue:43872", + "right": "issue:45538", + "accept": false, + "reason": "bitsandbytes constructor compatibility and CLIPTokenizer max-length behavior are unrelated." + }, + { + "left": "issue:41093", + "right": "issue:44805", + "accept": true, + "reason": "Same mask/index shape mismatch error; the titles describe the same underlying IndexError." + }, + { + "left": "issue:41553", + "right": "issue:44488", + "accept": false, + "reason": "Different tokenizer-loading failures for different models; not the same bug." + }, + { + "left": "issue:44479", + "right": "issue:44560", + "accept": false, + "reason": "Both are video-related Qwen regressions, but the concrete failures are different enough to keep separate." + }, + { + "left": "issue:44530", + "right": "issue:44863", + "accept": false, + "reason": "PagedAttentionCache linear_attention crash and NemotronH checkpoint loading failure are unrelated." + }, + { + "left": "issue:24643", + "right": "issue:30064", + "accept": false, + "reason": "Training with DeepSpeed and void segmentation map processing are unrelated issues." + }, + { + "left": "issue:45325", + "right": "issue:45902", + "accept": false, + "reason": "RoPE position-id scaling bug and uninitialized-memory materialization bug are different." + }, + { + "left": "issue:43366", + "right": "issue:43828", + "accept": false, + "reason": "GGUF architecture support and dtype mismatch under autocast are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The assessment is grounded in the packet: the cited issue titles support the main anchors, the summary stays appropriately cautious, and the soft-edge rejections are conservative. The accepted pairs are all at least plausibly same-bug duplicates from the text, and there are no PR pairs to evaluate." + }, + "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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "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: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:44991", + "issue:45030", + "issue:45276", + "issue:45313", + "issue:45357", + "issue:45584", + "issue:45663", + "issue:45685", + "issue:45823", + "issue:45834" + ], + "soft_pairs": [ + "issue:45663|issue:45823", + "issue:44155|issue:45584", + "issue:43366|issue:43531", + "issue:43950|issue:45834", + "issue:43824|issue:43957", + "issue:44560|issue:45685", + "issue:43550|issue:44910", + "issue:43645|issue:43646", + "issue:42915|issue:43957", + "issue:43366|issue:44589", + "issue:42617|issue:43366", + "issue:44560|issue:44918", + "issue:36010|issue:42915", + "issue:44661|issue:45823", + "issue:44560|issue:44805", + "issue:43632|issue:45834", + "issue:38175|issue:43994", + "issue:43638|issue:44661", + "issue:43596|issue:44661", + "issue:44661|issue:44805", + "issue:44877|issue:45030", + "issue:43317|issue:44756", + "issue:43644|issue:44534", + "issue:38175|issue:39692", + "issue:42491|issue:43720", + "issue:41720|issue:42915", + "issue:44960|issue:44977", + "issue:44451|issue:44488", + "issue:45313|issue:45357", + "issue:42915|issue:44756", + "issue:42491|issue:45276", + "issue:43708|issue:44075", + "issue:44488|issue:44991" + ], + "prepared_review_unit_hash": "2174bc32ae48c0c2a60dadbfb229a7393e36f267246c8e6f95e3e6d53c916ec0", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37489, + "estimated_input_tokens": 9373, + "estimated_eval_tokens": 19002 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This is a mixed cluster with several small duplicate islands rather than one unified bug. The clearest duplicates are around Transformers v5 regressions (non-persistent buffers, custom model init, ZeRO-3/BERT failures) and a SigLIP2 output issue; most other pairs are unrelated model-specific bugs.", + "confidence": 0.67, + "canonical_issue_reason": "No single cluster-wide canonical issue fits all items because the set splits into multiple unrelated bugs. If a representative anchor is needed, 43644 is the cleanest duplicate pair anchor for the non-persistent-buffer regression.", + "canonical_pr_reason": null, + "best_issue_reason": "43644 is the best single issue anchor: it is a crisp, well-scoped Transformers v5 regression and is duplicated almost verbatim by 44534.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45663", + "right": "issue:45823", + "accept": false, + "reason": "Both are Gemma4 issues, but one is an FSDP2 shared_kv_states bug and the other is a device_map=\"auto\" device mismatch; different code paths." + }, + { + "left": "issue:44155", + "right": "issue:45584", + "accept": false, + "reason": "AudioFlamingo3 batched inference leak and Whisper empty-transcription handling are unrelated bugs." + }, + { + "left": "issue:43366", + "right": "issue:43531", + "accept": false, + "reason": "GGUF gpt-oss support and Qwen3-MoE sliding_window behavior are different features/problems." + }, + { + "left": "issue:43950", + "right": "issue:45834", + "accept": false, + "reason": "Non-persistent buffer corruption and Kosmos2.5 long-ocr index errors are unrelated." + }, + { + "left": "issue:43824", + "right": "issue:43957", + "accept": false, + "reason": "One is a missing Qwen2_5_VL export/import, the other is meta-device loading breakage; not the same bug." + }, + { + "left": "issue:44560", + "right": "issue:45685", + "accept": false, + "reason": "Qwen3-VL video StopIteration and MPS histogram support for Int are unrelated." + }, + { + "left": "issue:43550", + "right": "issue:44910", + "accept": false, + "reason": "Different attention-backend failures on different models; too broad to be the same concrete bug." + }, + { + "left": "issue:43645", + "right": "issue:43646", + "accept": true, + "reason": "Same Transformers v5 custom model initialization regression; the notebook mention is just an environment-specific manifestation." + }, + { + "left": "issue:42915", + "right": "issue:43957", + "accept": false, + "reason": "Qwen3-MoE FP8 failure and meta-device loading problems are distinct issues." + }, + { + "left": "issue:43366", + "right": "issue:44589", + "accept": false, + "reason": "GGUF model support and Float8 storage import errors are unrelated." + }, + { + "left": "issue:42617", + "right": "issue:43366", + "accept": false, + "reason": "3d_parallel.py failure and GGUF gpt-oss support are different areas." + }, + { + "left": "issue:44560", + "right": "issue:44918", + "accept": false, + "reason": "Qwen3-VL video StopIteration and Qwen3.5 embedding unpacking with TRL are unrelated." + }, + { + "left": "issue:36010", + "right": "issue:42915", + "accept": false, + "reason": "GenerationMixin import failure and Qwen3-MoE FP8 failure are unrelated." + }, + { + "left": "issue:44661", + "right": "issue:45823", + "accept": false, + "reason": "Tokenizer-mapping model registration bug and Gemma4 PLE device mismatch are unrelated." + }, + { + "left": "issue:44560", + "right": "issue:44805", + "accept": false, + "reason": "Different indexing/sequence bugs in different model paths." + }, + { + "left": "issue:43632", + "right": "issue:45834", + "accept": false, + "reason": "_is_hf_initialized regression and Kosmos2.5 OCR index error are unrelated." + }, + { + "left": "issue:38175", + "right": "issue:43994", + "accept": true, + "reason": "Both report the same SigLIP2 bad-output regression on google/siglip2-base-patch16-224; 43994 is a later re-report of the same model/processor problem." + }, + { + "left": "issue:43638", + "right": "issue:44661", + "accept": false, + "reason": "ZeRO-3 BertModel index error and add-new-model-like tokenizer mapping failure are different bugs." + }, + { + "left": "issue:43596", + "right": "issue:44661", + "accept": false, + "reason": "ZeRO-3 BertModel index error and tokenizer-mapping registration are unrelated." + }, + { + "left": "issue:44661", + "right": "issue:44805", + "accept": false, + "reason": "Different model-registration vs tensor-mask shape error." + }, + { + "left": "issue:44877", + "right": "issue:45030", + "accept": false, + "reason": "Both involve config validation, but they affect different model families and appear to be separate breakages." + }, + { + "left": "issue:43317", + "right": "issue:44756", + "accept": false, + "reason": "device_map/offload load failure and Strix Halo mmap OOM are not the same concrete bug." + }, + { + "left": "issue:43644", + "right": "issue:44534", + "accept": true, + "reason": "Verbatim duplicate regression: Transformers v5 fills non-persistent buffers with junk." + }, + { + "left": "issue:38175", + "right": "issue:39692", + "accept": false, + "reason": "The docs-example issue also includes quantization/doc errors, so it is not clearly the same concrete bug as the runtime SigLIP2 zero-probability report." + }, + { + "left": "issue:42491", + "right": "issue:43720", + "accept": false, + "reason": "Qwen3_MoE LoRA compatibility on hf5.x and BitNet packed-weight loading are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:42915", + "accept": false, + "reason": "Auto device mapping cudaErrorAssert and Qwen3-MoE FP8 failure are different issues." + }, + { + "left": "issue:44960", + "right": "issue:44977", + "accept": false, + "reason": "GLM5 and Qwen3.5 flash-attention failures are unrelated." + }, + { + "left": "issue:44451", + "right": "issue:44488", + "accept": true, + "reason": "Both are current-version load failures for closely related BERT checkpoints; this looks like the same loader regression." + }, + { + "left": "issue:45313", + "right": "issue:45357", + "accept": false, + "reason": "DeepSpeed ZeRO-3 load failure and incorrect save_pretrained visual encoder keys are different Qwen3.5 bugs." + }, + { + "left": "issue:42915", + "right": "issue:44756", + "accept": false, + "reason": "Qwen3-MoE FP8 failure and Strix Halo mmap OOM are unrelated." + }, + { + "left": "issue:42491", + "right": "issue:45276", + "accept": false, + "reason": "LoRA/hf5.x incompatibility and Gemma4 resize_token_embeddings behavior are different bugs." + }, + { + "left": "issue:43708", + "right": "issue:44075", + "accept": false, + "reason": "Trainer resume/max_steps logic and SGD args not being used are unrelated training issues." + }, + { + "left": "issue:44488", + "right": "issue:44991", + "accept": false, + "reason": "BERT model load failure and tokenizer loading failure for a different checkpoint are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The cluster analysis is grounded in the packet and stays conservative. The accepted duplicate islands are supported by the titles, and the rejected pairs are generally distinguished by different models/code paths or distinct failure modes. The overall summary correctly treats this as a mixed cluster rather than a single unified bug." + }, + "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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:36010", + "issue:39404", + "issue:39692", + "issue:41720", + "issue:42491", + "issue:42947", + "issue:43257", + "issue:43335", + "issue:43381", + "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:44756", + "issue:44910", + "issue:44912", + "issue:44960", + "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", + "issue:46050" + ], + "soft_pairs": [ + "issue:45488|issue:45812", + "issue:43644|issue:43645", + "issue:43854|issue:43931", + "issue:39692|issue:43994", + "issue:43257|issue:43854", + "issue:43856|issue:43873", + "issue:42491|issue:43931", + "issue:45362|issue:45406", + "issue:43856|issue:44387", + "issue:44960|issue:46050", + "issue:42491|issue:45292", + "issue:44164|issue:44291", + "issue:44910|issue:45588", + "issue:45276|issue:45335", + "issue:36010|issue:39404", + "issue:43404|issue:43454", + "issue:41720|issue:44155", + "issue:43425|issue:43957", + "issue:39692|issue:44960", + "issue:44402|issue:44488", + "issue:42947|issue:45704", + "issue:43873|issue:44387", + "issue:45663|issue:45759", + "issue:44291|issue:44756", + "issue:45663|issue:45859", + "issue:44155|issue:45823", + "issue:44292|issue:44912", + "issue:44387|issue:44756", + "issue:43335|issue:45663", + "issue:43957|issue:44756", + "issue:42947|issue:43381", + "issue:45276|issue:45292", + "issue:44164|issue:44756", + "issue:43854|issue:45216", + "issue:45684|issue:45698" + ], + "prepared_review_unit_hash": "e89ded4b8eb0eaf4c1fa996ee77a6b982f229f3a21383326832bfd8c7db83423", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 35, + "serialized_chars": 38332, + "estimated_input_tokens": 9583, + "estimated_eval_tokens": 19422 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous issue reports around Transformers regressions. The only clear duplicate-like pair is the resize_token_embeddings regression across closely related Gemma/T5-Gemma variants; the rest look like separate bugs affecting different models or subsystems.", + "confidence": 0.74, + "canonical_issue_reason": "Issue 45276 is the broadest and clearest representative of the only near-duplicate pair, and it subsumes the narrower output_embeddings-only symptom in 45292.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45276 is the best canonical issue candidate because it describes the core resize_token_embeddings regression in a broader form that covers the related embedding-propagation failure.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45488", + "right": "issue:45812", + "accept": false, + "reason": "Both involve tokenizer regressions, but they affect different model families and describe different failure modes; not the same bug." + }, + { + "left": "issue:43644", + "right": "issue:43645", + "accept": false, + "reason": "Both are Transformers 5.0 regressions, but one is buffer initialization and the other is custom-model initialization in notebooks; separate issues." + }, + { + "left": "issue:43854", + "right": "issue:43931", + "accept": false, + "reason": "Both are model-loading problems, but they target different models and symptoms; no clear shared code-path bug." + }, + { + "left": "issue:39692", + "right": "issue:43994", + "accept": false, + "reason": "Same SigLIP2 family, but one is a broken documentation example and the other is incorrect inference results; too different to merge." + }, + { + "left": "issue:43257", + "right": "issue:43854", + "accept": false, + "reason": "Different models and different loading/dispatch paths; no evidence they share the same underlying bug." + }, + { + "left": "issue:43856", + "right": "issue:43873", + "accept": false, + "reason": "Both mention memory/quantization, but one is training memory usage and the other is offloading behavior; not the same defect." + }, + { + "left": "issue:42491", + "right": "issue:43931", + "accept": false, + "reason": "These are distinct issues: LoRA compatibility across versions versus a specific Qwen3-VL weight-shape mismatch." + }, + { + "left": "issue:45362", + "right": "issue:45406", + "accept": false, + "reason": "Different model families and different runtime failures; not a duplicate." + }, + { + "left": "issue:43856", + "right": "issue:44387", + "accept": false, + "reason": "Both are memory-related, but the causes differ (Qwen3 MoE training memory vs int4 quantization reserved-memory/OOM regression)." + }, + { + "left": "issue:44960", + "right": "issue:46050", + "accept": false, + "reason": "Unrelated models and different save/load behavior; no common underlying bug." + }, + { + "left": "issue:42491", + "right": "issue:45292", + "accept": false, + "reason": "Different topics: Qwen3 MoE LoRA version incompatibility versus resize_token_embeddings not propagating to outputs." + }, + { + "left": "issue:44164", + "right": "issue:44291", + "accept": false, + "reason": "Both touch model loading/saving internals, but one is extra_state handling and the other is init_empty_weights argument compatibility; separate bugs." + }, + { + "left": "issue:44910", + "right": "issue:45588", + "accept": false, + "reason": "Both are flash-attention crashes, but the root causes and affected model paths are different." + }, + { + "left": "issue:45276", + "right": "issue:45335", + "accept": true, + "reason": "Both report resize_token_embeddings failing to update tied internal embeddings across closely related model variants, which looks like the same underlying regression." + }, + { + "left": "issue:36010", + "right": "issue:39404", + "accept": false, + "reason": "ImportError for GenerationMixin and Whisper return_language pipeline breakage are unrelated." + }, + { + "left": "issue:43404", + "right": "issue:43454", + "accept": false, + "reason": "Both mention untied lm_head weights, but they are separate model implementations and do not clearly point to one shared bug." + }, + { + "left": "issue:41720", + "right": "issue:44155", + "accept": false, + "reason": "Different models, different inference paths, and different failures; not a duplicate." + }, + { + "left": "issue:43425", + "right": "issue:43957", + "accept": false, + "reason": "Torch version compatibility and meta-device loading are distinct issues." + }, + { + "left": "issue:39692", + "right": "issue:44960", + "accept": false, + "reason": "No meaningful overlap beyond being model-related issues." + }, + { + "left": "issue:44402", + "right": "issue:44488", + "accept": false, + "reason": "These both sound like tokenizer/model loading problems, but the affected models and reported symptoms are too different to confidently treat as the same bug." + }, + { + "left": "issue:42947", + "right": "issue:45704", + "accept": false, + "reason": "Gradient checkpointing with PEFT LoRA is unrelated to the apex RMSNorm memory leak." + }, + { + "left": "issue:43873", + "right": "issue:44387", + "accept": false, + "reason": "Both involve quantization and memory, but they describe different regressions with different triggers." + }, + { + "left": "issue:45663", + "right": "issue:45759", + "accept": false, + "reason": "Gemma-4 FSDP2 shared_kv_states failure and Qwen config unwrapping are unrelated." + }, + { + "left": "issue:44291", + "right": "issue:44756", + "accept": false, + "reason": "init_empty_weights compatibility and mmap/OOM on Strix Halo are unrelated." + }, + { + "left": "issue:45663", + "right": "issue:45859", + "accept": false, + "reason": "Different model families and different execution-path failures." + }, + { + "left": "issue:44155", + "right": "issue:45823", + "accept": false, + "reason": "AudioFlamingo3 batched inference leakage and Gemma4 PLE device mismatch are unrelated." + }, + { + "left": "issue:44292", + "right": "issue:44912", + "accept": false, + "reason": "Both are quantization/loading issues, but they involve different quantization formats and different failure modes." + }, + { + "left": "issue:44387", + "right": "issue:44756", + "accept": false, + "reason": "Both mention OOM, but the causes are different and not mergeable as one bug." + }, + { + "left": "issue:43335", + "right": "issue:45663", + "accept": false, + "reason": "SwitchTransformers sparse-layer config bug and Gemma-4 FSDP2 attention bug are unrelated." + }, + { + "left": "issue:43957", + "right": "issue:44756", + "accept": false, + "reason": "Meta-device loading failures and Strix Halo mmap OOM are different problems." + }, + { + "left": "issue:42947", + "right": "issue:43381", + "accept": false, + "reason": "Both concern gradient checkpointing, but one is ineffective training behavior and the other is eval-mode prohibition." + }, + { + "left": "issue:45276", + "right": "issue:45292", + "accept": true, + "reason": "These are near-direct duplicates: both report resize_token_embeddings failing to update model embeddings, with 45276 being the broader version." + }, + { + "left": "issue:44164", + "right": "issue:44756", + "accept": false, + "reason": "Save/load extra_state handling and mmap-related OOM are unrelated." + }, + { + "left": "issue:43854", + "right": "issue:45216", + "accept": false, + "reason": "Different models and different regression types; not the same underlying bug." + }, + { + "left": "issue:45684", + "right": "issue:45698", + "accept": false, + "reason": "Both involve save/pretrained custom-model workflows, but one is permissions propagation and the other is loading the wrong custom module; separate issues." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The cluster summary is grounded in the packet and stays conservative on the soft edges. The only accepted duplicate-like set is the resize_token_embeddings regression across closely related Gemma/T5-Gemma issues, which is supported by the titles and similarity scores. The other pairwise rejections do not overclaim a shared root cause." + }, + "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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:36032", + "issue:39404", + "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:43856", + "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:44479|issue:44877", + "issue:45588|issue:45663", + "issue:43646|issue:43708", + "issue:43645|issue:44164", + "issue:43828|issue:43957", + "issue:45292|issue:45335", + "issue:44402|issue:44451", + "issue:43425|issue:43828", + "issue:43257|issue:44863", + "issue:44589|issue:44756", + "issue:39404|issue:45701", + "issue:44683|issue:45823", + "issue:43425|issue:45823", + "issue:43611|issue:43645", + "issue:43425|issue:43716", + "issue:44530|issue:45084", + "issue:43906|issue:44530", + "issue:39404|issue:44912", + "issue:44265|issue:44898", + "issue:44479|issue:44805", + "issue:43994|issue:44079", + "issue:43901|issue:44509", + "issue:43425|issue:44918", + "issue:43299|issue:43931", + "issue:44589|issue:45084", + "issue:44164|issue:45759", + "issue:36032|issue:43452", + "issue:43596|issue:44683", + "issue:44671|issue:44991", + "issue:39404|issue:44671", + "issue:43856|issue:44756" + ], + "prepared_review_unit_hash": "bc2a010f431f82404c2020bf088ea1364a8079a78042798ddaa16e3e77c20832", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37346, + "estimated_input_tokens": 9337, + "estimated_eval_tokens": 18930 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a loose set of Transformers v5 regression reports around model loading/initialization/tokenizer behavior. Only one soft pair looks like a true duplicate; the rest are different bugs in adjacent areas.", + "confidence": 0.79, + "canonical_issue_reason": "issue:43646 is the broadest representative of the shared v5 model-initialization regression theme, spanning the same general loading path as several nearby reports without being tied to one narrow model variant.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43646 is the best cluster anchor: it is broad, version-wide, and captures the central regression pattern better than the model-specific or tokenizer-specific issues.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43381", + "right": "issue:44928", + "accept": false, + "reason": "Different failures: gradient checkpointing in eval mode vs Qwen3.5 RLHF NaNs from 3D position_ids/SDPA fallback." + }, + { + "left": "issue:44479", + "right": "issue:44877", + "accept": false, + "reason": "Both are Qwen-related, but one is a video-input regression and the other is a strict-config loading issue; not the same bug." + }, + { + "left": "issue:45588", + "right": "issue:45663", + "accept": false, + "reason": "Flash-attention crash on sink-less models is unrelated to Gemma4 FSDP2 shared_kv_states rebuilding." + }, + { + "left": "issue:43646", + "right": "issue:43708", + "accept": false, + "reason": "Custom model initialization breakage is unrelated to Trainer checkpoint-resume max_steps accounting." + }, + { + "left": "issue:43645", + "right": "issue:44164", + "accept": false, + "reason": "Jupyter custom-model initialization regression is different from save/from_pretrained extra_state handling." + }, + { + "left": "issue:43828", + "right": "issue:43957", + "accept": false, + "reason": "These are both dtype/loading problems, but one is an autocast mismatch on Phi-tiny-MoE and the other is meta-device model loading for specific models." + }, + { + "left": "issue:45292", + "right": "issue:45335", + "accept": true, + "reason": "Same underlying bug: resize_token_embeddings fails to update all output/decoder embedding weights for the related model family." + }, + { + "left": "issue:44402", + "right": "issue:44451", + "accept": false, + "reason": "One is a tokenizer vocab-size mismatch in a specific model; the other is a generic inability to load a different tokenizer/model." + }, + { + "left": "issue:43425", + "right": "issue:43828", + "accept": false, + "reason": "Torch 2.10 incompatibility is a broader dependency issue, not the same as the Phi-tiny-MoE autocast dtype mismatch." + }, + { + "left": "issue:43257", + "right": "issue:44863", + "accept": false, + "reason": "Qwen3 MoE conversion/deepspeed loading and NemotronH checkpoint loading are distinct model-loading bugs." + }, + { + "left": "issue:44589", + "right": "issue:44756", + "accept": false, + "reason": "Float8 storage lookup failure is unrelated to the Strix Halo mmap OOM workaround." + }, + { + "left": "issue:39404", + "right": "issue:45701", + "accept": false, + "reason": "Whisper pipeline return_language regression is not the same as a broad tokenization-change report." + }, + { + "left": "issue:44683", + "right": "issue:45823", + "accept": false, + "reason": "Compiled flex_attention on torch>=2.9 is a different code path from Gemma4 PLE device-mismatch forwarding." + }, + { + "left": "issue:43425", + "right": "issue:45823", + "accept": false, + "reason": "Torch version incompatibility is too broad to equate with Gemma4 device placement during forward." + }, + { + "left": "issue:43611", + "right": "issue:43645", + "accept": false, + "reason": "Both involve custom models under v5, but one is about base_model_prefix loading and the other about notebook initialization; not the same concrete bug." + }, + { + "left": "issue:43425", + "right": "issue:43716", + "accept": false, + "reason": "A dependency incompatibility is not the same as the Mistral-3 image-preprocessor/model dtype mismatch." + }, + { + "left": "issue:44530", + "right": "issue:45084", + "accept": false, + "reason": "PagedAttentionCache linear_attention failure is unrelated to the non-template-node compile error." + }, + { + "left": "issue:43906", + "right": "issue:44530", + "accept": false, + "reason": "An isolated reproduction of an earlier issue is not the same as a PagedAttentionCache crash on Qwen3.5." + }, + { + "left": "issue:39404", + "right": "issue:44912", + "accept": false, + "reason": "Whisper pipeline language behavior is unrelated to MXFP4 quantization fallback on git-oss-20b." + }, + { + "left": "issue:44265", + "right": "issue:44898", + "accept": false, + "reason": "torch.export.export failing under torch_compilable_check is a different bug from Perceiver non-default resolution handling." + }, + { + "left": "issue:44479", + "right": "issue:44805", + "accept": false, + "reason": "Video-input regression in Qwen models is not the same as the generic mask/index shape mismatch report." + }, + { + "left": "issue:43994", + "right": "issue:44079", + "accept": false, + "reason": "Wrong SigLIP2 outputs and ModelOutput key assignment are unrelated." + }, + { + "left": "issue:43901", + "right": "issue:44509", + "accept": false, + "reason": "Docs mentioning return_all_scores is unrelated to docs still listing removed pipeline tasks." + }, + { + "left": "issue:43425", + "right": "issue:44918", + "accept": false, + "reason": "Torch compatibility is not the same as unpacking Qwen3.5 input embeddings with trl SFT trainer." + }, + { + "left": "issue:43299", + "right": "issue:43931", + "accept": false, + "reason": "Both are Qwen3-VL loading errors, but the former is an accelerate/deepspeed conversion issue and the latter is a checkpoint shape-mismatch; not clearly the same bug." + }, + { + "left": "issue:44589", + "right": "issue:45084", + "accept": false, + "reason": "Float8 storage-object lookup and compile-template-node errors are different failures." + }, + { + "left": "issue:44164", + "right": "issue:45759", + "accept": false, + "reason": "extra_state serialization and AutoModelForCausalLM.from_config text_config unwrapping are separate code paths." + }, + { + "left": "issue:36032", + "right": "issue:43452", + "accept": false, + "reason": "T5Tokenizer add_special_tokens conflict is unrelated to gguf_file breaking from_pretrained for tokenizer/model classes." + }, + { + "left": "issue:43596", + "right": "issue:44683", + "accept": false, + "reason": "Deepspeed ZeRO3/BertModel index error is unrelated to compiled flex_attention on newer torch versions." + }, + { + "left": "issue:44671", + "right": "issue:44991", + "accept": false, + "reason": "CamemBERT masked-LM prediction regression and tokenizer load failure for EMBEDDIA/est-roberta are different issues." + }, + { + "left": "issue:39404", + "right": "issue:44671", + "accept": false, + "reason": "Whisper return_language regression is unrelated to CamemBERT masked-LM prediction changes." + }, + { + "left": "issue:43856", + "right": "issue:44756", + "accept": false, + "reason": "Qwen3 MoE training memory usage and Strix Halo mmap OOM are distinct performance/memory issues." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary stays within the packet: it frames the cluster as a loose set of v5 loading/initialization/tokenizer regressions and keeps the non-duplicate pairs conservative. The one accepted soft pair, issue:45292 vs issue:45335, is plausibly the same resize_token_embeddings bug in closely related embedding paths. No soft-edge verdict overstates evidence in a way that would require rejection." + }, + "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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:32090", + "issue:34567", + "issue:36032", + "issue:39404", + "issue:40444", + "issue:40990", + "issue:42175", + "issue:42915", + "issue:43089", + "issue:43262", + "issue:43317", + "issue:43377", + "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:43883", + "issue:44164", + "issue:44206", + "issue:44220", + "issue:44451", + "issue:44464", + "issue:44479", + "issue:44488", + "issue:44530", + "issue:44661", + "issue:44683", + "issue:44737", + "issue:44811", + "issue:44849", + "issue:44987", + "issue:44991", + "issue:45081", + "issue:45084", + "issue:45325", + "issue:45507", + "issue:45584", + "issue:45859", + "issue:45987", + "issue:46178" + ], + "soft_pairs": [ + "issue:44991|issue:45081", + "issue:32090|issue:39404", + "issue:44164|issue:44479", + "issue:44737|issue:45859", + "issue:43582|issue:43632", + "issue:44661|issue:44683", + "issue:44488|issue:45081", + "issue:44488|issue:44987", + "issue:43611|issue:43644", + "issue:40990|issue:43421", + "issue:43716|issue:45084", + "issue:44206|issue:44220", + "issue:42175|issue:46178", + "issue:36032|issue:42915", + "issue:43883|issue:44488", + "issue:43643|issue:44530", + "issue:34567|issue:40444", + "issue:44811|issue:45584", + "issue:43541|issue:45084", + "issue:44451|issue:44987", + "issue:42915|issue:44530", + "issue:43644|issue:43646", + "issue:44464|issue:45987", + "issue:43452|issue:43482", + "issue:36032|issue:43645", + "issue:43317|issue:43482", + "issue:44849|issue:45325", + "issue:44987|issue:44991", + "issue:45084|issue:45507", + "issue:43883|issue:44991", + "issue:43262|issue:43377", + "issue:43089|issue:45987" + ], + "prepared_review_unit_hash": "56cf52975c1b952feb4673c85565724bdb698e115ce771f3df23e32259366603", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37337, + "estimated_input_tokens": 9335, + "estimated_eval_tokens": 18926 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly heterogeneous. A few issues share broad themes like v5 loading/init regressions, tokenizer/model-loading failures, or audio/Whisper paths, but the soft pairs are generally only superficially similar and do not look like the same underlying bug.", + "confidence": 0.89, + "canonical_issue_reason": "Issue 43646 is the broadest representative of the v5 custom-model initialization regression subgroup and is more central than the more specific symptom reports around it.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43646 is the best overall representative of this cluster because it captures the widest, most general regression theme among the issues shown.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44991", + "right": "issue:45081", + "accept": false, + "reason": "Both are tokenizer/loading failures, but they involve different models and different failure modes; not the same bug." + }, + { + "left": "issue:32090", + "right": "issue:39404", + "accept": false, + "reason": "Trainer broadcast TypeError and Whisper `return_language` regression are unrelated." + }, + { + "left": "issue:44164", + "right": "issue:44479", + "accept": false, + "reason": "Save/from_pretrained extra_state handling and video-input regression are different code paths and symptoms." + }, + { + "left": "issue:44737", + "right": "issue:45859", + "accept": false, + "reason": "Both are device/offload-related, but one is XLNet CPU work each forward and the other is a Qwen MoE offload incompatibility." + }, + { + "left": "issue:43582", + "right": "issue:43632", + "accept": false, + "reason": "Apple Silicon allocator warmup TypeError and `_is_hf_initialized` flag breakage are distinct." + }, + { + "left": "issue:44661", + "right": "issue:44683", + "accept": false, + "reason": "Model-registry expansion failure and compiled flex_attention failure are unrelated." + }, + { + "left": "issue:44488", + "right": "issue:45081", + "accept": false, + "reason": "Both mention loading tokenizers/models, but one is a specific Mistral regex patch crash and the other is a different tokenizer load failure." + }, + { + "left": "issue:44488", + "right": "issue:44987", + "accept": false, + "reason": "Both are load failures on recent versions, but they involve different models and no shared concrete code-path evidence." + }, + { + "left": "issue:43611", + "right": "issue:43644", + "accept": false, + "reason": "Both are v5 regressions, but base_model_prefix loading and non-persistent buffer corruption are separate bugs." + }, + { + "left": "issue:40990", + "right": "issue:43421", + "accept": false, + "reason": "High perplexity on a model and tokenizer post-processor update behavior are not the same issue." + }, + { + "left": "issue:43716", + "right": "issue:45084", + "accept": false, + "reason": "Image-preprocessor dtype mismatch and template compilation failure are unrelated." + }, + { + "left": "issue:44206", + "right": "issue:44220", + "accept": false, + "reason": "These are both audio feature extraction reports, but one is specifically about an unsupported `center` argument and the other is a generic fbank helper issue; not clearly the same defect." + }, + { + "left": "issue:42175", + "right": "issue:46178", + "accept": false, + "reason": "Both involve backend packaging, but one is missing tensorflow in a torch extra install and the other is an unmapped tensorflow_text backend." + }, + { + "left": "issue:36032", + "right": "issue:42915", + "accept": false, + "reason": "Tokenizer special-token method conflict and FineGrainedFP8Config failure are unrelated." + }, + { + "left": "issue:43883", + "right": "issue:44488", + "accept": false, + "reason": "Missing `all_tied_weights_keys` and tokenizer/model load failure are distinct problems." + }, + { + "left": "issue:43643", + "right": "issue:44530", + "accept": false, + "reason": "Missing fields in AutoConfig and PagedAttentionCache group-type crash are unrelated." + }, + { + "left": "issue:34567", + "right": "issue:40444", + "accept": false, + "reason": "TrainerState token counting and Qwen2.5-VL iterable dataset failure are different bugs." + }, + { + "left": "issue:44811", + "right": "issue:45584", + "accept": false, + "reason": "Both are Whisper-related, but decoding `skip_special_tokens` behavior and empty-transcription generation failure are different issues." + }, + { + "left": "issue:43541", + "right": "issue:45084", + "accept": false, + "reason": "Grouped_mm tracing error and non-template-node compilation error are unrelated compilation/runtime bugs." + }, + { + "left": "issue:44451", + "right": "issue:44987", + "accept": false, + "reason": "Both are loading failures, but they affect different models and do not indicate the same underlying defect." + }, + { + "left": "issue:42915", + "right": "issue:44530", + "accept": false, + "reason": "Fine-grained FP8 loading failure and linear_attention cache crash are different model/runtime issues." + }, + { + "left": "issue:43644", + "right": "issue:43646", + "accept": false, + "reason": "Both are v5 init regressions, but junk-filled non-persistent buffers and broken custom model initialization are not the same bug." + }, + { + "left": "issue:44464", + "right": "issue:45987", + "accept": false, + "reason": "Chunked generation inconsistency and StaticCache seq-length contract mismatch are related to generation, but not the same underlying issue." + }, + { + "left": "issue:43452", + "right": "issue:43482", + "accept": false, + "reason": "Both concern GGUF loading, but one is a generic gguf_file breakage and the other is a specific Qwen2.5-GGUF version regression." + }, + { + "left": "issue:36032", + "right": "issue:43645", + "accept": false, + "reason": "Tokenizer special-token conflict and Jupyter custom-model initialization are unrelated." + }, + { + "left": "issue:43317", + "right": "issue:43482", + "accept": false, + "reason": "GPU/CPU offload loading failure and Qwen2.5-GGUF loading regression are distinct." + }, + { + "left": "issue:44849", + "right": "issue:45325", + "accept": false, + "reason": "Both are Qwen-family regressions, but hidden-states output and RoPE position scaling are different code paths." + }, + { + "left": "issue:44987", + "right": "issue:44991", + "accept": false, + "reason": "Both are version-related loading failures, but they hit different models and there is no evidence of a shared root cause." + }, + { + "left": "issue:45084", + "right": "issue:45507", + "accept": false, + "reason": "Template compilation and GraniteMoEHybrid invalid method calls are unrelated." + }, + { + "left": "issue:43883", + "right": "issue:44991", + "accept": false, + "reason": "Missing tied-weights metadata and tokenizer load regression are different bugs." + }, + { + "left": "issue:43262", + "right": "issue:43377", + "accept": false, + "reason": "Audio processor sample-rate defaulting and MIMI padding-mask batching are different issues." + }, + { + "left": "issue:43089", + "right": "issue:45987", + "accept": false, + "reason": "Generation sync overhead and cache sequence-length return type mismatch 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": 9, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:33666", + "issue:36032", + "issue:40444", + "issue:40990", + "issue:41553", + "issue:41720", + "issue:42915", + "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:44466", + "issue:44479", + "issue:44534", + "issue:44589", + "issue:44610", + "issue:44683", + "issue:44756", + "issue:44811", + "issue:44877", + "issue:44987", + "issue:45020", + "issue:45081", + "issue:45084", + "issue:45127", + "issue:45216", + "issue:45325", + "issue:45357", + "issue:45663" + ], + "soft_pairs": [ + "issue:43645|issue:44534", + "issue:43646|issue:44534", + "issue:43322|issue:43540", + "issue:43404|issue:44466", + "issue:44403|issue:45081", + "issue:43994|issue:44610", + "issue:42915|issue:45084", + "issue:43377|issue:43819", + "issue:44265|issue:44610", + "issue:44451|issue:45081", + "issue:44987|issue:45081", + "issue:44220|issue:44683", + "issue:42915|issue:44291", + "issue:45216|issue:45357", + "issue:43632|issue:44756", + "issue:44062|issue:44987", + "issue:36032|issue:43742", + "issue:44479|issue:45325", + "issue:42915|issue:44589", + "issue:43404|issue:45127", + "issue:43296|issue:43531", + "issue:40444|issue:45325", + "issue:36032|issue:41720", + "issue:43531|issue:44877", + "issue:43611|issue:44534", + "issue:43425|issue:44403", + "issue:41553|issue:43582", + "issue:43632|issue:44534", + "issue:40990|issue:44811", + "issue:44079|issue:45663", + "issue:43792|issue:44589", + "issue:33666|issue:40444", + "issue:44683|issue:45020" + ], + "prepared_review_unit_hash": "6a3e2022fe3ec4513f1a4e8730fc7c4f6534bc4751a52263b63ecf014d34a154", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37467, + "estimated_input_tokens": 9367, + "estimated_eval_tokens": 18990 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is mostly a grab bag of unrelated Transformers issues. Only the two Qwen3.5 save_pretrained reports look like the same underlying regression; the rest are distinct bugs or symptom families.", + "confidence": 0.92, + "canonical_issue_reason": "Issue 45216 is the broader regression report for the Qwen3.5 save_pretrained problem; 45357 reads like a narrower follow-up about one incorrect key set.", + "canonical_pr_reason": null, + "best_issue_reason": "45216 is the clearest representative of the only plausible duplicate family in this cluster and has the most general description of the bug.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43645", + "right": "issue:44534", + "accept": false, + "reason": "Different failures: custom model init in notebooks vs non-persistent buffer corruption." + }, + { + "left": "issue:43646", + "right": "issue:44534", + "accept": false, + "reason": "Custom model initialization regression and junk buffer filling are unrelated." + }, + { + "left": "issue:43322", + "right": "issue:43540", + "accept": false, + "reason": "Different model paths and symptoms: Llava Next loading segfault vs Qwen3OmniMoe video-input ValueError." + }, + { + "left": "issue:43404", + "right": "issue:44466", + "accept": false, + "reason": "Both mention tied lm_head weights, but one is a missing tie in a specific model and the other is a save_pretrained serialization inconsistency; not the same concrete bug." + }, + { + "left": "issue:44403", + "right": "issue:45081", + "accept": false, + "reason": "Unnecessary loading noise is unrelated to the Mistral regex patch crash." + }, + { + "left": "issue:43994", + "right": "issue:44610", + "accept": false, + "reason": "Different issues: Siglip2 output quality vs OmDet-Turbo image-size mismatch." + }, + { + "left": "issue:42915", + "right": "issue:45084", + "accept": false, + "reason": "Qwen3Moe FP8 config failure and template compilation TypeError are unrelated." + }, + { + "left": "issue:43377", + "right": "issue:43819", + "accept": false, + "reason": "Different audio-model bugs: padding-mask batching mismatch vs DAC latent/STE mismatch." + }, + { + "left": "issue:44265", + "right": "issue:44610", + "accept": false, + "reason": "torch.export with torch_compilable_check is unrelated to processor output size mismatch." + }, + { + "left": "issue:44451", + "right": "issue:45081", + "accept": false, + "reason": "ScandiBERT loading failure is unrelated to the Mistral tokenizer backend crash." + }, + { + "left": "issue:44987", + "right": "issue:45081", + "accept": false, + "reason": "Loading physical-intelligence/fast and patch_mistral_regex crash are different problems." + }, + { + "left": "issue:44220", + "right": "issue:44683", + "accept": false, + "reason": "Different code paths: fbank extraction issue vs flex_attention compilation on newer torch." + }, + { + "left": "issue:42915", + "right": "issue:44291", + "accept": false, + "reason": "FP8 config failure and unexpected _is_hf_initialized argument are separate incompatibilities." + }, + { + "left": "issue:45216", + "right": "issue:45357", + "accept": true, + "reason": "Same Qwen3.5 save_pretrained regression family; 45357 is a narrower manifestation involving incorrect visual encoder keys." + }, + { + "left": "issue:43632", + "right": "issue:44756", + "accept": false, + "reason": "_is_hf_initialized breakage is unrelated to Strix Halo mmap OOM behavior." + }, + { + "left": "issue:44062", + "right": "issue:44987", + "accept": false, + "reason": "AddedToken keyword collision is unrelated to the physical-intelligence/fast loading regression." + }, + { + "left": "issue:36032", + "right": "issue:43742", + "accept": false, + "reason": "T5 tokenizer special-token conflict and MobileLLM key error are different loading failures." + }, + { + "left": "issue:44479", + "right": "issue:45325", + "accept": false, + "reason": "Both are Qwen VL regressions, but one is video-input processing and the other is still-image rope-position scaling." + }, + { + "left": "issue:42915", + "right": "issue:44589", + "accept": false, + "reason": "FP8 config failure and Float8 storage lookup error are different issues." + }, + { + "left": "issue:43404", + "right": "issue:45127", + "accept": false, + "reason": "Both involve tied weights, but one is a missing tie in Mistral3 and the other is LoRA merging with extended vocab collapse." + }, + { + "left": "issue:43296", + "right": "issue:43531", + "accept": false, + "reason": "PaddleOCR-VL loading failure and Qwen3-MoE sliding_window behavior are unrelated." + }, + { + "left": "issue:40444", + "right": "issue:45325", + "accept": false, + "reason": "Qwen2.5-VL multi-image IterableDataset failure is not the same bug as still-image temporal position scaling." + }, + { + "left": "issue:36032", + "right": "issue:41720", + "accept": false, + "reason": "Tokenizer conflict and Qwen3 auto-device-map cuda assert are unrelated." + }, + { + "left": "issue:43531", + "right": "issue:44877", + "accept": false, + "reason": "Qwen3-MoE sliding_window bug and granite_speech strict-config loading are unrelated." + }, + { + "left": "issue:43611", + "right": "issue:44534", + "accept": false, + "reason": "base_model_prefix loading regression and non-persistent buffer junk are different Transformers v5 issues." + }, + { + "left": "issue:43425", + "right": "issue:44403", + "accept": false, + "reason": "Torch 2.10 compatibility and loading noise are unrelated." + }, + { + "left": "issue:41553", + "right": "issue:43582", + "accept": false, + "reason": "Bad AutoTokenizer error message and Apple Silicon warmup TypeError are unrelated." + }, + { + "left": "issue:43632", + "right": "issue:44534", + "accept": false, + "reason": "_is_hf_initialized breakage is unrelated to junk-filled non-persistent buffers." + }, + { + "left": "issue:40990", + "right": "issue:44811", + "accept": false, + "reason": "High perplexity on GPT-OSS and Whisper batch_decode skip_special_tokens are unrelated." + }, + { + "left": "issue:44079", + "right": "issue:45663", + "accept": false, + "reason": "ModelOutput key assignment and Gemma-4 shared_kv_states/FSDP2 are unrelated." + }, + { + "left": "issue:43792", + "right": "issue:44589", + "accept": false, + "reason": "Whisper runtime failure and Float8 storage lookup error are unrelated." + }, + { + "left": "issue:33666", + "right": "issue:40444", + "accept": false, + "reason": "Both are Qwen-VL training issues, but they affect different model versions and different failure modes." + }, + { + "left": "issue:44683", + "right": "issue:45020", + "accept": false, + "reason": "flex_attention compilation on torch>=2.9 and remote_code loading regressions are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The judgment is grounded in the packet and the soft-edge calls are conservative. The only accepted pair, issue:45216 and issue:45357, is well-supported by their shared Qwen3.5 save_pretrained regression theme and the titles\u2019 narrower/broader relationship. The rest are plausibly distinct bug families, and the summary does not overstate 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": 10, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:35707", + "issue:40444", + "issue:41720", + "issue:42175", + "issue:42915", + "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:43792", + "issue:43818", + "issue:43856", + "issue:43957", + "issue:43994", + "issue:44079", + "issue:44265", + "issue:44291", + "issue:44403", + "issue:44462", + "issue:44466", + "issue:44534", + "issue:44568", + "issue:44589", + "issue:44829", + "issue:44898", + "issue:44991", + "issue:45072", + "issue:45081", + "issue:45325", + "issue:45357", + "issue:45381", + "issue:45479", + "issue:45491", + "issue:45538", + "issue:45542", + "issue:45812", + "issue:45834", + "issue:45923" + ], + "soft_pairs": [ + "issue:43421|issue:44568", + "issue:44403|issue:44991", + "issue:35707|issue:40444", + "issue:43381|issue:45923", + "issue:42175|issue:45542", + "issue:44462|issue:45812", + "issue:43317|issue:43856", + "issue:43482|issue:45538", + "issue:44829|issue:45479", + "issue:44291|issue:44589", + "issue:43482|issue:43525", + "issue:44079|issue:44534", + "issue:43818|issue:45357", + "issue:43377|issue:45491", + "issue:43531|issue:44291", + "issue:41720|issue:45081", + "issue:40444|issue:45381", + "issue:44265|issue:45072", + "issue:43644|issue:44079", + "issue:43749|issue:44079", + "issue:45325|issue:45381", + "issue:42175|issue:43296", + "issue:43632|issue:45072", + "issue:43611|issue:43646", + "issue:43792|issue:43957", + "issue:45325|issue:45834", + "issue:43994|issue:44898", + "issue:43454|issue:44466", + "issue:42915|issue:43482" + ], + "prepared_review_unit_hash": "35947cd9c4de34070b1545a402d9830cd8fa685d985fb1954a1deb3fe144d078", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36687, + "estimated_input_tokens": 9172, + "estimated_eval_tokens": 18600 + }, + "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 v5 regressions and model-specific bugs; there isn\u2019t a single clear duplicate thread. The strongest common theme is general model/tokenizer loading regressions, but the soft pairs are still too specific to merge.", + "confidence": 0.52, + "canonical_issue_reason": "Issue 43611 is the broadest representative of the repeated v5 model-loading regressions in this set, but it is not an exact duplicate umbrella for the whole cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "43611 is the best anchor issue because it captures a high-level Transformers v5 loading regression with wide potential impact, even though most other issues here are separate bugs.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43421", + "right": "issue:44568", + "accept": false, + "reason": "Both are tokenizer-related, but one is runtime post-processor sync and the other is missing BOS/EOS insertion for a specific tokenizer; different bugs." + }, + { + "left": "issue:44403", + "right": "issue:44991", + "accept": false, + "reason": "One is about noisy loading logs, the other is a tokenizer-loading failure for a specific model; not the same issue." + }, + { + "left": "issue:35707", + "right": "issue:40444", + "accept": false, + "reason": "Different workflows and failures: generation with inputs_embeds/past_key_values vs VL finetuning with multiple images per prompt." + }, + { + "left": "issue:43381", + "right": "issue:45923", + "accept": false, + "reason": "Both mention gradient checkpointing, but one is eval-mode incompatibility and the other is a missing capability flag on a remote-code model." + }, + { + "left": "issue:42175", + "right": "issue:45542", + "accept": false, + "reason": "Both touch TensorFlow packaging, but one is missing TF in the torch extra and the other is a bad backend state when only tensorboard is installed." + }, + { + "left": "issue:44462", + "right": "issue:45812", + "accept": false, + "reason": "Tokenizer repository selection vs wrong token IDs for Granite models are different failure modes." + }, + { + "left": "issue:43317", + "right": "issue:43856", + "accept": false, + "reason": "Dequantized model offload loading and Qwen3 MoE memory usage are unrelated problems." + }, + { + "left": "issue:43482", + "right": "issue:45538", + "accept": false, + "reason": "GGUF loading failure and CLIPTokenizer max-length configuration are unrelated." + }, + { + "left": "issue:44829", + "right": "issue:45479", + "accept": false, + "reason": "One is flash_attention_3 training degeneration; the other is single-label classification with num_labels=1 causing zero loss across models." + }, + { + "left": "issue:44291", + "right": "issue:44589", + "accept": false, + "reason": "Both are v5 loading-related, but one is an init_empty_weights argument mismatch and the other is a float8 storage lookup error." + }, + { + "left": "issue:43482", + "right": "issue:43525", + "accept": false, + "reason": "Different concrete loading failures: GGUF support vs missing pad_token_id on Llama4Config." + }, + { + "left": "issue:44079", + "right": "issue:44534", + "accept": false, + "reason": "ModelOutput key assignment bug and non-persistent buffer initialization bug are separate code paths." + }, + { + "left": "issue:43818", + "right": "issue:45357", + "accept": false, + "reason": "Video-LLaVA tower initialization/weight sharing is unrelated to Qwen3.5 save_pretrained visual-encoder key serialization." + }, + { + "left": "issue:43377", + "right": "issue:45491", + "accept": false, + "reason": "Both involve batching, but one is a missing padding mask in MIMI and the other is NaNs from sliding-window/all-padding windows in Gemma3." + }, + { + "left": "issue:43531", + "right": "issue:44291", + "accept": false, + "reason": "Sliding-window behavior in Qwen3-MoE is a different bug from init_empty_weights/_is_hf_initialized argument handling." + }, + { + "left": "issue:41720", + "right": "issue:45081", + "accept": false, + "reason": "CUDA assert in Qwen3 auto device mapping is unrelated to the Mistral tokenizer regex patch crash." + }, + { + "left": "issue:40444", + "right": "issue:45381", + "accept": false, + "reason": "Both are Qwen2.5-VL, but one is training with multiple images and the other is video vision_position_ids being wrong." + }, + { + "left": "issue:44265", + "right": "issue:45072", + "accept": false, + "reason": "torch.export with torch_compilable_check and dtype mismatches in bfloat16 inference are different issues." + }, + { + "left": "issue:43644", + "right": "issue:44079", + "accept": false, + "reason": "Non-persistent buffer junk filling is unrelated to ModelOutput key assignment." + }, + { + "left": "issue:43749", + "right": "issue:44079", + "accept": false, + "reason": "FSDP CPU RAM efficient loading and ModelOutput key assignment are not the same bug." + }, + { + "left": "issue:45325", + "right": "issue:45381", + "accept": false, + "reason": "Both are Qwen2.5-VL position-id issues, but one is still-image temporal scaling and the other is video input position_ids; too different to merge." + }, + { + "left": "issue:42175", + "right": "issue:43296", + "accept": false, + "reason": "TensorFlow backend packaging and PaddleOCR-VL loading in vLLM are unrelated." + }, + { + "left": "issue:43632", + "right": "issue:45072", + "accept": false, + "reason": "_is_hf_initialized flag handling and bfloat16 dtype mismatches are different regressions." + }, + { + "left": "issue:43611", + "right": "issue:43646", + "accept": false, + "reason": "Both are v5 model-loading regressions, but base_model_prefix handling and custom model initialization are distinct failure modes." + }, + { + "left": "issue:43792", + "right": "issue:43957", + "accept": false, + "reason": "Whisper model runtime failure and meta-device loading breakage are not the same underlying bug." + }, + { + "left": "issue:45325", + "right": "issue:45834", + "accept": false, + "reason": "Different Qwen2.5-VL models and different OCR/position-id failure contexts." + }, + { + "left": "issue:43994", + "right": "issue:44898", + "accept": false, + "reason": "SigLIP2 nonsensical outputs and Perceiver non-default-resolution failure are unrelated model-specific issues." + }, + { + "left": "issue:43454", + "right": "issue:44466", + "accept": false, + "reason": "lm_head weight tying during generation vs serialization inconsistency depending on device are related in theme but not the same concrete bug." + }, + { + "left": "issue:42915", + "right": "issue:43482", + "accept": false, + "reason": "Qwen3Moe FP8 config failure and Qwen2.5-GGUF loading failure are separate model/runtime 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": 11, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:34634", + "issue:35707", + "issue:39692", + "issue:40444", + "issue:40990", + "issue:41720", + "issue:42947", + "issue:43257", + "issue:43262", + "issue:43296", + "issue:43317", + "issue:43322", + "issue:43377", + "issue:43454", + "issue:43526", + "issue:43550", + "issue:43572", + "issue:43606", + "issue:43701", + "issue:43720", + "issue:43746", + "issue:43819", + "issue:43873", + "issue:43881", + "issue:43883", + "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", + "issue:46050" + ], + "soft_pairs": [ + "issue:43296|issue:45800", + "issue:44387|issue:44617", + "issue:44479|issue:45823", + "issue:43701|issue:45325", + "issue:43881|issue:44488", + "issue:44291|issue:44877", + "issue:43606|issue:44265", + "issue:43262|issue:43746", + "issue:43873|issue:45701", + "issue:34634|issue:35707", + "issue:40990|issue:45584", + "issue:44568|issue:45920", + "issue:35707|issue:41720", + "issue:44186|issue:44265", + "issue:43606|issue:43819", + "issue:41720|issue:45823", + "issue:43454|issue:43550", + "issue:39692|issue:40444", + "issue:43377|issue:44610", + "issue:43317|issue:43873", + "issue:43454|issue:45072", + "issue:43572|issue:45759", + "issue:43257|issue:45923", + "issue:43377|issue:44898", + "issue:40990|issue:42947", + "issue:43526|issue:43883", + "issue:43322|issue:46050", + "issue:43881|issue:44991", + "issue:43454|issue:43720", + "issue:41720|issue:43322" + ], + "prepared_review_unit_hash": "fa2b47b8879dc51abb58353fb3bd8cde0f3ec4162f4ed7cb19ed651e8fc883ce", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36270, + "estimated_input_tokens": 9068, + "estimated_eval_tokens": 18392 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "No soft duplicate pairs look like the same underlying bug/change; the overlaps are mostly broad subsystem similarity (tokenization, offloading, device map, multimodal loading) but the concrete failure modes differ. No PRs were provided.", + "confidence": 0.94, + "canonical_issue_reason": "issue:43873 is the strongest hub candidate: it is open, has the most discussion/inbound references among these issues, and covers a broad, actively reported offloading/quantization failure mode.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45920 is the clearest high-impact report: it describes a concrete cross-model tokenizer regression with a well-scoped symptom and broad user impact.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43296", + "right": "issue:45800", + "accept": false, + "reason": "Different problems: a PaddleOCR-VL loading failure in vLLM vs a general torch/transformers version incompatibility." + }, + { + "left": "issue:44387", + "right": "issue:44617", + "accept": false, + "reason": "Both mention memory issues, but one is int4 CUDA reserved memory/OOM and the other is Sam3Video runtime OOM; not the same bug." + }, + { + "left": "issue:44479", + "right": "issue:45823", + "accept": false, + "reason": "Different model families and failures: video-input regression in Qwen VL models vs Gemma4 PLE device mismatch during forward." + }, + { + "left": "issue:43701", + "right": "issue:45325", + "accept": false, + "reason": "Resume-checkpoint key mismatch is unrelated to Qwen2.5-VL rope/position-id scaling." + }, + { + "left": "issue:43881", + "right": "issue:44488", + "accept": false, + "reason": "Both are load failures, but they involve different models and likely different root causes." + }, + { + "left": "issue:44291", + "right": "issue:44877", + "accept": false, + "reason": "Unexpected init_empty_weights argument vs strict config blocking granite_speech config loading are distinct initialization/config issues." + }, + { + "left": "issue:43606", + "right": "issue:44265", + "accept": false, + "reason": "CPU-offload device mismatch for bark-small is not the same as torch.export failures around torch_compilable_check." + }, + { + "left": "issue:43262", + "right": "issue:43746", + "accept": false, + "reason": "Audio chat-template sampling-rate defaulting and GraniteSpeech PEFT checkpoint loading are unrelated." + }, + { + "left": "issue:43873", + "right": "issue:45701", + "accept": false, + "reason": "Quantization/offloading behavior is unrelated to tokenization changes." + }, + { + "left": "issue:34634", + "right": "issue:35707", + "accept": false, + "reason": "BarkProcessor voice_preset failure and progressive generation with inputs_embeds/past_key_values are different code paths." + }, + { + "left": "issue:40990", + "right": "issue:45584", + "accept": false, + "reason": "High perplexity on GPT-OSS vs Whisper empty-transcription failure after align_special_tokens are different bugs." + }, + { + "left": "issue:44568", + "right": "issue:45920", + "accept": false, + "reason": "Both are tokenizer regressions, but one is a specific special-token insertion bug for a single tokenizer while the other is a broader wrong-token-IDs regression across many models." + }, + { + "left": "issue:35707", + "right": "issue:41720", + "accept": false, + "reason": "Progressive generation inputs/past_key_values and Qwen3 auto device-map cudaErrorAssert are unrelated." + }, + { + "left": "issue:44186", + "right": "issue:44265", + "accept": false, + "reason": "LayoutLMv2Tokenizer padding/truncation crashes are not the same as torch.export failures in models using torch_compilable_check." + }, + { + "left": "issue:43606", + "right": "issue:43819", + "accept": false, + "reason": "Both are model-specific generation/load problems, but bark-small CPU offload mismatch and DAC from_latents/forward mismatch are distinct." + }, + { + "left": "issue:41720", + "right": "issue:45823", + "accept": false, + "reason": "Both involve device placement, but the affected models and failure modes differ substantially." + }, + { + "left": "issue:43454", + "right": "issue:43550", + "accept": false, + "reason": "lm_head tying in AyaVisionConfig is unrelated to Bamba-9B-v2 torch.compile SDPA failure." + }, + { + "left": "issue:39692", + "right": "issue:40444", + "accept": false, + "reason": "Documentation/model-processor mismatch and quantization errors are unrelated to iterable dataset multi-image finetuning failures." + }, + { + "left": "issue:43377", + "right": "issue:44610", + "accept": false, + "reason": "MIMI padding-mask batch-vs-single inconsistency is unrelated to OmDet-Turbo processor/model input-size mismatch." + }, + { + "left": "issue:43317", + "right": "issue:43873", + "accept": false, + "reason": "Both concern offloading/quantization, but one is dequantized model loading with auto device_map while the other is a broader offloading-not-working report; not enough evidence of the same bug." + }, + { + "left": "issue:43454", + "right": "issue:45072", + "accept": false, + "reason": "Weight tying in AyaVisionConfig and bf16 dtype mismatches in different models are unrelated." + }, + { + "left": "issue:43572", + "right": "issue:45759", + "accept": false, + "reason": "Missing pad_token_idx in StableLmConfig is unrelated to unwrapping text_config for composite Qwen multimodal configs." + }, + { + "left": "issue:43257", + "right": "issue:45923", + "accept": false, + "reason": "Qwen3 MoE weight conversion under accelerate+deepspeed and a missing supports_gradient_checkpointing flag are separate issues." + }, + { + "left": "issue:43377", + "right": "issue:44898", + "accept": false, + "reason": "Padding-mask support in MIMI and Perceiver non-default-resolution failures are different models and mechanisms." + }, + { + "left": "issue:40990", + "right": "issue:42947", + "accept": false, + "reason": "Perplexity regression on GPT-OSS is unrelated to gradient checkpointing ineffectiveness with PEFT LoRA." + }, + { + "left": "issue:43526", + "right": "issue:43883", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug and Molmo all_tied_weights_keys missing are unrelated." + }, + { + "left": "issue:43322", + "right": "issue:46050", + "accept": false, + "reason": "Llava Next segmentation fault while loading and sinq save/load quantization breakage are different failure modes." + }, + { + "left": "issue:43881", + "right": "issue:44991", + "accept": false, + "reason": "Different model/tokenizer loading failures with no clear shared code-path." + }, + { + "left": "issue:43454", + "right": "issue:43720", + "accept": false, + "reason": "AyaVision lm_head tying and BitNet packed-weight unpacking are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:43322", + "accept": false, + "reason": "Both are load/runtime failures, but one is Qwen3 device-map assertion and the other is Llava Next segmentation fault; not the same bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 12, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:36010", + "issue:36331", + "issue:40990", + "issue:41720", + "issue:42617", + "issue:42915", + "issue:43295", + "issue:43296", + "issue:43317", + "issue:43404", + "issue:43450", + "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:44918", + "issue:44977", + "issue:44991", + "issue:45072", + "issue:45081", + "issue:45161", + "issue:45357", + "issue:45406", + "issue:45632", + "issue:45684", + "issue:45701", + "issue:45704", + "issue:45812", + "issue:45823" + ], + "soft_pairs": [ + "issue:43749|issue:44534", + "issue:43296|issue:44877", + "issue:44466|issue:45357", + "issue:41720|issue:44977", + "issue:42617|issue:42915", + "issue:40990|issue:45701", + "issue:44008|issue:45823", + "issue:44387|issue:45704", + "issue:44186|issue:45072", + "issue:36331|issue:42617", + "issue:43577|issue:43708", + "issue:43404|issue:45357", + "issue:44877|issue:44991", + "issue:43873|issue:44756", + "issue:36331|issue:42915", + "issue:43450|issue:45701", + "issue:43550|issue:43720", + "issue:44423|issue:45406", + "issue:45632|issue:45684", + "issue:41720|issue:42617", + "issue:44479|issue:44918", + "issue:44610|issue:44898", + "issue:43550|issue:43606", + "issue:44186|issue:44610", + "issue:42915|issue:43317", + "issue:43295|issue:45701", + "issue:43526|issue:43881", + "issue:41720|issue:45161", + "issue:44671|issue:44743", + "issue:36010|issue:42617", + "issue:45081|issue:45812" + ], + "prepared_review_unit_hash": "3dbd092e1710d91cd5111729438996bc1496d499f12ad85343abb30f6731a78c", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "serialized_chars": 36661, + "estimated_input_tokens": 9166, + "estimated_eval_tokens": 18588 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is not a true duplicate set; it mixes unrelated issues across tokenization, loading/offload, multimodal processors, training, and model-specific regressions. No single issue or PR is a good canonical representative.", + "confidence": 0.97, + "canonical_issue_reason": "No single issue is canonical because the artifacts describe different bugs in different code paths and models.", + "canonical_pr_reason": null, + "best_issue_reason": "No global best issue: the cluster is too heterogeneous, so a representative should be chosen per subtopic rather than across the whole set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43749", + "right": "issue:44534", + "accept": false, + "reason": "Both are loading/memory-related, but one is broken FSDP CPU RAM-efficient loading and the other is non-persistent buffer corruption; different bugs." + }, + { + "left": "issue:43296", + "right": "issue:44877", + "accept": false, + "reason": "Different failures: PaddleOCR-VL model loading in vLLM versus strict config blocking granite_speech config." + }, + { + "left": "issue:44466", + "right": "issue:45357", + "accept": false, + "reason": "Both involve save_pretrained/serialization, but one is lm_head.weight serialization and the other is incorrect visual encoder keys in Qwen3.5." + }, + { + "left": "issue:41720", + "right": "issue:44977", + "accept": false, + "reason": "Different code paths and symptoms: auto device mapping cuda assert versus flash-attention generation regression." + }, + { + "left": "issue:42617", + "right": "issue:42915", + "accept": false, + "reason": "3d_parallel.py startup failure is unrelated to Qwen3Moe failing with FineGrainedFP8Config." + }, + { + "left": "issue:40990", + "right": "issue:45701", + "accept": false, + "reason": "Perplexity anomaly on gpt-oss-20b is not the same underlying bug as a tokenization-behavior change across versions." + }, + { + "left": "issue:44008", + "right": "issue:45823", + "accept": false, + "reason": "Gemma3n forward variable collision and Gemma4 PLE device mismatch are unrelated bugs." + }, + { + "left": "issue:44387", + "right": "issue:45704", + "accept": false, + "reason": "Both mention memory, but one is int4 quantization OOM in v5 and the other is a T5 apex RMSNorm memory leak." + }, + { + "left": "issue:44186", + "right": "issue:45072", + "accept": false, + "reason": "Tokenizer padding/truncation crash and dtype mismatch in inference are distinct problems." + }, + { + "left": "issue:36331", + "right": "issue:42617", + "accept": false, + "reason": "Trainer compute_loss signature regression is unrelated to 3d_parallel.py failing to run." + }, + { + "left": "issue:43577", + "right": "issue:43708", + "accept": false, + "reason": "BLIP2 dtype-loading issue and Trainer resume/max_steps calculation bug are different training/loading defects." + }, + { + "left": "issue:43404", + "right": "issue:45357", + "accept": false, + "reason": "Mistral3 lm_head tying bug and Qwen3.5 visual encoder key serialization bug are unrelated." + }, + { + "left": "issue:44877", + "right": "issue:44991", + "accept": false, + "reason": "Strict config rejection for granite_speech and tokenizer loading failure for est-roberta do not share the same underlying cause." + }, + { + "left": "issue:43873", + "right": "issue:44756", + "accept": false, + "reason": "Both relate to memory/offload, but one is quantization offloading and the other is mmap-induced OOM on Strix Halo." + }, + { + "left": "issue:36331", + "right": "issue:42915", + "accept": false, + "reason": "Trainer custom loss signature mismatch is unrelated to Qwen3Moe FineGrainedFP8Config failure." + }, + { + "left": "issue:43450", + "right": "issue:45701", + "accept": false, + "reason": "Video batch-shape bug and tokenization-version behavior change are unrelated." + }, + { + "left": "issue:43550", + "right": "issue:43720", + "accept": false, + "reason": "torch.compile SDPA failure in Bamba and packed-weight unpacking failure in BitNet are different model-loading/runtime bugs." + }, + { + "left": "issue:44423", + "right": "issue:45406", + "accept": false, + "reason": "Both crash in serving, but one is continuous-batching multimodal input handling and the other is Gemma4Processor missing _tokenizer." + }, + { + "left": "issue:45632", + "right": "issue:45684", + "accept": false, + "reason": "Cache-path collision for trust_remote_code and read-only permission propagation in save_pretrained are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:42617", + "accept": false, + "reason": "Different problems: Qwen3 auto device mapping assert versus a separate 3d_parallel.py execution failure." + }, + { + "left": "issue:44479", + "right": "issue:44918", + "accept": false, + "reason": "Video-input regression for Qwen models and SFT embedding unpacking failure are not the same bug." + }, + { + "left": "issue:44610", + "right": "issue:44898", + "accept": false, + "reason": "Both involve image sizes, but one is a processor/model size mismatch and the other is a Perceiver interpolation failure." + }, + { + "left": "issue:43550", + "right": "issue:43606", + "accept": false, + "reason": "Bamba SDPA compile failure and Bark CPU-offload device mismatch are unrelated." + }, + { + "left": "issue:44186", + "right": "issue:44610", + "accept": false, + "reason": "LayoutLMv2 tokenizer crash and OmDet-Turbo processor resolution mismatch are different subsystems and failure modes." + }, + { + "left": "issue:42915", + "right": "issue:43317", + "accept": false, + "reason": "Both are model loading/offload issues, but one is Qwen3Moe FineGrainedFP8Config and the other is dequantized model loading with gpu+cpu offload." + }, + { + "left": "issue:43295", + "right": "issue:45701", + "accept": false, + "reason": "Regression in processor.tokenizer/images handling is not the same as a broader tokenization-version change." + }, + { + "left": "issue:43526", + "right": "issue:43881", + "accept": false, + "reason": "BeitImageProcessorFast reduce_labels bug and glm-4v-9b loading failure are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:45161", + "accept": false, + "reason": "Both concern device/sharding behavior, but the concrete failures differ: cuda assert on A800 versus only tensor parallel not working." + }, + { + "left": "issue:44671", + "right": "issue:44743", + "accept": false, + "reason": "CamemBERT masked LM regression and Qwen3.5 recurrent-state reset bug are unrelated model behaviors." + }, + { + "left": "issue:36010", + "right": "issue:42617", + "accept": false, + "reason": "ImportError for GenerationMixin and 3d_parallel.py execution failure have no shared underlying bug." + }, + { + "left": "issue:45081", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer-related regressions, but one is Mistral regex patching and the other is Granite token ID generation; different code paths and models." + } + ] + }, + "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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:29159", + "issue:30064", + "issue:33357", + "issue:34567", + "issue:34634", + "issue:35707", + "issue:36032", + "issue:36331", + "issue:41720", + "issue:42490", + "issue:42915", + "issue:43316", + "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:44451", + "issue:44492", + "issue:44509", + "issue:44514", + "issue:44545", + "issue:44625", + "issue:44898", + "issue:44913", + "issue:44991", + "issue:45059", + "issue:45072", + "issue:45381", + "issue:45406", + "issue:45464", + "issue:45479", + "issue:45701", + "issue:45704", + "issue:45759", + "issue:45812" + ], + "soft_pairs": [ + "issue:43531|issue:43572", + "issue:43316|issue:44913", + "issue:43540|issue:43782", + "issue:42915|issue:43322", + "issue:43421|issue:45812", + "issue:44186|issue:44361", + "issue:36331|issue:41720", + "issue:29159|issue:36032", + "issue:43388|issue:45059", + "issue:45406|issue:45464", + "issue:33357|issue:35707", + "issue:30064|issue:34634", + "issue:41720|issue:43746", + "issue:43606|issue:43720", + "issue:43550|issue:43653", + "issue:43873|issue:45704", + "issue:43421|issue:45701", + "issue:44492|issue:44509", + "issue:43606|issue:43653", + "issue:34634|issue:41720", + "issue:43531|issue:45759", + "issue:42490|issue:43329", + "issue:34567|issue:35707", + "issue:44514|issue:44545", + "issue:44625|issue:45479", + "issue:43421|issue:43927", + "issue:44898|issue:45072", + "issue:44451|issue:44991", + "issue:43782|issue:45381" + ], + "prepared_review_unit_hash": "9b55c0f519cab024e3e7f669471115564adfdb8336b3d7b08cca4866caf594a3", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36540, + "estimated_input_tokens": 9135, + "estimated_eval_tokens": 18526 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly heterogeneous cluster of issue reports across unrelated tokenizer, config, processor, loading, and training paths. The only clear duplicate pair in the packet is 44514/44545, which share the same title about `Qwen2_5_VLProcessor.apply_chat_template` crashing on batched input with `padding=False`.", + "confidence": 0.82, + "canonical_issue_reason": "44514 is the better canonical issue because it is the earlier of the exact title match with 44545.", + "canonical_pr_reason": null, + "best_issue_reason": "44514 is the strongest representative issue because it is the earlier exact duplicate pair in the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43531", + "right": "issue:43572", + "accept": false, + "reason": "Different titles and model areas: Qwen3-MoE `sliding_window` vs StableLmConfig `pad_token_idx`." + }, + { + "left": "issue:43316", + "right": "issue:44913", + "accept": false, + "reason": "Both are config-related, but they describe different fields and different models." + }, + { + "left": "issue:43540", + "right": "issue:43782", + "accept": false, + "reason": "Both mention Qwen models, but one is about video input processing and the other about `from_pretrained` weight loading." + }, + { + "left": "issue:42915", + "right": "issue:43322", + "accept": false, + "reason": "Different model families and failure types: FineGrainedFP8Config vs loading Llava Next models." + }, + { + "left": "issue:43421", + "right": "issue:45812", + "accept": false, + "reason": "Tokenizer-related, but one is runtime post-processor updates and the other is a tokenizer loading regression for Granite models." + }, + { + "left": "issue:44186", + "right": "issue:44361", + "accept": false, + "reason": "Both are tokenizer issues, but the titles point to different tokenizer classes and different failures." + }, + { + "left": "issue:36331", + "right": "issue:41720", + "accept": false, + "reason": "Trainer loss-signature error vs auto device mapping CUDA assert are unrelated." + }, + { + "left": "issue:29159", + "right": "issue:36032", + "accept": false, + "reason": "Both are tokenizer issues, but one is slow/fast behavior inconsistency and the other is a T5Tokenizer load-time error." + }, + { + "left": "issue:43388", + "right": "issue:45059", + "accept": false, + "reason": "Different subsystems: metric gathering vs SAM3 text/bounding-box behavior." + }, + { + "left": "issue:45406", + "right": "issue:45464", + "accept": false, + "reason": "Different components and symptoms: Gemma4Processor missing `_tokenizer` vs Qwen3.5 streaming API failure." + }, + { + "left": "issue:33357", + "right": "issue:35707", + "accept": false, + "reason": "MacOS CLIP bus error vs progressive generation with `inputs_embeds`/`past_key_values` are separate issues." + }, + { + "left": "issue:30064", + "right": "issue:34634", + "accept": false, + "reason": "Different processors and modalities: segmentation maps vs Bark voice preset handling." + }, + { + "left": "issue:41720", + "right": "issue:43746", + "accept": false, + "reason": "CUDA assert during device mapping vs PEFT local checkpoint loading are distinct problems." + }, + { + "left": "issue:43606", + "right": "issue:43720", + "accept": false, + "reason": "Both involve loading/offloading, but the titles describe different model paths and failures." + }, + { + "left": "issue:43550", + "right": "issue:43653", + "accept": false, + "reason": "torch.compile/SDPA vs tokenizer special-token registration are unrelated." + }, + { + "left": "issue:43873", + "right": "issue:45704", + "accept": false, + "reason": "Quantization offloading vs T5/apex memory leak are different issues." + }, + { + "left": "issue:43421", + "right": "issue:45701", + "accept": false, + "reason": "Both relate to tokenization broadly, but one is runtime special-token updates and the other is a version-wide tokenization change report." + }, + { + "left": "issue:44492", + "right": "issue:44509", + "accept": false, + "reason": "A typo in cache strategies is unrelated to outdated pipeline task documentation." + }, + { + "left": "issue:43606", + "right": "issue:43653", + "accept": false, + "reason": "Device offload/loading mismatch vs tokenizer special-token bug are different code paths." + }, + { + "left": "issue:34634", + "right": "issue:41720", + "accept": false, + "reason": "Voice preset handling vs CUDA assert on auto device mapping are unrelated." + }, + { + "left": "issue:43531", + "right": "issue:45759", + "accept": false, + "reason": "Both mention Qwen3-family models, but the titles describe different config issues." + }, + { + "left": "issue:42490", + "right": "issue:43329", + "accept": false, + "reason": "Trailing-slash path warning is unrelated to multimodal token counting." + }, + { + "left": "issue:34567", + "right": "issue:35707", + "accept": false, + "reason": "TrainerState token counter vs progressive generation are different features." + }, + { + "left": "issue:44514", + "right": "issue:44545", + "accept": true, + "reason": "Same title and same reported crash condition for `Qwen2_5_VLProcessor.apply_chat_template` with batched input and `padding=False`." + }, + { + "left": "issue:44625", + "right": "issue:45479", + "accept": false, + "reason": "Different sequence-classification reports: `num_labels` propagation vs zero-loss behavior." + }, + { + "left": "issue:43421", + "right": "issue:43927", + "accept": false, + "reason": "Runtime tokenizer post-processing update vs save/load loss of custom token IDs are different metadata issues." + }, + { + "left": "issue:44898", + "right": "issue:45072", + "accept": false, + "reason": "Perceiver resolution failure vs bfloat16 dtype mismatch are unrelated." + }, + { + "left": "issue:44451", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer-loading regressions, but they refer to different models and titles." + }, + { + "left": "issue:43782", + "right": "issue:45381", + "accept": false, + "reason": "Qwen vision-language load error vs Qwen2.5-VL video position IDs issue are different." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The overall cluster summary is mostly grounded, but the justification is a bit too assertive for the packet. In particular, the reasons for 44514/44545 claim \"precise repro details\" and \"more detailed report\" without body text evidence; from the packet you can safely say they have the same title and 44514 is earlier. A few soft-edge reasons also infer specific root causes beyond what the titles support. Please keep the verdicts and reasons tighter to the observable metadata." + }, + "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": 14, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:30064", + "issue:36010", + "issue:39692", + "issue:40444", + "issue:41720", + "issue:42886", + "issue:43381", + "issue:43421", + "issue:43531", + "issue:43540", + "issue:43596", + "issue:43645", + "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:44368", + "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:45356", + "issue:45357", + "issue:45588", + "issue:45663", + "issue:45704", + "issue:45759", + "issue:45859", + "issue:45907", + "issue:45923", + "issue:46050" + ], + "soft_pairs": [ + "issue:44077|issue:44625", + "issue:45759|issue:45859", + "issue:43531|issue:44589", + "issue:44987|issue:45042", + "issue:44368|issue:45357", + "issue:44062|issue:44451", + "issue:45588|issue:45759", + "issue:43746|issue:46050", + "issue:39692|issue:44610", + "issue:45704|issue:45923", + "issue:44918|issue:44936", + "issue:43421|issue:43653", + "issue:45663|issue:45923", + "issue:43381|issue:43844", + "issue:42886|issue:44843", + "issue:43421|issue:44186", + "issue:45704|issue:45859", + "issue:43994|issue:44671", + "issue:43531|issue:43645", + "issue:41720|issue:45704", + "issue:43746|issue:43873", + "issue:45081|issue:45356", + "issue:39692|issue:43873", + "issue:40444|issue:43746", + "issue:43596|issue:44220", + "issue:45356|issue:45907", + "issue:30064|issue:36010", + "issue:43720|issue:43819", + "issue:44220|issue:44661", + "issue:43653|issue:43720", + "issue:43540|issue:44008" + ], + "prepared_review_unit_hash": "495696192fbb85804da218aaccc56383ae1c115a4c02541079891d64d1f32714", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "serialized_chars": 36823, + "estimated_input_tokens": 9206, + "estimated_eval_tokens": 18668 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous model/tokenizer bugs. Only one soft duplicate looks plausible: the HF_HUB_OFFLINE tokenizer-loading regression pair.", + "confidence": 0.59, + "canonical_issue_reason": "issue:44843 is the most concrete, root-caused representative of the only plausible duplicate pair: it pinpoints the offline tokenizer failure to _patch_mistral_regex/model_info.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44843 is the best overall issue here because it is actionable, specific, and ties the symptom to a concrete code path.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44077", + "right": "issue:44625", + "accept": false, + "reason": "Different problems: patchtsmixer post-init policy vs Qwen3.5 num_labels propagation." + }, + { + "left": "issue:45759", + "right": "issue:45859", + "accept": false, + "reason": "Different code paths: composite config unwrapping vs CPU offload rotary embedding compatibility." + }, + { + "left": "issue:43531", + "right": "issue:44589", + "accept": false, + "reason": "Unrelated failures: Qwen3-MoE sliding_window behavior vs Float8 storage lookup." + }, + { + "left": "issue:44987", + "right": "issue:45042", + "accept": false, + "reason": "Different subsystems and symptoms: loading a specific model vs PIL backend wrongly requiring torchvision." + }, + { + "left": "issue:44368", + "right": "issue:45357", + "accept": false, + "reason": "One is a warning about tied embeddings, the other is incorrect visual encoder keys on save_pretrained." + }, + { + "left": "issue:44062", + "right": "issue:44451", + "accept": false, + "reason": "Both are tokenizer-related, but one is an AddedToken argument error and the other is a model loading failure for ScandiBERT." + }, + { + "left": "issue:45588", + "right": "issue:45759", + "accept": false, + "reason": "Different issues: flash-attention sink handling vs from_config text_config unwrapping." + }, + { + "left": "issue:43746", + "right": "issue:46050", + "accept": false, + "reason": "Different load/save bugs: PEFT local checkpoint loading vs quantized model save_pretrained/from_pretrained behavior." + }, + { + "left": "issue:39692", + "right": "issue:44610", + "accept": false, + "reason": "Both mention processor/model mismatch, but they concern different models and different failure modes." + }, + { + "left": "issue:45704", + "right": "issue:45923", + "accept": false, + "reason": "Different topics: apex RMSNorm memory leak vs missing supports_gradient_checkpointing flag." + }, + { + "left": "issue:44918", + "right": "issue:44936", + "accept": false, + "reason": "Different trainer failures: SFT embedding unpacking vs evaluate-after-train behavior." + }, + { + "left": "issue:43421", + "right": "issue:43653", + "accept": false, + "reason": "Both touch special tokens, but one is a runtime post-processor update feature and the other is a BigBirdTokenizer CI bug." + }, + { + "left": "issue:45663", + "right": "issue:45923", + "accept": false, + "reason": "Different model internals: Gemma4 FSDP2 shared_kv_states bug vs a missing gradient-checkpointing capability flag." + }, + { + "left": "issue:43381", + "right": "issue:43844", + "accept": false, + "reason": "Not the same bug: eval-mode checkpointing restriction vs abnormal gradient growth under ZeRO-3." + }, + { + "left": "issue:42886", + "right": "issue:44843", + "accept": true, + "reason": "Both describe tokenizer loading failures in HF_HUB_OFFLINE mode; 44843 provides the concrete Mistral-regex/model_info root cause." + }, + { + "left": "issue:43421", + "right": "issue:44186", + "accept": false, + "reason": "Shared tokenization theme, but different bugs: dynamic special-token post-processing vs LayoutLMv2 NER/batching crashes." + }, + { + "left": "issue:45704", + "right": "issue:45859", + "accept": false, + "reason": "Different issues: T5 apex RMSNorm leak vs Qwen3_5MoeTextRotaryEmbedding CPU-offload compatibility." + }, + { + "left": "issue:43994", + "right": "issue:44671", + "accept": false, + "reason": "Different models and failure signatures: SigLIP2 nonsensical outputs vs CamemBERT masked LM regression." + }, + { + "left": "issue:43531", + "right": "issue:43645", + "accept": false, + "reason": "Different problems: Qwen3-MoE sliding_window handling vs custom model initialization in Jupyter notebooks." + }, + { + "left": "issue:41720", + "right": "issue:45704", + "accept": false, + "reason": "Different subsystems: Qwen3 auto device mapping CUDA assert vs T5 RMSNorm memory leak." + }, + { + "left": "issue:43746", + "right": "issue:43873", + "accept": false, + "reason": "Both involve loading/offloading, but one is PEFT checkpoint loading and the other is quantization offloading behavior." + }, + { + "left": "issue:45081", + "right": "issue:45356", + "accept": false, + "reason": "Related tokenizer regex area, but not clearly the same bug: one crashes on missing backend_tokenizer, the other is a codec/regression report." + }, + { + "left": "issue:39692", + "right": "issue:43873", + "accept": false, + "reason": "Different scopes: documentation/example errors vs quantization offloading behavior." + }, + { + "left": "issue:40444", + "right": "issue:43746", + "accept": false, + "reason": "Different model pipelines: multi-image IterableDataset fine-tuning vs PEFT local checkpoint loading." + }, + { + "left": "issue:43596", + "right": "issue:44220", + "accept": false, + "reason": "Completely different failures: Deepspeed ZeRO-3/BertModel indexing vs audio fbank extraction." + }, + { + "left": "issue:45356", + "right": "issue:45907", + "accept": false, + "reason": "Different areas: tokenizer codec/regression vs Hub API revision forwarding." + }, + { + "left": "issue:30064", + "right": "issue:36010", + "accept": false, + "reason": "Unrelated bugs: image processor segmentation-map handling vs GenerationMixin import error." + }, + { + "left": "issue:43720", + "right": "issue:43819", + "accept": false, + "reason": "Different code paths: accelerate loading of packed BitNet weights vs DAC.from_latents/STE mismatch." + }, + { + "left": "issue:44220", + "right": "issue:44661", + "accept": false, + "reason": "No clear overlap: fbank feature extraction vs add-new-model-like failing inside TOKENIZER_MAPPING_NAMES." + }, + { + "left": "issue:43653", + "right": "issue:43720", + "accept": false, + "reason": "Different tokenizer CI bug vs BitNet packed-weight loading bug." + }, + { + "left": "issue:43540", + "right": "issue:44008", + "accept": false, + "reason": "Different modalities and models: Qwen3OmniMoe video processing vs Gemma 3n audio_mel_mask name collision." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The assessment is conservative and well grounded in the packet. The only accepted soft pair, issue:42886 with issue:44843, is plausibly the same HF_HUB_OFFLINE tokenizer-loading regression, while the rest of the rejections are appropriately cautious given the differing titles and problem descriptions. No evidence of overstatement or mergeability issues." + }, + "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": 15, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:30064", + "issue:36331", + "issue:39692", + "issue:41720", + "issue:43295", + "issue:43322", + "issue:43335", + "issue:43388", + "issue:43421", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43577", + "issue:43618", + "issue:43643", + "issue:43653", + "issue:43697", + "issue:43716", + "issue:43756", + "issue:43782", + "issue:43818", + "issue:43819", + "issue:43950", + "issue:44008", + "issue:44062", + "issue:44186", + "issue:44442", + "issue:44448", + "issue:44488", + "issue:44671", + "issue:44811", + "issue:44821", + "issue:44843", + "issue:44877", + "issue:44898", + "issue:44977", + "issue:44991", + "issue:45072", + "issue:45081", + "issue:45084", + "issue:45183", + "issue:45381", + "issue:45479", + "issue:45584", + "issue:45685", + "issue:45834", + "issue:45987", + "issue:46032" + ], + "soft_pairs": [ + "issue:43618|issue:43697", + "issue:45183|issue:45479", + "issue:43550|issue:45072", + "issue:43295|issue:45834", + "issue:43550|issue:43819", + "issue:43388|issue:46032", + "issue:44062|issue:44488", + "issue:43716|issue:44008", + "issue:43322|issue:45685", + "issue:43335|issue:43756", + "issue:44186|issue:44898", + "issue:43653|issue:43819", + "issue:43531|issue:43643", + "issue:43950|issue:45987", + "issue:44843|issue:45081", + "issue:43643|issue:44877", + "issue:43540|issue:45381", + "issue:30064|issue:36331", + "issue:44448|issue:44671", + "issue:43421|issue:44811", + "issue:41720|issue:44991", + "issue:43577|issue:43818", + "issue:43782|issue:44977", + "issue:39692|issue:45834", + "issue:45584|issue:45834", + "issue:44821|issue:45084", + "issue:44186|issue:44442" + ], + "prepared_review_unit_hash": "622e4d1b4968df95fe761173a9cd5ee20abc46bbcf0f9191edb6b997ee9dbd50", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "serialized_chars": 36205, + "estimated_input_tokens": 9052, + "estimated_eval_tokens": 18360 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a loose mix of mostly unrelated transformer regressions and loading bugs. The soft links are mostly superficial (same tokenizer/processor/model-loading vocabulary) but the concrete failure paths, affected models, and code paths differ, so I would not merge any of them as duplicates.", + "confidence": 0.93, + "canonical_issue_reason": "Issue #44843 is the strongest representative to anchor this cluster because it has a concrete, reproducible tokenizer-loading regression with a clear root cause (`_patch_mistral_regex` / offline behavior) and broader relevance to the surrounding tokenizer/config loading reports.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue #44843 is the best single issue in the set because it is well-scoped, clearly described, and points to a specific code path that can be fixed and validated. The other issues are mostly separate bugs rather than duplicates of one another.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43618", + "right": "issue:43697", + "accept": false, + "reason": "Different bugs: CLIPOutput attentions assignment vs RTDetrV2 output drift in v5; separate models and code paths." + }, + { + "left": "issue:45183", + "right": "issue:45479", + "accept": false, + "reason": "One is an input validation/XOR error, the other is a zero-loss classification bug with `num_labels=1`; not the same underlying issue." + }, + { + "left": "issue:43550", + "right": "issue:45072", + "accept": false, + "reason": "Bamba `torch.compile`+SDPA failure and SwitchTransformers/TimmWrapper dtype mismatch are unrelated failures." + }, + { + "left": "issue:43295", + "right": "issue:45834", + "accept": false, + "reason": "Processor/tokenizer access regression vs Kosmos2.5 long-OCR index error; different models and failure modes." + }, + { + "left": "issue:43550", + "right": "issue:43819", + "accept": false, + "reason": "Bamba compile/SDPA bug is unrelated to DAC `from_latents` vs forward mismatch." + }, + { + "left": "issue:43388", + "right": "issue:46032", + "accept": false, + "reason": "`gather_for_metrics` last-batch label truncation and Mamba2 cache corruption are distinct issues." + }, + { + "left": "issue:44062", + "right": "issue:44488", + "accept": false, + "reason": "`AddedToken(special=...)` argument collision is a tokenizer API bug, while `sleng-bert` is a separate model-loading failure." + }, + { + "left": "issue:43716", + "right": "issue:44008", + "accept": false, + "reason": "BLIP/Mistral image-preprocessor dtype mismatch vs Gemma3n variable-name collision in forward; different root causes." + }, + { + "left": "issue:43322", + "right": "issue:45685", + "accept": false, + "reason": "Llava Next load segfault and MPS histogram-on-Int error are unrelated model/runtime bugs." + }, + { + "left": "issue:43335", + "right": "issue:43756", + "accept": false, + "reason": "SwitchTransformers sparse-layer config bug is not the same as Smollm3 RoPE-layer dropping." + }, + { + "left": "issue:44186", + "right": "issue:44898", + "accept": false, + "reason": "LayoutLMv2 tokenizer crash on NER/padding and Perceiver interpolation failure are separate bugs." + }, + { + "left": "issue:43653", + "right": "issue:43819", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and DAC latent/forward mismatch do not share the same code path." + }, + { + "left": "issue:43531", + "right": "issue:43643", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior and `trust_remote_code` config field loss are unrelated." + }, + { + "left": "issue:43950", + "right": "issue:45987", + "accept": false, + "reason": "Non-persistent buffer corruption on `from_pretrained` is different from `StaticCache.get_seq_length()` returning a tensor." + }, + { + "left": "issue:44843", + "right": "issue:45081", + "accept": false, + "reason": "Both involve Mistral tokenizer patching, but one is an unconditional `model_info()` offline regression and the other is a missing `backend_tokenizer` attribute; not the same bug." + }, + { + "left": "issue:43643", + "right": "issue:44877", + "accept": false, + "reason": "`trust_remote_code` missing fields and strict config blocking `granite_speech` are different configuration-loading problems." + }, + { + "left": "issue:43540", + "right": "issue:45381", + "accept": false, + "reason": "Qwen3OmniMoe video-input ValueError and qwen2.5-vl video position-id bug affect different models and logic." + }, + { + "left": "issue:30064", + "right": "issue:36331", + "accept": false, + "reason": "Image processor void-segmentation failure and `CustomTrainer.compute_loss()` signature mismatch are completely unrelated." + }, + { + "left": "issue:44448", + "right": "issue:44671", + "accept": false, + "reason": "Pegasus v4/v5 output drift and CamemBERT masked-LM regression are separate model-specific bugs." + }, + { + "left": "issue:43421", + "right": "issue:44811", + "accept": false, + "reason": "Runtime post-processor updates for special tokens and Whisper `batch_decode()` ignoring `skip_special_tokens` are different tokenizer/processor issues." + }, + { + "left": "issue:41720", + "right": "issue:44991", + "accept": false, + "reason": "Qwen3 auto-device-map CUDA assert and tokenizer-loading failure for `est-roberta` are unrelated." + }, + { + "left": "issue:43577", + "right": "issue:43818", + "accept": false, + "reason": "BLIP2 dtype propagation and Video-LLaVA temporal-attention/weight-sharing issues are distinct." + }, + { + "left": "issue:43782", + "right": "issue:44977", + "accept": false, + "reason": "Qwen3VL `weight_only=True` loading error and Qwen3.5 flash-attention generation failure are different concrete problems." + }, + { + "left": "issue:39692", + "right": "issue:45834", + "accept": false, + "reason": "SigLIP2 documentation example errors are documentation/usage issues, not the same as Kosmos2.5 OCR index failure." + }, + { + "left": "issue:45584", + "right": "issue:45834", + "accept": false, + "reason": "Whisper empty transcription after `align_special_tokens` and Kosmos2.5 OCR index error are unrelated." + }, + { + "left": "issue:44821", + "right": "issue:45084", + "accept": false, + "reason": "AutoImageProcessor URL loading and a template-node compile error do not share an underlying bug." + }, + { + "left": "issue:44186", + "right": "issue:44442", + "accept": false, + "reason": "LayoutLMv2 tokenizer crash and AutoTokenizer failing to load FastSpeech2ConformerTokenizer are separate tokenizer bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 16, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:28218", + "issue:29159", + "issue:34634", + "issue:36010", + "issue:36331", + "issue:42175", + "issue:43262", + "issue:43526", + "issue:43577", + "issue:43582", + "issue:43606", + "issue:43644", + "issue:43650", + "issue:43653", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43749", + "issue:43782", + "issue:43819", + "issue:43825", + "issue:43827", + "issue:43906", + "issue:43994", + "issue:44060", + "issue:44291", + "issue:44368", + "issue:44479", + "issue:44485", + "issue:44509", + "issue:44554", + "issue:44561", + "issue:44610", + "issue:44671", + "issue:44805", + "issue:44857", + "issue:44912", + "issue:44936", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45325", + "issue:45406", + "issue:45701", + "issue:45834", + "issue:45987", + "issue:46192" + ], + "soft_pairs": [ + "issue:43644|issue:43749", + "issue:44561|issue:45020", + "issue:43606|issue:45072", + "issue:44479|issue:45834", + "issue:43825|issue:43994", + "issue:34634|issue:36010", + "issue:43577|issue:43582", + "issue:44805|issue:44936", + "issue:45987|issue:46192", + "issue:44485|issue:44509", + "issue:44671|issue:45701", + "issue:43825|issue:43827", + "issue:28218|issue:29159", + "issue:44610|issue:45072", + "issue:43720|issue:45072", + "issue:43782|issue:45325", + "issue:42175|issue:45081", + "issue:43749|issue:44291", + "issue:45081|issue:45406", + "issue:43582|issue:44857", + "issue:43262|issue:43819", + "issue:43650|issue:43906", + "issue:43526|issue:43697", + "issue:34634|issue:36331", + "issue:44060|issue:44368", + "issue:43653|issue:44912", + "issue:43742|issue:45020", + "issue:43526|issue:44554" + ], + "prepared_review_unit_hash": "774763107c560c200136fac80cb8173d70108106852d730265213758465b7f0f", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 28, + "serialized_chars": 35776, + "estimated_input_tokens": 8944, + "estimated_eval_tokens": 18144 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly unrelated issue cluster spanning many distinct regressions. The only strong duplicate candidate is the tokenizer added-token spacing vs slow/fast tokenizer inconsistency pair; the rest are separate model, loading, docs, or runtime bugs.", + "confidence": 0.58, + "canonical_issue_reason": "issue:28218 is the most specific and concrete report of the tokenizer added-token spacing regression, and it plausibly anchors the only true duplicate-style pair in the set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:28218 is the best global issue anchor because it is specific, symptom-focused, and the clearest duplicate target among the tokenizer-related items.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43644", + "right": "issue:43749", + "accept": false, + "reason": "Both concern loading/runtime behavior, but one is junk non-persistent buffers and the other is FSDP CPU RAM-efficient loading; different bugs and code paths." + }, + { + "left": "issue:44561", + "right": "issue:45020", + "accept": false, + "reason": "Both mention remote_code breakage in v5, but they describe different failure modes and likely different underlying compatibility issues." + }, + { + "left": "issue:43606", + "right": "issue:45072", + "accept": false, + "reason": "Different models and different mismatch classes (device offload vs dtype/bfloat16); too broad to be the same fix." + }, + { + "left": "issue:44479", + "right": "issue:45834", + "accept": false, + "reason": "Separate model-specific input regressions: video input handling for Qwen VL variants versus OCR index errors in Kosmos2.5." + }, + { + "left": "issue:43825", + "right": "issue:43994", + "accept": false, + "reason": "One is an error-message/docs issue about removed translation tasks; the other is a model output quality regression. Not the same bug." + }, + { + "left": "issue:34634", + "right": "issue:36010", + "accept": false, + "reason": "BarkProcessor voice_preset failure and GenerationMixin import failure are unrelated." + }, + { + "left": "issue:43577", + "right": "issue:43582", + "accept": false, + "reason": "Blip2 dtype propagation and Apple Silicon caching allocator warmup TypeError are unrelated runtime problems." + }, + { + "left": "issue:44805", + "right": "issue:44936", + "accept": false, + "reason": "Mask/index shape mismatch in tensor ops versus trainer evaluate-after-train failure; no shared concrete code path." + }, + { + "left": "issue:45987", + "right": "issue:46192", + "accept": false, + "reason": "StaticCache return type contract and text_kwargs/return_tensors handling are different API bugs." + }, + { + "left": "issue:44485", + "right": "issue:44509", + "accept": false, + "reason": "One is a RoPE implementation discussion, the other is docs referencing removed pipeline tasks; different issues." + }, + { + "left": "issue:44671", + "right": "issue:45701", + "accept": false, + "reason": "CamemBERT masked-LM regression and a broad tokenization-version complaint are not the same underlying defect." + }, + { + "left": "issue:43825", + "right": "issue:43827", + "accept": false, + "reason": "Both relate to v5 pipeline removals, but one is an error message and the other is docs drift; separate fixes." + }, + { + "left": "issue:28218", + "right": "issue:29159", + "accept": true, + "reason": "Both describe the same tokenizer added-token spacing inconsistency, likely the same slow-vs-fast tokenizer bug." + }, + { + "left": "issue:44610", + "right": "issue:45072", + "accept": false, + "reason": "OmDet-Turbo processor input-size mismatch and dtype mismatch in other models are unrelated." + }, + { + "left": "issue:43720", + "right": "issue:45072", + "accept": false, + "reason": "BitNet packed-weight loading and dtype mismatch inference are different failure modes." + }, + { + "left": "issue:43782", + "right": "issue:45325", + "accept": false, + "reason": "Different Qwen VL issues with different symptoms and likely different fixes." + }, + { + "left": "issue:42175", + "right": "issue:45081", + "accept": false, + "reason": "Package/backend dependency omission is unrelated to a Mistral tokenizer regex crash." + }, + { + "left": "issue:43749", + "right": "issue:44291", + "accept": false, + "reason": "FSDP CPU RAM-efficient loading and init_empty_weights/_is_hf_initialized are distinct loading bugs." + }, + { + "left": "issue:45081", + "right": "issue:45406", + "accept": false, + "reason": "Tokenizer backend regex crash and Gemma4Processor missing _tokenizer are separate processor/tokenizer initialization problems." + }, + { + "left": "issue:43582", + "right": "issue:44857", + "accept": false, + "reason": "Apple Silicon warmup TypeError and CUDA float16 loss crash are unrelated platform-specific bugs." + }, + { + "left": "issue:43262", + "right": "issue:43819", + "accept": false, + "reason": "Audio chat-template sampling-rate defaulting and DAC.from_latents STE mismatch are different subsystems and symptoms." + }, + { + "left": "issue:43650", + "right": "issue:43906", + "accept": false, + "reason": "Placeholder issue text and an isolated reproduction of another bug are not duplicates." + }, + { + "left": "issue:43526", + "right": "issue:43697", + "accept": false, + "reason": "BeitImageProcessorFast reduce_labels and RTDetrV2 output drift are different model/data-processing bugs." + }, + { + "left": "issue:34634", + "right": "issue:36331", + "accept": false, + "reason": "BarkProcessor voice_preset and CustomTrainer.compute_loss signature mismatch are unrelated." + }, + { + "left": "issue:44060", + "right": "issue:44368", + "accept": false, + "reason": "Both mention tied-weights warnings, but one is a Qwen3-Next incorrect tying bug and the other is a LoRA warning nuisance; not the same concrete issue." + }, + { + "left": "issue:43653", + "right": "issue:44912", + "accept": false, + "reason": "BigBirdTokenizer special-token decoding and MXFP4 quantization fallback are unrelated." + }, + { + "left": "issue:43742", + "right": "issue:45020", + "accept": false, + "reason": "KeyError on MobileLLM loading and broad remote_code breakage are not the same specific bug." + }, + { + "left": "issue:43526", + "right": "issue:44554", + "accept": false, + "reason": "BeitImageProcessorFast label reduction and MPS attention correctness are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The analysis is grounded in the packet and stays conservative on the soft edges. The only accepted pair, issue:28218 vs issue:29159, is a plausible tokenizer duplicate based on the titles, and the rest are reasonably separated by symptom/code path. The summary does not overstate 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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:29159", + "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:43696", + "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:44912", + "issue:44936", + "issue:44977", + "issue:44991", + "issue:45042", + "issue:45084", + "issue:45356", + "issue:45459", + "issue:45538", + "issue:45600", + "issue:45759", + "issue:45803", + "issue:45859" + ], + "soft_pairs": [ + "issue:45084|issue:45538", + "issue:43329|issue:45600", + "issue:43746|issue:44811", + "issue:44589|issue:45042", + "issue:43452|issue:44991", + "issue:43638|issue:44936", + "issue:43550|issue:44912", + "issue:45459|issue:45803", + "issue:43819|issue:43927", + "issue:36010|issue:43645", + "issue:43257|issue:43329", + "issue:43854|issue:44977", + "issue:39692|issue:44912", + "issue:38175|issue:44610", + "issue:43720|issue:44610", + "issue:36010|issue:36331", + "issue:43454|issue:43577", + "issue:43531|issue:45042", + "issue:43262|issue:44811", + "issue:43257|issue:43696", + "issue:42490|issue:43257", + "issue:43329|issue:44479", + "issue:43643|issue:45759", + "issue:43749|issue:44756", + "issue:43329|issue:43450", + "issue:43606|issue:45859", + "issue:34567|issue:40990", + "issue:44568|issue:45356", + "issue:43257|issue:43931", + "issue:29159|issue:34567" + ], + "prepared_review_unit_hash": "33c530de1100908d00b417d38048a713fe989b9bfcedc317d310b1cac34a0e9f", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36933, + "estimated_input_tokens": 9234, + "estimated_eval_tokens": 18724 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is highly heterogeneous: tokenizer, trainer, loading, multimodal, quantization, and model-specific bugs are all mixed together. None of the soft pairs look like the same underlying defect or change, so they should all remain separate.", + "confidence": 0.98, + "canonical_issue_reason": "Issue 43329 is the most concrete code-path bug report in the set and is broad enough to serve as an anchor if a single issue must be chosen, but the cluster itself is not a true duplicate set.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43329 is the strongest standalone issue: it names a specific failing branch, concrete undefined variables, and a clear reproduction surface across multiple VLM processors.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45084", + "right": "issue:45538", + "accept": false, + "reason": "Different problems: template compilation error vs tokenizer max_length configuration." + }, + { + "left": "issue:43329", + "right": "issue:45600", + "accept": false, + "reason": "Multimodal token counting bug vs stale auto_mappings reference; unrelated code paths." + }, + { + "left": "issue:43746", + "right": "issue:44811", + "accept": false, + "reason": "Local PEFT checkpoint loading vs Whisper batch_decode skip_special_tokens behavior." + }, + { + "left": "issue:44589", + "right": "issue:45042", + "accept": false, + "reason": "Storage lookup/type issue vs PIL backend dependency regression; not the same bug." + }, + { + "left": "issue:43452", + "right": "issue:44991", + "accept": false, + "reason": "gguf_file loading breakage vs tokenizer loading failure for a specific model." + }, + { + "left": "issue:43638", + "right": "issue:44936", + "accept": false, + "reason": "DeepSpeed Zero3 index error vs trainer.evaluate() failure after train()." + }, + { + "left": "issue:43550", + "right": "issue:44912", + "accept": false, + "reason": "torch.compile/SDPA failure in Bamba vs MXFP4 quantization fallback in gpt-oss." + }, + { + "left": "issue:45459", + "right": "issue:45803", + "accept": false, + "reason": "Exception handling around protobuf decode vs bare except in Fuyu tensor conversion." + }, + { + "left": "issue:43819", + "right": "issue:43927", + "accept": false, + "reason": "DAC latent/from-forward mismatch vs DiaConfig save/load token ID loss." + }, + { + "left": "issue:36010", + "right": "issue:43645", + "accept": false, + "reason": "GenerationMixin import error vs Jupyter custom model initialization regression." + }, + { + "left": "issue:43257", + "right": "issue:43329", + "accept": false, + "reason": "Qwen3 MoE weight conversion/loading issue vs multimodal token counting video-branch bug." + }, + { + "left": "issue:43854", + "right": "issue:44977", + "accept": false, + "reason": "Unit test load failure for GLM-4.7-Flash vs Qwen3.5 flash-attention generation bug." + }, + { + "left": "issue:39692", + "right": "issue:44912", + "accept": false, + "reason": "SigLIP2 docs example errors vs quantization fallback/loading issue; different surfaces." + }, + { + "left": "issue:38175", + "right": "issue:44610", + "accept": false, + "reason": "Unexpected zero probabilities in SigLIP2 vs OmDet-Turbo processor/model input size mismatch." + }, + { + "left": "issue:43720", + "right": "issue:44610", + "accept": false, + "reason": "BitNet packed-weight unpacking during accelerate loading vs OmDet-Turbo shape/size mismatch." + }, + { + "left": "issue:36010", + "right": "issue:36331", + "accept": false, + "reason": "ImportError for GenerationMixin vs custom trainer compute_loss signature mismatch." + }, + { + "left": "issue:43454", + "right": "issue:43577", + "accept": false, + "reason": "AyaVision lm_head tying bug vs Blip2 dtype propagation problem." + }, + { + "left": "issue:43531", + "right": "issue:45042", + "accept": false, + "reason": "Qwen3-MoE sliding_window issue vs PIL image processor torchvision dependency regression." + }, + { + "left": "issue:43262", + "right": "issue:44811", + "accept": false, + "reason": "Audio chat template sampling-rate default vs Whisper batch_decode special-token handling." + }, + { + "left": "issue:43257", + "right": "issue:43696", + "accept": false, + "reason": "MoE weight conversion/loading vs plain CUDA OOM on GPT-oss-20b." + }, + { + "left": "issue:42490", + "right": "issue:43257", + "accept": false, + "reason": "Trailing-slash local path warning/loading issue vs Qwen3 MoE accelerate/deepspeed weight conversion." + }, + { + "left": "issue:43329", + "right": "issue:44479", + "accept": false, + "reason": "Undefined video token-counting branch variables vs v5.3.0 video input regression across Qwen VL models." + }, + { + "left": "issue:43643", + "right": "issue:45759", + "accept": false, + "reason": "trust_remote_code config field loss vs from_config not unwrapping text_config in multimodal Qwen configs." + }, + { + "left": "issue:43749", + "right": "issue:44756", + "accept": false, + "reason": "FSDP CPU RAM efficient loading regression vs mmap/OOM issue on Strix Halo." + }, + { + "left": "issue:43329", + "right": "issue:43450", + "accept": false, + "reason": "Video token counting bug vs batched video processor output shape bug; separate failures." + }, + { + "left": "issue:43606", + "right": "issue:45859", + "accept": false, + "reason": "CPU offload device mismatch in Bark vs Qwen3_5 MoE rotary embedding CPU-offload incompatibility." + }, + { + "left": "issue:34567", + "right": "issue:40990", + "accept": false, + "reason": "TrainerState token counter not updating vs extremely high perplexity on GPT-oss-20b." + }, + { + "left": "issue:44568", + "right": "issue:45356", + "accept": false, + "reason": "add_special_tokens BOS/EOS regression vs Kimi-K2.5 tokenizer codec/warning regression." + }, + { + "left": "issue:43257", + "right": "issue:43931", + "accept": false, + "reason": "Qwen3 MoE loading/conversion issue vs Qwen3-VL-30B-A3B weight shape mismatch." + }, + { + "left": "issue:29159", + "right": "issue:34567", + "accept": false, + "reason": "Tokenizer slow/fast inconsistency vs TrainerState num_input_tokens_seen not updating." + } + ] + }, + "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": 18, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:24643", + "issue:28282", + "issue:29127", + "issue:29159", + "issue:33357", + "issue:34567", + "issue:34689", + "issue:38175", + "issue:41720", + "issue:42175", + "issue:42915", + "issue:43257", + "issue:43317", + "issue:43452", + "issue:43540", + "issue:43577", + "issue:43582", + "issue:43697", + "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:44568", + "issue:44821", + "issue:44849", + "issue:44898", + "issue:44912", + "issue:44987", + "issue:44991", + "issue:45042", + "issue:45072", + "issue:45137", + "issue:45357", + "issue:45381", + "issue:45405", + "issue:45488", + "issue:45538", + "issue:45701", + "issue:45907" + ], + "soft_pairs": [ + "issue:44849|issue:45701", + "issue:42915|issue:43742", + "issue:44291|issue:45042", + "issue:44568|issue:45488", + "issue:42915|issue:44821", + "issue:41720|issue:43540", + "issue:44987|issue:45538", + "issue:43697|issue:45357", + "issue:43452|issue:43582", + "issue:44479|issue:45381", + "issue:43927|issue:44912", + "issue:42915|issue:45538", + "issue:33357|issue:34567", + "issue:43540|issue:44479", + "issue:42175|issue:43824", + "issue:43540|issue:44560", + "issue:43317|issue:45538", + "issue:44987|issue:45907", + "issue:44062|issue:44991", + "issue:24643|issue:29159", + "issue:45137|issue:45405", + "issue:43257|issue:43756", + "issue:28282|issue:34689", + "issue:43577|issue:45072", + "issue:43742|issue:44291", + "issue:42175|issue:44488", + "issue:42915|issue:43749", + "issue:28282|issue:29127", + "issue:38175|issue:44898", + "issue:43582|issue:43782", + "issue:43906|issue:45381" + ], + "prepared_review_unit_hash": "b0a2169d4bbc8f35e2753d6cb879268338d312caa0d8fdf6fb2674303f1f777c", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "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": "These items are mostly unrelated issues across different subsystems and models. Only one soft pair looks like the same underlying bug: the Qwen video-input regression around qwen2.5-vl/qwen3-vl position handling.", + "confidence": 0.82, + "canonical_issue_reason": "issue:45488 is the strongest canonical representative here: it has the most concrete tokenizer regression description, good discussion/inbound references, and a broad downstream impact on DeepSeek V3/R1 loading behavior.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45488 is the best single issue to anchor the set because it is specific enough to be actionable yet broad enough to represent the tokenizer regression theme better than the more generic or narrower alternatives.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44849", + "right": "issue:45701", + "accept": false, + "reason": "Different problems: hidden-states output bug in Qwen3.5 vs a broad tokenization-change report." + }, + { + "left": "issue:42915", + "right": "issue:43742", + "accept": false, + "reason": "Different models and failures: Qwen3Moe FP8 loading vs MobileLLM key error." + }, + { + "left": "issue:44291", + "right": "issue:45042", + "accept": false, + "reason": "Different code paths: init_empty_weights argument handling vs PIL image processor torchvision dependency." + }, + { + "left": "issue:44568", + "right": "issue:45488", + "accept": false, + "reason": "Both tokenizer regressions, but on different tokenizers and mechanisms; not the same concrete bug." + }, + { + "left": "issue:42915", + "right": "issue:44821", + "accept": false, + "reason": "Unrelated: FP8 model loading vs AutoImageProcessor URL loading." + }, + { + "left": "issue:41720", + "right": "issue:43540", + "accept": false, + "reason": "Different subsystems: auto device mapping cuda assert vs video input parsing in Qwen3OmniMoe." + }, + { + "left": "issue:44987", + "right": "issue:45538", + "accept": false, + "reason": "Different bugs: model load regression for a specific repo vs CLIPTokenizer max_length behavior." + }, + { + "left": "issue:43697", + "right": "issue:45357", + "accept": false, + "reason": "Different issues: RTDetrV2 output drift vs incorrect visual encoder keys on save_pretrained." + }, + { + "left": "issue:43452", + "right": "issue:43582", + "accept": false, + "reason": "Unrelated: gguf_file tokenizer/model loading breakage vs Apple Silicon allocator TypeError." + }, + { + "left": "issue:44479", + "right": "issue:45381", + "accept": true, + "reason": "45381 is a concrete narrower instance of the same Qwen2.5-VL/Qwen3-VL video-input position regression described broadly in 44479." + }, + { + "left": "issue:43927", + "right": "issue:44912", + "accept": false, + "reason": "Different bugs: DiaConfig save/load token IDs vs MXFP4 quantization falling back to bf16." + }, + { + "left": "issue:42915", + "right": "issue:45538", + "accept": false, + "reason": "Different failure modes: Qwen3Moe FP8 loading vs CLIPTokenizer model_max_length behavior." + }, + { + "left": "issue:33357", + "right": "issue:34567", + "accept": false, + "reason": "Unrelated: Mac bus error with CLIP model vs TrainerState token-count tracking." + }, + { + "left": "issue:43540", + "right": "issue:44479", + "accept": false, + "reason": "Both mention video inputs, but they involve different Qwen model families and likely different failures." + }, + { + "left": "issue:42175", + "right": "issue:43824", + "accept": false, + "reason": "Different problems: packaging backend contents vs missing import/export for Qwen2_5_VL class." + }, + { + "left": "issue:43540", + "right": "issue:44560", + "accept": false, + "reason": "Different Qwen video bugs with different symptoms and model variants; not clearly the same underlying defect." + }, + { + "left": "issue:43317", + "right": "issue:45538", + "accept": false, + "reason": "Unrelated: dequantized model offload loading vs tokenizer max_length default." + }, + { + "left": "issue:44987", + "right": "issue:45907", + "accept": false, + "reason": "Different scopes: model loading regression vs list_repo_files not forwarding revision." + }, + { + "left": "issue:44062", + "right": "issue:44991", + "accept": false, + "reason": "Both tokenizer-related, but one is an AddedToken TypeError and the other is a model-specific tokenizer load failure." + }, + { + "left": "issue:24643", + "right": "issue:29159", + "accept": false, + "reason": "Unrelated: DeepSpeed training weight shape error vs tokenizer slow/fast inconsistency." + }, + { + "left": "issue:45137", + "right": "issue:45405", + "accept": false, + "reason": "Different bugs: ZeRO3 deque error vs PEFT version pin mismatch." + }, + { + "left": "issue:43257", + "right": "issue:43756", + "accept": false, + "reason": "Different model-specific loading/configuration issues with no clear shared code-path." + }, + { + "left": "issue:28282", + "right": "issue:34689", + "accept": false, + "reason": "Different failures: missing PyTorch dependency detection vs Llama 3.2 vision model loading regression." + }, + { + "left": "issue:43577", + "right": "issue:45072", + "accept": false, + "reason": "Both are dtype-related, but they affect different models and inference paths." + }, + { + "left": "issue:43742", + "right": "issue:44291", + "accept": false, + "reason": "Different issues: MobileLLM key error vs init_empty_weights argument mismatch." + }, + { + "left": "issue:42175", + "right": "issue:44488", + "accept": false, + "reason": "Unrelated: packaging/backends issue vs a specific model loading failure." + }, + { + "left": "issue:42915", + "right": "issue:43749", + "accept": false, + "reason": "Different topics: Qwen3Moe FP8 load failure vs FSDP CPU RAM efficient loading breakage." + }, + { + "left": "issue:28282", + "right": "issue:29127", + "accept": false, + "reason": "Unrelated: PyTorch import availability vs LayoutLMv3 error-message clarity." + }, + { + "left": "issue:38175", + "right": "issue:44898", + "accept": false, + "reason": "Different vision-model bugs affecting different architectures and failure modes." + }, + { + "left": "issue:43582", + "right": "issue:43782", + "accept": false, + "reason": "Unrelated: Apple Silicon allocator TypeError vs Qwen3VL weight_only load error." + }, + { + "left": "issue:43906", + "right": "issue:45381", + "accept": false, + "reason": "One is a reproduction of an older issue; the other is a Qwen2.5-VL video regression. No clear identity." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet, and the only accepted soft pair (44479/45381) is plausibly the same Qwen video-position regression. The other pair verdicts stay conservative and do not overclaim shared bugs." + }, + "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": 19, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:24643", + "issue:29127", + "issue:34567", + "issue:36331", + "issue:41762", + "issue:43404", + "issue:43452", + "issue:43493", + "issue:43526", + "issue:43531", + "issue:43540", + "issue:43643", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43756", + "issue:43906", + "issue:43994", + "issue:44062", + "issue:44291", + "issue:44488", + "issue:44514", + "issue:44589", + "issue:44625", + "issue:44737", + "issue:44792", + "issue:44821", + "issue:44877", + "issue:44898", + "issue:44913", + "issue:44936", + "issue:44964", + "issue:45042", + "issue:45081", + "issue:45216", + "issue:45325", + "issue:45357", + "issue:45375", + "issue:45381", + "issue:45405", + "issue:45479", + "issue:45588", + "issue:45600", + "issue:45823", + "issue:45920", + "issue:45987", + "issue:46121", + "issue:46202" + ], + "soft_pairs": [ + "issue:43404|issue:45987", + "issue:43540|issue:45823", + "issue:44737|issue:45588", + "issue:43526|issue:45479", + "issue:43493|issue:43994", + "issue:43756|issue:45325", + "issue:34567|issue:36331", + "issue:44291|issue:44821", + "issue:44913|issue:46121", + "issue:44062|issue:45081", + "issue:44792|issue:44964", + "issue:45357|issue:45920", + "issue:45042|issue:45081", + "issue:43452|issue:44488", + "issue:43742|issue:44589", + "issue:43643|issue:45375", + "issue:43531|issue:44821", + "issue:45405|issue:45600", + "issue:44625|issue:44877", + "issue:43906|issue:46202", + "issue:43697|issue:45216", + "issue:24643|issue:29127", + "issue:43720|issue:44898", + "issue:44514|issue:45381", + "issue:41762|issue:44936" + ], + "prepared_review_unit_hash": "8314ad4d62f8dff8bb3a4652ed3e450176131603af3295ad2442a64e697c887d", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 25, + "serialized_chars": 35640, + "estimated_input_tokens": 8910, + "estimated_eval_tokens": 18076 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a set of mostly unrelated Transformers bugs and regressions spanning tokenization, model loading, config serialization, training APIs, and multimodal processors. Despite some surface-level similarity, none of the listed pairs look like the same underlying bug or change.", + "confidence": 0.96, + "canonical_issue_reason": "issue:45920 is the strongest representative: it is an open, broad regression affecting tokenization across multiple models, with clear user impact and multiple references.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45920 is the best overall issue candidate because it is broad, current, and actionable, and it likely subsumes the highest-value bug report in the set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43404", + "right": "issue:45987", + "accept": false, + "reason": "Different subsystems: tied-weight loading bug in Mistral3 vs. a cache length return-type bug." + }, + { + "left": "issue:43540", + "right": "issue:45823", + "accept": false, + "reason": "Both are multimodal, but one is a video-input processing error in Qwen3OmniMoe and the other is a device placement mismatch in Gemma4 PLE." + }, + { + "left": "issue:44737", + "right": "issue:45588", + "accept": false, + "reason": "XLNet CPU/device inefficiency is unrelated to a flash-attention crash on sink-less models." + }, + { + "left": "issue:43526", + "right": "issue:45479", + "accept": false, + "reason": "Beit image label reduction bug is unrelated to the sequence-classification zero-loss issue across several models." + }, + { + "left": "issue:43493", + "right": "issue:43994", + "accept": false, + "reason": "Same model family, but one is a HF-vs-JAX implementation discrepancy and the other is bad AutoModel/pipeline outputs for a specific checkpoint." + }, + { + "left": "issue:43756", + "right": "issue:45325", + "accept": false, + "reason": "Both mention Qwen/rope behavior, but they describe different RoPE bugs in different models and code paths." + }, + { + "left": "issue:34567", + "right": "issue:36331", + "accept": false, + "reason": "Trainer state token counter not updating is separate from a custom compute_loss signature breakage." + }, + { + "left": "issue:44291", + "right": "issue:44821", + "accept": false, + "reason": "Unexpected model init argument during init_empty_weights is unrelated to loading AutoImageProcessor from a URL." + }, + { + "left": "issue:44913", + "right": "issue:46121", + "accept": false, + "reason": "Config reload losing rotary_pct is a different bug from rope validation rejecting JSON-loaded lists." + }, + { + "left": "issue:44062", + "right": "issue:45081", + "accept": false, + "reason": "Tokenizer AddedToken keyword collision is unrelated to the Mistral regex patch crash." + }, + { + "left": "issue:44792", + "right": "issue:44964", + "accept": false, + "reason": "Both involve model loading/testing failures, but they affect different models and failure modes." + }, + { + "left": "issue:45357", + "right": "issue:45920", + "accept": false, + "reason": "Qwen3.5 save_pretrained serialization bug is distinct from the broader AutoTokenizer token-ID regression." + }, + { + "left": "issue:45042", + "right": "issue:45081", + "accept": false, + "reason": "PIL backend torchvision dependency regression is unrelated to Mistral tokenizer regex handling." + }, + { + "left": "issue:43452", + "right": "issue:44488", + "accept": false, + "reason": "Both are loading failures, but one is about gguf_file handling in AutoTokenizer/AutoModel and the other is a specific model load failure." + }, + { + "left": "issue:43742", + "right": "issue:44589", + "accept": false, + "reason": "MobileLLM key lookup failure and Float8 storage lookup failure are separate loading/runtime issues." + }, + { + "left": "issue:43643", + "right": "issue:45375", + "accept": false, + "reason": "AutoConfig missing fields with trust_remote_code is a different config-loading issue from strict-dropping a Qwen3_5MoeVisionConfig field." + }, + { + "left": "issue:43531", + "right": "issue:44821", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior is unrelated to loading an image processor from a URL." + }, + { + "left": "issue:45405", + "right": "issue:45600", + "accept": false, + "reason": "Unreleased PEFT version bump is a dependency metadata issue, not the same as stale auto_mappings references breaking CI." + }, + { + "left": "issue:44625", + "right": "issue:44877", + "accept": false, + "reason": "Qwen3.5 num_labels propagation bug is distinct from strict config blocking granite_speech loading." + }, + { + "left": "issue:43906", + "right": "issue:46202", + "accept": false, + "reason": "An isolated reproduction of another issue is not the same as the Gemma pipeline roundtrip failure." + }, + { + "left": "issue:43697", + "right": "issue:45216", + "accept": false, + "reason": "RTDetrV2 output drift in v5 is unrelated to Qwen3.5 save_pretrained checkpoint corruption." + }, + { + "left": "issue:24643", + "right": "issue:29127", + "accept": false, + "reason": "DeepSpeed training RuntimeError and LayoutLMv3 box-count error are completely different problems." + }, + { + "left": "issue:43720", + "right": "issue:44898", + "accept": false, + "reason": "BitNet packed-weight loading failure is unrelated to Perceiver interpolation on non-default image sizes." + }, + { + "left": "issue:44514", + "right": "issue:45381", + "accept": false, + "reason": "Both are Qwen2.5-VL-related, but one is processor chat-template batching and the other is video vision_position_ids scaling." + }, + { + "left": "issue:41762", + "right": "issue:44936", + "accept": false, + "reason": "Gemma3 ZeRO-3 load failure is unrelated to trainer.evaluate() failing after trainer.train()." + } + ] + }, + "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": 20, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:28282", + "issue:29159", + "issue:30064", + "issue:32090", + "issue:33357", + "issue:33666", + "issue:35141", + "issue:38175", + "issue:41720", + "issue:43295", + "issue:43452", + "issue:43577", + "issue:43646", + "issue:43653", + "issue:43688", + "issue:43697", + "issue:43749", + "issue:43819", + "issue:43906", + "issue:43927", + "issue:44361", + "issue:44442", + "issue:44464", + "issue:44466", + "issue:44484", + "issue:44493", + "issue:44514", + "issue:44568", + "issue:44704", + "issue:44743", + "issue:44811", + "issue:44843", + "issue:44936", + "issue:44991", + "issue:45005", + "issue:45290", + "issue:45356", + "issue:45372", + "issue:45440", + "issue:45491", + "issue:45542", + "issue:45701", + "issue:45704", + "issue:45823", + "issue:46002", + "issue:46050", + "issue:46170", + "issue:46178" + ], + "soft_pairs": [ + "issue:45372|issue:46170", + "issue:43688|issue:43749", + "issue:45542|issue:46178", + "issue:43452|issue:44843", + "issue:44466|issue:45005", + "issue:43452|issue:43577", + "issue:44493|issue:46050", + "issue:43819|issue:44811", + "issue:44514|issue:45290", + "issue:44936|issue:45823", + "issue:30064|issue:33666", + "issue:43295|issue:45356", + "issue:44484|issue:44704", + "issue:28282|issue:32090", + "issue:43653|issue:44361", + "issue:44361|issue:44442", + "issue:28282|issue:33357", + "issue:44464|issue:44743", + "issue:38175|issue:43295", + "issue:28282|issue:35141", + "issue:41720|issue:43906", + "issue:45491|issue:46002", + "issue:43653|issue:44568", + "issue:43577|issue:43697", + "issue:43688|issue:45704", + "issue:44843|issue:44991", + "issue:43646|issue:43749", + "issue:43688|issue:45440", + "issue:29159|issue:33357", + "issue:43688|issue:45701", + "issue:43653|issue:43927" + ], + "prepared_review_unit_hash": "1d781ad054998710fb69225f2303ede736533f692f0d60c1ca6240ff87302dbc", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "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 heterogeneous: tokenizer loading/serialization regressions, training/device-map bugs, model-specific numerical issues, and backend/dependency errors. I don\u2019t see any soft pair that is clearly the same underlying bug/change.", + "confidence": 0.78, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45701 is the broadest open report and has the most inbound references, so it is the closest thing to an umbrella issue here, but the cluster is too mixed for a true duplicate canonical.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45372", + "right": "issue:46170", + "accept": false, + "reason": "Both are import/dependency failures, but they stem from different packages and code paths (mistral_common ReasoningEffort vs torch.distributed on Windows/ROCm)." + }, + { + "left": "issue:43688", + "right": "issue:43749", + "accept": false, + "reason": "Aux-loss normalization and FSDP CPU RAM efficient loading are unrelated bugs in different subsystems." + }, + { + "left": "issue:45542", + "right": "issue:46178", + "accept": false, + "reason": "These are both backend-related, but one is a TensorBoard/TensorFlow availability issue and the other is a tensorflow_text backend mapping error." + }, + { + "left": "issue:43452", + "right": "issue:44843", + "accept": false, + "reason": "Both involve loading paths, but gguf_file breakage and the unconditional model_info() call in _patch_mistral_regex are different failures." + }, + { + "left": "issue:44466", + "right": "issue:45005", + "accept": false, + "reason": "Both mention tied weights, but one is device-dependent lm_head serialization and the other is a broader translation-model tied-weights report without the same concrete code path." + }, + { + "left": "issue:43452", + "right": "issue:43577", + "accept": false, + "reason": "GGUF loading breakage and BLIP2 dtype staying float32 are unrelated." + }, + { + "left": "issue:44493", + "right": "issue:46050", + "accept": false, + "reason": "Unexpected position-id keys and NaNs in classification heads are different symptoms with no shared bug mechanism." + }, + { + "left": "issue:43819", + "right": "issue:44811", + "accept": false, + "reason": "DAC.from_latents mismatch and Whisper batch_decode skip_special_tokens handling are unrelated processor/model behaviors." + }, + { + "left": "issue:44514", + "right": "issue:45290", + "accept": false, + "reason": "Both hit apply_chat_template, but the triggering conditions differ: batched padding=False vs assistant tool-call messages with no content." + }, + { + "left": "issue:44936", + "right": "issue:45823", + "accept": false, + "reason": "trainer.evaluate() after train and Gemma4 PLE device mismatch under auto device_map are different bugs." + }, + { + "left": "issue:30064", + "right": "issue:33666", + "accept": false, + "reason": "Image segmentation-map processing and Qwen2-VL multi-GPU training are unrelated." + }, + { + "left": "issue:43295", + "right": "issue:45356", + "accept": false, + "reason": "These are different tokenizer/processor regressions affecting different models and code paths." + }, + { + "left": "issue:44484", + "right": "issue:44704", + "accept": false, + "reason": "A save_pretrained shard-size question and an AutoProcessor kwargs-passing bug are not the same issue." + }, + { + "left": "issue:28282", + "right": "issue:32090", + "accept": false, + "reason": "Missing PyTorch for AutoModel and a Trainer _gpu_broadcast_one NoneType TypeError are unrelated." + }, + { + "left": "issue:43653", + "right": "issue:44361", + "accept": false, + "reason": "Two tokenizer bugs, but on different tokenizers and different failure modes." + }, + { + "left": "issue:44361", + "right": "issue:44442", + "accept": false, + "reason": "MLukeTokenizer AttributeError and AutoTokenizer failing to load FastSpeech2ConformerTokenizer are separate loading/tokenization issues." + }, + { + "left": "issue:28282", + "right": "issue:33357", + "accept": false, + "reason": "Missing PyTorch import and a MacOS bus error on a CLIP model do not share a concrete root cause." + }, + { + "left": "issue:44464", + "right": "issue:44743", + "accept": false, + "reason": "Both concern generation/cache behavior, but chunked generation with compiled forward and Qwen3 recurrent-state resets are different code paths and models." + }, + { + "left": "issue:38175", + "right": "issue:43295", + "accept": false, + "reason": "Unexpected zero probabilities in SigLIP2 is unrelated to processor.tokenizer regressions in custom model code." + }, + { + "left": "issue:28282", + "right": "issue:35141", + "accept": false, + "reason": "A missing PyTorch import error is unrelated to embedding reinitialization in post_init." + }, + { + "left": "issue:41720", + "right": "issue:43906", + "accept": false, + "reason": "Qwen3 auto device mapping cudaErrorAssert and an isolated reproduction of another issue are not enough to establish the same bug." + }, + { + "left": "issue:45491", + "right": "issue:46002", + "accept": false, + "reason": "Both mention NaNs, but one is a Gemma3 sliding-window attention problem and the other is a classification-head init/checkpoint issue." + }, + { + "left": "issue:43653", + "right": "issue:44568", + "accept": false, + "reason": "Both are tokenizer special-token regressions, but they affect different tokenizers and likely different code paths." + }, + { + "left": "issue:43577", + "right": "issue:43697", + "accept": false, + "reason": "A dtype-loading bug in BLIP2 and an RTDetrV2 output divergence are unrelated." + }, + { + "left": "issue:43688", + "right": "issue:45704", + "accept": false, + "reason": "Aux-loss normalization and a T5/apex RMSNorm memory leak are different problems." + }, + { + "left": "issue:44843", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer-loading regressions, but one is offline model_info() behavior in _patch_mistral_regex and the other is a tokenizer load failure for EMBEDDIA/est-roberta." + }, + { + "left": "issue:43646", + "right": "issue:43749", + "accept": false, + "reason": "Custom model initialization breakage in v5 and FSDP CPU RAM efficient loading are unrelated." + }, + { + "left": "issue:43688", + "right": "issue:45440", + "accept": false, + "reason": "Aux-loss normalization and DeepseekV3MoE divergence from remote implementation are different bugs." + }, + { + "left": "issue:29159", + "right": "issue:33357", + "accept": false, + "reason": "Slow/fast tokenizer inconsistency and a MacOS CLIP bus error do not appear to share the same underlying defect." + }, + { + "left": "issue:43688", + "right": "issue:45701", + "accept": false, + "reason": "Aux-loss normalization and a generic tokenization-change report are unrelated." + }, + { + "left": "issue:43653", + "right": "issue:43927", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and DiaConfig losing custom token IDs after save/load are different config/tokenizer persistence 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": 21, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:28218", + "issue:32090", + "issue:33357", + "issue:33666", + "issue:34567", + "issue:36010", + "issue:36331", + "issue:41720", + "issue:43262", + "issue:43278", + "issue:43295", + "issue:43452", + "issue:43493", + "issue:43504", + "issue:43525", + "issue:43531", + "issue:43550", + "issue:43572", + "issue:43577", + "issue:43606", + "issue:43643", + "issue:43688", + "issue:43720", + "issue:43742", + "issue:43756", + "issue:43825", + "issue:43927", + "issue:43994", + "issue:44361", + "issue:44451", + "issue:44464", + "issue:44466", + "issue:44479", + "issue:44554", + "issue:44561", + "issue:44610", + "issue:44625", + "issue:44821", + "issue:44849", + "issue:44913", + "issue:44977", + "issue:45357", + "issue:45588", + "issue:45823", + "issue:46002", + "issue:46050", + "issue:46192" + ], + "soft_pairs": [ + "issue:43531|issue:43742", + "issue:44464|issue:44977", + "issue:43550|issue:43927", + "issue:43643|issue:44561", + "issue:44479|issue:44625", + "issue:43550|issue:44361", + "issue:41720|issue:44464", + "issue:43577|issue:45588", + "issue:32090|issue:34567", + "issue:43577|issue:44554", + "issue:43504|issue:43550", + "issue:43504|issue:43720", + "issue:43504|issue:44610", + "issue:44466|issue:46050", + "issue:32090|issue:33666", + "issue:33666|issue:36010", + "issue:43742|issue:44821", + "issue:45823|issue:46050", + "issue:43452|issue:44451", + "issue:43720|issue:43927", + "issue:43606|issue:43927", + "issue:43262|issue:43295", + "issue:43994|issue:46192", + "issue:43278|issue:43688", + "issue:43525|issue:43572", + "issue:33666|issue:36331", + "issue:44625|issue:46002", + "issue:43720|issue:44361", + "issue:44849|issue:45357", + "issue:43756|issue:44913", + "issue:43493|issue:43825", + "issue:28218|issue:33357" + ], + "prepared_review_unit_hash": "f064ea31720a4900e0f617599bd957da9363f6a9a817310a90578e1cae8436f9", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 32, + "serialized_chars": 36710, + "estimated_input_tokens": 9178, + "estimated_eval_tokens": 18612 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is very noisy: the issues span unrelated bugs across tokenization, training, loading, generation, config serialization, and model-specific regressions. The soft links mostly reflect superficial theme overlap rather than the same underlying defect, so I would not merge any pair.", + "confidence": 0.23, + "canonical_issue_reason": "issue:43927 is the closest hub in the noisy save/load/config-regression subgroup, but it still is not a true duplicate representative of the whole set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43927 is the best single representative only because it has the strongest soft connectivity among the mostly unrelated issues; it still does not justify duplicate clustering.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43531", + "right": "issue:43742", + "accept": false, + "reason": "Different problems: Qwen3-MoE sliding-window behavior vs a MobileLLM load key error." + }, + { + "left": "issue:44464", + "right": "issue:44977", + "accept": false, + "reason": "Both concern generation, but one is compiled chunked decoding and the other is flash-attention on Qwen3.5; different code paths and symptoms." + }, + { + "left": "issue:43550", + "right": "issue:43927", + "accept": false, + "reason": "Torch.compile/SDPA failure in Bamba-9B-v2 is unrelated to DiaConfig losing custom token IDs on save/load." + }, + { + "left": "issue:43643", + "right": "issue:44561", + "accept": false, + "reason": "Both mention trust_remote_code, but one is missing fields from AutoConfig and the other is removal of is_torch_fx_available breaking remote-code models." + }, + { + "left": "issue:44479", + "right": "issue:44625", + "accept": false, + "reason": "Video-input regression for Qwen VL models vs num_labels propagation bug; not the same defect." + }, + { + "left": "issue:43550", + "right": "issue:44361", + "accept": false, + "reason": "Bamba torch.compile/SDPA issue is unrelated to MLukeTokenizer task AttributeError." + }, + { + "left": "issue:41720", + "right": "issue:44464", + "accept": false, + "reason": "CUDA assert under auto device mapping for Qwen3 is not the same as inconsistent outputs in compiled chunked generation." + }, + { + "left": "issue:43577", + "right": "issue:45588", + "accept": false, + "reason": "Model dtype-loading bug for Blip2 is unrelated to flash_attention crashing on s_aux=None." + }, + { + "left": "issue:32090", + "right": "issue:34567", + "accept": false, + "reason": "Both are Trainer-related, but one is a GPU broadcast TypeError and the other is a token-counting state update bug." + }, + { + "left": "issue:43577", + "right": "issue:44554", + "accept": false, + "reason": "Different subsystems: Blip2 dtype handling vs MPS attention correctness with mismatched head dims." + }, + { + "left": "issue:43504", + "right": "issue:43550", + "accept": false, + "reason": "Legacy-field pretrained loading bug is unrelated to Bamba torch.compile/SDPA failure." + }, + { + "left": "issue:43504", + "right": "issue:43720", + "accept": false, + "reason": "Both involve loading, but one is a legacy preset field and the other is packed-weight unpacking during accelerate loading; different bugs." + }, + { + "left": "issue:43504", + "right": "issue:44610", + "accept": false, + "reason": "Model preset loading bug is unrelated to OmDet-Turbo processor producing the wrong image size." + }, + { + "left": "issue:44466", + "right": "issue:46050", + "accept": false, + "reason": "Both touch save/load behavior, but one is tied-weight serialization by device and the other is quantized sinq checkpoint restoration." + }, + { + "left": "issue:32090", + "right": "issue:33666", + "accept": false, + "reason": "Trainer broadcast failure is unrelated to Qwen2-VL multi-GPU training support." + }, + { + "left": "issue:33666", + "right": "issue:36010", + "accept": false, + "reason": "Multi-GPU training request vs GenerationMixin import error; unrelated issues." + }, + { + "left": "issue:43742", + "right": "issue:44821", + "accept": false, + "reason": "MobileLLM checkpoint key error is unrelated to AutoImageProcessor URL loading." + }, + { + "left": "issue:45823", + "right": "issue:46050", + "accept": false, + "reason": "Device-mismatch forward bug in Gemma4 PLE is unrelated to sinq save/load corruption." + }, + { + "left": "issue:43452", + "right": "issue:44451", + "accept": false, + "reason": "gguf_file from_pretrained breakage and ScandiBERT loading failure are separate loading problems with different causes." + }, + { + "left": "issue:43720", + "right": "issue:43927", + "accept": false, + "reason": "Packed-weight unpacking during accelerate loading is not the same as DiaConfig custom token ID persistence." + }, + { + "left": "issue:43606", + "right": "issue:43927", + "accept": false, + "reason": "CPU-offload device mismatch in bark-small is unrelated to config token ID loss." + }, + { + "left": "issue:43262", + "right": "issue:43295", + "accept": false, + "reason": "Audio chat-template sampling-rate default bug is unrelated to processor.tokenizer / image-passing regression." + }, + { + "left": "issue:43994", + "right": "issue:46192", + "accept": false, + "reason": "SigLIP2 nonsensical outputs and return_tensors being ignored are different API bugs." + }, + { + "left": "issue:43278", + "right": "issue:43688", + "accept": false, + "reason": "Embedding dtype drift in evaluation is unrelated to auxiliary-loss normalization in OLMoE/GPT Oss." + }, + { + "left": "issue:43525", + "right": "issue:43572", + "accept": false, + "reason": "Similar symptom class, but different models and fields; not enough evidence of the same underlying bug." + }, + { + "left": "issue:33666", + "right": "issue:36331", + "accept": false, + "reason": "Multi-GPU training request vs custom compute_loss kwarg incompatibility are unrelated." + }, + { + "left": "issue:44625", + "right": "issue:46002", + "accept": false, + "reason": "num_labels propagation bug is unrelated to NaNs in classification heads after checkout/init." + }, + { + "left": "issue:43720", + "right": "issue:44361", + "accept": false, + "reason": "Packed-weight loading bug and MLukeTokenizer AttributeError do not share a code path." + }, + { + "left": "issue:44849", + "right": "issue:45357", + "accept": false, + "reason": "Qwen3.5 hidden-states bug and incorrect visual-encoder key serialization are distinct regressions." + }, + { + "left": "issue:43756", + "right": "issue:44913", + "accept": false, + "reason": "Smollm3 RoPE-layer omission is not the same as GPTNeoXConfig rotary_pct not persisting on reload." + }, + { + "left": "issue:43493", + "right": "issue:43825", + "accept": false, + "reason": "SigLIP2 implementation mismatch and pipeline translation-task error messaging are unrelated." + }, + { + "left": "issue:28218", + "right": "issue:33357", + "accept": false, + "reason": "Tokenizer extra-space behavior is unrelated to the MacOS CLIP bus 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": 22, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:33357", + "issue:33666", + "issue:39692", + "issue:43257", + "issue:43278", + "issue:43295", + "issue:43299", + "issue:43334", + "issue:43493", + "issue:43504", + "issue:43540", + "issue:43572", + "issue:43575", + "issue:43606", + "issue:43646", + "issue:43653", + "issue:43701", + "issue:43756", + "issue:43824", + "issue:43844", + "issue:43873", + "issue:43927", + "issue:43994", + "issue:44112", + "issue:44291", + "issue:44361", + "issue:44423", + "issue:44464", + "issue:44466", + "issue:44488", + "issue:44493", + "issue:44568", + "issue:44589", + "issue:44734", + "issue:44792", + "issue:44843", + "issue:44964", + "issue:44977", + "issue:45083", + "issue:45200", + "issue:45229", + "issue:45405", + "issue:45520", + "issue:45584", + "issue:45759", + "issue:45812", + "issue:45823", + "issue:46050" + ], + "soft_pairs": [ + "issue:44568|issue:45812", + "issue:44964|issue:45405", + "issue:39692|issue:43493", + "issue:43540|issue:44977", + "issue:44488|issue:44843", + "issue:45200|issue:45229", + "issue:43334|issue:43572", + "issue:43278|issue:43844", + "issue:43493|issue:43844", + "issue:43257|issue:43299", + "issue:43334|issue:45759", + "issue:43756|issue:45083", + "issue:39692|issue:43295", + "issue:43646|issue:44466", + "issue:45229|issue:45823", + "issue:43824|issue:44589", + "issue:33357|issue:33666", + "issue:43504|issue:43606", + "issue:43927|issue:44361", + "issue:44589|issue:45520", + "issue:43572|issue:44291", + "issue:44464|issue:45584", + "issue:43504|issue:43653", + "issue:43606|issue:44112", + "issue:43278|issue:43701", + "issue:43575|issue:45405", + "issue:44792|issue:45405", + "issue:43994|issue:44493", + "issue:44423|issue:44734", + "issue:43873|issue:46050" + ], + "prepared_review_unit_hash": "097ec11d0ff9b53230ed663a3b3982a026e3d5c9dcb3d7c76529adf2ec533c7c", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36879, + "estimated_input_tokens": 9220, + "estimated_eval_tokens": 18696 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is mostly a grab-bag of unrelated regression reports. A few pairs share a broad theme (v5 tokenizer/config/model-loading regressions, Qwen/Gemma/Multimodal issues), but the concrete failure modes and code paths differ too much to merge.", + "confidence": 0.7, + "canonical_issue_reason": "Issue 45812 is the clearest representative: it is a concrete, user-visible v4\u2192v5 regression affecting a broad family of models (Granite) and points to a specific tokenizer path rather than a vague symptom.", + "canonical_pr_reason": null, + "best_issue_reason": "45812 is the best standalone issue to anchor the cluster because it describes a specific, reproducible regression with wide impact and a clear affected surface.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44568", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions in v5, but one is about add_special_tokens on mdeberta-v3 and the other is about Granite token IDs; different model-specific code paths." + }, + { + "left": "issue:44964", + "right": "issue:45405", + "accept": false, + "reason": "Unrelated: model loading failure for Phi-4 multimodal vs a version-bump/package availability issue for MIN_PEFT_VERSION." + }, + { + "left": "issue:39692", + "right": "issue:43493", + "accept": false, + "reason": "Both mention SigLIP2, but one is a docs/example mismatch and quantization problem while the other is an implementation-vs-JAX discrepancy." + }, + { + "left": "issue:43540", + "right": "issue:44977", + "accept": false, + "reason": "Different bugs: Qwen3OmniMoe video input processing ValueError vs Qwen3.5 flash-attention generation behavior." + }, + { + "left": "issue:44488", + "right": "issue:44843", + "accept": false, + "reason": "Different failure modes: loading cjvt/sleng-bert vs offline-mode breakage caused by an unconditional model_info() call." + }, + { + "left": "issue:45200", + "right": "issue:45229", + "accept": false, + "reason": "Not the same bug: mm_token_type_ids defaulting for text-only fine-tuning vs Gemma4 multi-GPU OOM." + }, + { + "left": "issue:43334", + "right": "issue:43572", + "accept": false, + "reason": "Both are missing config fields, but they affect different models and different attributes (pad_token_id vs pad_token_idx)." + }, + { + "left": "issue:43278", + "right": "issue:43844", + "accept": false, + "reason": "Embedding dtype drift in eval is unrelated to the ZeRO-3 gradient growth problem." + }, + { + "left": "issue:43493", + "right": "issue:43844", + "accept": false, + "reason": "SigLIP2 implementation mismatch and ZeRO-3 gradient anomalies are distinct issues." + }, + { + "left": "issue:43257", + "right": "issue:43299", + "accept": false, + "reason": "Both involve Qwen3 MoE, but one is about weight conversion with accelerate+deepspeed and the other is a model-loading regression in dev." + }, + { + "left": "issue:43334", + "right": "issue:45759", + "accept": false, + "reason": "Missing pad_token_id on Qwen3-VL config is unrelated to AutoModelForCausalLM.from_config not unwrapping text_config." + }, + { + "left": "issue:43756", + "right": "issue:45083", + "accept": false, + "reason": "Smollm3 RoPE-layer count bug and qwen3_omni_moe feature-length helper behavior are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:43295", + "accept": false, + "reason": "SigLIP2 docs/example errors do not match the processor.tokenizer regression in custom model code." + }, + { + "left": "issue:43646", + "right": "issue:44466", + "accept": false, + "reason": "Custom model initialization breakage and lm_head.weight serialization inconsistency are separate problems." + }, + { + "left": "issue:45229", + "right": "issue:45823", + "accept": false, + "reason": "Same model family, different bugs: multi-GPU inference OOM vs device mismatch with device_map=auto." + }, + { + "left": "issue:43824", + "right": "issue:44589", + "accept": false, + "reason": "Import error for Qwen2_5_VL is unrelated to the Float8 storage lookup failure." + }, + { + "left": "issue:33357", + "right": "issue:33666", + "accept": false, + "reason": "Different subsystems and symptoms: MacOS CLIP bus error vs Qwen2-VL multi-GPU training." + }, + { + "left": "issue:43504", + "right": "issue:43606", + "accept": false, + "reason": "BEiT legacy-field loading and bark-small CPU offload device mismatch are unrelated." + }, + { + "left": "issue:43927", + "right": "issue:44361", + "accept": false, + "reason": "DiaConfig save/load token ID loss and MLukeTokenizer AttributeError are different tokenizer/config bugs." + }, + { + "left": "issue:44589", + "right": "issue:45520", + "accept": false, + "reason": "Float8 storage lookup and flash_attn import handling on Python 3.13 are unrelated." + }, + { + "left": "issue:43572", + "right": "issue:44291", + "accept": false, + "reason": "Both are initialization/config regressions, but the concrete defects differ (_pad_token_idx missing vs unexpected _is_hf_initialized argument)." + }, + { + "left": "issue:44464", + "right": "issue:45584", + "accept": false, + "reason": "Chunked generation with compiled forward is a different code path from Whisper empty-transcription failure after align_special_tokens." + }, + { + "left": "issue:43504", + "right": "issue:43653", + "accept": false, + "reason": "Legacy-field load failure in BEiT and BigBirdTokenizer special-token registration are unrelated." + }, + { + "left": "issue:43606", + "right": "issue:44112", + "accept": false, + "reason": "Both mention devices/CI, but they target different models and different failure modes; not the same bug." + }, + { + "left": "issue:43278", + "right": "issue:43701", + "accept": false, + "reason": "Evaluation dtype drift and resume_from_checkpoint key mismatch are unrelated." + }, + { + "left": "issue:43575", + "right": "issue:45405", + "accept": false, + "reason": "TP-induced OOM on Qwen2-57B is unrelated to a dependency version bump." + }, + { + "left": "issue:44792", + "right": "issue:45405", + "accept": false, + "reason": "janus image-generation test failure is unrelated to the PEFT version availability issue." + }, + { + "left": "issue:43994", + "right": "issue:44493", + "accept": false, + "reason": "Nonsensical SigLIP2 outputs and unexpected position-id keys in many models are too different to be the same underlying bug." + }, + { + "left": "issue:44423", + "right": "issue:44734", + "accept": false, + "reason": "Different serve paths and failures: multimodal continuous batching crashes on .to() vs KV-cache continuation indexing bug." + }, + { + "left": "issue:43873", + "right": "issue:46050", + "accept": false, + "reason": "Offloading-not-working-with-quantization and quantized-model save/load breakage are related only at a high level, not the same concrete bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 23, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:15354", + "issue:28218", + "issue:29159", + "issue:29942", + "issue:30333", + "issue:32090", + "issue:34567", + "issue:37428", + "issue:38175", + "issue:39692", + "issue:42490", + "issue:43232", + "issue:43295", + "issue:43450", + "issue:43493", + "issue:43540", + "issue:43572", + "issue:43582", + "issue:43696", + "issue:43701", + "issue:43824", + "issue:43844", + "issue:43957", + "issue:44186", + "issue:44315", + "issue:44521", + "issue:44554", + "issue:44610", + "issue:44849", + "issue:44964", + "issue:44977", + "issue:44987", + "issue:45072", + "issue:45084", + "issue:45198", + "issue:45200", + "issue:45290", + "issue:45325", + "issue:45356", + "issue:45406", + "issue:45446", + "issue:45520", + "issue:45588", + "issue:45823", + "issue:46050", + "issue:46121", + "issue:46178", + "issue:46192" + ], + "soft_pairs": [ + "issue:45406|issue:46121", + "issue:29942|issue:30333", + "issue:45588|issue:46050", + "issue:42490|issue:43696", + "issue:43844|issue:44964", + "issue:44521|issue:45290", + "issue:28218|issue:34567", + "issue:29159|issue:32090", + "issue:43582|issue:44977", + "issue:44554|issue:45446", + "issue:45084|issue:45520", + "issue:43540|issue:45200", + "issue:15354|issue:38175", + "issue:45072|issue:45198", + "issue:45200|issue:45823", + "issue:37428|issue:43957", + "issue:43232|issue:44849", + "issue:44186|issue:46192", + "issue:43493|issue:43701", + "issue:45823|issue:46192", + "issue:44315|issue:44849", + "issue:43295|issue:44610", + "issue:43295|issue:43450", + "issue:44554|issue:45356", + "issue:43572|issue:44987", + "issue:37428|issue:43824", + "issue:43572|issue:43957", + "issue:45200|issue:45325", + "issue:39692|issue:46192", + "issue:45520|issue:46178" + ], + "prepared_review_unit_hash": "41a86659b29789e33f9696424e5dc27d80127dbea2d2e2f40d6794ba251cbdfa", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36816, + "estimated_input_tokens": 9204, + "estimated_eval_tokens": 18664 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is not a duplicate set; it is a loose collection of unrelated transformers issues with only superficial title similarity. None of the soft edges should be merged.", + "confidence": 0.97, + "canonical_issue_reason": "No single canonical issue fits well: the items cover unrelated failures across tokenization, chat templates, flash-attention, model loading, training state, and backend/import behavior.", + "canonical_pr_reason": null, + "best_issue_reason": "No issue is a good global representative for the whole cluster; picking one would hide the fact that the pairwise matches are mostly incidental.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45406", + "right": "issue:46121", + "accept": false, + "reason": "Gemma4 processor `_tokenizer` attribute error is unrelated to rope validation TypeError." + }, + { + "left": "issue:29942", + "right": "issue:30333", + "accept": false, + "reason": "Flash Attention 2 test failures and MLFlow job reporting are different subsystems and bugs." + }, + { + "left": "issue:45588", + "right": "issue:46050", + "accept": false, + "reason": "Sinkless flash-attention `s_aux=None` crash is unrelated to sinq save/load breakage." + }, + { + "left": "issue:42490", + "right": "issue:43696", + "accept": false, + "reason": "Trailing-slash local import warning and CUDA OOM are not the same underlying issue." + }, + { + "left": "issue:43844", + "right": "issue:44964", + "accept": false, + "reason": "ZeRO-3 gradient anomaly and Phi-4 multimodal loading failure are different code paths." + }, + { + "left": "issue:44521", + "right": "issue:45290", + "accept": false, + "reason": "Both involve chat templates, but one is all-zero assistant masks for multimodal inputs and the other is a crash on tool-call messages; not the same bug." + }, + { + "left": "issue:28218", + "right": "issue:34567", + "accept": false, + "reason": "Tokenizer spacing after added tokens is unrelated to `num_input_tokens_seen` tracking." + }, + { + "left": "issue:29159", + "right": "issue:32090", + "accept": false, + "reason": "Slow/fast tokenizer inconsistency and `_gpu_broadcast_one` NoneType errors are unrelated." + }, + { + "left": "issue:43582", + "right": "issue:44977", + "accept": false, + "reason": "Apple Silicon allocator TypeError is unrelated to Qwen3.5 flash-attention generation failure." + }, + { + "left": "issue:44554", + "right": "issue:45446", + "accept": false, + "reason": "MPS attention correctness and a PyTorch version check bug are different issues." + }, + { + "left": "issue:45084", + "right": "issue:45520", + "accept": false, + "reason": "Non-template-node compile error and Python 3.13 flash_attn import KeyError are unrelated." + }, + { + "left": "issue:43540", + "right": "issue:45200", + "accept": false, + "reason": "Qwen3OmniMoe video-processing error and Gemma4 token-type-id defaulting are different bugs." + }, + { + "left": "issue:15354", + "right": "issue:38175", + "accept": false, + "reason": "TorchScript GeneratorExp export failure is unrelated to SigLIP2 zero probabilities." + }, + { + "left": "issue:45072", + "right": "issue:45198", + "accept": false, + "reason": "bf16 dtype mismatch CI failure and Wav2Vec2 save/tokenization failure are not the same problem." + }, + { + "left": "issue:45200", + "right": "issue:45823", + "accept": false, + "reason": "Gemma4 mm_token_type_ids handling and PLE device-mapping mismatch are distinct forward-pass issues." + }, + { + "left": "issue:37428", + "right": "issue:43957", + "accept": false, + "reason": "Different import/load failures affecting different symbols and model-loading paths." + }, + { + "left": "issue:43232", + "right": "issue:44849", + "accept": false, + "reason": "Generation kwargs sync bug and Qwen3.5 hidden-states bug are unrelated." + }, + { + "left": "issue:44186", + "right": "issue:46192", + "accept": false, + "reason": "LayoutLMv2 NER/padding crash and `return_tensors` being ignored are different tokenizer behaviors." + }, + { + "left": "issue:43493", + "right": "issue:43701", + "accept": false, + "reason": "SigLIP2 implementation mismatch and checkpoint resume key mismatch do not share a code-path." + }, + { + "left": "issue:45823", + "right": "issue:46192", + "accept": false, + "reason": "Gemma4 device mismatch and `return_tensors` ignore are unrelated processing bugs." + }, + { + "left": "issue:44315", + "right": "issue:44849", + "accept": false, + "reason": "Liger Kernel not applied via `model_init` is unrelated to Qwen3.5 hidden-state output behavior." + }, + { + "left": "issue:43295", + "right": "issue:44610", + "accept": false, + "reason": "Processor/tokenizer API regression and OmDet processor image-size mismatch are different model families and failures." + }, + { + "left": "issue:43295", + "right": "issue:43450", + "accept": false, + "reason": "Processor/tokenizer regression and batched video shape bug are unrelated." + }, + { + "left": "issue:44554", + "right": "issue:45356", + "accept": false, + "reason": "MPS attention correctness bug and Kimi-K2.5 tokenizer codec regression are unrelated." + }, + { + "left": "issue:43572", + "right": "issue:44987", + "accept": false, + "reason": "StableLm config `pad_token_idx` regression and physical-intelligence/fast load failure are different issues." + }, + { + "left": "issue:37428", + "right": "issue:43824", + "accept": false, + "reason": "Both are import errors, but they involve different missing symbols and model paths; not the same bug." + }, + { + "left": "issue:43572", + "right": "issue:43957", + "accept": false, + "reason": "Missing `pad_token_idx` in StableLmConfig is unrelated to meta-device model loading breakage." + }, + { + "left": "issue:45200", + "right": "issue:45325", + "accept": false, + "reason": "Gemma4 token-type defaults and Qwen2.5-VL temporal RoPE scaling are different mechanisms." + }, + { + "left": "issue:39692", + "right": "issue:46192", + "accept": false, + "reason": "SigLIP2 documentation errors are unrelated to `return_tensors` being ignored." + }, + { + "left": "issue:45520", + "right": "issue:46178", + "accept": false, + "reason": "flash_attn backend KeyError on Python 3.13 and tensorflow_text backend lookup error are unrelated import/config 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": 24, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:28218", + "issue:35141", + "issue:37428", + "issue:38175", + "issue:42490", + "issue:42915", + "issue:43262", + "issue:43278", + "issue:43295", + "issue:43334", + "issue:43335", + "issue:43388", + "issue:43425", + "issue:43450", + "issue:43493", + "issue:43525", + "issue:43526", + "issue:43550", + "issue:43575", + "issue:43606", + "issue:43653", + "issue:43819", + "issue:43824", + "issue:43827", + "issue:43844", + "issue:43856", + "issue:43873", + "issue:43901", + "issue:43975", + "issue:44112", + "issue:44206", + "issue:44442", + "issue:44466", + "issue:44514", + "issue:44521", + "issue:44610", + "issue:44792", + "issue:44857", + "issue:44898", + "issue:45083", + "issue:45127", + "issue:45198", + "issue:45412", + "issue:45520", + "issue:45563", + "issue:45584", + "issue:46170", + "issue:46192" + ], + "soft_pairs": [ + "issue:43295|issue:43873", + "issue:44898|issue:45412", + "issue:43550|issue:43844", + "issue:44466|issue:45127", + "issue:43334|issue:43525", + "issue:44792|issue:45563", + "issue:43824|issue:43975", + "issue:42915|issue:43824", + "issue:43388|issue:43526", + "issue:43450|issue:43575", + "issue:42490|issue:43493", + "issue:43278|issue:43856", + "issue:28218|issue:35141", + "issue:43975|issue:45520", + "issue:43526|issue:46192", + "issue:38175|issue:43493", + "issue:43653|issue:44112", + "issue:44442|issue:45198", + "issue:44514|issue:44521", + "issue:45520|issue:46170", + "issue:38175|issue:45412", + "issue:44206|issue:45584", + "issue:43262|issue:43450", + "issue:43827|issue:43901", + "issue:43819|issue:44112", + "issue:44610|issue:44857", + "issue:43819|issue:45083", + "issue:37428|issue:43425", + "issue:43335|issue:43550", + "issue:43606|issue:45083" + ], + "prepared_review_unit_hash": "caa5e63a998710f41cd432d5acba6f51093bb8978109f7d08ed51981ab96b841", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36918, + "estimated_input_tokens": 9230, + "estimated_eval_tokens": 18716 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is highly heterogeneous: most pairs only share a broad subsystem or model family, not the same concrete bug. I would not merge any of the soft-edge candidates. If one issue has to stand in as the representative, `issue:44521` is the strongest due to higher activity and inbound references, but the cluster does not look like a true duplicate set.", + "confidence": 0.78, + "canonical_issue_reason": "`issue:44521` has the most inbound references/discussion and is a user-facing bug in a broadly reused path (`apply_chat_template` for multimodal inputs), so it is the best representative of the noisy cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "`issue:44521` is the most impactful and central issue in the set based on activity and references, even though the surrounding items are not true duplicates.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43295", + "right": "issue:43873", + "accept": false, + "reason": "Different failures: processor/tokenizer regression vs quantization/offloading behavior. Same general area, not the same bug." + }, + { + "left": "issue:44898", + "right": "issue:45412", + "accept": false, + "reason": "Unrelated components: Perceiver interpolation shape handling vs RT-DETR memory release." + }, + { + "left": "issue:43550", + "right": "issue:43844", + "accept": false, + "reason": "Different code paths: torch.compile+SDPA on Bamba vs ZeRO-3 gradient growth in DeepSpeed." + }, + { + "left": "issue:44466", + "right": "issue:45127", + "accept": false, + "reason": "Both mention tied weights, but one is serialization/device-dependent and the other is LoRA merge collapse with extended vocab. Not the same defect." + }, + { + "left": "issue:43334", + "right": "issue:43525", + "accept": false, + "reason": "Same symptom class (`pad_token_id` missing) but on different model configs and likely separate fixes." + }, + { + "left": "issue:44792", + "right": "issue:45563", + "accept": false, + "reason": "Janus image-generation test failure is unrelated to a stale warning about `num_return_sequences`." + }, + { + "left": "issue:43824", + "right": "issue:43975", + "accept": false, + "reason": "ImportError for a missing class vs incorrect detokenization in a specific model; different problems." + }, + { + "left": "issue:42915", + "right": "issue:43824", + "accept": false, + "reason": "Qwen3 MoE FP8 failure and Qwen2.5-VL import error are unrelated." + }, + { + "left": "issue:43388", + "right": "issue:43526", + "accept": false, + "reason": "Both involve labels, but one is gather/evaluation batching and the other is image-processor label reduction. Different bugs." + }, + { + "left": "issue:43450", + "right": "issue:43575", + "accept": false, + "reason": "Video processor batch-shape bug vs tensor-parallel OOM when loading a large model." + }, + { + "left": "issue:42490", + "right": "issue:43493", + "accept": false, + "reason": "Import warning for a trailing-slash path is unrelated to SigLIP2 implementation discrepancies." + }, + { + "left": "issue:43278", + "right": "issue:43856", + "accept": false, + "reason": "Embedding dtype drift and MoE memory usage are different issues." + }, + { + "left": "issue:28218", + "right": "issue:35141", + "accept": false, + "reason": "Tokenizer spacing bug and embedding reinitialization after resizing are distinct tokenizer/model-init issues." + }, + { + "left": "issue:43975", + "right": "issue:45520", + "accept": false, + "reason": "Detokenization regression and Python 3.13 flash-attn import handling are unrelated." + }, + { + "left": "issue:43526", + "right": "issue:46192", + "accept": false, + "reason": "Image label reduction bug vs `text_kwargs` silently overriding `return_tensors`; different API paths." + }, + { + "left": "issue:38175", + "right": "issue:43493", + "accept": false, + "reason": "Same model family, but one report is zero probabilities and the other is a general HF-vs-JAX discrepancy; not enough evidence of the same concrete bug." + }, + { + "left": "issue:43653", + "right": "issue:44112", + "accept": false, + "reason": "BigBird tokenizer special-token registration and a GraniteSpeech CI test issue are unrelated." + }, + { + "left": "issue:44442", + "right": "issue:45198", + "accept": false, + "reason": "Different tokenizers and different failure modes; not duplicates." + }, + { + "left": "issue:44514", + "right": "issue:44521", + "accept": false, + "reason": "Both hit `apply_chat_template`, but one crashes on batched padding=False input while the other returns zero assistant masks. Related area, different bug." + }, + { + "left": "issue:45520", + "right": "issue:46170", + "accept": false, + "reason": "Different platform/import failures: flash-attn on Python 3.13 vs Windows ROCm distributed dependency." + }, + { + "left": "issue:38175", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 zero-probability behavior is unrelated to RT-DETR memory reclamation." + }, + { + "left": "issue:44206", + "right": "issue:45584", + "accept": false, + "reason": "Audio feature extractor argument regression vs Whisper empty-transcription generation failure are distinct issues." + }, + { + "left": "issue:43262", + "right": "issue:43450", + "accept": false, + "reason": "Audio chat-template sampling-rate default and batched video processor shape are unrelated." + }, + { + "left": "issue:43827", + "right": "issue:43901", + "accept": false, + "reason": "Both are docs-related, but they cover different APIs and different stale references." + }, + { + "left": "issue:43819", + "right": "issue:44112", + "accept": false, + "reason": "DAC latent conversion mismatch and GraniteSpeech CI device override test are unrelated." + }, + { + "left": "issue:44610", + "right": "issue:44857", + "accept": false, + "reason": "Wrong processor image size and AMP/CUDA loss crash are different problems." + }, + { + "left": "issue:43819", + "right": "issue:45083", + "accept": false, + "reason": "DAC STE mismatch vs Qwen3 Omni-MoE feature-length helper behavior are unrelated." + }, + { + "left": "issue:37428", + "right": "issue:43425", + "accept": false, + "reason": "A missing internal import and Torch 2.10 incompatibility are different release issues." + }, + { + "left": "issue:43335", + "right": "issue:43550", + "accept": false, + "reason": "SwitchTransformers config bug and Bamba torch.compile/SDPA failure are unrelated." + }, + { + "left": "issue:43606", + "right": "issue:45083", + "accept": false, + "reason": "CPU-offload device mismatch and Qwen3 Omni-MoE helper behavior are not the same bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 25, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:29127", + "issue:29942", + "issue:32090", + "issue:37428", + "issue:38175", + "issue:39692", + "issue:42490", + "issue:43278", + "issue:43335", + "issue:43504", + "issue:43526", + "issue:43550", + "issue:43606", + "issue:43611", + "issue:43653", + "issue:43720", + "issue:43819", + "issue:43825", + "issue:43854", + "issue:43931", + "issue:44112", + "issue:44206", + "issue:44351", + "issue:44360", + "issue:44448", + "issue:44493", + "issue:44561", + "issue:44743", + "issue:44779", + "issue:44855", + "issue:44857", + "issue:44977", + "issue:45072", + "issue:45083", + "issue:45127", + "issue:45200", + "issue:45229", + "issue:45245", + "issue:45290", + "issue:45310", + "issue:45381", + "issue:45478", + "issue:45588", + "issue:45593", + "issue:45823", + "issue:45859", + "issue:45920", + "issue:46192" + ], + "soft_pairs": [ + "issue:44857|issue:45593", + "issue:44448|issue:44743", + "issue:45290|issue:45381", + "issue:45127|issue:45245", + "issue:29942|issue:32090", + "issue:45200|issue:45588", + "issue:37428|issue:44351", + "issue:43278|issue:43825", + "issue:43335|issue:43653", + "issue:44206|issue:45823", + "issue:43611|issue:43931", + "issue:43550|issue:44112", + "issue:43819|issue:44493", + "issue:44855|issue:45083", + "issue:43335|issue:43504", + "issue:45588|issue:45859", + "issue:29127|issue:32090", + "issue:43335|issue:45083", + "issue:39692|issue:43526", + "issue:45310|issue:45478", + "issue:39692|issue:44493", + "issue:43720|issue:44112", + "issue:43335|issue:45072", + "issue:44448|issue:44779", + "issue:43335|issue:44112", + "issue:44360|issue:44561", + "issue:45920|issue:46192", + "issue:42490|issue:43854", + "issue:44977|issue:45229", + "issue:43606|issue:44857", + "issue:38175|issue:44493" + ], + "prepared_review_unit_hash": "5c361e0f0d7949927c8792b3d313b6fc7ec88a8fc23f120bab0c8a823d72ffdf", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37157, + "estimated_input_tokens": 9290, + "estimated_eval_tokens": 18836 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is mostly a heterogeneous grab-bag of closed bug reports across unrelated subsystems, with only one clear duplicate pair: the Qwen3.5 MoE from_pretrained regression reports.", + "confidence": 0.87, + "canonical_issue_reason": "No single issue cleanly represents the whole set because the reports cover unrelated failures; among the items, 45310 is the clearest local canonical only for the exact Qwen3.5 MoE duplicate pair.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45310 is the best issue candidate because it is the earlier, more central report for the only true duplicate pair, and 45478 is essentially the same bug report with a later timestamp.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44857", + "right": "issue:45593", + "accept": false, + "reason": "Both are model-specific training losses, but one is an AMP/CUDA crash and the other is denoising/aux-loss behavior; different bug surfaces." + }, + { + "left": "issue:44448", + "right": "issue:44743", + "accept": false, + "reason": "Both mention v4/v5 differences, but one is a Pegasus output regression and the other is a recurrent-state reset bug in modular_qwen3_5.py." + }, + { + "left": "issue:45290", + "right": "issue:45381", + "accept": false, + "reason": "These are different pipeline areas: tokenization crashes on tool-call messages versus wrong vision_position_ids for Qwen2.5-VL video input." + }, + { + "left": "issue:45127", + "right": "issue:45245", + "accept": false, + "reason": "LoRA merge collapse with tied embeddings is unrelated to the category-cardinality runtime error." + }, + { + "left": "issue:29942", + "right": "issue:32090", + "accept": false, + "reason": "One is failing Flash Attention 2 tests; the other is a Trainer/_gpu_broadcast_one NoneType error. Different failure modes." + }, + { + "left": "issue:45200", + "right": "issue:45588", + "accept": false, + "reason": "Gemma4 mm_token_type_ids defaults and flash_attention s_aux=None handling are separate code paths and problems." + }, + { + "left": "issue:37428", + "right": "issue:44351", + "accept": false, + "reason": "These are different import-level API breakages: a missing flash-attention helper versus missing HybridCache export." + }, + { + "left": "issue:43278", + "right": "issue:43825", + "accept": false, + "reason": "Embedding dtype drift during evaluate is not the same as pipeline() advertising unsupported translation tasks." + }, + { + "left": "issue:43335", + "right": "issue:43653", + "accept": false, + "reason": "SwitchTransformers sparse-layer creation and BigBirdTokenizer special-token registration are unrelated bugs." + }, + { + "left": "issue:44206", + "right": "issue:45823", + "accept": false, + "reason": "Both are Gemma4-related, but one is a feature-extractor arg regression and the other is a device-map forward mismatch." + }, + { + "left": "issue:43611", + "right": "issue:43931", + "accept": false, + "reason": "Base_model_prefix loading breakage and Qwen3-VL weight-shape mismatch are distinct model-loading failures." + }, + { + "left": "issue:43550", + "right": "issue:44112", + "accept": false, + "reason": "Torch.compile+SDPA failure in Bamba is unrelated to the GraniteSpeech stale device-override CI test." + }, + { + "left": "issue:43819", + "right": "issue:44493", + "accept": false, + "reason": "DAC.from_latents/STE mismatch is a model-specific forward-vs-latents bug, not the broad position-id key issue." + }, + { + "left": "issue:44855", + "right": "issue:45083", + "accept": false, + "reason": "Python 3.13 IndentationError in DebertaV2 import is unrelated to qwen3_omni_moe feature-extraction length behavior." + }, + { + "left": "issue:43335", + "right": "issue:43504", + "accept": false, + "reason": "SwitchTransformers sparse-layer creation and BEiT semantic-segmentation legacy-field loading are different subsystems and defects." + }, + { + "left": "issue:45588", + "right": "issue:45859", + "accept": false, + "reason": "Both involve offload/flash-related behavior, but one is an AttributeError on s_aux=None and the other is a CPU-offload incompatibility in rotary embedding." + }, + { + "left": "issue:29127", + "right": "issue:32090", + "accept": false, + "reason": "LayoutLMv3 box-info error messaging and Trainer GPU broadcast NoneType are clearly unrelated." + }, + { + "left": "issue:43335", + "right": "issue:45083", + "accept": false, + "reason": "SwitchTransformers sparse-layer config and qwen3_omni_moe length helper behavior do not describe the same bug." + }, + { + "left": "issue:39692", + "right": "issue:43526", + "accept": false, + "reason": "SigLIP2 doc example errors and BEiT Fast image processor label reduction are unrelated issues." + }, + { + "left": "issue:45310", + "right": "issue:45478", + "accept": true, + "reason": "Same exact reported bug: transformers>=5.4.0 breaks Qwen3.5 MoE from_pretrained; 45478 is a later duplicate of 45310." + }, + { + "left": "issue:39692", + "right": "issue:44493", + "accept": false, + "reason": "Documentation example failures are not the same as a general unexpected key/position-id issue across models." + }, + { + "left": "issue:43720", + "right": "issue:44112", + "accept": false, + "reason": "BitNet packed-weight unpacking during accelerate loading is unrelated to the GraniteSpeech CI device-override test." + }, + { + "left": "issue:43335", + "right": "issue:45072", + "accept": false, + "reason": "A sparse-layer config bug is not the same as dtype mismatches in SwitchTransformers/TimmWrapperModel inference." + }, + { + "left": "issue:44448", + "right": "issue:44779", + "accept": false, + "reason": "Pegasus v4/v5 output differences and Deepseek tokenizer regressions are separate model/tokenizer bugs." + }, + { + "left": "issue:43335", + "right": "issue:44112", + "accept": false, + "reason": "SwitchTransformers sparse-layer creation and a GraniteSpeech CI test failure are not the same underlying problem." + }, + { + "left": "issue:44360", + "right": "issue:44561", + "accept": false, + "reason": "A discussion about the DSA indexer lacking ReLU is not the same as trust_remote_code breakage from removing is_torch_fx_available." + }, + { + "left": "issue:45920", + "right": "issue:46192", + "accept": false, + "reason": "Both involve tokenizer/text kwargs behavior, but one is wrong token IDs across multiple models and the other is return_tensors being ignored when text_kwargs is passed." + }, + { + "left": "issue:42490", + "right": "issue:43854", + "accept": false, + "reason": "A local-path import warning and a unit-test model loading failure for GLM-4.7-Flash are different issues." + }, + { + "left": "issue:44977", + "right": "issue:45229", + "accept": false, + "reason": "Qwen3.5 flash-attention generation issues and Gemma4 multi-GPU CUDA OOM are different failure modes." + }, + { + "left": "issue:43606", + "right": "issue:44857", + "accept": false, + "reason": "CPU-offload device mismatch in bark-small and LwDetrImageLoss AMP/CUDA crash are unrelated." + }, + { + "left": "issue:38175", + "right": "issue:44493", + "accept": false, + "reason": "Unexpected zero probabilities in siglip2-base-patch16-224 is not the same as a general unexpected position-id key issue." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: the set is heterogeneous, and the only accepted soft pair is 45310/45478, which are near-identical Qwen3.5 MoE from_pretrained reports. The other pairwise rejections are conservative and the reasons stay aligned with the issue titles." + }, + "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": 26, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "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:43381", + "issue:43412", + "issue:43526", + "issue:43550", + "issue:43575", + "issue:43701", + "issue:43723", + "issue:43873", + "issue:43927", + "issue:43976", + "issue:44448", + "issue:44462", + "issue:44554", + "issue:44561", + "issue:44568", + "issue:44779", + "issue:44857", + "issue:44977", + "issue:44987", + "issue:45072", + "issue:45083", + "issue:45198", + "issue:45229", + "issue:45372", + "issue:45406", + "issue:45440", + "issue:45459", + "issue:45491", + "issue:45563", + "issue:45588", + "issue:45698", + "issue:45712", + "issue:45803", + "issue:45823" + ], + "soft_pairs": [ + "issue:34689|issue:35141", + "issue:44857|issue:45072", + "issue:44448|issue:44977", + "issue:40444|issue:43526", + "issue:28218|issue:32090", + "issue:43701|issue:45083", + "issue:43723|issue:44554", + "issue:29942|issue:35141", + "issue:32090|issue:33357", + "issue:43550|issue:45083", + "issue:44561|issue:44779", + "issue:43873|issue:45229", + "issue:43927|issue:45698", + "issue:37428|issue:44987", + "issue:44462|issue:44561", + "issue:41720|issue:45229", + "issue:44977|issue:45563", + "issue:43278|issue:43329", + "issue:42490|issue:43575", + "issue:10000|issue:15354", + "issue:44568|issue:45491", + "issue:45372|issue:45588", + "issue:45198|issue:45803", + "issue:44857|issue:45588", + "issue:43412|issue:45588", + "issue:43976|issue:45440", + "issue:45372|issue:45406", + "issue:43278|issue:43381", + "issue:45459|issue:45712", + "issue:45588|issue:45823" + ], + "prepared_review_unit_hash": "abbe3156575e09aca9c1d08f1ffbcef69a286916204599f69de0f94fb85cc993", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36872, + "estimated_input_tokens": 9218, + "estimated_eval_tokens": 18692 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items are largely unrelated issues; the soft pairs mostly share only broad subsystem keywords (tokenizers, attention, loading, dtype, Gemma/Qwen, etc.) but not the same concrete bug. No pull requests are present.", + "confidence": 0.97, + "canonical_issue_reason": "Issue #43873 is the best canonical issue candidate: it is open, has the strongest cross-references among the set, and describes a broader, actively discussed quantization/offloading malfunction.", + "canonical_pr_reason": null, + "best_issue_reason": "#43873 is the best representative issue because it is open and appears to be the most central/highly referenced problem in this set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:34689", + "right": "issue:35141", + "accept": false, + "reason": "One is a model-loading regression for Llama 3.2 Vision; the other is a post-init embedding reinitialization bug. Different code paths and failure modes." + }, + { + "left": "issue:44857", + "right": "issue:45072", + "accept": false, + "reason": "Both mention dtype problems, but they affect different models and distinct behaviors (loss crash vs inference mismatches). Not the same bug." + }, + { + "left": "issue:44448", + "right": "issue:44977", + "accept": false, + "reason": "Different models and different symptoms: Pegasus output drift across versions vs Qwen3.5 flash-attention generation failure." + }, + { + "left": "issue:40444", + "right": "issue:43526", + "accept": false, + "reason": "IterableDataset multi-image finetuning failure is unrelated to BeitImageProcessorFast reduce_labels behavior." + }, + { + "left": "issue:28218", + "right": "issue:32090", + "accept": false, + "reason": "Tokenizer spacing after added tokens and Trainer/_gpu_broadcast_one NoneType errors are unrelated." + }, + { + "left": "issue:43701", + "right": "issue:45083", + "accept": false, + "reason": "Checkpoint resume key mismatch is unrelated to a Qwen3 Omni feature-length helper bug." + }, + { + "left": "issue:43723", + "right": "issue:44554", + "accept": false, + "reason": "Tokenizer loading in v5 and an MPS attention correctness issue are different subsystems and failure modes." + }, + { + "left": "issue:29942", + "right": "issue:35141", + "accept": false, + "reason": "Flash Attention 2 test failures are unrelated to embedding reinitialization in post_init." + }, + { + "left": "issue:32090", + "right": "issue:33357", + "accept": false, + "reason": "Trainer broadcast TypeError and MacOS bus error with a CLIP model are not the same underlying defect." + }, + { + "left": "issue:43550", + "right": "issue:45083", + "accept": false, + "reason": "torch.compile/SDPA failure for Bamba is unrelated to the qwen3_omni_moe helper-length bug." + }, + { + "left": "issue:44561", + "right": "issue:44779", + "accept": false, + "reason": "A v5 remote-code compatibility break is not the same as DeepSeek tokenizer incorrect results." + }, + { + "left": "issue:43873", + "right": "issue:45229", + "accept": false, + "reason": "Quantization/offloading issues and a Gemma4 multi-GPU OOM are both memory-related but not the same bug." + }, + { + "left": "issue:43927", + "right": "issue:45698", + "accept": false, + "reason": "DiaConfig token-ID persistence and wrong custom module loading after save/load are related to serialization, but they are different concrete failures." + }, + { + "left": "issue:37428", + "right": "issue:44987", + "accept": false, + "reason": "Import error for a flash-attention helper and a model load failure in transformers>=5.1.0 are different incompatibilities." + }, + { + "left": "issue:44462", + "right": "issue:44561", + "accept": false, + "reason": "AutoTokenizer ignoring tokenizer.json is unrelated to the removal of is_torch_fx_available." + }, + { + "left": "issue:41720", + "right": "issue:45229", + "accept": false, + "reason": "Qwen3 device-mapping cudaErrorAssert and Gemma4 multi-GPU OOM are separate runtime failures." + }, + { + "left": "issue:44977", + "right": "issue:45563", + "accept": false, + "reason": "Flash-attention generation malfunction and a stale warning in paged generate() are not the same issue." + }, + { + "left": "issue:43278", + "right": "issue:43329", + "accept": false, + "reason": "Embedding dtype drift in evaluation is unrelated to an undefined-variable bug in multimodal token counting." + }, + { + "left": "issue:42490", + "right": "issue:43575", + "accept": false, + "reason": "Local-path import warning and tensor-parallel OOM when loading Qwen2-57B are different problems." + }, + { + "left": "issue:10000", + "right": "issue:15354", + "accept": false, + "reason": "German DistilBertModel issue and torch.jit GeneratorExp export failure for ViT are unrelated." + }, + { + "left": "issue:44568", + "right": "issue:45491", + "accept": false, + "reason": "Tokenizer special-token insertion bug and Gemma3 NaN embeddings with sliding-window attention are unrelated." + }, + { + "left": "issue:45372", + "right": "issue:45588", + "accept": false, + "reason": "Gemma4 processor import failure and flash_attention.py crashing on s_aux=None are distinct bugs." + }, + { + "left": "issue:45198", + "right": "issue:45803", + "accept": false, + "reason": "Wav2Vec2 save/tokenization failure and a bare-except issue in Fuyu tensor conversion are different code paths." + }, + { + "left": "issue:44857", + "right": "issue:45588", + "accept": false, + "reason": "Float16 AMP crash in LwDetrImageLoss and sink-less flash_attention AttributeError are unrelated." + }, + { + "left": "issue:43412", + "right": "issue:45588", + "accept": false, + "reason": "Executorch export failures for gemma3n and flash_attention s_aux=None crashes are unrelated." + }, + { + "left": "issue:43976", + "right": "issue:45440", + "accept": false, + "reason": "Python version compatibility break and DeepSeekV3MoE divergence from remote implementation are different issues." + }, + { + "left": "issue:45372", + "right": "issue:45406", + "accept": false, + "reason": "Gemma4 processor loading import error and Gemma4 serve missing _tokenizer are separate failures." + }, + { + "left": "issue:43278", + "right": "issue:43381", + "accept": false, + "reason": "BF16/FP32 dtype drift during evaluate and gradient checkpointing in eval mode are not the same bug." + }, + { + "left": "issue:45459", + "right": "issue:45712", + "accept": false, + "reason": "Tokenizer error masking when protobuf is absent and leftover dummy classes in dummy_pt_objects.py are unrelated." + }, + { + "left": "issue:45588", + "right": "issue:45823", + "accept": false, + "reason": "Gemma4 flash-attention AttributeError and Gemma4 PLE device-mapping mismatch affect different parts of the model stack." + } + ] + }, + "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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:25251", + "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:43611", + "issue:43653", + "issue:43701", + "issue:43756", + "issue:43824", + "issue:43873", + "issue:43994", + "issue:44186", + "issue:44206", + "issue:44265", + "issue:44279", + "issue:44361", + "issue:44442", + "issue:44448", + "issue:44462", + "issue:44466", + "issue:44479", + "issue:44610", + "issue:44743", + "issue:44871", + "issue:44977", + "issue:45198", + "issue:45245", + "issue:45372", + "issue:45412", + "issue:45440", + "issue:45459", + "issue:45491", + "issue:45563", + "issue:46121" + ], + "soft_pairs": [ + "issue:44448|issue:44466", + "issue:45245|issue:45563", + "issue:43653|issue:44743", + "issue:25251|issue:32090", + "issue:44206|issue:44479", + "issue:43065|issue:43994", + "issue:45372|issue:45459", + "issue:44186|issue:45198", + "issue:43065|issue:45412", + "issue:44871|issue:44977", + "issue:43611|issue:46121", + "issue:44361|issue:45198", + "issue:32090|issue:33290", + "issue:42490|issue:43873", + "issue:42915|issue:42994", + "issue:33357|issue:39692", + "issue:29127|issue:34567", + "issue:29942|issue:30064", + "issue:43994|issue:45412", + "issue:44265|issue:45198", + "issue:43066|issue:44462", + "issue:43756|issue:45440", + "issue:43257|issue:43278", + "issue:43421|issue:45491", + "issue:43653|issue:44442", + "issue:43381|issue:43701", + "issue:44610|issue:45412", + "issue:43824|issue:44279" + ], + "prepared_review_unit_hash": "b56ac7102ffbd5e201e0cdfebe12109ead5409c6b3afc2d9b4c674bc9cd59590", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36084, + "estimated_input_tokens": 9021, + "estimated_eval_tokens": 18298 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The items are a heterogeneous set of unrelated bugs/features. None of the soft pairs look like the same underlying issue, so all candidate duplicate links should be rejected.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44448", + "right": "issue:44466", + "accept": false, + "reason": "Different regressions: Pegasus output differences vs lm_head.weight serialization/tied-weights behavior." + }, + { + "left": "issue:45245", + "right": "issue:45563", + "accept": false, + "reason": "Unrelated: category-count overflow error vs stale num_return_sequences warning in paged generate()." + }, + { + "left": "issue:43653", + "right": "issue:44743", + "accept": false, + "reason": "Different components and failure modes: BigBirdTokenizer special-token decode vs Qwen3.5 recurrent state reset." + }, + { + "left": "issue:25251", + "right": "issue:32090", + "accept": false, + "reason": "Top-k pipeline nested-list output is unrelated to Trainer NoneType broadcast errors." + }, + { + "left": "issue:44206", + "right": "issue:44479", + "accept": false, + "reason": "Different subsystems: LasrFeatureExtractor center-arg crash vs Qwen VL video-input regression." + }, + { + "left": "issue:43065", + "right": "issue:43994", + "accept": false, + "reason": "Sam3PixelDecoder dummy Conv2d is unrelated to SigLIP2 AutoModel/pipeline bad results." + }, + { + "left": "issue:45372", + "right": "issue:45459", + "accept": false, + "reason": "Separate tokenizer/processor import issues: ReasoningEffort missing vs protobuf-decode errors being hidden." + }, + { + "left": "issue:44186", + "right": "issue:45198", + "accept": false, + "reason": "Different tokenizers and failures: LayoutLMv2 NER/padding crash vs Wav2Vec2 save/tokenization failure." + }, + { + "left": "issue:43065", + "right": "issue:45412", + "accept": false, + "reason": "Model architecture placeholder vs RT-DETR memory not being released." + }, + { + "left": "issue:44871", + "right": "issue:44977", + "accept": false, + "reason": "EOS config mismatch is unrelated to Qwen3.5 flash-attention generation bugs." + }, + { + "left": "issue:43611", + "right": "issue:46121", + "accept": false, + "reason": "Base-model-prefix loading regression is distinct from rope validation TypeError on JSON-loaded lists." + }, + { + "left": "issue:44361", + "right": "issue:45198", + "accept": false, + "reason": "MLukeTokenizer AttributeError and Wav2Vec2 save/tokenization problems are different code paths." + }, + { + "left": "issue:32090", + "right": "issue:33290", + "accept": false, + "reason": "Trainer broadcast NoneType error is unrelated to AdaFactor + DeepSpeed OOM." + }, + { + "left": "issue:42490", + "right": "issue:43873", + "accept": false, + "reason": "Local-path import warning and quantization offloading behavior are separate issues." + }, + { + "left": "issue:42915", + "right": "issue:42994", + "accept": false, + "reason": "FineGrainedFP8Config failure for Qwen3MoE is different from quantized model saving failure." + }, + { + "left": "issue:33357", + "right": "issue:39692", + "accept": false, + "reason": "MacOS bus error with a CLIP model is unrelated to SigLIP2 documentation example mistakes." + }, + { + "left": "issue:29127", + "right": "issue:34567", + "accept": false, + "reason": "LayoutLMv3 error-message clarity and TrainerState token counter updating are unrelated." + }, + { + "left": "issue:29942", + "right": "issue:30064", + "accept": false, + "reason": "Flash Attention 2 test failures do not match void segmentation-map processing failures." + }, + { + "left": "issue:43994", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 inference mismatch is unrelated to RT-DETR memory cleanup." + }, + { + "left": "issue:44265", + "right": "issue:45198", + "accept": false, + "reason": "torch.export.export with torch_compilable_check is a different bug from Wav2Vec2 tokenization/save issues." + }, + { + "left": "issue:43066", + "right": "issue:44462", + "accept": false, + "reason": "Tokenizer decoder type bug is unrelated to AutoTokenizer ignoring tokenizer.json." + }, + { + "left": "issue:43756", + "right": "issue:45440", + "accept": false, + "reason": "Smollm3 RoPE-layer count mismatch and DeepseekV3MoE divergence are different model bugs." + }, + { + "left": "issue:43257", + "right": "issue:43278", + "accept": false, + "reason": "MoE weight conversion with accelerate/deepspeed is unrelated to embedding dtype drift in eval." + }, + { + "left": "issue:43421", + "right": "issue:45491", + "accept": false, + "reason": "Runtime post-processor updates and Gemma3 NaN embeddings are separate tokenizer/model problems." + }, + { + "left": "issue:43653", + "right": "issue:44442", + "accept": false, + "reason": "BigBirdTokenizer mask-token decode bug is not the same as AutoTokenizer failing to load FastSpeech2ConformerTokenizer." + }, + { + "left": "issue:43381", + "right": "issue:43701", + "accept": false, + "reason": "Gradient checkpointing in eval mode is unrelated to resume_from_checkpoint key mismatches." + }, + { + "left": "issue:44610", + "right": "issue:45412", + "accept": false, + "reason": "OmDet-Turbo processor size mismatch is unrelated to RT-DETR memory leaks." + }, + { + "left": "issue:43824", + "right": "issue:44279", + "accept": false, + "reason": "Missing Qwen2.5-VL import is a specific API break, not the same as a generic 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": 28, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:29127", + "issue:29942", + "issue:33357", + "issue:35141", + "issue:36010", + "issue:42490", + "issue:42915", + "issue:43262", + "issue:43334", + "issue:43381", + "issue:43441", + "issue:43526", + "issue:43531", + "issue:43575", + "issue:43646", + "issue:43701", + "issue:43723", + "issue:43761", + "issue:43931", + "issue:44062", + "issue:44077", + "issue:44079", + "issue:44186", + "issue:44206", + "issue:44387", + "issue:44442", + "issue:44464", + "issue:44625", + "issue:44743", + "issue:44811", + "issue:44857", + "issue:44898", + "issue:44977", + "issue:45003", + "issue:45072", + "issue:45103", + "issue:45245", + "issue:45372", + "issue:45440", + "issue:45479", + "issue:45491", + "issue:45584", + "issue:45588", + "issue:45593", + "issue:45834", + "issue:45859", + "issue:45907" + ], + "soft_pairs": [ + "issue:45440|issue:45593", + "issue:29127|issue:33357", + "issue:29942|issue:36010", + "issue:43526|issue:45834", + "issue:43761|issue:45859", + "issue:43526|issue:44186", + "issue:45103|issue:45372", + "issue:44625|issue:45584", + "issue:29127|issue:35141", + "issue:44442|issue:45072", + "issue:43334|issue:43531", + "issue:44977|issue:45245", + "issue:42915|issue:43931", + "issue:43526|issue:44857", + "issue:42490|issue:43381", + "issue:43575|issue:43701", + "issue:43262|issue:44206", + "issue:43575|issue:44387", + "issue:44464|issue:45491", + "issue:43646|issue:44077", + "issue:44743|issue:44811", + "issue:43441|issue:45588", + "issue:44062|issue:45907", + "issue:43761|issue:44079", + "issue:45003|issue:45440", + "issue:43723|issue:45479", + "issue:44442|issue:44898" + ], + "prepared_review_unit_hash": "63dce8e618a9013cd4464f71e8e187a704bd0398dc28b23d8ab176f2d77606f8", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 27, + "serialized_chars": 35252, + "estimated_input_tokens": 8813, + "estimated_eval_tokens": 17882 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a mixed bag of unrelated Transformers bugs/regressions across model families, tokenizers, generation, audio, and utility code. None of the soft pairs look like the same underlying issue, so no duplicate merge is justified.", + "confidence": 0.9, + "canonical_issue_reason": "Issue 45479 is the clearest representative: it describes a concrete, reproducible regression with broader cross-model impact than the other items.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45479 is the best standalone bug report here because it is self-contained, specific, and clearly framed as a general sequence-classification regression.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45440", + "right": "issue:45593", + "accept": false, + "reason": "Different bugs in different model paths: DeepseekV3MoE divergence vs D-FINE auxiliary loss handling." + }, + { + "left": "issue:29127", + "right": "issue:33357", + "accept": false, + "reason": "Unrelated failures: LayoutLMv3 error messaging vs a MacOS CLIP bus error." + }, + { + "left": "issue:29942", + "right": "issue:36010", + "accept": false, + "reason": "Flash Attention 2 test failure and GenerationMixin import error are separate subsystems." + }, + { + "left": "issue:43526", + "right": "issue:45834", + "accept": false, + "reason": "BEiTImageProcessorFast label reduction bug vs Kosmos2.5 OCR index error; different code paths." + }, + { + "left": "issue:43761", + "right": "issue:45859", + "accept": false, + "reason": "CLIPVisionModel hidden_states regression and Qwen3_5Moe rotary CPU-offload failure are unrelated." + }, + { + "left": "issue:43526", + "right": "issue:44186", + "accept": false, + "reason": "Both are preprocessing issues, but they affect different processors and failure modes." + }, + { + "left": "issue:45103", + "right": "issue:45372", + "accept": false, + "reason": "auto_docstring annotation parsing crash vs ReasoningEffort import failure; unrelated." + }, + { + "left": "issue:44625", + "right": "issue:45584", + "accept": false, + "reason": "Qwen3.5 num_labels propagation and Whisper empty-transcription generation are different bugs." + }, + { + "left": "issue:29127", + "right": "issue:35141", + "accept": false, + "reason": "LayoutLMv3 error clarity and token-embedding reinitialization are unrelated issues." + }, + { + "left": "issue:44442", + "right": "issue:45072", + "accept": false, + "reason": "Tokenizer loading failure vs dtype mismatch in inference; no shared concrete code-path bug." + }, + { + "left": "issue:43334", + "right": "issue:43531", + "accept": false, + "reason": "Both are Qwen3-family issues, but one is a missing config attr and the other is sliding-window behavior." + }, + { + "left": "issue:44977", + "right": "issue:45245", + "accept": false, + "reason": "Flash-attention generation bug and category-count limit error are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:43931", + "accept": false, + "reason": "FP8 config failure in Qwen3Moe and Qwen3-VL weight-shape mismatch are distinct load-time problems." + }, + { + "left": "issue:43526", + "right": "issue:44857", + "accept": false, + "reason": "Different models and failure mechanisms: label reduction vs float16 AMP crash." + }, + { + "left": "issue:42490", + "right": "issue:43381", + "accept": false, + "reason": "Local-path import warning and gradient-checkpointing eval-mode restriction are separate." + }, + { + "left": "issue:43575", + "right": "issue:43701", + "accept": false, + "reason": "Tensor-parallel OOM and resume_from_checkpoint key mismatch are unrelated training/load issues." + }, + { + "left": "issue:43262", + "right": "issue:44206", + "accept": false, + "reason": "Audio chat-template sampling-rate default and LasrFeatureExtractor center-arg crash are different bugs." + }, + { + "left": "issue:43575", + "right": "issue:44387", + "accept": false, + "reason": "Both mention memory, but one is tp OOM on a specific model and the other is int4 reserved-memory growth; not the same bug." + }, + { + "left": "issue:44464", + "right": "issue:45491", + "accept": false, + "reason": "Chunked generation inconsistency with compiled forward is unrelated to Gemma3 NaN embeddings from sliding-window attention." + }, + { + "left": "issue:43646", + "right": "issue:44077", + "accept": false, + "reason": "Custom-model init breakage in v5 and patchtsmixer post_init policy are different issues." + }, + { + "left": "issue:44743", + "right": "issue:44811", + "accept": false, + "reason": "Recurrent-state reset with cache and Whisper batch_decode skip_special_tokens are unrelated." + }, + { + "left": "issue:43441", + "right": "issue:45588", + "accept": false, + "reason": "Both involve flash attention, but they hit different models and distinct crash conditions." + }, + { + "left": "issue:44062", + "right": "issue:45907", + "accept": false, + "reason": "AddedToken keyword conflict and list_repo_files revision forwarding are separate API bugs." + }, + { + "left": "issue:43761", + "right": "issue:44079", + "accept": false, + "reason": "Hidden_states regression in CLIPVisionModel is not the same as ModelOutput key assignment issues." + }, + { + "left": "issue:45003", + "right": "issue:45440", + "accept": false, + "reason": "Unsafe sys.modules access in modeling_utils and DeepseekV3MoE divergence are unrelated." + }, + { + "left": "issue:43723", + "right": "issue:45479", + "accept": false, + "reason": "Tokenizer loading failure and zero-loss sequence-classification regression do not share the same bug." + }, + { + "left": "issue:44442", + "right": "issue:44898", + "accept": false, + "reason": "FastSpeech2ConformerTokenizer loading and Perceiver non-default resolution failure are different 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": 29, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:25251", + "issue:28282", + "issue:33290", + "issue:34567", + "issue:34689", + "issue:35141", + "issue:36010", + "issue:36331", + "issue:42490", + "issue:42907", + "issue:43065", + "issue:43232", + "issue:43295", + "issue:43316", + "issue:43381", + "issue:43388", + "issue:43493", + "issue:43525", + "issue:43611", + "issue:43643", + "issue:43650", + "issue:43720", + "issue:43749", + "issue:43761", + "issue:43825", + "issue:43827", + "issue:43873", + "issue:43931", + "issue:44077", + "issue:44188", + "issue:44190", + "issue:44442", + "issue:44479", + "issue:44496", + "issue:44617", + "issue:44743", + "issue:44855", + "issue:44871", + "issue:44913", + "issue:44987", + "issue:45137", + "issue:45216", + "issue:45290", + "issue:45698", + "issue:45759", + "issue:45803", + "issue:46178", + "issue:46202" + ], + "soft_pairs": [ + "issue:33290|issue:34689", + "issue:33290|issue:34567", + "issue:43232|issue:43388", + "issue:44479|issue:45290", + "issue:33290|issue:35141", + "issue:42490|issue:44743", + "issue:43316|issue:43525", + "issue:43381|issue:43873", + "issue:43761|issue:44188", + "issue:44442|issue:45803", + "issue:34689|issue:43611", + "issue:44987|issue:46178", + "issue:43720|issue:44442", + "issue:44077|issue:44479", + "issue:43931|issue:45216", + "issue:43493|issue:43827", + "issue:42907|issue:45698", + "issue:34689|issue:36010", + "issue:33290|issue:36331", + "issue:43316|issue:45759", + "issue:43749|issue:43931", + "issue:43873|issue:44871", + "issue:43650|issue:46202", + "issue:43643|issue:44913", + "issue:44190|issue:44496", + "issue:44855|issue:45137", + "issue:25251|issue:28282", + "issue:43065|issue:44617", + "issue:43295|issue:43825" + ], + "prepared_review_unit_hash": "1984db3e7c7754d3733638ba4ca5fc5ed1093e07e3b76e702f5f4ddf3254e17f", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36551, + "estimated_input_tokens": 9138, + "estimated_eval_tokens": 18532 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: the items span unrelated Transformers issues across loading, training, generation, quantization, vision, docs, and model config. None of the soft pairs look like the same underlying bug/change, so no merges are justified.", + "confidence": 0.95, + "canonical_issue_reason": "No single issue cleanly represents a shared underlying defect; the cluster is a semantic grab-bag of distinct problems rather than a true duplicate set.", + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:33290", + "right": "issue:34689", + "accept": false, + "reason": "Different failures: DeepSpeed/Adafactor OOM vs Llama 3.2 Vision model loading regression." + }, + { + "left": "issue:33290", + "right": "issue:34567", + "accept": false, + "reason": "Optimizer memory blow-up is unrelated to TrainerState token-count tracking." + }, + { + "left": "issue:43232", + "right": "issue:43388", + "accept": false, + "reason": "Generation kwargs update after sync_gpus is unrelated to metric gathering dropping tuple labels." + }, + { + "left": "issue:44479", + "right": "issue:45290", + "accept": false, + "reason": "Video-input regression in v5.3.0 is not the same as chat-template tool-call crash." + }, + { + "left": "issue:33290", + "right": "issue:35141", + "accept": false, + "reason": "Adafactor OOM in deepspeed and embedding reinit on resize are different code paths." + }, + { + "left": "issue:42490", + "right": "issue:44743", + "accept": false, + "reason": "Path-with-slash warning and Qwen recurrent-state cache reset are unrelated." + }, + { + "left": "issue:43316", + "right": "issue:43525", + "accept": false, + "reason": "Both are config-related, but Gemma3TextConfig API mismatch and Llama4 missing pad_token_id are distinct bugs." + }, + { + "left": "issue:43381", + "right": "issue:43873", + "accept": false, + "reason": "Gradient checkpointing in eval mode and offloading with quantization do not share the same bug." + }, + { + "left": "issue:43761", + "right": "issue:44188", + "accept": false, + "reason": "CLIPVision hidden_states regression is unrelated to torch.compile attention-kernel divergence." + }, + { + "left": "issue:44442", + "right": "issue:45803", + "accept": false, + "reason": "Tokenizer load failure and bare-except swallowing errors in Fuyu conversion are different issues." + }, + { + "left": "issue:34689", + "right": "issue:43611", + "accept": false, + "reason": "Both involve loading, but one is a specific Llama vision model break while the other is a generic base_model_prefix regression." + }, + { + "left": "issue:44987", + "right": "issue:46178", + "accept": false, + "reason": "Model loading failure with transformers>=5.1.0 is unrelated to missing BACKENDS_MAPPING entry for tensorflow_text." + }, + { + "left": "issue:43720", + "right": "issue:44442", + "accept": false, + "reason": "Packed-weight unpacking during accelerate loading is unrelated to AutoTokenizer failing on FastSpeech2ConformerTokenizer." + }, + { + "left": "issue:44077", + "right": "issue:44479", + "accept": false, + "reason": "Optional post_init policy for patchtsmixer and a video-input regression are not the same issue." + }, + { + "left": "issue:43931", + "right": "issue:45216", + "accept": false, + "reason": "Qwen3-VL shape mismatch on load and Qwen3.5 save_pretrained checkpoint corruption are different lifecycle stages and causes." + }, + { + "left": "issue:43493", + "right": "issue:43827", + "accept": false, + "reason": "SigLIP2 implementation discrepancy and stale docs referencing pipeline() are unrelated." + }, + { + "left": "issue:42907", + "right": "issue:45698", + "accept": false, + "reason": "Dequantized save failure and wrong custom module loaded after save_pretrained are both serialization-related but not the same defect." + }, + { + "left": "issue:34689", + "right": "issue:36010", + "accept": false, + "reason": "Model loading break for a specific Llama model is unrelated to GenerationMixin import errors." + }, + { + "left": "issue:33290", + "right": "issue:36331", + "accept": false, + "reason": "OOM with Adafactor/DeepSpeed is unrelated to CustomTrainer.compute_loss signature breakage." + }, + { + "left": "issue:43316", + "right": "issue:45759", + "accept": false, + "reason": "Gemma3TextConfig API discrepancy and missing text_config unwrap in AutoModelForCausalLM.from_config are distinct multimodal config bugs." + }, + { + "left": "issue:43749", + "right": "issue:43931", + "accept": false, + "reason": "FSDP CPU RAM efficient loading failure and Qwen3-VL weight-shape mismatch are different load-time problems." + }, + { + "left": "issue:43873", + "right": "issue:44871", + "accept": false, + "reason": "Quantization/offloading behavior and eos_token_id list-vs-scalar inconsistency are unrelated." + }, + { + "left": "issue:43650", + "right": "issue:46202", + "accept": false, + "reason": "A vague data request issue is not the same as Gemma pipeline roundtrip failure on the \u2581 token." + }, + { + "left": "issue:43643", + "right": "issue:44913", + "accept": false, + "reason": "trust_remote_code missing fields and GPTNeoX rotary_pct reset on reload are separate config-roundtrip bugs." + }, + { + "left": "issue:44190", + "right": "issue:44496", + "accept": false, + "reason": "Local dataset loading in an example script is unrelated to unrecognized model_type in config.json." + }, + { + "left": "issue:44855", + "right": "issue:45137", + "accept": false, + "reason": "Python 3.13 JIT parsing error and DeepSpeed ZeRO3 deque underflow are entirely different failures." + }, + { + "left": "issue:25251", + "right": "issue:28282", + "accept": false, + "reason": "Pipeline top_k nesting bug and missing PyTorch ImportError are unrelated." + }, + { + "left": "issue:43065", + "right": "issue:44617", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder and Sam3Video CUDA OOM are not the same code-path problem." + }, + { + "left": "issue:43295", + "right": "issue:43825", + "accept": false, + "reason": "Processor/tokenizer regression and an incorrect pipeline translation-support error message are different v5 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": 30, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:16998", + "issue:22355", + "issue:32090", + "issue:35141", + "issue:41950", + "issue:42617", + "issue:43295", + "issue:43316", + "issue:43388", + "issue:43404", + "issue:43441", + "issue:43452", + "issue:43475", + "issue:43504", + "issue:43540", + "issue:43550", + "issue:43572", + "issue:43575", + "issue:43606", + "issue:43646", + "issue:43673", + "issue:43688", + "issue:43701", + "issue:43716", + "issue:43742", + "issue:43761", + "issue:44077", + "issue:44162", + "issue:44479", + "issue:44496", + "issue:44514", + "issue:44534", + "issue:44617", + "issue:44734", + "issue:44743", + "issue:44792", + "issue:44871", + "issue:44877", + "issue:44913", + "issue:45127", + "issue:45200", + "issue:45406", + "issue:45584", + "issue:45698", + "issue:45803", + "issue:46050", + "issue:46170", + "issue:46178" + ], + "soft_pairs": [ + "issue:43540|issue:44514", + "issue:43316|issue:43716", + "issue:43550|issue:43701", + "issue:43316|issue:44877", + "issue:44162|issue:44792", + "issue:43606|issue:43701", + "issue:44077|issue:44534", + "issue:45803|issue:46170", + "issue:43404|issue:43441", + "issue:42617|issue:43575", + "issue:16998|issue:22355", + "issue:44871|issue:45584", + "issue:43673|issue:44743", + "issue:43575|issue:43742", + "issue:41950|issue:43475", + "issue:43295|issue:44871", + "issue:43761|issue:44479", + "issue:43388|issue:43688", + "issue:43452|issue:44496", + "issue:45127|issue:45200", + "issue:43646|issue:44913", + "issue:44871|issue:46050", + "issue:43572|issue:46178", + "issue:32090|issue:35141", + "issue:43504|issue:45698", + "issue:44734|issue:45406", + "issue:44617|issue:45584" + ], + "prepared_review_unit_hash": "0c46592f3d61d1e369fa97beae739b64664a8f4beca8a482e18f99e771c66da4", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "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 cluster is very heterogeneous: it mixes unrelated Transformers bugs across loading, generation, vision/video, config, training, and distributed/runtime paths. None of the soft pairs look like true duplicates, so they should stay separate.", + "confidence": 0.92, + "canonical_issue_reason": "Issue 43646 is the broadest representative in the set because it concerns a generic Transformers v5.0 custom-model initialization regression, but the cluster is too mixed to have a real canonical duplicate.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43646 is the closest thing to a cluster representative, but only as a loose umbrella for init/load regressions; it does not subsume the other reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43540", + "right": "issue:44514", + "accept": false, + "reason": "Different failures in different processor/model paths: Qwen3OmniMoe video input processing vs Qwen2_5_VL batched chat-template padding." + }, + { + "left": "issue:43316", + "right": "issue:43716", + "accept": false, + "reason": "Gemma3TextConfig API mismatch and Mistral-3 image-preprocessor dtype mismatch are unrelated bugs." + }, + { + "left": "issue:43550", + "right": "issue:43701", + "accept": false, + "reason": "torch.compile/SDPA failure is a runtime/model bug; resume_from_checkpoint key mismatch is a separate checkpoint-loading issue." + }, + { + "left": "issue:43316", + "right": "issue:44877", + "accept": false, + "reason": "Both are config-related, but they affect different models and different symptoms: Gemma3TextConfig discrepancy vs granite_speech loading strictness." + }, + { + "left": "issue:44162", + "right": "issue:44792", + "accept": false, + "reason": "ESM2 breakage and a janus test failure are not the same underlying bug." + }, + { + "left": "issue:43606", + "right": "issue:43701", + "accept": false, + "reason": "CPU offload device mismatch is unrelated to checkpoint key mismatch on resume." + }, + { + "left": "issue:44077", + "right": "issue:44534", + "accept": false, + "reason": "Both touch v5 behavior, but one is about optional post_init policy and the other about non-persistent buffer initialization." + }, + { + "left": "issue:45803", + "right": "issue:46170", + "accept": false, + "reason": "Fuyu exception handling and Windows ROCm/torch.distributed import issues are separate code paths." + }, + { + "left": "issue:43404", + "right": "issue:43441", + "accept": false, + "reason": "Weight tying in Mistral3ForConditionalGeneration and FlashAttention failures in Ministral-3 are different concrete defects." + }, + { + "left": "issue:42617", + "right": "issue:43575", + "accept": false, + "reason": "3d_parallel execution failure and tensor-parallel OOM are different symptoms with no shared bug evidence." + }, + { + "left": "issue:16998", + "right": "issue:22355", + "accept": false, + "reason": "A model_max_length question and a missing transformers.onnx module are unrelated." + }, + { + "left": "issue:44871", + "right": "issue:45584", + "accept": false, + "reason": "EOS token config inconsistency and Whisper empty-transcription handling are different bugs." + }, + { + "left": "issue:43673", + "right": "issue:44743", + "accept": false, + "reason": "Both involve cache, but one is missing GenerationMixin cache in chunked_prefill while the other is recurrent-state reset in a specific modular model." + }, + { + "left": "issue:43575", + "right": "issue:43742", + "accept": false, + "reason": "Tensor-parallel OOM and MobileLLM key errors are unrelated load/runtime problems." + }, + { + "left": "issue:41950", + "right": "issue:43475", + "accept": false, + "reason": "Video-classification processor selection and SAM3 vision encoder attribute access are different failure modes." + }, + { + "left": "issue:43295", + "right": "issue:44871", + "accept": false, + "reason": "Processor.tokenizer regression and Gemma-3 EOS config mismatch are not the same bug." + }, + { + "left": "issue:43761", + "right": "issue:44479", + "accept": false, + "reason": "CLIPVision hidden_states regression and Qwen VL video-input regression affect different models and code paths." + }, + { + "left": "issue:43388", + "right": "issue:43688", + "accept": false, + "reason": "Label truncation in gather_for_metrics is unrelated to auxiliary-loss normalization." + }, + { + "left": "issue:43452", + "right": "issue:44496", + "accept": false, + "reason": "Both are loading issues, but gguf_file breakage and missing model_type in config.json have different causes." + }, + { + "left": "issue:45127", + "right": "issue:45200", + "accept": false, + "reason": "LoRA merge collapse and Gemma 4 mm_token_type_ids defaults are unrelated." + }, + { + "left": "issue:43646", + "right": "issue:44913", + "accept": false, + "reason": "Generic custom-model initialization break and rotary_pct reload default are both config/init-adjacent, but not the same underlying defect." + }, + { + "left": "issue:44871", + "right": "issue:46050", + "accept": false, + "reason": "EOS token inconsistency and quantized save/load corruption are distinct serialization/config problems." + }, + { + "left": "issue:43572", + "right": "issue:46178", + "accept": false, + "reason": "Missing pad_token_idx in StableLmConfig and tensorflow_text backend mapping errors are unrelated." + }, + { + "left": "issue:32090", + "right": "issue:35141", + "accept": false, + "reason": "GPU broadcast NoneType failure and embedding reinitialization after resize are different bugs." + }, + { + "left": "issue:43504", + "right": "issue:45698", + "accept": false, + "reason": "Legacy-field preset loading and wrong custom-module loading after save_pretrained are both loading-related, but not the same concrete issue." + }, + { + "left": "issue:44734", + "right": "issue:45406", + "accept": false, + "reason": "KV-cache continuation indexing and Gemma4Processor missing _tokenizer are separate serve/processor bugs." + }, + { + "left": "issue:44617", + "right": "issue:45584", + "accept": false, + "reason": "CUDA OOM in Sam3Video and Whisper empty-transcription handling 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": 31, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:35141", + "issue:41720", + "issue:42490", + "issue:43065", + "issue:43335", + "issue:43525", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43644", + "issue:43761", + "issue:43827", + "issue:43931", + "issue:43976", + "issue:43994", + "issue:44060", + "issue:44077", + "issue:44112", + "issue:44190", + "issue:44242", + "issue:44462", + "issue:44464", + "issue:44479", + "issue:44521", + "issue:44534", + "issue:44610", + "issue:44734", + "issue:44737", + "issue:44792", + "issue:44855", + "issue:44877", + "issue:44913", + "issue:44933", + "issue:44964", + "issue:44977", + "issue:45127", + "issue:45245", + "issue:45290", + "issue:45357", + "issue:45362", + "issue:45381", + "issue:45563", + "issue:45584", + "issue:45588", + "issue:45600", + "issue:45803", + "issue:45907", + "issue:45987" + ], + "soft_pairs": [ + "issue:45563|issue:45584", + "issue:43761|issue:44242", + "issue:43525|issue:43531", + "issue:44792|issue:44977", + "issue:43931|issue:44060", + "issue:44479|issue:44734", + "issue:44534|issue:44913", + "issue:44190|issue:44964", + "issue:44464|issue:45563", + "issue:44792|issue:45600", + "issue:44521|issue:45381", + "issue:43827|issue:43994", + "issue:43540|issue:45290", + "issue:41720|issue:45245", + "issue:45803|issue:45987", + "issue:43065|issue:44610", + "issue:44855|issue:45588", + "issue:35141|issue:42490", + "issue:44933|issue:45362", + "issue:43335|issue:44855", + "issue:44077|issue:44877", + "issue:43976|issue:44855", + "issue:43644|issue:44913", + "issue:43550|issue:44190", + "issue:43540|issue:44734", + "issue:45127|issue:45357", + "issue:44737|issue:45803", + "issue:44462|issue:45907", + "issue:44112|issue:45600", + "issue:43335|issue:44190" + ], + "prepared_review_unit_hash": "52451cabab33906c249ddca2fd95319d094e29348ef833045f8dd0bf01204d44", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36705, + "estimated_input_tokens": 9177, + "estimated_eval_tokens": 18610 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "All proposed soft edges look like false positives. The cluster is a grab-bag of unrelated issues across model bugs, config/loading regressions, docs, and CI/test failures, not a duplicate set.", + "confidence": 0.98, + "canonical_issue_reason": "No single canonical issue fits: the items span many unrelated code paths and failure modes, so there is no clear duplicate anchor.", + "canonical_pr_reason": null, + "best_issue_reason": "No issue is globally representative enough to serve as a canonical duplicate target for this cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45563", + "right": "issue:45584", + "accept": false, + "reason": "Both are generation-related, but one is a stale warning and the other is an empty-transcription crash after token alignment; different bugs." + }, + { + "left": "issue:43761", + "right": "issue:44242", + "accept": false, + "reason": "CLIPVision hidden_states regression and MoE load-balancing loss omission are unrelated model-path issues." + }, + { + "left": "issue:43525", + "right": "issue:43531", + "accept": false, + "reason": "Missing pad_token_id on Llama4Config and Qwen3-MoE sliding_window behavior are distinct config/model bugs." + }, + { + "left": "issue:44792", + "right": "issue:44977", + "accept": false, + "reason": "A failing Janus image-generation test and Qwen3.5 flash-attention generation issue are different code paths." + }, + { + "left": "issue:43931", + "right": "issue:44060", + "accept": false, + "reason": "Weight-shape mismatch on model load is not the same as an incorrect tied-weights warning in Qwen3-Next." + }, + { + "left": "issue:44479", + "right": "issue:44734", + "accept": false, + "reason": "Video-input regression in several Qwen VL models and KV-cache continuation crash in serve are unrelated." + }, + { + "left": "issue:44534", + "right": "issue:44913", + "accept": false, + "reason": "Non-persistent buffer initialization bug and GPTNeoX rotary_pct reload bug are separate issues." + }, + { + "left": "issue:44190", + "right": "issue:44964", + "accept": false, + "reason": "Local dataset loading failure in an example script is unrelated to loading Phi-4-multimodal-instruct." + }, + { + "left": "issue:44464", + "right": "issue:45563", + "accept": false, + "reason": "Compiled-forward chunked generation inconsistency and a stale num_return_sequences warning are different behaviors." + }, + { + "left": "issue:44792", + "right": "issue:45600", + "accept": false, + "reason": "A Janus test failure does not match a CI break from removed Sam3LiteText config references." + }, + { + "left": "issue:44521", + "right": "issue:45381", + "accept": false, + "reason": "All-zero assistant masks in chat templating and wrong vision_position_ids for Qwen2.5-VL video inputs are different bugs." + }, + { + "left": "issue:43827", + "right": "issue:43994", + "accept": false, + "reason": "Docs still referencing pipeline() and SigLIP2 nonsensical outputs are not the same issue." + }, + { + "left": "issue:43540", + "right": "issue:45290", + "accept": false, + "reason": "Video processing ValueError in Qwen3OmniMoe and chat-template crashes on tool-call messages are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:45245", + "accept": false, + "reason": "Qwen3 auto device mapping cuda assert and category-count runtime error do not share a code path." + }, + { + "left": "issue:45803", + "right": "issue:45987", + "accept": false, + "reason": "Bare except swallowing interrupts in Fuyu batch conversion and StaticCache return-type mismatch are unrelated." + }, + { + "left": "issue:43065", + "right": "issue:44610", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder and processor/model image-size mismatch are different problems." + }, + { + "left": "issue:44855", + "right": "issue:45588", + "accept": false, + "reason": "Python 3.13 import parsing failure in DebertaV2 and flash_attention sink-less AttributeError are unrelated." + }, + { + "left": "issue:35141", + "right": "issue:42490", + "accept": false, + "reason": "Embedding reinitialization in post_init and trailing-slash local model loading warning are different loading behaviors." + }, + { + "left": "issue:44933", + "right": "issue:45362", + "accept": false, + "reason": "Missing image_utils import and Qwen3.5 chat crash are not the same bug." + }, + { + "left": "issue:43335", + "right": "issue:44855", + "accept": false, + "reason": "Sparse-layer creation in SwitchTransformersConfig and DebertaV2 import parsing error are unrelated." + }, + { + "left": "issue:44077", + "right": "issue:44877", + "accept": false, + "reason": "Optional post_init deprecation and strict-config loading failure are different config validation issues." + }, + { + "left": "issue:43976", + "right": "issue:44855", + "accept": false, + "reason": "Python version support regression and DebertaV2 import parsing failure are unrelated." + }, + { + "left": "issue:43644", + "right": "issue:44913", + "accept": false, + "reason": "Non-persistent buffer junk in v5 and GPTNeoX rotary_pct reload defaulting are separate bugs." + }, + { + "left": "issue:43550", + "right": "issue:44190", + "accept": false, + "reason": "torch.compile SDPA failure in Bamba and local dataset loading failure are unrelated." + }, + { + "left": "issue:45127", + "right": "issue:45357", + "accept": false, + "reason": "LoRA merge with extended vocab corrupting tied embeddings and incorrect visual encoder keys on save_pretrained are different code paths." + }, + { + "left": "issue:44737", + "right": "issue:45803", + "accept": false, + "reason": "CPU device omission in XLNet positional encoding and Fuyu bare-except error masking are unrelated." + }, + { + "left": "issue:44462", + "right": "issue:45907", + "accept": false, + "reason": "Tokenizer.json being ignored and list_repo_files not forwarding revision are separate Hub-loading issues." + }, + { + "left": "issue:44112", + "right": "issue:45600", + "accept": false, + "reason": "GraniteSpeech CI device-override test flake and auto_mappings references to removed configs are different CI problems." + }, + { + "left": "issue:43335", + "right": "issue:44190", + "accept": false, + "reason": "SwitchTransformers sparse-layer bug and local dataset loading issue do not share a concrete failure 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": 32, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "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:43526", + "issue:43531", + "issue:43643", + "issue:43650", + "issue:43854", + "issue:43901", + "issue:43976", + "issue:44016", + "issue:44112", + "issue:44186", + "issue:44190", + "issue:44220", + "issue:44246", + "issue:44279", + "issue:44496", + "issue:44561", + "issue:44683", + "issue:44734", + "issue:44938", + "issue:44964", + "issue:44987", + "issue:45003", + "issue:45216", + "issue:45245", + "issue:45276", + "issue:45335", + "issue:45375", + "issue:45446", + "issue:45542", + "issue:45584", + "issue:45600", + "issue:45632", + "issue:46082", + "issue:46121" + ], + "soft_pairs": [ + "issue:46082|issue:46121", + "issue:44938|issue:45542", + "issue:39692|issue:44190", + "issue:43479|issue:45375", + "issue:45276|issue:45584", + "issue:36246|issue:41628", + "issue:43295|issue:45276", + "issue:45245|issue:45584", + "issue:43650|issue:44220", + "issue:44186|issue:44734", + "issue:41950|issue:44016", + "issue:36246|issue:38617", + "issue:42175|issue:44279", + "issue:44246|issue:45003", + "issue:44683|issue:45446", + "issue:43404|issue:45216", + "issue:38175|issue:43065", + "issue:44016|issue:44220", + "issue:43643|issue:44496", + "issue:44734|issue:45632", + "issue:43854|issue:44964", + "issue:44964|issue:45600", + "issue:44112|issue:44964", + "issue:44561|issue:45632", + "issue:43976|issue:44987", + "issue:42907|issue:43441", + "issue:43531|issue:45600", + "issue:42490|issue:45632", + "issue:43295|issue:45335", + "issue:43526|issue:43901" + ], + "prepared_review_unit_hash": "d7500632ffd1006b1d1ec7cea492a4eb0b231ef51f490f0b7a0c20d63b108d4d", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36663, + "estimated_input_tokens": 9166, + "estimated_eval_tokens": 18588 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly same broad Transformers regression family, but the individual reports are about different APIs, models, and failure modes. I would not deduplicate any of the soft pairs.", + "confidence": 0.84, + "canonical_issue_reason": "issue:44964 is the clearest concrete, user-facing loading regression with a specific model and version context, so it is the best representative issue in this mixed set.", + "canonical_pr_reason": null, + "best_issue_reason": "It is specific, reproducible, and representative of the common \"latest Transformers breaks model loading\" theme.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:46082", + "right": "issue:46121", + "accept": false, + "reason": "Different bugs: LlamaConfig head_dim validation vs. rope-parameter JSON list handling." + }, + { + "left": "issue:44938", + "right": "issue:45542", + "accept": false, + "reason": "Unrelated failures: Python 3.14 import/load issue vs. missing TensorFlow backend dependency." + }, + { + "left": "issue:39692", + "right": "issue:44190", + "accept": false, + "reason": "Docs/example errors for SigLIP2 vs. local dataset loading failure in a training script." + }, + { + "left": "issue:43479", + "right": "issue:45375", + "accept": false, + "reason": "Different model configs and different missing/defaulted fields; not the same bug." + }, + { + "left": "issue:45276", + "right": "issue:45584", + "accept": false, + "reason": "Gemma4 embedding resize bug is unrelated to Whisper empty-transcription generation failure." + }, + { + "left": "issue:36246", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but they concern different symbols and different API breakages." + }, + { + "left": "issue:43295", + "right": "issue:45276", + "accept": false, + "reason": "Processor/tokenizer regression is a different code path from token embedding resizing." + }, + { + "left": "issue:45245", + "right": "issue:45584", + "accept": false, + "reason": "Category-count runtime error and Whisper empty-output bug are unrelated." + }, + { + "left": "issue:43650", + "right": "issue:44220", + "accept": false, + "reason": "Placeholder data issue vs. audio feature extraction bug; no common underlying defect." + }, + { + "left": "issue:44186", + "right": "issue:44734", + "accept": false, + "reason": "Tokenizer padding/truncation crash is unrelated to serve KV-cache indexing." + }, + { + "left": "issue:41950", + "right": "issue:44016", + "accept": false, + "reason": "Pipeline processor lookup bug vs. notebook syntax error; completely different problems." + }, + { + "left": "issue:36246", + "right": "issue:38617", + "accept": false, + "reason": "Both are import failures, but they are for different removed/missing symbols in different modules." + }, + { + "left": "issue:42175", + "right": "issue:44279", + "accept": false, + "reason": "Specific missing TensorFlow backend dependency vs. vague dependency issue; not the same fix." + }, + { + "left": "issue:44246", + "right": "issue:45003", + "accept": false, + "reason": "Import performance regression is not the same as unsafe sys.modules access." + }, + { + "left": "issue:44683", + "right": "issue:45446", + "accept": false, + "reason": "Both mention flex_attention, but one is a compiled-kernel failure and the other is a version-check/import gating bug." + }, + { + "left": "issue:43404", + "right": "issue:45216", + "accept": false, + "reason": "Mistral3 weight-tying bug and Qwen3.5 save_pretrained regression are different model-specific issues." + }, + { + "left": "issue:38175", + "right": "issue:43065", + "accept": false, + "reason": "SigLIP2 probability behavior and Sam3PixelDecoder dummy conv are unrelated model bugs." + }, + { + "left": "issue:44016", + "right": "issue:44220", + "accept": false, + "reason": "Notebook syntax error vs. audio feature extraction bug; no overlap in code path." + }, + { + "left": "issue:43643", + "right": "issue:44496", + "accept": false, + "reason": "trust_remote_code field loss and unrecognized model_type are different config-loading failures." + }, + { + "left": "issue:44734", + "right": "issue:45632", + "accept": false, + "reason": "Serve KV-cache continuation crash is unrelated to local-model cache-path collision." + }, + { + "left": "issue:43854", + "right": "issue:44964", + "accept": false, + "reason": "Different models and likely different root causes; both are load failures but not the same bug." + }, + { + "left": "issue:44964", + "right": "issue:45600", + "accept": false, + "reason": "Model loading regression vs. auto_mappings CI breakage from removed configs." + }, + { + "left": "issue:44112", + "right": "issue:44964", + "accept": false, + "reason": "CI test flake in GraniteSpeech is unrelated to Phi-4 multimodal loading." + }, + { + "left": "issue:44561", + "right": "issue:45632", + "accept": false, + "reason": "Trust-remote-code breakage from removed helper is different from cache-path collision." + }, + { + "left": "issue:43976", + "right": "issue:44987", + "accept": false, + "reason": "Python version compatibility issue vs. a specific model loading failure." + }, + { + "left": "issue:42907", + "right": "issue:43441", + "accept": false, + "reason": "Saving dequantized Ministral/Devstral and FlashAttention failures are different failure modes." + }, + { + "left": "issue:43531", + "right": "issue:45600", + "accept": false, + "reason": "Qwen3-MoE sliding_window bug is unrelated to Sam3LiteText auto-mapping CI breakage." + }, + { + "left": "issue:42490", + "right": "issue:45632", + "accept": false, + "reason": "Trailing-slash import warning and leaf-directory cache collision are different path-handling issues." + }, + { + "left": "issue:43295", + "right": "issue:45335", + "accept": false, + "reason": "Processor-tokenizer regression is unrelated to t5gemma embedding resize propagation." + }, + { + "left": "issue:43526", + "right": "issue:43901", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug and a docs/behavior mismatch for text classification are not duplicates." + } + ] + }, + "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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:38175", + "issue:39692", + "issue:41950", + "issue:43295", + "issue:43299", + "issue:43335", + "issue:43381", + "issue:43479", + "issue:43525", + "issue:43577", + "issue:43650", + "issue:43673", + "issue:43824", + "issue:43854", + "issue:43901", + "issue:43976", + "issue:44016", + "issue:44062", + "issue:44075", + "issue:44242", + "issue:44279", + "issue:44336", + "issue:44351", + "issue:44368", + "issue:44462", + "issue:44496", + "issue:44521", + "issue:44617", + "issue:44683", + "issue:44779", + "issue:44933", + "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:46132" + ], + "soft_pairs": [ + "issue:44496|issue:45042", + "issue:44016|issue:44062", + "issue:43673|issue:44336", + "issue:43335|issue:45593", + "issue:43824|issue:44933", + "issue:44075|issue:44368", + "issue:43299|issue:45216", + "issue:43976|issue:44279", + "issue:43381|issue:45593", + "issue:43901|issue:44496", + "issue:44496|issue:45759", + "issue:45335|issue:45584", + "issue:43479|issue:43525", + "issue:44521|issue:45325", + "issue:44242|issue:45200", + "issue:43299|issue:45357", + "issue:44351|issue:45278", + "issue:43577|issue:45216", + "issue:41950|issue:45020", + "issue:38175|issue:44617", + "issue:41950|issue:45823", + "issue:44779|issue:45812", + "issue:44279|issue:45405", + "issue:39692|issue:43901", + "issue:44683|issue:45542", + "issue:43295|issue:44779", + "issue:43976|issue:45405", + "issue:43299|issue:43854", + "issue:43650|issue:46132", + "issue:44462|issue:45081" + ], + "prepared_review_unit_hash": "8aab79cfa70a733fea1d6ae08b2745f2829d233ee373f2ad9e45c735c9bc9d0f", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36712, + "estimated_input_tokens": 9178, + "estimated_eval_tokens": 18612 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "No soft-edge pair looks like a true duplicate or the same fix; the set is mostly heterogeneous regressions, docs issues, and tokenizer/import bugs across different models and code paths.", + "confidence": 0.94, + "canonical_issue_reason": "issue:44521 is the most central user-facing bug in the set: it is open, has the most inbound references, and reports a broad multimodal chat-template failure.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44521 is the best representative issue to keep because it is actionable, well-scoped, and impacts a common multimodal API path.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44496", + "right": "issue:45042", + "accept": false, + "reason": "Different bugs: model-loading/config resolution versus PIL image processor dependency handling." + }, + { + "left": "issue:44016", + "right": "issue:44062", + "accept": false, + "reason": "Unrelated failures: a notebook syntax error versus an AddedToken constructor keyword collision." + }, + { + "left": "issue:43673", + "right": "issue:44336", + "accept": false, + "reason": "Different subsystems and symptoms: chunked prefill cache plumbing versus ANSI output formatting." + }, + { + "left": "issue:43335", + "right": "issue:45593", + "accept": false, + "reason": "Different model paths and behaviors: SwitchTransformers sparse-layer construction versus D-FINE auxiliary-loss handling." + }, + { + "left": "issue:43824", + "right": "issue:44933", + "accept": false, + "reason": "Both are import-related, but they concern different missing symbols/modules and different underlying fixes." + }, + { + "left": "issue:44075", + "right": "issue:44368", + "accept": false, + "reason": "Optimizer argument usage and a tie_word_embeddings warning are unrelated issues." + }, + { + "left": "issue:43299", + "right": "issue:45216", + "accept": false, + "reason": "Different regression surfaces: Qwen3VL model loading versus Qwen3.5 save_pretrained checkpoint content." + }, + { + "left": "issue:43976", + "right": "issue:44279", + "accept": false, + "reason": "The first is a Python-version compatibility claim; the second is a vague dependency issue with no matching concrete failure." + }, + { + "left": "issue:43381", + "right": "issue:45593", + "accept": false, + "reason": "Gradient-checkpointing eval-mode behavior is unrelated to D-FINE auxiliary losses." + }, + { + "left": "issue:43901", + "right": "issue:44496", + "accept": false, + "reason": "Docs mention of return_all_scores is unrelated to a model import/config error." + }, + { + "left": "issue:44496", + "right": "issue:45759", + "accept": false, + "reason": "Both involve model resolution, but one is a missing model_type import failure and the other is a composite-config unwrap bug." + }, + { + "left": "issue:45335", + "right": "issue:45584", + "accept": false, + "reason": "Tokenizer embedding resize and Whisper empty-transcription generation are different code paths." + }, + { + "left": "issue:43479", + "right": "issue:43525", + "accept": false, + "reason": "Different config initialization bug versus a missing pad_token_id attribute error." + }, + { + "left": "issue:44521", + "right": "issue:45325", + "accept": false, + "reason": "Assistant-mask generation in chat templates and rope-index temporal scaling are distinct multimodal bugs." + }, + { + "left": "issue:44242", + "right": "issue:45200", + "accept": false, + "reason": "Load-balancing loss gating and mm_token_type_ids defaults are separate model-loss/config issues." + }, + { + "left": "issue:43299", + "right": "issue:45357", + "accept": false, + "reason": "Both are Qwen3.5-related, but one is a loading regression and the other is incorrect save_pretrained key serialization." + }, + { + "left": "issue:44351", + "right": "issue:45278", + "accept": false, + "reason": "A specific HybridCache import failure is not the same as a broad collection of import errors." + }, + { + "left": "issue:43577", + "right": "issue:45216", + "accept": false, + "reason": "BLIP2 dtype propagation and Qwen3.5 checkpoint saving are unrelated regressions." + }, + { + "left": "issue:41950", + "right": "issue:45020", + "accept": false, + "reason": "Video-classification processor lookup and remote_code model breakage do not share the same concrete bug." + }, + { + "left": "issue:38175", + "right": "issue:44617", + "accept": false, + "reason": "Zero probabilities in SigLIP2 and Sam3Video OOM are unrelated symptoms and fixes." + }, + { + "left": "issue:41950", + "right": "issue:45823", + "accept": false, + "reason": "Image-processor lookup in video classification is unrelated to Gemma4 device-map placement." + }, + { + "left": "issue:44779", + "right": "issue:45812", + "accept": false, + "reason": "Different tokenizer regressions affecting different model families; not the same underlying bug." + }, + { + "left": "issue:44279", + "right": "issue:45405", + "accept": false, + "reason": "A general dependency issue is not the same as a PEFT minimum-version bump." + }, + { + "left": "issue:39692", + "right": "issue:43901", + "accept": false, + "reason": "Both are documentation-related, but they refer to different docs and different failures." + }, + { + "left": "issue:44683", + "right": "issue:45542", + "accept": false, + "reason": "Compiled flex_attention on torch>=2.9 and a missing TensorFlow backend are unrelated." + }, + { + "left": "issue:43295", + "right": "issue:44779", + "accept": false, + "reason": "Processor/tokenizer API regression versus Deepseek tokenization output regression are different bugs." + }, + { + "left": "issue:43976", + "right": "issue:45405", + "accept": false, + "reason": "Python support mismatch and unreleased PEFT version pin are unrelated dependency problems." + }, + { + "left": "issue:43299", + "right": "issue:43854", + "accept": false, + "reason": "Different Qwen-related loading/import failures for different models and failure modes." + }, + { + "left": "issue:43650", + "right": "issue:46132", + "accept": false, + "reason": "A placeholder data issue and an AttentionInterface.register behavior change are unrelated." + }, + { + "left": "issue:44462", + "right": "issue:45081", + "accept": false, + "reason": "Tokenizer.json precedence and a Mistral regex patch crash are different tokenizer-loading 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": 34, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:33290", + "issue:41950", + "issue:42175", + "issue:42994", + "issue:43065", + "issue:43262", + "issue:43317", + "issue:43441", + "issue:43450", + "issue:43650", + "issue:43653", + "issue:43673", + "issue:43723", + "issue:43761", + "issue:43784", + "issue:43824", + "issue:43901", + "issue:43976", + "issue:43994", + "issue:44016", + "issue:44162", + "issue:44261", + "issue:44263", + "issue:44279", + "issue:44291", + "issue:44297", + "issue:44361", + "issue:44462", + "issue:44466", + "issue:44521", + "issue:44617", + "issue:44623", + "issue:44671", + "issue:44683", + "issue:44749", + "issue:44779", + "issue:44898", + "issue:45081", + "issue:45276", + "issue:45397", + "issue:45542", + "issue:45593", + "issue:45600", + "issue:45656", + "issue:45712", + "issue:45823", + "issue:45834", + "issue:45907" + ], + "soft_pairs": [ + "issue:43450|issue:44279", + "issue:44297|issue:44462", + "issue:45081|issue:45907", + "issue:44016|issue:44291", + "issue:43441|issue:45834", + "issue:41950|issue:43650", + "issue:44466|issue:45276", + "issue:45600|issue:45712", + "issue:42994|issue:43317", + "issue:33290|issue:45656", + "issue:43653|issue:45593", + "issue:44623|issue:44749", + "issue:44623|issue:45397", + "issue:43065|issue:44898", + "issue:44261|issue:44263", + "issue:43441|issue:44683", + "issue:44016|issue:45823", + "issue:44361|issue:45593", + "issue:43723|issue:44162", + "issue:42175|issue:43976", + "issue:44671|issue:44779", + "issue:43262|issue:44521", + "issue:43901|issue:43994", + "issue:43673|issue:43761", + "issue:43784|issue:45542", + "issue:43824|issue:43976", + "issue:44297|issue:45397", + "issue:43450|issue:44617" + ], + "prepared_review_unit_hash": "fbae76c87136d040cc365101d3d2bb364b54bd1d1d2fe78612ae157c4fce5da9", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 35994, + "estimated_input_tokens": 8999, + "estimated_eval_tokens": 18254 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This is a very heterogeneous similarity cluster: tokenizer I/O, processor/chat-template bugs, quantization/load issues, vision/audio regressions, DeepSpeed optimizer problems, and unrelated docs/CI items. None of the soft-edge pairs look like the same underlying bug/change, so I would not merge any of them as duplicates.", + "confidence": 0.93, + "canonical_issue_reason": "There is no strong single canonical issue for the whole cluster; if forced to anchor a subgroup, issue 44462 (\"AutoTokenizer ignores tokenizer.json from the repository\") is the most concrete and broadly representative tokenizer-loading regression. Even so, the cluster is too mixed to treat it as the true canonical for all items.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44462 is the best issue anchor only in a narrow tokenizer-loading sense: it is concrete, user-facing, and closest to the other tokenizer-related reports. It is not a good global representative of this cluster because most items are unrelated.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43450 \u2013 Video processors return incorrect shape when input is batched", + "right": "issue:44279 \u2013 Dependency issue with transformers", + "accept": false, + "reason": "Different problem domains: a batched video-processor shape bug vs a generic dependency complaint. No shared code-path." + }, + { + "left": "issue:44297 \u2013 tokenizer.save_pretrained: tokenizer_class in tokenizer_config.json doesn't match the original", + "right": "issue:44462 \u2013 AutoTokenizer ignores tokenizer.json from the repository", + "accept": false, + "reason": "Both are tokenizer-related, but one is save/serialization metadata and the other is load-time file selection. Related area, not the same bug." + }, + { + "left": "issue:45081 \u2013 _patch_mistral_regex crashes with AttributeError on loading Mistral tokenizer with fix_mistral_regex=True", + "right": "issue:45907 \u2013 list_repo_files should forward the revision argument", + "accept": false, + "reason": "Unrelated utility/CI issue vs tokenizer regex patch crash. Different APIs and failure modes." + }, + { + "left": "issue:44016 \u2013 Syntax error in Transformer section 3 notebook", + "right": "issue:44291 \u2013 TypeError when loading model with init_empty_weights due to unexpected _is_hf_initialized argument", + "accept": false, + "reason": "Docs/notebook syntax issue vs model-loading API regression. Not the same underlying bug." + }, + { + "left": "issue:43441 \u2013 Ministral-3 fails with FlashAttention in Transformers v5 RC", + "right": "issue:45834 \u2013 Kosmos2.5: index error on long ocr input", + "accept": false, + "reason": "Both are model runtime failures, but the model, trigger, and stack are different; no evidence of a shared code-path." + }, + { + "left": "issue:41950 \u2013 video-classification pipeline looks for image processors", + "right": "issue:43650 \u2013 ADD THE DATA", + "accept": false, + "reason": "The second issue is too vague and does not describe the same concrete pipeline bug." + }, + { + "left": "issue:44466 \u2013 Inconsistent serialization of lm_head.weight depending on model device", + "right": "issue:45276 \u2013 resize_token_embeddings does not affect embed_tokens_per_layer or output_embeddings", + "accept": false, + "reason": "Both touch Gemma4/model weight handling, but one is serialization/tied-weights behavior and the other is embedding resize propagation. Different defects." + }, + { + "left": "issue:45600 \u2013 auto_mappings.py references removed Sam3LiteText configs", + "right": "issue:45712 \u2013 leftover dummy classes in dummy_pt_objects.py fail check_repo.py", + "accept": false, + "reason": "Both are maintenance/CI cleanup issues, but they involve different files and independent breakages." + }, + { + "left": "issue:42994 \u2013 quantized model saving failed", + "right": "issue:43317 \u2013 device_map=auto fails to load the dequantized model on gpu+cpu offload", + "accept": false, + "reason": "Save-time quantization failure vs load-time/offload placement failure. Same broad area, not the same bug." + }, + { + "left": "issue:33290 \u2013 oom when using adafactor optimizer in deepspeed", + "right": "issue:45656 \u2013 Optimizer step being called 2 times when using deepspeed", + "accept": false, + "reason": "Both mention DeepSpeed, but one is OOM with Adafactor and the other is double-stepping. Different concrete issues." + }, + { + "left": "issue:43653 \u2013 BigBirdTokenizer mask token not registered as special token, gives empty decode output", + "right": "issue:45593 \u2013 D-FINE not using any auxiliary losses when denoising is turned off", + "accept": false, + "reason": "Tokenizer special-token registration bug vs model training-loss behavior. No shared bug." + }, + { + "left": "issue:44623 \u2013 processor.save_pretrained(...) missing files", + "right": "issue:44749 \u2013 Transformer upgrade makes filtering data much slower", + "accept": false, + "reason": "Save-pretrained file emission vs performance regression in filtering. Unrelated." + }, + { + "left": "issue:44623 \u2013 processor.save_pretrained(...) missing files", + "right": "issue:45397 \u2013 gemma-4 zero3 from_pretrained", + "accept": false, + "reason": "Processor save bug vs Gemma-4 DeepSpeed zero3 loading issue. Different code paths." + }, + { + "left": "issue:43065 \u2013 Dummy nn.Conv2d in Sam3PixelDecoder", + "right": "issue:44898 \u2013 Perceiver image classification non-default res fails even with interpolate_pos_encoding=True", + "accept": false, + "reason": "Both are vision-model bugs, but one is a dummy layer placeholder and the other is resolution/interpolation handling. Not the same issue." + }, + { + "left": "issue:44261 \u2013 MLA q_a_layernorm missing config.rms_norm_eps", + "right": "issue:44263 \u2013 The torch.split() return values in GlmMoeDsaIndexer", + "accept": false, + "reason": "Unrelated model-specific numerical/config bug vs tensor split semantics." + }, + { + "left": "issue:43441 \u2013 Ministral-3 fails with FlashAttention in Transformers v5 RC", + "right": "issue:44683 \u2013 Compiled flex_attention fails on torch >= 2.9", + "accept": false, + "reason": "Both involve attention backends, but one is a model-specific FlashAttention regression and the other is a torch-version compiled flex_attention incompatibility." + }, + { + "left": "issue:44016 \u2013 Syntax error in Transformer section 3 notebook", + "right": "issue:45823 \u2013 Gemma4 PLE device mismatch with device_map=\"auto\" during forward", + "accept": false, + "reason": "Notebook syntax/docs issue vs runtime device-placement bug. Different artifacts." + }, + { + "left": "issue:44361 \u2013 MLukeTokenizer fails with AttributeError on tasks", + "right": "issue:45593 \u2013 D-FINE not using any auxiliary losses when denoising is turned off", + "accept": false, + "reason": "Tokenizer task failure vs detection-loss behavior. No meaningful overlap." + }, + { + "left": "issue:43723 \u2013 Issue loading tokenizer using AutoTokenizer.from_pretrained in v5", + "right": "issue:44162 \u2013 ESM2 is broken, impacting 1000s of scientists workflows", + "accept": false, + "reason": "Tokenizer-loading regression vs ESM2 model breakage. Same library, different underlying defects." + }, + { + "left": "issue:42175 \u2013 Tensorflow not include in the backend when using pip install '.[torch]'", + "right": "issue:43976 \u2013 Transformers 5.1.0 does not work with Python3.9+ but Python3.10+", + "accept": false, + "reason": "Dependency/extras installation issue vs Python-version compatibility issue. Not the same bug." + }, + { + "left": "issue:44671 \u2013 CamemBERT produces incorrect masked LM predictions in v5", + "right": "issue:44779 \u2013 Deepseek tokenizer produces incorrect results as of v5", + "accept": false, + "reason": "Both are v5 regressions, but one is CamemBERT masked-LM predictions and the other is Deepseek tokenizer behavior. Different failure surfaces." + }, + { + "left": "issue:43262 \u2013 Audio processors: apply_chat_template() defaults to 16kHz sampling rate", + "right": "issue:44521 \u2013 apply_chat_template returns all-zero assistant_masks for multimodal inputs", + "accept": false, + "reason": "Both mention apply_chat_template, but one is audio sampling-rate defaulting and the other is multimodal assistant-mask generation. Different bugs." + }, + { + "left": "issue:43901 \u2013 TextClassificationPipeline docs still mention return_all_scores, but behavior differs", + "right": "issue:43994 \u2013 google/siglip2-base-patch16-224 produces nonsensical results with AutoModel and pipeline", + "accept": false, + "reason": "Docs mismatch vs incorrect model output. The shared pipeline mention is too broad to treat as a duplicate." + }, + { + "left": "issue:43673 \u2013 GenerationMixin cache missing in v5.0.0 during chunked_prefill", + "right": "issue:43761 \u2013 CLIPVisionModel.forward returns hidden_states=None even when output_hidden_states=True", + "accept": false, + "reason": "Both are v5 regressions, but one is generation cache handling and the other is vision model hidden-state outputs. Different code paths." + }, + { + "left": "issue:43784 \u2013 NameError: name 'nn' is not defined when importing sentence-transformers with latest transformers", + "right": "issue:45542 \u2013 Only tensorboard is installed without TensorFlow, causing undefined tf backend error", + "accept": false, + "reason": "Both are optional-backend/import issues, but they involve different missing dependencies and different failure points." + }, + { + "left": "issue:43824 \u2013 ImportError: cannot import name 'Qwen2_5_VLForConditionalGeneration' from 'transformers'", + "right": "issue:43976 \u2013 Transformers 5.1.0 does not work with Python3.9+ but Python3.10+", + "accept": false, + "reason": "Missing class export/import issue vs Python version compatibility issue. Not duplicates." + }, + { + "left": "issue:44297 \u2013 tokenizer.save_pretrained: tokenizer_class in tokenizer_config.json doesn't match the original", + "right": "issue:45397 \u2013 gemma-4 zero3 from_pretrained", + "accept": false, + "reason": "Tokenizer serialization metadata bug vs model loading with zero3. Different concerns." + }, + { + "left": "issue:43450 \u2013 Video processors return incorrect shape when input is batched", + "right": "issue:44617 \u2013 Sam3Video: CUDA out of memory", + "accept": false, + "reason": "Both are video-related, but one is an output-shape bug and the other is memory exhaustion. No shared underlying 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": 35, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:36246", + "issue:41628", + "issue:41950", + "issue:42491", + "issue:42757", + "issue:42886", + "issue:43299", + "issue:43352", + "issue:43525", + "issue:43526", + "issue:43531", + "issue:43596", + "issue:43643", + "issue:43673", + "issue:43881", + "issue:43901", + "issue:43976", + "issue:44162", + "issue:44188", + "issue:44220", + "issue:44242", + "issue:44246", + "issue:44295", + "issue:44336", + "issue:44351", + "issue:44373", + "issue:44485", + "issue:44496", + "issue:44561", + "issue:44589", + "issue:44749", + "issue:44779", + "issue:44857", + "issue:44871", + "issue:44877", + "issue:45003", + "issue:45200", + "issue:45250", + "issue:45292", + "issue:45362", + "issue:45375", + "issue:45397", + "issue:45412", + "issue:45561", + "issue:45563", + "issue:45593", + "issue:46123", + "issue:46132" + ], + "soft_pairs": [ + "issue:43525|issue:43881", + "issue:43901|issue:44246", + "issue:43525|issue:43643", + "issue:44188|issue:44336", + "issue:44589|issue:45362", + "issue:41628|issue:43976", + "issue:42491|issue:43299", + "issue:45561|issue:45563", + "issue:44336|issue:44373", + "issue:44295|issue:45397", + "issue:44242|issue:45593", + "issue:44246|issue:44496", + "issue:41950|issue:44220", + "issue:43531|issue:45362", + "issue:43526|issue:45003", + "issue:42886|issue:46132", + "issue:36246|issue:42757", + "issue:36246|issue:44351", + "issue:44336|issue:44485", + "issue:44246|issue:44871", + "issue:45003|issue:45561", + "issue:43673|issue:44561", + "issue:44242|issue:44857", + "issue:36246|issue:43596", + "issue:44779|issue:45292", + "issue:44295|issue:44749", + "issue:43352|issue:45250", + "issue:44162|issue:45200", + "issue:43901|issue:45003", + "issue:45412|issue:46123", + "issue:44496|issue:45003", + "issue:44877|issue:45375" + ], + "prepared_review_unit_hash": "cf4eacca07be7cf678fef5b190342fe6c1d7f1459e4e856e1f7af2486ce325e7", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 36987, + "estimated_input_tokens": 9247, + "estimated_eval_tokens": 18750 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is highly heterogeneous: most pairs are only superficially similar (imports, config loading, or generic model bugs) but do not describe the same underlying defect or change. No soft pair is a safe duplicate merge.", + "confidence": 0.87, + "canonical_issue_reason": "Issue 44246 is the broadest, most cross-cutting report in the set; it is the closest thing to a cluster anchor, but the surrounding issues are not true duplicates of it.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44246 is the most generally representative and high-impact issue here, though the cluster overall is not a single duplicate family.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43525", + "right": "issue:43881", + "accept": false, + "reason": "Different models and different failures: Llama4 config attr error vs GLM-4V loading failure." + }, + { + "left": "issue:43901", + "right": "issue:44246", + "accept": false, + "reason": "Docs mismatch for TextClassificationPipeline vs import-time performance complaint; unrelated bugs." + }, + { + "left": "issue:43525", + "right": "issue:43643", + "accept": false, + "reason": "Both are config-related, but one is a missing pad_token_id attr and the other is trust_remote_code dropping fields; not the same bug." + }, + { + "left": "issue:44188", + "right": "issue:44336", + "accept": false, + "reason": "Attention-kernel divergence under torch.compile is unrelated to ANSI codes in loading_report." + }, + { + "left": "issue:44589", + "right": "issue:45362", + "accept": false, + "reason": "Different runtime errors on different model paths; no shared code-path bug is evident." + }, + { + "left": "issue:41628", + "right": "issue:43976", + "accept": false, + "reason": "ImportError for AutoImageProcessor is not the same as Python-version compatibility breaking Transformers." + }, + { + "left": "issue:42491", + "right": "issue:43299", + "accept": false, + "reason": "Both mention Qwen3 MoE, but one is an hf4.x/hf5.x LoRA compatibility issue and the other is a v5.0.0.dev0 Qwen3VL loading breakage." + }, + { + "left": "issue:45561", + "right": "issue:45563", + "accept": false, + "reason": "A pytest-xdist file race and a stale generation warning are unrelated." + }, + { + "left": "issue:44336", + "right": "issue:44373", + "accept": false, + "reason": "Terminal ANSI output bug vs a wrong docstring; not the same underlying change." + }, + { + "left": "issue:44295", + "right": "issue:45397", + "accept": false, + "reason": "Position_ids buffer access error and gemma-4 zero3 loading are different code paths." + }, + { + "left": "issue:44242", + "right": "issue:45593", + "accept": false, + "reason": "Both concern missing loss terms, but they affect different models and mechanisms; too broad to merge." + }, + { + "left": "issue:44246", + "right": "issue:44496", + "accept": false, + "reason": "Import performance issue vs unrecognized model/config_type error; unrelated." + }, + { + "left": "issue:41950", + "right": "issue:44220", + "accept": false, + "reason": "Video-classification image-processor lookup and audio fbank extraction are different pipelines." + }, + { + "left": "issue:43531", + "right": "issue:45362", + "accept": false, + "reason": "Both involve Qwen variants, but one is a sliding_window bug and the other is a chat crash; different fixes." + }, + { + "left": "issue:43526", + "right": "issue:45003", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug is unrelated to sys.modules access in modeling_utils." + }, + { + "left": "issue:42886", + "right": "issue:46132", + "accept": false, + "reason": "Offline cache loading and AttentionInterface.register behavior are unrelated." + }, + { + "left": "issue:36246", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but for different symbols and different subsystems." + }, + { + "left": "issue:36246", + "right": "issue:44351", + "accept": false, + "reason": "Different missing exports: Qwen2_5_VLImageProcessor vs HybridCache." + }, + { + "left": "issue:44336", + "right": "issue:44485", + "accept": false, + "reason": "ANSI rendering bug vs GLM-5 RoPE implementation discussion; no shared defect." + }, + { + "left": "issue:44246", + "right": "issue:44871", + "accept": false, + "reason": "Import-time slowdown and Gemma eos_token_id inconsistency are unrelated." + }, + { + "left": "issue:45003", + "right": "issue:45561", + "accept": false, + "reason": "Unsafe sys.modules access and xdist file races are unrelated." + }, + { + "left": "issue:43673", + "right": "issue:44561", + "accept": false, + "reason": "Generation cache missing in chunked_prefill and removal of is_torch_fx_available break different APIs." + }, + { + "left": "issue:44242", + "right": "issue:44857", + "accept": false, + "reason": "Different auxiliary-loss/AMP crashes in different models; not the same bug." + }, + { + "left": "issue:36246", + "right": "issue:43596", + "accept": false, + "reason": "ImportError for a vision processor is unrelated to a Deepspeed/BertModel index error." + }, + { + "left": "issue:44779", + "right": "issue:45292", + "accept": false, + "reason": "Tokenizer regression and resize_token_embeddings not updating output embeddings are different issues." + }, + { + "left": "issue:44295", + "right": "issue:44749", + "accept": false, + "reason": "Position_ids buffer handling and data-filtering slowdown are unrelated." + }, + { + "left": "issue:43352", + "right": "issue:45250", + "accept": false, + "reason": "Model-specific Flash Attention unsupported vs a generic Flash Attention 2.0 topic; not the same fix." + }, + { + "left": "issue:44162", + "right": "issue:45200", + "accept": false, + "reason": "ESM2 breakage and Gemma 4 mm_token_type_ids defaulting are unrelated model bugs." + }, + { + "left": "issue:43901", + "right": "issue:45003", + "accept": false, + "reason": "Pipeline docs issue vs sys.modules access bug; different code areas." + }, + { + "left": "issue:45412", + "right": "issue:46123", + "accept": false, + "reason": "Memory cleanup after deletion and partial-batch is_last handling are unrelated." + }, + { + "left": "issue:44496", + "right": "issue:45003", + "accept": false, + "reason": "Unrecognized model/config loading and sys.modules access are different failure modes." + }, + { + "left": "issue:44877", + "right": "issue:45375", + "accept": false, + "reason": "Both involve strict config, but one blocks granite_speech loading while the other silently drops a field in Qwen3_5MoeVisionConfig; not the same bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 36, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:42886", + "issue:43065", + "issue:43232", + "issue:43257", + "issue:43262", + "issue:43408", + "issue:43475", + "issue:43540", + "issue:43653", + "issue:43673", + "issue:43931", + "issue:44060", + "issue:44077", + "issue:44162", + "issue:44188", + "issue:44246", + "issue:44336", + "issue:44368", + "issue:44466", + "issue:44479", + "issue:44483", + "issue:44530", + "issue:44734", + "issue:44877", + "issue:44933", + "issue:44977", + "issue:44987", + "issue:44995", + "issue:45137", + "issue:45200", + "issue:45229", + "issue:45292", + "issue:45335", + "issue:45375", + "issue:45397", + "issue:45459", + "issue:45563", + "issue:45584", + "issue:45588", + "issue:45600", + "issue:45656", + "issue:45701", + "issue:45759", + "issue:45987", + "issue:46082", + "issue:46123", + "issue:46170", + "issue:46202" + ], + "soft_pairs": [ + "issue:45987|issue:46082", + "issue:43262|issue:44246", + "issue:45375|issue:45759", + "issue:43257|issue:45137", + "issue:45292|issue:45584", + "issue:45292|issue:45701", + "issue:44987|issue:45459", + "issue:43232|issue:44336", + "issue:44995|issue:45200", + "issue:44479|issue:46170", + "issue:43065|issue:43408", + "issue:43475|issue:43540", + "issue:44466|issue:45335", + "issue:44483|issue:46202", + "issue:42886|issue:45229", + "issue:45397|issue:45656", + "issue:44188|issue:46202", + "issue:44060|issue:44077", + "issue:43653|issue:44162", + "issue:44995|issue:45588", + "issue:44368|issue:44977", + "issue:45137|issue:45600", + "issue:44368|issue:45563", + "issue:44877|issue:46170", + "issue:43673|issue:44734", + "issue:43931|issue:44368", + "issue:44530|issue:46170", + "issue:43065|issue:46123", + "issue:44933|issue:45459" + ], + "prepared_review_unit_hash": "e1f61cacba98cbecd17dcba9ae163712b92d20e1895ec4f0c8375c55fb74d60a", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36417, + "estimated_input_tokens": 9105, + "estimated_eval_tokens": 18466 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These are mostly unrelated bug reports with title-level keyword overlap only. None of the soft pairs look like the same underlying issue or fix path, so there is no true duplicate cluster here.", + "confidence": 0.95, + "canonical_issue_reason": "No single canonical issue: the items span unrelated areas (tokenizers, generation/cache, multimodal configs, SAM3, DeepSpeed, import/runtime warnings), so there is no clear duplicate anchor.", + "canonical_pr_reason": null, + "best_issue_reason": "No issue is a good global representative because the cluster is heterogeneous; any one choice would misrepresent the rest.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45987", + "right": "issue:46082", + "accept": false, + "reason": "Cache-return type bug vs LlamaConfig head_dim validation; different components and failure modes." + }, + { + "left": "issue:43262", + "right": "issue:44246", + "accept": false, + "reason": "Audio chat-template sampling-rate default vs import-time performance; unrelated concerns." + }, + { + "left": "issue:45375", + "right": "issue:45759", + "accept": false, + "reason": "Missing config field dropped by @strict vs from_config unwrapping composite text_config; both config-related but different bugs." + }, + { + "left": "issue:43257", + "right": "issue:45137", + "accept": false, + "reason": "MOE weight conversion under accelerate+deepspeed vs ZeRO3 deque IndexError; different code paths and symptoms." + }, + { + "left": "issue:45292", + "right": "issue:45584", + "accept": false, + "reason": "Embedding resize propagation vs Whisper empty-transcription generation failure; unrelated." + }, + { + "left": "issue:45292", + "right": "issue:45701", + "accept": false, + "reason": "resize_token_embeddings propagation bug vs version-dependent tokenization changes; not the same issue." + }, + { + "left": "issue:44987", + "right": "issue:45459", + "accept": false, + "reason": "Model load failure for a specific repo vs tokenizer error masking when protobuf is absent; different root causes." + }, + { + "left": "issue:43232", + "right": "issue:44336", + "accept": false, + "reason": "Generation kwargs update after sync_gpus vs ANSI output formatting in loading_report; unrelated." + }, + { + "left": "issue:44995", + "right": "issue:45200", + "accept": false, + "reason": "GlmMoeDsa stale cache on second forward vs Gemma4 mm_token_type_ids defaulting; different subsystems." + }, + { + "left": "issue:44479", + "right": "issue:46170", + "accept": false, + "reason": "Video-input regression in Qwen models vs Windows ROCm import/dependency issue; unrelated." + }, + { + "left": "issue:43065", + "right": "issue:43408", + "accept": false, + "reason": "Dummy Conv2d in SAM3 pixel decoder vs SAM3 model-type warning; same broad family but not the same bug." + }, + { + "left": "issue:43475", + "right": "issue:43540", + "accept": false, + "reason": "Missing Sam3VisionEncoderOutput attribute vs Qwen3OmniMoe video processing ValueError; different models and failures." + }, + { + "left": "issue:44466", + "right": "issue:45335", + "accept": false, + "reason": "Device-dependent tied-weight serialization vs resize_token_embeddings not updating decoder embeddings; related theme, different concrete bugs." + }, + { + "left": "issue:44483", + "right": "issue:46202", + "accept": false, + "reason": "Chat/completions request rejection vs Gemma pipeline roundtrip tokenization failure; unrelated API vs tokenizer bug." + }, + { + "left": "issue:42886", + "right": "issue:45229", + "accept": false, + "reason": "Offline tokenizer cache load failure vs Gemma4 multi-GPU CUDA OOM; clearly different problems." + }, + { + "left": "issue:45397", + "right": "issue:45656", + "accept": false, + "reason": "Gemma4 zero3 from_pretrained issue vs optimizer.step called twice under deepspeed; different deepspeed behavior." + }, + { + "left": "issue:44188", + "right": "issue:46202", + "accept": false, + "reason": "torch.compile attention-kernel divergence vs token roundtrip failure; unrelated." + }, + { + "left": "issue:44060", + "right": "issue:44077", + "accept": false, + "reason": "Incorrect tied-weights warning vs patchtsmixer post_init policy; different validation paths." + }, + { + "left": "issue:43653", + "right": "issue:44162", + "accept": false, + "reason": "BigBirdTokenizer special-token registration bug vs ESM2 model breakage; unrelated." + }, + { + "left": "issue:44995", + "right": "issue:45588", + "accept": false, + "reason": "Stale indexer cache on second forward vs flash_attention AttributeError on s_aux=None; different bugs." + }, + { + "left": "issue:44368", + "right": "issue:44977", + "accept": false, + "reason": "Warning about tie_word_embeddings in fine-tuning vs actual flash-attention generation failure; not the same issue." + }, + { + "left": "issue:45137", + "right": "issue:45600", + "accept": false, + "reason": "DeepSpeed ZeRO3 deque error vs auto_mappings referencing removed SAM3LiteText configs; unrelated." + }, + { + "left": "issue:44368", + "right": "issue:45563", + "accept": false, + "reason": "Tie-word-embeddings warning vs stale num_return_sequences warning in paged generate; different warnings and triggers." + }, + { + "left": "issue:44877", + "right": "issue:46170", + "accept": false, + "reason": "Strict config rejecting granite_speech vs Windows ROCm distributed import failure; unrelated." + }, + { + "left": "issue:43673", + "right": "issue:44734", + "accept": false, + "reason": "Missing cache in GenerationMixin during chunked_prefill vs wrong tensor indexing in /v1/responses KV continuation; both cache-related but distinct bugs." + }, + { + "left": "issue:43931", + "right": "issue:44368", + "accept": false, + "reason": "Qwen3-VL weight-shape mismatch on load vs tie_word_embeddings warning in Qwen3.5 fine-tuning; unrelated." + }, + { + "left": "issue:44530", + "right": "issue:46170", + "accept": false, + "reason": "PagedAttentionCache invalid group type on Qwen3.5 vs Windows ROCm import error; different layers entirely." + }, + { + "left": "issue:43065", + "right": "issue:46123", + "accept": false, + "reason": "SAM3 pixel decoder dummy layer vs MaskGenerationPipeline final-batch result drop; unrelated." + }, + { + "left": "issue:44933", + "right": "issue:45459", + "accept": false, + "reason": "Nonexistent image_utils import vs protobuf error masking in tokenizer load; different modules and 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": 37, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:28282", + "issue:30990", + "issue:41628", + "issue:42371", + "issue:42673", + "issue:42831", + "issue:42994", + "issue:43232", + "issue:43475", + "issue:43482", + "issue:43525", + "issue:43643", + "issue:43646", + "issue:43673", + "issue:43701", + "issue:43704", + "issue:43873", + "issue:44038", + "issue:44162", + "issue:44188", + "issue:44222", + "issue:44297", + "issue:44351", + "issue:44361", + "issue:44623", + "issue:44661", + "issue:44749", + "issue:44869", + "issue:44871", + "issue:44933", + "issue:44945", + "issue:45081", + "issue:45092", + "issue:45103", + "issue:45230", + "issue:45278", + "issue:45310", + "issue:45356", + "issue:45375", + "issue:45381", + "issue:45397", + "issue:45406", + "issue:45478", + "issue:45656", + "issue:46077", + "issue:46123", + "issue:46132", + "issue:46202" + ], + "soft_pairs": [ + "issue:44297|issue:44623", + "issue:44869|issue:45356", + "issue:44361|issue:44749", + "issue:43646|issue:44162", + "issue:43232|issue:43673", + "issue:44623|issue:45656", + "issue:44749|issue:45656", + "issue:44871|issue:46132", + "issue:43673|issue:45278", + "issue:43701|issue:44749", + "issue:42994|issue:43482", + "issue:43475|issue:45381", + "issue:45230|issue:45397", + "issue:43475|issue:43643", + "issue:28282|issue:30990", + "issue:44038|issue:44623", + "issue:45406|issue:46202", + "issue:46077|issue:46123", + "issue:41628|issue:44933", + "issue:42371|issue:45092", + "issue:43475|issue:44661", + "issue:45375|issue:45478", + "issue:42994|issue:43525", + "issue:45081|issue:45103", + "issue:45310|issue:45375", + "issue:43873|issue:44945", + "issue:41628|issue:44351", + "issue:43232|issue:44188", + "issue:42673|issue:43704", + "issue:42831|issue:44222" + ], + "prepared_review_unit_hash": "44a2fd77b4ff511baa1ca76b5d3cd5f2a6a702975a43f3bb5fc4b8139142c89b", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36389, + "estimated_input_tokens": 9098, + "estimated_eval_tokens": 18452 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a heterogeneous Transformers issue cluster spanning import errors, tokenizer/config regressions, generation bugs, and model-specific failures. There are at least two duplicate-like pockets: the Qwen3ForCausalLM VRAM-leak pair (42673/43704) and an exact Qwen3.5 Moe title duplicate pair (45310/45478), but most other pairs are not the same underlying bug.", + "confidence": 0.79, + "canonical_issue_reason": "issue:42673 is the strongest canonical anchor for one true duplicate pocket because it has the clearest, most specific bug description (Qwen3ForCausalLM VRAM leak in multiple dataloader threads) and a later duplicate in 43704. The cluster also contains an exact Qwen3.5 Moe duplicate pair (45310/45478), but that is a separate smaller pocket.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the best global representative because it is the broadest umbrella-style regression report in the set and sits near the center of the upgrade/import-failure theme, while many others are narrower model- or path-specific bugs.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44297", + "right": "issue:44623", + "accept": false, + "reason": "Both involve save_pretrained, but one is a tokenizer_config mismatch and the other is missing processor files; different bugs." + }, + { + "left": "issue:44869", + "right": "issue:45356", + "accept": false, + "reason": "Whisper timestamp decoding crash and Kimi tokenizer regression are unrelated code paths." + }, + { + "left": "issue:44361", + "right": "issue:44749", + "accept": false, + "reason": "MLukeTokenizer AttributeError and a 10x filtering slowdown are different failure modes." + }, + { + "left": "issue:43646", + "right": "issue:44162", + "accept": false, + "reason": "Custom model initialization breakage and ESM2 being broken are separate model-specific issues." + }, + { + "left": "issue:43232", + "right": "issue:43673", + "accept": false, + "reason": "Both touch generation, but sync_gpus kwargs handling and missing GenerationMixin cache in chunked_prefill are distinct problems." + }, + { + "left": "issue:44623", + "right": "issue:45656", + "accept": false, + "reason": "Processor save_pretrained file loss and deepspeed optimizer stepping are unrelated." + }, + { + "left": "issue:44749", + "right": "issue:45656", + "accept": false, + "reason": "A filtering performance regression is not the same as the deepspeed double-step bug." + }, + { + "left": "issue:44871", + "right": "issue:46132", + "accept": false, + "reason": "Gemma eos_token_id inconsistency and AttentionInterface.register behavior changes are different issues." + }, + { + "left": "issue:43673", + "right": "issue:45278", + "accept": false, + "reason": "A specific generation-cache bug is not the same as broad import failures after upgrade." + }, + { + "left": "issue:43701", + "right": "issue:44749", + "accept": false, + "reason": "Checkpoint key mismatch and dataloader filtering slowdown are unrelated." + }, + { + "left": "issue:42994", + "right": "issue:43482", + "accept": false, + "reason": "Quantized model saving failure and Qwen2.5-GGUF loading failure are different code paths." + }, + { + "left": "issue:43475", + "right": "issue:45381", + "accept": false, + "reason": "SAM3 vision encoder missing attribute and Qwen2.5-VL video position-id bug are unrelated models." + }, + { + "left": "issue:45230", + "right": "issue:45397", + "accept": false, + "reason": "The generic bug report does not establish the same issue as the Gemma-4 ZeRO3 from_pretrained failure." + }, + { + "left": "issue:43475", + "right": "issue:43643", + "accept": false, + "reason": "Different problems: missing fpn_position_embeddings vs trust_remote_code returning incomplete configs." + }, + { + "left": "issue:28282", + "right": "issue:30990", + "accept": false, + "reason": "Missing PyTorch import error and Sentence Transformers hanging on load are not the same bug." + }, + { + "left": "issue:44038", + "right": "issue:44623", + "accept": false, + "reason": "Qwen3-VL-Moe v5 incompatibility and processor.save_pretrained missing files are unrelated." + }, + { + "left": "issue:45406", + "right": "issue:46202", + "accept": false, + "reason": "Gemma4Processor missing _tokenizer and Gemma pipeline roundtrip failure are different issues." + }, + { + "left": "issue:46077", + "right": "issue:46123", + "accept": false, + "reason": "Bidirectional-attention masking and partial-batch result dropping are different pipeline behaviors." + }, + { + "left": "issue:41628", + "right": "issue:44933", + "accept": false, + "reason": "Both are import errors, but they refer to different missing symbols/modules and do not appear to share one fix." + }, + { + "left": "issue:42371", + "right": "issue:45092", + "accept": false, + "reason": "TF32 settings guidance and InternVL2 meta-initialization incompatibility are unrelated." + }, + { + "left": "issue:43475", + "right": "issue:44661", + "accept": false, + "reason": "A model output attribute bug and a tokenizer-mapping add-new-model-like failure are different code paths." + }, + { + "left": "issue:45375", + "right": "issue:45478", + "accept": false, + "reason": "Related Qwen3.5 Moe titles, but one is a specific config-field loss under strict serialization and the other is a broader from_pretrained failure; not enough to call them the same bug." + }, + { + "left": "issue:42994", + "right": "issue:43525", + "accept": false, + "reason": "Quantized save failure and Llama4Config missing pad_token_id are separate regressions." + }, + { + "left": "issue:45081", + "right": "issue:45103", + "accept": false, + "reason": "Mistral regex patch crash and auto_docstring future-annotations crash are unrelated AttributeErrors." + }, + { + "left": "issue:45310", + "right": "issue:45375", + "accept": false, + "reason": "Both are Qwen3.5 Moe related, but one is a general from_pretrained error while the other is a specific missing config field; too little evidence they are the same underlying bug." + }, + { + "left": "issue:43873", + "right": "issue:44945", + "accept": false, + "reason": "Quantization offloading behavior and pipeline-parallel LLM output correctness are different problems." + }, + { + "left": "issue:41628", + "right": "issue:44351", + "accept": false, + "reason": "Two import errors, but for different missing names with no clear shared root cause." + }, + { + "left": "issue:43232", + "right": "issue:44188", + "accept": false, + "reason": "Generation kwargs syncing and attention-kernel divergence under torch.compile are distinct issues." + }, + { + "left": "issue:42673", + "right": "issue:43704", + "accept": true, + "reason": "Same Qwen3ForCausalLM VRAM leak in multiple dataloader threads; 43704 is a later duplicate of 42673." + }, + { + "left": "issue:42831", + "right": "issue:44222", + "accept": false, + "reason": "FineGrainedFP8 accuracy loss and FP8 save_pretrained failure are different bugs." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The soft-edge false verdicts are mostly conservative and grounded in the titles, but the summary is not fully grounded: the packet also contains an exact duplicate Qwen3.5 Moe pair (`issue:45310` and `issue:45478`) with identical titles, so saying the only clear duplicate pair is the Qwen3ForCausalLM VRAM leak overstates the uniqueness of that pair. The cluster is still largely heterogeneous, but the duplicate-summary claim should be toned down or expanded." + }, + "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": 38, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:30333", + "issue:30990", + "issue:33290", + "issue:35141", + "issue:36010", + "issue:41628", + "issue:42175", + "issue:42222", + "issue:42898", + "issue:42994", + "issue:43232", + "issue:43278", + "issue:43377", + "issue:43479", + "issue:43504", + "issue:43526", + "issue:43673", + "issue:43723", + "issue:43784", + "issue:43824", + "issue:43874", + "issue:43976", + "issue:44038", + "issue:44079", + "issue:44188", + "issue:44222", + "issue:44242", + "issue:44448", + "issue:44496", + "issue:44568", + "issue:44623", + "issue:44734", + "issue:44779", + "issue:44792", + "issue:44869", + "issue:44933", + "issue:44945", + "issue:44964", + "issue:45092", + "issue:45103", + "issue:45137", + "issue:45200", + "issue:45310", + "issue:45356", + "issue:45561", + "issue:45712", + "issue:45753", + "issue:45812" + ], + "soft_pairs": [ + "issue:44945|issue:45753", + "issue:36010|issue:41628", + "issue:44222|issue:45310", + "issue:42994|issue:43824", + "issue:44964|issue:45137", + "issue:43232|issue:44792", + "issue:44038|issue:45310", + "issue:43673|issue:44188", + "issue:42175|issue:45712", + "issue:43526|issue:45561", + "issue:44496|issue:45561", + "issue:43504|issue:45561", + "issue:43377|issue:44242", + "issue:42175|issue:44933", + "issue:42898|issue:44568", + "issue:42222|issue:45200", + "issue:43976|issue:44933", + "issue:30990|issue:35141", + "issue:43479|issue:44869", + "issue:43278|issue:45137", + "issue:43479|issue:44079", + "issue:44623|issue:45310", + "issue:30333|issue:33290", + "issue:42898|issue:45812", + "issue:43784|issue:43824", + "issue:44734|issue:45103", + "issue:43723|issue:44568", + "issue:42898|issue:44779", + "issue:42898|issue:45356", + "issue:43874|issue:45092", + "issue:42898|issue:44448" + ], + "prepared_review_unit_hash": "e277b2826e1380358e66e0ec26401b24c66ae541286927effdfbe4ffaf9ce89c", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37049, + "estimated_input_tokens": 9263, + "estimated_eval_tokens": 18782 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is heterogeneous: it mixes unrelated import/load, tokenizer, multimodal, generation, and training/runtime bugs. Despite some superficial overlap around Transformers v5 regressions, none of the soft edges look like the same underlying issue, so all candidate duplicate links should be rejected.", + "confidence": 0.9, + "canonical_issue_reason": "issue:42898 is the broadest, most central v5-regression report in the set and a plausible anchor for the cluster, but it is still only a representative issue rather than an exact duplicate of the others.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:42898 is the best single issue to anchor the cluster because it is a general user-facing regression report that overlaps thematically with several tokenizer/version-change complaints, even though the underlying bugs differ.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44945", + "right": "issue:45753", + "accept": false, + "reason": "Pipeline-parallel output mismatch and a Qwen3_5 image loop are different symptoms, models, and code paths." + }, + { + "left": "issue:36010", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but for different symbols and different missing/exported APIs." + }, + { + "left": "issue:44222", + "right": "issue:45310", + "accept": false, + "reason": "FP8 save_pretrained for MoE is a save-path bug; Qwen3.5 from_pretrained failure is a load-path bug on a different model family." + }, + { + "left": "issue:42994", + "right": "issue:43824", + "accept": false, + "reason": "Quantized save failure and a Qwen2.5-VL import error are unrelated subsystems." + }, + { + "left": "issue:44964", + "right": "issue:45137", + "accept": false, + "reason": "Phi-4 multimodal load failure and DeepSpeed ZeRO3 deque underflow are unrelated." + }, + { + "left": "issue:43232", + "right": "issue:44792", + "accept": false, + "reason": "Generation kwargs handling after sync_gpus is not the same bug as the janus image-generation test failure." + }, + { + "left": "issue:44038", + "right": "issue:45310", + "accept": false, + "reason": "Both mention Qwen MoE, but one is a Qwen3-VL issue and the other is a Qwen3.5 from_pretrained regression." + }, + { + "left": "issue:43673", + "right": "issue:44188", + "accept": false, + "reason": "Chunked prefill cache missing and torch.compile attention-kernel divergence are different generation/runtime problems." + }, + { + "left": "issue:42175", + "right": "issue:45712", + "accept": false, + "reason": "Dependency/backend packaging is unrelated to leftover dummy class cleanup." + }, + { + "left": "issue:43526", + "right": "issue:45561", + "accept": false, + "reason": "Beit label reduction is a model-specific preprocessing bug, not the xdist file-race issue." + }, + { + "left": "issue:44496", + "right": "issue:45561", + "accept": false, + "reason": "Unrecognized model config loading and captured_info.txt race are unrelated." + }, + { + "left": "issue:43504", + "right": "issue:45561", + "accept": false, + "reason": "Legacy field loading for Beit semantic segmentation is unrelated to the xdist testing-utils race." + }, + { + "left": "issue:43377", + "right": "issue:44242", + "accept": false, + "reason": "MIMI padding-mask mismatch and MoE router-loss omission are different model-behavior bugs." + }, + { + "left": "issue:42175", + "right": "issue:44933", + "accept": false, + "reason": "Backend packaging and a nonexistent image_utils import are unrelated." + }, + { + "left": "issue:42898", + "right": "issue:44568", + "accept": false, + "reason": "Both are tokenizer regressions in v5, but one is clean-up spacing behavior and the other is special-token insertion; not the same bug." + }, + { + "left": "issue:42222", + "right": "issue:45200", + "accept": false, + "reason": "VitPose breakage and Gemma 4 mm_token_type_ids defaults affect different models and code paths." + }, + { + "left": "issue:43976", + "right": "issue:44933", + "accept": false, + "reason": "Python-version compatibility and a missing image_utils import are unrelated." + }, + { + "left": "issue:30990", + "right": "issue:35141", + "accept": false, + "reason": "Sentence-transformers loading hang and token-embedding resizing/post_init reinit are different bugs." + }, + { + "left": "issue:43479", + "right": "issue:44869", + "accept": false, + "reason": "Phi-4 multimodal config defaults and Whisper timestamp decoding are unrelated." + }, + { + "left": "issue:43278", + "right": "issue:45137", + "accept": false, + "reason": "Embedding dtype drift in eval and a ZeRO3 deque error are different problems." + }, + { + "left": "issue:43479", + "right": "issue:44079", + "accept": false, + "reason": "Multimodal config initialization and ModelOutput key assignment are unrelated." + }, + { + "left": "issue:44623", + "right": "issue:45310", + "accept": false, + "reason": "Missing processor save files and Qwen3.5 MoE from_pretrained failure are different operations." + }, + { + "left": "issue:30333", + "right": "issue:33290", + "accept": false, + "reason": "MLflow reporting on failed training jobs and DeepSpeed Adafactor OOM are not the same bug." + }, + { + "left": "issue:42898", + "right": "issue:45812", + "accept": false, + "reason": "Both are v5 tokenizer regressions, but clean_up_tokenization_spaces and Granite token IDs are distinct behaviors." + }, + { + "left": "issue:43784", + "right": "issue:43824", + "accept": false, + "reason": "Sentence-transformers import NameError and Qwen2.5-VL import failure are unrelated import issues." + }, + { + "left": "issue:44734", + "right": "issue:45103", + "accept": false, + "reason": "KV-cache continuation crash in serve and auto_docstring future-annotations crash are unrelated." + }, + { + "left": "issue:43723", + "right": "issue:44568", + "accept": false, + "reason": "AutoTokenizer loading regression and special-token insertion regression are different tokenizer failure modes." + }, + { + "left": "issue:42898", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer regressions, but one is a spacing cleanup change and the other is DeepSeek codec handling; not the same underlying defect." + }, + { + "left": "issue:42898", + "right": "issue:45356", + "accept": false, + "reason": "General v5 tokenization behavior change and Kimi-K2.5 codec-handling regression are separate tokenizer issues." + }, + { + "left": "issue:43874", + "right": "issue:45092", + "accept": false, + "reason": "Missing image-patch counting and old InternVL2 meta-init incompatibility are different multimodal loading bugs." + }, + { + "left": "issue:42898", + "right": "issue:44448", + "accept": false, + "reason": "Tokenizer clean-up behavior and Pegasus output drift are different regression classes." + } + ] + }, + "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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:22355", + "issue:28282", + "issue:30333", + "issue:34689", + "issue:35141", + "issue:36331", + "issue:41628", + "issue:42757", + "issue:42831", + "issue:43116", + "issue:43232", + "issue:43479", + "issue:43644", + "issue:43723", + "issue:43761", + "issue:44060", + "issue:44190", + "issue:44206", + "issue:44222", + "issue:44263", + "issue:44295", + "issue:44297", + "issue:44360", + "issue:44373", + "issue:44448", + "issue:44483", + "issue:44484", + "issue:44485", + "issue:44514", + "issue:44623", + "issue:44871", + "issue:44933", + "issue:44977", + "issue:45071", + "issue:45092", + "issue:45103", + "issue:45125", + "issue:45245", + "issue:45310", + "issue:45357", + "issue:45405", + "issue:45406", + "issue:45656", + "issue:45712", + "issue:45834", + "issue:46082", + "issue:46132" + ], + "soft_pairs": [ + "issue:45405|issue:45712", + "issue:44060|issue:45125", + "issue:44295|issue:45656", + "issue:44448|issue:46132", + "issue:44933|issue:45712", + "issue:44222|issue:44297", + "issue:44297|issue:45656", + "issue:43116|issue:44190", + "issue:43479|issue:43644", + "issue:44190|issue:46082", + "issue:44222|issue:44623", + "issue:42831|issue:44623", + "issue:30333|issue:34689", + "issue:45245|issue:46132", + "issue:30333|issue:36331", + "issue:22355|issue:28282", + "issue:45071|issue:46082", + "issue:41628|issue:42757", + "issue:28282|issue:30333", + "issue:30333|issue:35141", + "issue:44206|issue:45103", + "issue:44297|issue:45310", + "issue:44222|issue:44484", + "issue:43723|issue:44977", + "issue:43232|issue:45834", + "issue:44263|issue:45092", + "issue:43761|issue:46082", + "issue:44295|issue:44623", + "issue:44483|issue:45406", + "issue:44373|issue:44485", + "issue:44514|issue:45103", + "issue:43723|issue:44871", + "issue:45092|issue:45357", + "issue:44263|issue:44360" + ], + "prepared_review_unit_hash": "66754c136a053313fdfbab24b43d3358f4c5be3fb0d5addebfe2eb88b1feab01", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 34, + "serialized_chars": 37148, + "estimated_input_tokens": 9287, + "estimated_eval_tokens": 18830 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is highly heterogeneous: most items are superficial keyword matches around imports, configs, or save/load behavior, but they describe different code paths and failures. No soft pair looks like a true duplicate, so I rejected them all. There are no PRs in the set; issue 44623 is the clearest standalone representative of the cluster's serialization/save-pretrained theme.", + "confidence": 0.63, + "canonical_issue_reason": "Issue 44623 is the most concrete and self-contained bug report in the set: it names a specific API (`processor.save_pretrained(...)`) and a clear failure mode (missing files).", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44623 is the best standalone issue to anchor this cluster because it is actionable, specific, and broadly representative of the save/load serialization problems that several nearby items loosely resemble.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45405", + "right": "issue:45712", + "accept": false, + "reason": "Unrelated: one is a PEFT version bump, the other is leftover dummy classes leaking into exports/check_repo." + }, + { + "left": "issue:44060", + "right": "issue:45125", + "accept": false, + "reason": "Both mention Qwen3 MoE, but one is a tied-weights warning and the other is missing `_tp_plan`; different bugs." + }, + { + "left": "issue:44295", + "right": "issue:45656", + "accept": false, + "reason": "Different subsystems: `position_ids` buffer access vs. a deepspeed double optimizer-step report." + }, + { + "left": "issue:44448", + "right": "issue:46132", + "accept": false, + "reason": "Different issues: model output drift across versions vs. `AttentionInterface.register` changing function behavior." + }, + { + "left": "issue:44933", + "right": "issue:45712", + "accept": false, + "reason": "Both touch import/export surfaces, but one is a missing image_utils import and the other is dummy class cleanup." + }, + { + "left": "issue:44222", + "right": "issue:44297", + "accept": false, + "reason": "Both involve `save_pretrained`, but one is FP8 MoE model saving and the other is tokenizer class metadata; not the same bug." + }, + { + "left": "issue:44297", + "right": "issue:45656", + "accept": false, + "reason": "Tokenizer save metadata mismatch is unrelated to a deepspeed optimizer-step problem." + }, + { + "left": "issue:43116", + "right": "issue:44190", + "accept": false, + "reason": "Both concern example scripts, but one is multi-label classification output and the other is local dataset loading." + }, + { + "left": "issue:43479", + "right": "issue:43644", + "accept": false, + "reason": "Different bugs: multimodal config defaults vs. non-persistent buffers being filled with junk." + }, + { + "left": "issue:44190", + "right": "issue:46082", + "accept": false, + "reason": "Unrelated: dataset loading in an example script vs. LlamaConfig head_dim validation." + }, + { + "left": "issue:44222", + "right": "issue:44623", + "accept": false, + "reason": "Same general save-pretrained area, but one is FP8 MoE model saving and the other is processor file omission." + }, + { + "left": "issue:42831", + "right": "issue:44623", + "accept": false, + "reason": "Accuracy regression in FineGrainedFP8 is unrelated to missing processor files during save_pretrained." + }, + { + "left": "issue:30333", + "right": "issue:34689", + "accept": false, + "reason": "Different failures: MLflow reporting on failed training vs. model loading regression for Llama 3.2 Vision." + }, + { + "left": "issue:45245", + "right": "issue:46132", + "accept": false, + "reason": "Categorical-cardinality runtime error is unrelated to attention registration behavior." + }, + { + "left": "issue:30333", + "right": "issue:36331", + "accept": false, + "reason": "MLflow reporting bug is unrelated to the trainer `compute_loss` signature change." + }, + { + "left": "issue:22355", + "right": "issue:28282", + "accept": false, + "reason": "Both are import errors, but one is missing `transformers.onnx` and the other is PyTorch dependency detection." + }, + { + "left": "issue:45071", + "right": "issue:46082", + "accept": false, + "reason": "Type-checking breakage in `PretrainedConfig` is unrelated to LlamaConfig head_dim rejection." + }, + { + "left": "issue:41628", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but they involve different missing symbols and different packages." + }, + { + "left": "issue:28282", + "right": "issue:30333", + "accept": false, + "reason": "PyTorch import detection and MLflow reporting are unrelated." + }, + { + "left": "issue:30333", + "right": "issue:35141", + "accept": false, + "reason": "Failed-job reporting has nothing to do with embedding resizing/reinitialization." + }, + { + "left": "issue:44206", + "right": "issue:45103", + "accept": false, + "reason": "Different code paths: feature extractor argument mismatch vs. auto-docstring annotation handling." + }, + { + "left": "issue:44297", + "right": "issue:45310", + "accept": false, + "reason": "Tokenizer save metadata mismatch is not the same as the Qwen3.5 MoE from_pretrained regression." + }, + { + "left": "issue:44222", + "right": "issue:44484", + "accept": false, + "reason": "FP8 MoE save_pretrained bug is unrelated to max_shard_size default behavior." + }, + { + "left": "issue:43723", + "right": "issue:44977", + "accept": false, + "reason": "Tokenizer loading regression and flash-attention generation issues are different bugs." + }, + { + "left": "issue:43232", + "right": "issue:45834", + "accept": false, + "reason": "Generation kwargs update after sync_gpus is unrelated to Kosmos2.5 long OCR index errors." + }, + { + "left": "issue:44263", + "right": "issue:45092", + "accept": false, + "reason": "Torch.split return handling in a MoE indexer is unrelated to remote-code checkpoint meta-initialization." + }, + { + "left": "issue:43761", + "right": "issue:46082", + "accept": false, + "reason": "Hidden-states regression in CLIPVisionModel is unrelated to LlamaConfig head_dim validation." + }, + { + "left": "issue:44295", + "right": "issue:44623", + "accept": false, + "reason": "Reading `position_ids` after buffer registration is unrelated to processor save_pretrained file omission." + }, + { + "left": "issue:44483", + "right": "issue:45406", + "accept": false, + "reason": "Chat/completions request handling is unrelated to Gemma4Processor missing `_tokenizer`." + }, + { + "left": "issue:44373", + "right": "issue:44485", + "accept": false, + "reason": "Wrong docstring for `position_ids` is a documentation issue; GLM-5 RoPE is an implementation discussion." + }, + { + "left": "issue:44514", + "right": "issue:45103", + "accept": false, + "reason": "Processor batch-padding crash is unrelated to auto-docstring annotation processing." + }, + { + "left": "issue:43723", + "right": "issue:44871", + "accept": false, + "reason": "Tokenizer loading regression and eos_token_id inconsistency are separate issues." + }, + { + "left": "issue:45092", + "right": "issue:45357", + "accept": false, + "reason": "Both involve model loading/saving, but they affect different models and different serialization problems." + }, + { + "left": "issue:45405", + "right": "issue:45712", + "accept": false, + "reason": "PEFT version pinning is unrelated to dummy class cleanup/export leakage." + }, + { + "left": "issue:45656", + "right": "issue:45834", + "accept": false, + "reason": "Double optimizer-step in deepspeed is unrelated to Kosmos2.5 OCR index errors." + }, + { + "left": "issue:44263", + "right": "issue:44360", + "accept": false, + "reason": "Both mention DSA indexer, but one is about torch.split return values and the other about a missing ReLU; not the same bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 40, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:22355", + "issue:28218", + "issue:30990", + "issue:33357", + "issue:38175", + "issue:39401", + "issue:41628", + "issue:42371", + "issue:42757", + "issue:42831", + "issue:42886", + "issue:42907", + "issue:42994", + "issue:43066", + "issue:43122", + "issue:43232", + "issue:43479", + "issue:43576", + "issue:43646", + "issue:43723", + "issue:43756", + "issue:43784", + "issue:43824", + "issue:44038", + "issue:44060", + "issue:44117", + "issue:44261", + "issue:44263", + "issue:44295", + "issue:44297", + "issue:44373", + "issue:44442", + "issue:44521", + "issue:44568", + "issue:44671", + "issue:44704", + "issue:44829", + "issue:44913", + "issue:44991", + "issue:45092", + "issue:45278", + "issue:45290", + "issue:45310", + "issue:45593", + "issue:45753", + "issue:46002", + "issue:46050", + "issue:46132" + ], + "soft_pairs": [ + "issue:30990|issue:38175", + "issue:42907|issue:46050", + "issue:43723|issue:44991", + "issue:44829|issue:46002", + "issue:44261|issue:45092", + "issue:43723|issue:44442", + "issue:41628|issue:43824", + "issue:42831|issue:45310", + "issue:43479|issue:44913", + "issue:42831|issue:44038", + "issue:44263|issue:44373", + "issue:39401|issue:44568", + "issue:42757|issue:45278", + "issue:42886|issue:42994", + "issue:43232|issue:45593", + "issue:42831|issue:45753", + "issue:42886|issue:43066", + "issue:22355|issue:28218", + "issue:43756|issue:44060", + "issue:44671|issue:46132", + "issue:43122|issue:44521", + "issue:43576|issue:43784", + "issue:44117|issue:44704", + "issue:43646|issue:46002", + "issue:30990|issue:33357", + "issue:42371|issue:44263", + "issue:44295|issue:44297", + "issue:44704|issue:45290" + ], + "prepared_review_unit_hash": "28f145cd17438926d9ae0188f8bb266d2cb1c875672396b3e34a1efb099d6ebe", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 35659, + "estimated_input_tokens": 8915, + "estimated_eval_tokens": 18086 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly unrelated issues with only one credible duplicate pair in the tokenizer-loading regression area. Most other soft matches are superficial (same broad subsystem, same model family, or generic failure type) but do not look like the same underlying bug.", + "confidence": 0.76, + "canonical_issue_reason": "issue:43723 is the broadest representative of the only credible duplicate subcluster: a v5 AutoTokenizer loading regression that also covers the specific tokenizer-load failure in issue:44991.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43723 is the strongest umbrella issue for the tokenizer-loading regression theme; it is more general than the specific model report in issue:44991 and best fits the duplicate cluster if one is chosen.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:30990", + "right": "issue:38175", + "accept": false, + "reason": "Different symptoms and code paths: loading hangs in Sentence Transformers vs zero probabilities in SigLIP2 inference." + }, + { + "left": "issue:42907", + "right": "issue:46050", + "accept": false, + "reason": "Both involve quantized-model saving, but the models and failure modes differ (dequantized Ministrals/Devstrals vs sinq save_pretrained/from_pretrained breakage)." + }, + { + "left": "issue:43723", + "right": "issue:44991", + "accept": true, + "reason": "Both describe a v5 AutoTokenizer.from_pretrained/tokenizer-loading regression; 44991 looks like a specific model instance of the broader failure in 43723." + }, + { + "left": "issue:44829", + "right": "issue:46002", + "accept": false, + "reason": "Both mention bad training/NaNs, but one is tied to flash_attention_3 in sequence classification and the other to checkout/init NaNs in classification heads; not the same bug." + }, + { + "left": "issue:44261", + "right": "issue:45092", + "accept": false, + "reason": "Different root causes: missing rms_norm_eps in MLA layernorm vs remote-code/meta-initialization incompatibility for InternVL2." + }, + { + "left": "issue:43723", + "right": "issue:44442", + "accept": false, + "reason": "Both are tokenizer-loading failures, but the titles only show a generic v5 regression versus a specific FastSpeech2ConformerTokenizer load issue; not enough to treat as the same bug." + }, + { + "left": "issue:41628", + "right": "issue:43824", + "accept": false, + "reason": "Both are import errors, but they concern different missing symbols/classes and likely different export paths." + }, + { + "left": "issue:42831", + "right": "issue:45310", + "accept": false, + "reason": "Different issues: FineGrainedFP8 accuracy vs a Qwen3.5 MoE from_pretrained error." + }, + { + "left": "issue:43479", + "right": "issue:44913", + "accept": false, + "reason": "Both are config/default handling bugs, but they affect different models and different config fields/behaviors." + }, + { + "left": "issue:42831", + "right": "issue:44038", + "accept": false, + "reason": "Not the same problem: one is an FP8 accuracy issue, the other a Qwen3-VL-Moe bug report." + }, + { + "left": "issue:44263", + "right": "issue:44373", + "accept": false, + "reason": "One is a runtime tensor split issue; the other is just a docstring problem." + }, + { + "left": "issue:39401", + "right": "issue:44568", + "accept": false, + "reason": "Both are tokenizer behavior bugs, but one is wrong offset_mapping and the other is missing BOS/EOS insertion; different concrete defects." + }, + { + "left": "issue:42757", + "right": "issue:45278", + "accept": false, + "reason": "45278 is a broad import-error regression, but 42757 is specifically about is_offline_mode; too generic to call the same bug." + }, + { + "left": "issue:42886", + "right": "issue:42994", + "accept": false, + "reason": "Offline tokenizer cache loading and quantized model saving are unrelated." + }, + { + "left": "issue:43232", + "right": "issue:45593", + "accept": false, + "reason": "Generation kwarg syncing and D-FINE auxiliary losses are unrelated subsystems." + }, + { + "left": "issue:42831", + "right": "issue:45753", + "accept": false, + "reason": "A numerical accuracy issue is not the same as an infinite-loop bug on a specific image." + }, + { + "left": "issue:42886", + "right": "issue:43066", + "accept": false, + "reason": "Offline cache loading failure and wrong tokenizer decoder type are different tokenizer bugs." + }, + { + "left": "issue:22355", + "right": "issue:28218", + "accept": false, + "reason": "Missing transformers.onnx import and extra tokenizer space after added token are unrelated." + }, + { + "left": "issue:43756", + "right": "issue:44060", + "accept": false, + "reason": "Different model-specific architecture/config problems with no shared concrete code path." + }, + { + "left": "issue:44671", + "right": "issue:46132", + "accept": false, + "reason": "CamemBERT MLM predictions vs AttentionInterface.register behavior are unrelated." + }, + { + "left": "issue:43122", + "right": "issue:44521", + "accept": false, + "reason": "Different tokenizer/chat-template problems: tokenization drift across versions vs multimodal assistant mask generation." + }, + { + "left": "issue:43576", + "right": "issue:43784", + "accept": false, + "reason": "A broken CLI command and an import NameError in sentence-transformers are not the same issue." + }, + { + "left": "issue:44117", + "right": "issue:44704", + "accept": false, + "reason": "Both are from_pretrained-related, but one is a tokenizer-mapping None bug and the other is AutoProcessor kwarg forwarding; different code paths." + }, + { + "left": "issue:43646", + "right": "issue:46002", + "accept": false, + "reason": "Custom model initialization breakage is not the same as NaNs in classification heads after init." + }, + { + "left": "issue:30990", + "right": "issue:33357", + "accept": false, + "reason": "Sentence Transformers loading stall and a MacOS bus error in CLIP inference are different failures." + }, + { + "left": "issue:42371", + "right": "issue:44263", + "accept": false, + "reason": "TF32 API guidance and a torch.split return-value issue are unrelated." + }, + { + "left": "issue:44295", + "right": "issue:44297", + "accept": false, + "reason": "Reading position_ids after buffer registration and tokenizer save_pretrained metadata mismatch are unrelated." + }, + { + "left": "issue:44704", + "right": "issue:45290", + "accept": false, + "reason": "AutoProcessor kwarg forwarding and chat-template crashes on tool-call assistant messages are different bugs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The single accepted duplicate pair is plausibly the same v5 AutoTokenizer/tokenizer-loading regression, and the other soft-edge rejections are appropriately cautious given only title-level evidence. No pair appears overstated or clearly non-mergeable." + }, + "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": 41, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:22355", + "issue:28218", + "issue:29159", + "issue:30990", + "issue:36296", + "issue:39401", + "issue:41628", + "issue:42757", + "issue:42907", + "issue:43116", + "issue:43122", + "issue:43232", + "issue:43278", + "issue:43408", + "issue:43452", + "issue:43475", + "issue:43784", + "issue:43824", + "issue:43906", + "issue:43937", + "issue:43976", + "issue:44038", + "issue:44188", + "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:44743", + "issue:44779", + "issue:44829", + "issue:44945", + "issue:44964", + "issue:44977", + "issue:45200", + "issue:45216", + "issue:45278", + "issue:45446", + "issue:45478", + "issue:45600" + ], + "soft_pairs": [ + "issue:44188|issue:44373", + "issue:42907|issue:44945", + "issue:41628|issue:45278", + "issue:43232|issue:44743", + "issue:43784|issue:45600", + "issue:43976|issue:44945", + "issue:39401|issue:44488", + "issue:44261|issue:44373", + "issue:43122|issue:44514", + "issue:43408|issue:43475", + "issue:42907|issue:43937", + "issue:39401|issue:44521", + "issue:44625|issue:44829", + "issue:43116|issue:45200", + "issue:42907|issue:44964", + "issue:44360|issue:44485", + "issue:44038|issue:44297", + "issue:28218|issue:30990", + "issue:44038|issue:44295", + "issue:43122|issue:44779", + "issue:42907|issue:43452", + "issue:36296|issue:43116", + "issue:43824|issue:44351", + "issue:44038|issue:44222", + "issue:43122|issue:43906", + "issue:45216|issue:45478", + "issue:42757|issue:44351", + "issue:43784|issue:45446", + "issue:43278|issue:44945", + "issue:22355|issue:29159", + "issue:43122|issue:44977" + ], + "prepared_review_unit_hash": "f58cb17fb0986388ea2df0d280e6b69fb4806c75568c9e675322a80eea4ad18f", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "serialized_chars": 35997, + "estimated_input_tokens": 9000, + "estimated_eval_tokens": 18256 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "No clear duplicate cluster here: the issues span unrelated tokenizer, import, model-loading, generation, and training problems, so no soft-edge pair is strong enough to merge.", + "confidence": 0.93, + "canonical_issue_reason": "No single canonical issue stands out; the set is heterogeneous and the titles point to different bugs rather than one underlying defect.", + "canonical_pr_reason": null, + "best_issue_reason": "45216 is the most concrete regression report, but it is only a representative example\u2014not a duplicate anchor for the rest of the set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44188", + "right": "issue:44373", + "accept": false, + "reason": "Different problems: torch.compile attention-kernel branching vs a docstring typo for position_ids." + }, + { + "left": "issue:42907", + "right": "issue:44945", + "accept": false, + "reason": "Unrelated: saving a dequantized model vs incorrect output under pipeline parallelism." + }, + { + "left": "issue:41628", + "right": "issue:45278", + "accept": false, + "reason": "One is a single AutoImageProcessor import failure; the other is a broad upgrade-related import-breakage report." + }, + { + "left": "issue:43232", + "right": "issue:44743", + "accept": false, + "reason": "Both are generation-related, but they describe different bugs and code paths." + }, + { + "left": "issue:43784", + "right": "issue:45600", + "accept": false, + "reason": "Importing sentence-transformers vs CI break from removed Sam3LiteText config references are not the same bug." + }, + { + "left": "issue:43976", + "right": "issue:44945", + "accept": false, + "reason": "Python-version compatibility regression vs pipeline-parallel output corruption." + }, + { + "left": "issue:39401", + "right": "issue:44488", + "accept": false, + "reason": "Different tokenizer failures: offset_mapping mismatch vs a model load failure." + }, + { + "left": "issue:44261", + "right": "issue:44373", + "accept": false, + "reason": "Numerical precision/config issue in MLA layer vs a docstring issue." + }, + { + "left": "issue:43122", + "right": "issue:44514", + "accept": false, + "reason": "Tokenizer-version regression vs batched chat-template crash; different failure modes." + }, + { + "left": "issue:43408", + "right": "issue:43475", + "accept": false, + "reason": "Same model family, but one is a config/model-type warning and the other is an attribute error." + }, + { + "left": "issue:42907", + "right": "issue:43937", + "accept": false, + "reason": "Saving dequantized models is unrelated to invalid GenerationConfig." + }, + { + "left": "issue:39401", + "right": "issue:44521", + "accept": false, + "reason": "Offset-mapping bug vs assistant_mask generation bug; different tokenizer paths." + }, + { + "left": "issue:44625", + "right": "issue:44829", + "accept": false, + "reason": "num_labels propagation in Qwen3.5 is unrelated to flash_attention_3 training degeneration." + }, + { + "left": "issue:43116", + "right": "issue:45200", + "accept": false, + "reason": "Example-script multi-label output bug vs Gemma 4 multimodal token-type defaults." + }, + { + "left": "issue:42907", + "right": "issue:44964", + "accept": false, + "reason": "Model save/dequantization issue vs a specific multimodal model load failure." + }, + { + "left": "issue:44360", + "right": "issue:44485", + "accept": false, + "reason": "DSA ReLU discussion vs GLM-5 RoPE implementation; no shared underlying defect." + }, + { + "left": "issue:44038", + "right": "issue:44297", + "accept": false, + "reason": "Qwen3-VL-Moe load bug vs tokenizer save metadata mismatch." + }, + { + "left": "issue:28218", + "right": "issue:30990", + "accept": false, + "reason": "Tokenizer spacing bug vs Sentence Transformers loading hang; unrelated." + }, + { + "left": "issue:44038", + "right": "issue:44295", + "accept": false, + "reason": "Model-load issue vs position_ids buffer access error." + }, + { + "left": "issue:43122", + "right": "issue:44779", + "accept": false, + "reason": "Both mention tokenization regressions, but they concern different models and symptoms." + }, + { + "left": "issue:42907", + "right": "issue:43452", + "accept": false, + "reason": "Dequantized save failure vs gguf_file handling for from_pretrained; different code paths." + }, + { + "left": "issue:36296", + "right": "issue:43116", + "accept": false, + "reason": "Tensor-parallel training bug vs example-script classification output bug." + }, + { + "left": "issue:43824", + "right": "issue:44351", + "accept": false, + "reason": "Different missing imports: Qwen2_5_VLForConditionalGeneration vs HybridCache." + }, + { + "left": "issue:44038", + "right": "issue:44222", + "accept": false, + "reason": "Qwen3-VL-Moe model loading issue vs FP8 save_pretrained bug; not the same bug." + }, + { + "left": "issue:43122", + "right": "issue:43906", + "accept": false, + "reason": "Tokenizer regression vs an isolated reproduction of a different issue; no concrete overlap." + }, + { + "left": "issue:45216", + "right": "issue:45478", + "accept": false, + "reason": "Related Qwen3.5 regression theme, but save_pretrained checkpoint corruption and from_pretrained load error are not clearly the same code-path bug." + }, + { + "left": "issue:42757", + "right": "issue:44351", + "accept": false, + "reason": "ImportError from huggingface_hub vs ImportError from transformers; different missing symbols." + }, + { + "left": "issue:43784", + "right": "issue:45446", + "accept": false, + "reason": "Sentence-transformers import NameError vs incorrect PyTorch version gating for AuxRequest." + }, + { + "left": "issue:43278", + "right": "issue:44945", + "accept": false, + "reason": "Dtype drift in evaluation vs incorrect LLM output under pipeline parallelism." + }, + { + "left": "issue:22355", + "right": "issue:29159", + "accept": false, + "reason": "onnx module import failure vs slow/fast tokenizer inconsistency; unrelated." + }, + { + "left": "issue:44261", + "right": "issue:44485", + "accept": false, + "reason": "Layer norm epsilon mismatch vs RoPE implementation discussion; different model components." + } + ] + }, + "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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:22355", + "issue:29127", + "issue:33453", + "issue:38617", + "issue:39401", + "issue:42175", + "issue:42222", + "issue:42371", + "issue:42673", + "issue:43064", + "issue:43066", + "issue:43116", + "issue:43441", + "issue:43450", + "issue:43493", + "issue:43611", + "issue:43673", + "issue:43825", + "issue:43827", + "issue:43874", + "issue:43906", + "issue:43937", + "issue:43976", + "issue:43986", + "issue:43992", + "issue:44038", + "issue:44075", + "issue:44117", + "issue:44291", + "issue:44380", + "issue:44485", + "issue:44704", + "issue:44779", + "issue:44936", + "issue:44938", + "issue:44977", + "issue:45071", + "issue:45072", + "issue:45083", + "issue:45278", + "issue:45357", + "issue:45446", + "issue:45478", + "issue:45563", + "issue:45588", + "issue:45753", + "issue:46002", + "issue:46077" + ], + "soft_pairs": [ + "issue:42175|issue:44938", + "issue:43493|issue:45753", + "issue:42673|issue:45072", + "issue:38617|issue:45278", + "issue:43066|issue:44779", + "issue:43992|issue:44704", + "issue:22355|issue:29127", + "issue:43611|issue:46002", + "issue:43937|issue:44485", + "issue:43976|issue:45446", + "issue:42222|issue:43441", + "issue:43116|issue:43493", + "issue:42371|issue:43874", + "issue:44075|issue:44936", + "issue:43064|issue:43673", + "issue:45357|issue:45478", + "issue:44038|issue:45478", + "issue:43116|issue:43825", + "issue:45083|issue:45446", + "issue:43937|issue:45563", + "issue:44380|issue:46077", + "issue:33453|issue:39401", + "issue:44117|issue:45588", + "issue:43827|issue:45446", + "issue:39401|issue:44779", + "issue:42673|issue:43906", + "issue:44291|issue:45071", + "issue:43937|issue:44977", + "issue:43450|issue:43986" + ], + "prepared_review_unit_hash": "f85ba557decb255e5a12f13ab1f4a3b9ee72857ea3d85c59135be4c6a99a3451", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36035, + "estimated_input_tokens": 9009, + "estimated_eval_tokens": 18274 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a loose semantic bucket of mostly unrelated Transformers v5 regressions, model-specific bugs, and a few packaging/docs/deprecation issues; none of the suggested soft pairs look like true duplicates.", + "confidence": 0.19, + "canonical_issue_reason": "issue:45278 is the best umbrella representative because it captures the broad post-upgrade breakage theme that recurs across several reports, even though the cluster is too heterogeneous for a true canonical duplicate.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 has the widest scope and strongest tie to the recurring v5 import/regression pattern, so it is the most suitable representative issue.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42175", + "right": "issue:44938", + "accept": false, + "reason": "Different failures: missing TensorFlow backend from a torch-only install vs Python 3.14 import/load failure." + }, + { + "left": "issue:43493", + "right": "issue:45753", + "accept": false, + "reason": "Both are Qwen3.5-related, but one is a SigLIP2 implementation discrepancy and the other is an infinite-loop generation bug on a specific image." + }, + { + "left": "issue:42673", + "right": "issue:45072", + "accept": false, + "reason": "VRAM leak in Qwen3ForCausalLM multi-threaded dataloader use is unrelated to dtype mismatches in CI inference." + }, + { + "left": "issue:38617", + "right": "issue:45278", + "accept": false, + "reason": "One is an import failure for a missing symbol; the other is a broad upgrade report about many import errors, not the same underlying bug." + }, + { + "left": "issue:43066", + "right": "issue:44779", + "accept": false, + "reason": "Wrong tokenizer decoder type in v5 is a different tokenizer bug than Deepseek producing incorrect results." + }, + { + "left": "issue:43992", + "right": "issue:44704", + "accept": false, + "reason": "Missing embed_tokens.weight in UMT5Encoder loading is unrelated to AutoProcessor not forwarding kwargs to cached_file." + }, + { + "left": "issue:22355", + "right": "issue:29127", + "accept": false, + "reason": "Module import failure for transformers.onnx and a LayoutLMv3 error-message clarity issue are unrelated." + }, + { + "left": "issue:43611", + "right": "issue:46002", + "accept": false, + "reason": "base_model_prefix loading breakage and NaNs in classification heads after checkout/init are different code paths and symptoms." + }, + { + "left": "issue:43937", + "right": "issue:44485", + "accept": false, + "reason": "Invalid GenerationConfig for GLM-5 is not the same as a RoPE implementation discussion." + }, + { + "left": "issue:43976", + "right": "issue:45446", + "accept": false, + "reason": "Python version compatibility for Transformers v5.1.0 is unrelated to a PyTorch version check bug in flex_attention." + }, + { + "left": "issue:42222", + "right": "issue:43441", + "accept": false, + "reason": "VitPose model breakage and Ministral-3 FlashAttention failure are distinct model-specific regressions." + }, + { + "left": "issue:43116", + "right": "issue:43493", + "accept": false, + "reason": "Empty results in the example classification script is unrelated to a SigLIP2 implementation discrepancy." + }, + { + "left": "issue:42371", + "right": "issue:43874", + "accept": false, + "reason": "TF32 settings warning and a missing image-patch helper in GLM46V are different issues." + }, + { + "left": "issue:44075", + "right": "issue:44936", + "accept": false, + "reason": "Optimizer SGD args ignored is unrelated to trainer.evaluate() failing after train()." + }, + { + "left": "issue:43064", + "right": "issue:43673", + "accept": false, + "reason": "FSDP2/PEFT optimizer-state corruption is a different bug from missing GenerationMixin cache during chunked_prefill." + }, + { + "left": "issue:45357", + "right": "issue:45478", + "accept": false, + "reason": "Both involve Qwen3.5, but one is a save_pretrained key regression and the other is a from_pretrained load error; not the same fix." + }, + { + "left": "issue:44038", + "right": "issue:45478", + "accept": false, + "reason": "Qwen3-VL-Moe and Qwen3.5-Moe are different model families and symptoms, so this is not one underlying bug." + }, + { + "left": "issue:43116", + "right": "issue:43825", + "accept": false, + "reason": "Example-script multi-label behavior and pipeline() translation support/error messaging are unrelated." + }, + { + "left": "issue:45083", + "right": "issue:45446", + "accept": false, + "reason": "A Qwen3_omni_moe helper-length bug is unrelated to the flex_attention import/version check issue." + }, + { + "left": "issue:43937", + "right": "issue:45563", + "accept": false, + "reason": "Invalid GenerationConfig and a stale warning for num_return_sequences are not the same defect." + }, + { + "left": "issue:44380", + "right": "issue:46077", + "accept": false, + "reason": "GPT2 attention scaling under SDPA/FlashAttention is unrelated to Gemma4 building causal masks when bidirectional attention is requested." + }, + { + "left": "issue:33453", + "right": "issue:39401", + "accept": false, + "reason": "Tokenizer loading regression and Qwen3 offset_mapping errors are different tokenizer problems with different failure modes." + }, + { + "left": "issue:44117", + "right": "issue:45588", + "accept": false, + "reason": "TOKENIZER_MAPPING_NAMES returning None and a flash_attention crash on s_aux=None are unrelated." + }, + { + "left": "issue:43827", + "right": "issue:45446", + "accept": false, + "reason": "Docs still referencing pipeline() after v5 removals is unrelated to an AuxRequest import version check bug." + }, + { + "left": "issue:39401", + "right": "issue:44779", + "accept": false, + "reason": "Wrong Qwen3 offset_mapping and incorrect Deepseek tokenizer results are separate tokenizer regressions." + }, + { + "left": "issue:42673", + "right": "issue:43906", + "accept": false, + "reason": "A VRAM leak in multi-threaded Qwen3ForCausalLM use is not the same as an isolated reproduction of another issue." + }, + { + "left": "issue:44291", + "right": "issue:45071", + "accept": false, + "reason": "Unexpected _is_hf_initialized argument during init_empty_weights is unrelated to PretrainedConfig type-checking breakage." + }, + { + "left": "issue:43937", + "right": "issue:44977", + "accept": false, + "reason": "GLM-5 GenerationConfig invalidity and Qwen3.5 flash-attention generation problems are different model/runtime failures." + }, + { + "left": "issue:43450", + "right": "issue:43986", + "accept": false, + "reason": "Video processor batch-shape bug and missing-torchvision AutoProcessor crash are related to video processing but not the same code-path problem." + } + ] + }, + "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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "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:43097", + "issue:43122", + "issue:43408", + "issue:43421", + "issue:43577", + "issue:43582", + "issue:43673", + "issue:43742", + "issue:43937", + "issue:44075", + "issue:44117", + "issue:44220", + "issue:44261", + "issue:44410", + "issue:44466", + "issue:44483", + "issue:44484", + "issue:44493", + "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", + "issue:46002", + "issue:46178" + ], + "soft_pairs": [ + "issue:44466|issue:46002", + "issue:45405|issue:45446", + "issue:44117|issue:45081", + "issue:45341|issue:45561", + "issue:42222|issue:46178", + "issue:38617|issue:41628", + "issue:44410|issue:45310", + "issue:44829|issue:45216", + "issue:39401|issue:43421", + "issue:42617|issue:45341", + "issue:44484|issue:45310", + "issue:42673|issue:43582", + "issue:42490|issue:42673", + "issue:43408|issue:43742", + "issue:42371|issue:44261", + "issue:44933|issue:45278", + "issue:38617|issue:44220", + "issue:42222|issue:45542", + "issue:43937|issue:44496", + "issue:44483|issue:45464", + "issue:43066|issue:43122", + "issue:42175|issue:42222", + "issue:42371|issue:42831", + "issue:44075|issue:45656", + "issue:44410|issue:45478", + "issue:43673|issue:45341", + "issue:43012|issue:43577", + "issue:44484|issue:45478", + "issue:43097|issue:44493", + "issue:41628|issue:45071" + ], + "prepared_review_unit_hash": "8d3f62a26dbbbd1800fb448b123f42a482ab4b82b8109daa179b0053f966a952", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36435, + "estimated_input_tokens": 9109, + "estimated_eval_tokens": 18474 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is highly heterogeneous: most items are unrelated bug reports, with only a small import-regression subgroup. None of the soft pairs look like the same concrete bug/change, and there are no PRs in the set.", + "confidence": 0.79, + "canonical_issue_reason": "issue:45278 is the broadest umbrella report about import failures after upgrading, so it is the best anchor for the small import-regression subgroup.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the most representative issue in this mixed set; it is broader than the other import-related reports and closer to a possible cluster summary.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44466", + "right": "issue:46002", + "accept": false, + "reason": "Both mention model weights/training behavior, but one is a serialization/tied-weights issue and the other is NaNs in classification heads; different bugs." + }, + { + "left": "issue:45405", + "right": "issue:45446", + "accept": false, + "reason": "Unrelated topics: PEFT version pinning vs a PyTorch version-check bug in flex_attention." + }, + { + "left": "issue:44117", + "right": "issue:45081", + "accept": false, + "reason": "Both are tokenizer-related, but one is a mapping lookup bug and the other is a Mistral regex crash; different code paths." + }, + { + "left": "issue:45341", + "right": "issue:45561", + "accept": false, + "reason": "The second is a pytest-xdist race in captured_info.txt; the first is only a vague testing_utils bug and is not clearly the same issue." + }, + { + "left": "issue:42222", + "right": "issue:46178", + "accept": false, + "reason": "VitPose model breakage and a tensorflow_text backend lookup error are different failures." + }, + { + "left": "issue:38617", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but for different missing symbols and likely different fixes." + }, + { + "left": "issue:44410", + "right": "issue:45310", + "accept": false, + "reason": "Different model families and symptoms: missing Qwen3Next projections vs Qwen3.5-MoE from_pretrained failure." + }, + { + "left": "issue:44829", + "right": "issue:45216", + "accept": false, + "reason": "One is an FA3 training-degeneration issue; the other is a save_pretrained regression for Qwen3.5 checkpoints." + }, + { + "left": "issue:39401", + "right": "issue:43421", + "accept": false, + "reason": "Both involve tokenizers, but offset_mapping errors and runtime post-processor updates are distinct bugs." + }, + { + "left": "issue:42617", + "right": "issue:45341", + "accept": false, + "reason": "A 3d_parallel.py runtime problem is unrelated to a small testing_utils bug." + }, + { + "left": "issue:44484", + "right": "issue:45310", + "accept": false, + "reason": "max_shard_size behavior in save_pretrained is unrelated to a Qwen3.5-MoE from_pretrained error." + }, + { + "left": "issue:42673", + "right": "issue:43582", + "accept": false, + "reason": "A VRAM leak in multi-threaded dataloading and an Apple Silicon TypeError are different issues." + }, + { + "left": "issue:42490", + "right": "issue:42673", + "accept": false, + "reason": "Import warning on local model paths and a Qwen3ForCausalLM VRAM leak are unrelated." + }, + { + "left": "issue:43408", + "right": "issue:43742", + "accept": false, + "reason": "Model-type warning for sam3 variants is not the same as a key error loading facebook/MobileLLM-125M." + }, + { + "left": "issue:42371", + "right": "issue:44261", + "accept": false, + "reason": "TF32 configuration guidance and an MLA rms_norm_eps precision bug are unrelated." + }, + { + "left": "issue:44933", + "right": "issue:45278", + "accept": false, + "reason": "A missing image_utils import may be related to import regressions, but it is not the same concrete bug as the broad upgrade-related report." + }, + { + "left": "issue:38617", + "right": "issue:44220", + "accept": false, + "reason": "A missing configuration import and an fbank feature-extraction issue are different code paths." + }, + { + "left": "issue:42222", + "right": "issue:45542", + "accept": false, + "reason": "VitPose model breakage is unrelated to a missing TensorFlow backend when only tensorboard is installed." + }, + { + "left": "issue:43937", + "right": "issue:44496", + "accept": false, + "reason": "GenerationConfig validation for GLM-5 and unrecognized-model loading for Olmo-Hybrid are distinct failures." + }, + { + "left": "issue:44483", + "right": "issue:45464", + "accept": false, + "reason": "Both mention chat/completions failures, but one is a generic request rejection and the other is a streaming inference symptom on a specific model; not clearly the same bug." + }, + { + "left": "issue:43066", + "right": "issue:43122", + "accept": false, + "reason": "Tokenizer decoder-type mismatch and version-to-version tokenization differences are related only at a high level, not the same concrete issue." + }, + { + "left": "issue:42175", + "right": "issue:42222", + "accept": false, + "reason": "Missing TensorFlow in a torch-only install and broken VitPose models are unrelated." + }, + { + "left": "issue:42371", + "right": "issue:42831", + "accept": false, + "reason": "TF32 behavior controls and FineGrainedFP8 accuracy problems are different topics." + }, + { + "left": "issue:44075", + "right": "issue:45656", + "accept": false, + "reason": "SGD arguments not being used and an optimizer step firing twice under deepspeed are separate optimizer bugs." + }, + { + "left": "issue:44410", + "right": "issue:45478", + "accept": false, + "reason": "Missing Qwen3Next projections and Qwen3.5-MoE from_pretrained failures do not look like the same defect." + }, + { + "left": "issue:43673", + "right": "issue:45341", + "accept": false, + "reason": "Generation cache behavior during chunked_prefill is unrelated to a testing_utils bug." + }, + { + "left": "issue:43012", + "right": "issue:43577", + "accept": false, + "reason": "A bfloat16 precision warning and Blip2 dtype remaining float32 are different dtype-related symptoms." + }, + { + "left": "issue:44484", + "right": "issue:45478", + "accept": false, + "reason": "save_pretrained shard sizing and Qwen3.5-MoE loading failures are unrelated." + }, + { + "left": "issue:43097", + "right": "issue:44493", + "accept": false, + "reason": "A removed config attribute and unexpected position-id keys are different regression surfaces." + }, + { + "left": "issue:41628", + "right": "issue:45071", + "accept": false, + "reason": "An AutoImageProcessor import error and a PreTrainedConfig type-checking regression 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": 44, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:38617", + "issue:42757", + "issue:43012", + "issue:43064", + "issue:43066", + "issue:43097", + "issue:43335", + "issue:43408", + "issue:43441", + "issue:43452", + "issue:43502", + "issue:43531", + "issue:43673", + "issue:43824", + "issue:43873", + "issue:43874", + "issue:43906", + "issue:43931", + "issue:43986", + "issue:43992", + "issue:44038", + "issue:44062", + "issue:44117", + "issue:44261", + "issue:44263", + "issue:44315", + "issue:44351", + "issue:44360", + "issue:44368", + "issue:44410", + "issue:44484", + "issue:44485", + "issue:44704", + "issue:44829", + "issue:44987", + "issue:45003", + "issue:45071", + "issue:45103", + "issue:45341", + "issue:45372", + "issue:45375", + "issue:45440", + "issue:45542", + "issue:45588", + "issue:46050", + "issue:46123", + "issue:46172" + ], + "soft_pairs": [ + "issue:43874|issue:44261", + "issue:44263|issue:44485", + "issue:45071|issue:45542", + "issue:44360|issue:46172", + "issue:44263|issue:46172", + "issue:43012|issue:43408", + "issue:43441|issue:44829", + "issue:43931|issue:44410", + "issue:43931|issue:44038", + "issue:43335|issue:45071", + "issue:43673|issue:46123", + "issue:43097|issue:43452", + "issue:45003|issue:45341", + "issue:43986|issue:45341", + "issue:44117|issue:44987", + "issue:43408|issue:44368", + "issue:43986|issue:44484", + "issue:43874|issue:44263", + "issue:45440|issue:46172", + "issue:43986|issue:45372", + "issue:43531|issue:45341", + "issue:38617|issue:42757", + "issue:44261|issue:44485", + "issue:43064|issue:44315", + "issue:43097|issue:46050", + "issue:43097|issue:45588", + "issue:44062|issue:44117", + "issue:44410|issue:45375", + "issue:38617|issue:44351", + "issue:44038|issue:44410", + "issue:43502|issue:43992", + "issue:43097|issue:43873", + "issue:44704|issue:45103", + "issue:43986|issue:44117", + "issue:43824|issue:43986", + "issue:43066|issue:43906" + ], + "prepared_review_unit_hash": "8856ca51782a93d16b788a20366e7fd4a77e4eaad7781c66ba11d500ed3d64db", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 36, + "serialized_chars": 37926, + "estimated_input_tokens": 9482, + "estimated_eval_tokens": 19220 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items do not form a real duplicate cluster; they cover many unrelated Transformers bugs and regressions. I found no PRs to compare, and I would not merge any of the soft pairs based on the available evidence.", + "confidence": 0.97, + "canonical_issue_reason": "No single canonical issue exists here: the set spans unrelated problems across imports, model loading, quantization, configuration, tokenizers, and generation.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43502 is the strongest standalone bug report: it is a clear, reproducible user-facing loading-path regression with broad impact.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43874", + "right": "issue:44261", + "accept": false, + "reason": "Different bugs: missing image-processor method vs MLA layernorm config precision handling." + }, + { + "left": "issue:44263", + "right": "issue:44485", + "accept": false, + "reason": "Different code paths: GlmMoeDsaIndexer split behavior vs GLM-5 RoPE implementation." + }, + { + "left": "issue:45071", + "right": "issue:45542", + "accept": false, + "reason": "Unrelated: PretrainedConfig type-checking regression vs backend detection when only tensorboard is installed." + }, + { + "left": "issue:44360", + "right": "issue:46172", + "accept": false, + "reason": "Different DeepSeek/GLM internals: DSA ReLU discussion vs deepseek-v4 transpose issue." + }, + { + "left": "issue:44263", + "right": "issue:46172", + "accept": false, + "reason": "Different bugs in different model internals; no shared failing code path." + }, + { + "left": "issue:43012", + "right": "issue:43408", + "accept": false, + "reason": "Different symptoms and subsystems: bfloat16 compile warning vs model-type mismatch warning." + }, + { + "left": "issue:43441", + "right": "issue:44829", + "accept": false, + "reason": "Both mention FlashAttention, but they are different failures on different models and code paths." + }, + { + "left": "issue:43931", + "right": "issue:44410", + "accept": false, + "reason": "Different model-loading problems: weight shape mismatch vs missing projections in a different architecture." + }, + { + "left": "issue:43931", + "right": "issue:44038", + "accept": false, + "reason": "Different Qwen/VL issues with different failure modes; not the same bug." + }, + { + "left": "issue:43335", + "right": "issue:45071", + "accept": false, + "reason": "Unrelated: SwitchTransformers sparse-layer construction vs PretrainedConfig type-checking." + }, + { + "left": "issue:43673", + "right": "issue:46123", + "accept": false, + "reason": "Different generation bugs: missing cache during chunked prefill vs final partial batch handling." + }, + { + "left": "issue:43097", + "right": "issue:43452", + "accept": false, + "reason": "Different problems: removed tie_embeddings behavior vs gguf_file breaking model/tokenizer loading." + }, + { + "left": "issue:45003", + "right": "issue:45341", + "accept": false, + "reason": "Different areas: unsafe sys.modules access vs a testing_utils bug." + }, + { + "left": "issue:43986", + "right": "issue:45341", + "accept": false, + "reason": "Different issues: missing torchvision handling in AutoProcessor vs testing_utils." + }, + { + "left": "issue:44117", + "right": "issue:44987", + "accept": false, + "reason": "Different failures: tokenizer mapping assumptions vs a specific model-loading regression in 5.1.0." + }, + { + "left": "issue:43408", + "right": "issue:44368", + "accept": false, + "reason": "Both are warnings, but they concern different warnings and different configuration fields." + }, + { + "left": "issue:43986", + "right": "issue:44484", + "accept": false, + "reason": "Unrelated: video-model loading without torchvision vs max_shard_size question." + }, + { + "left": "issue:43874", + "right": "issue:44263", + "accept": false, + "reason": "Different GLM bugs: missing image-processor method vs torch.split return handling." + }, + { + "left": "issue:45440", + "right": "issue:46172", + "accept": false, + "reason": "Different DeepSeek model discrepancies; not the same concrete defect." + }, + { + "left": "issue:43986", + "right": "issue:45372", + "accept": false, + "reason": "Different import/loading failures affecting different dependencies and model paths." + }, + { + "left": "issue:43531", + "right": "issue:45341", + "accept": false, + "reason": "Different areas: Qwen3-MoE sliding_window behavior vs testing_utils." + }, + { + "left": "issue:38617", + "right": "issue:42757", + "accept": false, + "reason": "Both are ImportErrors, but for different missing symbols from different modules." + }, + { + "left": "issue:44261", + "right": "issue:44485", + "accept": false, + "reason": "Different model internals and unrelated fixes: rms_norm_eps precision issue vs GLM-5 RoPE implementation." + }, + { + "left": "issue:43064", + "right": "issue:44315", + "accept": false, + "reason": "Different training issues: FSDP2/PEFT optimizer-state bug vs Liger Kernel not applied with model_init." + }, + { + "left": "issue:43097", + "right": "issue:46050", + "accept": false, + "reason": "Different failures: removed embedding-tie config warning vs sinq quantization save/load breakage." + }, + { + "left": "issue:43097", + "right": "issue:45588", + "accept": false, + "reason": "Different subsystems: tie_embeddings deprecation/removal vs flash_attention sinkless-model crash." + }, + { + "left": "issue:44062", + "right": "issue:44117", + "accept": false, + "reason": "Tokenizer construction error vs tokenizer mapping None; not the same bug." + }, + { + "left": "issue:44410", + "right": "issue:45375", + "accept": false, + "reason": "Different Qwen-family configuration bugs with different missing fields/projections." + }, + { + "left": "issue:38617", + "right": "issue:44351", + "accept": false, + "reason": "Different missing imports from different modules and different upstream API breakages." + }, + { + "left": "issue:44038", + "right": "issue:44410", + "accept": false, + "reason": "Different Qwen model families and different failure modes; not mergeable as one fix." + }, + { + "left": "issue:43502", + "right": "issue:43992", + "accept": false, + "reason": "Different loading regressions: local_files_only network requests vs missing embed_tokens.weight for UMT5." + }, + { + "left": "issue:43097", + "right": "issue:43873", + "accept": false, + "reason": "Different issues: tie_embeddings removal vs quantization/offloading behavior." + }, + { + "left": "issue:44704", + "right": "issue:45103", + "accept": false, + "reason": "Different code paths: AutoProcessor kwargs forwarding vs auto_docstring annotation processing." + }, + { + "left": "issue:43986", + "right": "issue:44117", + "accept": false, + "reason": "Different failures in processor loading vs tokenizer mapping resolution." + }, + { + "left": "issue:43824", + "right": "issue:43986", + "accept": false, + "reason": "Different problems: missing Qwen2.5-VL export vs AutoProcessor crashing without torchvision." + }, + { + "left": "issue:43066", + "right": "issue:43906", + "accept": false, + "reason": "Insufficient evidence of the same bug; one is a tokenizer-decoder mismatch, the other is only a reproduction of another 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": 45, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:36683", + "issue:38617", + "issue:42490", + "issue:42757", + "issue:42907", + "issue:43012", + "issue:43064", + "issue:43208", + "issue:43299", + "issue:43352", + "issue:43475", + "issue:43502", + "issue:43526", + "issue:43550", + "issue:43582", + "issue:43618", + "issue:43756", + "issue:43761", + "issue:43792", + "issue:43824", + "issue:43825", + "issue:43867", + "issue:43976", + "issue:43992", + "issue:44038", + "issue:44162", + "issue:44222", + "issue:44230", + "issue:44368", + "issue:44380", + "issue:44483", + "issue:44484", + "issue:44485", + "issue:44514", + "issue:44655", + "issue:44683", + "issue:44938", + "issue:45276", + "issue:45290", + "issue:45478", + "issue:45479", + "issue:45698", + "issue:45753", + "issue:46077", + "issue:46123", + "issue:46132", + "issue:46172", + "issue:46178" + ], + "soft_pairs": [ + "issue:44938|issue:46178", + "issue:43208|issue:43550", + "issue:43992|issue:44484", + "issue:43012|issue:43550", + "issue:43825|issue:44655", + "issue:43012|issue:44368", + "issue:42907|issue:44655", + "issue:42907|issue:45753", + "issue:43352|issue:44380", + "issue:44162|issue:46172", + "issue:43352|issue:43976", + "issue:44380|issue:46132", + "issue:44380|issue:45479", + "issue:43792|issue:46123", + "issue:43064|issue:44380", + "issue:44483|issue:44514", + "issue:44222|issue:45478", + "issue:36683|issue:43582", + "issue:43208|issue:43526", + "issue:43012|issue:44683", + "issue:42757|issue:43824", + "issue:43618|issue:43761", + "issue:42490|issue:43012", + "issue:45698|issue:46172", + "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:36683|issue:43475", + "issue:45276|issue:46077" + ], + "prepared_review_unit_hash": "8295e67fced754fd2c585756d9070e3809e35a4ca0076292b8be1cc2bcf847e3", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37020, + "estimated_input_tokens": 9255, + "estimated_eval_tokens": 18766 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is not a duplicate set: it mixes unrelated import errors, model-specific regressions, attention/backends bugs, save/load issues, and API/pipeline behavior changes. The soft edges are mostly superficial keyword similarity rather than the same underlying bug.", + "confidence": 0.94, + "canonical_issue_reason": "No single canonical issue fits this cluster; the items are too heterogeneous, and the proposed soft matches are only broad topic overlaps.", + "canonical_pr_reason": null, + "best_issue_reason": "No issue is a strong global representative for deduping because none covers the others' concrete failure modes.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44938", + "right": "issue:46178", + "accept": false, + "reason": "Different failure classes: Python 3.14 import/load breakage vs an invalid backend mapping for tensorflow_text." + }, + { + "left": "issue:43208", + "right": "issue:43550", + "accept": false, + "reason": "Different models and different bugs: xLSTM training blockers vs Bamba torch.compile/SDPA failure." + }, + { + "left": "issue:43992", + "right": "issue:44484", + "accept": false, + "reason": "Load-state missing weight vs save_pretrained shard-size behavior; not the same underlying issue." + }, + { + "left": "issue:43012", + "right": "issue:43550", + "accept": false, + "reason": "A PyTorch warning on bfloat16 compilation is not the same as a hard compile/SDPA failure." + }, + { + "left": "issue:43825", + "right": "issue:44655", + "accept": false, + "reason": "Pipeline error-message regression vs inability to save pipeline objects are different code paths." + }, + { + "left": "issue:43012", + "right": "issue:44368", + "accept": false, + "reason": "Both are warnings, but they stem from unrelated causes and model/config paths." + }, + { + "left": "issue:42907", + "right": "issue:44655", + "accept": false, + "reason": "Saving dequantized model variants is distinct from saving Pipeline objects." + }, + { + "left": "issue:42907", + "right": "issue:45753", + "accept": false, + "reason": "Dequantized save failure and an image-specific infinite loop are unrelated bugs." + }, + { + "left": "issue:43352", + "right": "issue:44380", + "accept": false, + "reason": "Different attention issues on different models; one is backend support, the other ignores a scaling config." + }, + { + "left": "issue:44162", + "right": "issue:46172", + "accept": false, + "reason": "Completely different model-specific regressions." + }, + { + "left": "issue:43352", + "right": "issue:43976", + "accept": false, + "reason": "Model/backend support bug is unrelated to a Python-version compatibility problem." + }, + { + "left": "issue:44380", + "right": "issue:46132", + "accept": false, + "reason": "Attention scaling ignored and register-changing behavior are distinct attention subsystem bugs." + }, + { + "left": "issue:44380", + "right": "issue:45479", + "accept": false, + "reason": "Attention scaling regression is unrelated to the zero-loss classification bug." + }, + { + "left": "issue:43792", + "right": "issue:46123", + "accept": false, + "reason": "Whisper model runtime failure and MaskGenerationPipeline batching logic are unrelated." + }, + { + "left": "issue:43064", + "right": "issue:44380", + "accept": false, + "reason": "Trainer/FSDP/PEFT optimizer-state corruption is not the same as an attention backend config bug." + }, + { + "left": "issue:44483", + "right": "issue:44514", + "accept": false, + "reason": "Both involve chat-style APIs, but one is a server endpoint acceptance issue and the other is a processor/template crash." + }, + { + "left": "issue:44222", + "right": "issue:45478", + "accept": false, + "reason": "Saving FP8 MoE models and loading Qwen3.5 MoE under v5.4 are different save/load paths." + }, + { + "left": "issue:36683", + "right": "issue:43582", + "accept": false, + "reason": "Gemma3 config attribute error and AppleSilicon allocator TypeError are unrelated." + }, + { + "left": "issue:43208", + "right": "issue:43526", + "accept": false, + "reason": "xLSTM training bugs and BeitImageProcessorFast label reduction bug are unrelated." + }, + { + "left": "issue:43012", + "right": "issue:44683", + "accept": false, + "reason": "A warning during compilation is not the same as a compiled flex_attention failure on newer torch." + }, + { + "left": "issue:42757", + "right": "issue:43824", + "accept": false, + "reason": "Both are import errors, but they concern different symbols and different root causes." + }, + { + "left": "issue:43618", + "right": "issue:43761", + "accept": false, + "reason": "Both are CLIP regressions, but they affect different outputs and code paths; not the same bug." + }, + { + "left": "issue:42490", + "right": "issue:43012", + "accept": false, + "reason": "Local-path slash warning is unrelated to a bfloat16 compilation warning." + }, + { + "left": "issue:45698", + "right": "issue:46172", + "accept": false, + "reason": "Custom-module deserialization after save_pretrained is unrelated to a DeepSeek tensor transpose/dtype bug." + }, + { + "left": "issue:43618", + "right": "issue:44380", + "accept": false, + "reason": "CLIP attentions regression and GPT2 attention scaling regression are different issues." + }, + { + "left": "issue:38617", + "right": "issue:43502", + "accept": false, + "reason": "Importing a removed utility and local_files_only still triggering network calls are unrelated." + }, + { + "left": "issue:44038", + "right": "issue:44230", + "accept": false, + "reason": "Same broad Qwen/MoE family, but one is a loading regression and the other is FP8 inference support." + }, + { + "left": "issue:44483", + "right": "issue:45290", + "accept": false, + "reason": "Both are chat/template-related, but they hit different APIs and failure modes." + }, + { + "left": "issue:43756", + "right": "issue:44485", + "accept": false, + "reason": "Both mention RoPE, but they describe different model implementations and different bugs." + }, + { + "left": "issue:43299", + "right": "issue:43867", + "accept": false, + "reason": "Qwen3-VL-Moe load regression and sorted-state_dict load error are not the same underlying defect." + }, + { + "left": "issue:45276", + "right": "issue:46077", + "accept": false, + "reason": "Gemma4 embedding resize behavior and Gemma4 bidirectional-attention mask construction are separate 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": 46, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:36010", + "issue:36683", + "issue:41669", + "issue:42490", + "issue:42757", + "issue:42890", + "issue:42898", + "issue:42994", + "issue:43010", + "issue:43064", + "issue:43066", + "issue:43299", + "issue:43352", + "issue:43525", + "issue:43611", + "issue:43618", + "issue:43867", + "issue:43901", + "issue:43931", + "issue:43937", + "issue:43976", + "issue:43992", + "issue:44075", + "issue:44077", + "issue:44242", + "issue:44246", + "issue:44355", + "issue:44380", + "issue:44492", + "issue:44625", + "issue:44655", + "issue:44855", + "issue:44938", + "issue:45071", + "issue:45216", + "issue:45278", + "issue:45310", + "issue:45357", + "issue:45375", + "issue:45478", + "issue:45561", + "issue:45593", + "issue:45753", + "issue:45850", + "issue:46077", + "issue:46082", + "issue:46202" + ], + "soft_pairs": [ + "issue:42994|issue:44655", + "issue:43901|issue:44655", + "issue:42898|issue:43066", + "issue:43299|issue:45753", + "issue:36010|issue:42757", + "issue:44077|issue:44380", + "issue:36683|issue:44077", + "issue:43611|issue:44655", + "issue:43352|issue:43937", + "issue:43867|issue:45216", + "issue:44625|issue:46077", + "issue:43976|issue:44938", + "issue:46077|issue:46082", + "issue:43352|issue:45593", + "issue:36683|issue:43525", + "issue:43618|issue:45216", + "issue:36683|issue:44242", + "issue:43352|issue:43931", + "issue:43064|issue:44492", + "issue:43010|issue:45278", + "issue:43992|issue:45310", + "issue:43867|issue:46202", + "issue:44355|issue:44855", + "issue:43867|issue:45375", + "issue:41669|issue:44246", + "issue:36683|issue:43064", + "issue:44938|issue:45071", + "issue:42890|issue:45561", + "issue:43010|issue:45850", + "issue:43867|issue:45357", + "issue:42490|issue:44075", + "issue:43010|issue:43976", + "issue:43618|issue:44077", + "issue:43992|issue:45478" + ], + "prepared_review_unit_hash": "17ba71d62e04ccdf19cbe2eeb7179dbefef7cd6be0a73b1093b14a2dc9a314f0", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 34, + "serialized_chars": 36810, + "estimated_input_tokens": 9203, + "estimated_eval_tokens": 18662 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These are mostly unrelated Transformers regression reports that only share broad surface themes like imports, saving/loading, or config changes. No soft pair looks like the same underlying bug/change, so I would not merge any of them as duplicates.", + "confidence": 0.93, + "canonical_issue_reason": "issue:45278 is the broadest umbrella symptom in the set (\u201cmany import errors after update\u201d), so it is the most representative issue, though the cluster is heterogeneous and not a true duplicate set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the best single representative of the cluster because it captures the broad v5 import-regression theme better than the more model-specific reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42994", + "right": "issue:44655", + "accept": false, + "reason": "Both mention save_pretrained, but one is quantized model saving and the other is saving Pipeline objects; different code paths." + }, + { + "left": "issue:43901", + "right": "issue:44655", + "accept": false, + "reason": "Docs/runtime mismatch about return_all_scores vs pipeline save_pretrained failure; not the same bug." + }, + { + "left": "issue:42898", + "right": "issue:43066", + "accept": false, + "reason": "Both are tokenizer/config behavior changes, but they concern different settings and symptoms." + }, + { + "left": "issue:43299", + "right": "issue:45753", + "accept": false, + "reason": "Different model families and failures: load-time MoE breakage vs an infinite loop on a specific image." + }, + { + "left": "issue:36010", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but for different symbols from different packages and different root causes." + }, + { + "left": "issue:44077", + "right": "issue:44380", + "accept": false, + "reason": "PatchTSMixer optional post_init vs GPT2 attention scaling under SDPA/FlashAttention are unrelated bugs." + }, + { + "left": "issue:36683", + "right": "issue:44077", + "accept": false, + "reason": "Gemma3 config missing vocab_size is unrelated to PatchTSMixer post_init handling." + }, + { + "left": "issue:43611", + "right": "issue:44655", + "accept": false, + "reason": "base_model_prefix loading regression and pipeline save_pretrained are different code paths." + }, + { + "left": "issue:43352", + "right": "issue:43937", + "accept": false, + "reason": "Nemotron FlashAttention support and invalid GenerationConfig for GLM-5 are unrelated issues." + }, + { + "left": "issue:43867", + "right": "issue:45216", + "accept": false, + "reason": "Both are Qwen3.5-related, but one is state_dict ordering/load failure and the other is incorrect saved checkpoint content." + }, + { + "left": "issue:44625", + "right": "issue:46077", + "accept": false, + "reason": "num_labels propagation and Gemma4 bidirectional attention masks are different config bugs." + }, + { + "left": "issue:43976", + "right": "issue:44938", + "accept": false, + "reason": "Both are Python-version breakages, but they involve different versions and different causes." + }, + { + "left": "issue:46077", + "right": "issue:46082", + "accept": false, + "reason": "Both are config issues, but one is attention masking and the other is head_dim validation; not the same fix." + }, + { + "left": "issue:43352", + "right": "issue:45593", + "accept": false, + "reason": "Nemotron FlashAttention support and D-FINE auxiliary-loss behavior are unrelated." + }, + { + "left": "issue:36683", + "right": "issue:43525", + "accept": false, + "reason": "Gemma3 missing vocab_size vs Llama4 missing pad_token_id are different model-specific config gaps." + }, + { + "left": "issue:43618", + "right": "issue:45216", + "accept": false, + "reason": "CLIPOutput attentions regression is unrelated to Qwen3.5 save_pretrained checkpoint corruption." + }, + { + "left": "issue:36683", + "right": "issue:44242", + "accept": false, + "reason": "Gemma3 vocab_size and load balancing loss omission are unrelated bugs." + }, + { + "left": "issue:43352", + "right": "issue:43931", + "accept": false, + "reason": "FlashAttention support for Nemotron and Qwen3-VL weight-shape mismatch are different failures." + }, + { + "left": "issue:43064", + "right": "issue:44492", + "accept": false, + "reason": "FSDP2/PEFT optimizer-state corruption is unrelated to a typo in cache strategy names." + }, + { + "left": "issue:43010", + "right": "issue:45278", + "accept": false, + "reason": "Both are broad v5 regressions, but one is cache update decoration and the other is import errors; not the same concrete bug." + }, + { + "left": "issue:43992", + "right": "issue:45310", + "accept": false, + "reason": "UMT5Encoder missing embed_tokens.weight and Qwen3.5 MoE from_pretrained failure are different model/load bugs." + }, + { + "left": "issue:43867", + "right": "issue:46202", + "accept": false, + "reason": "State_dict-sorted load failure and Gemma pipeline roundtrip failure are unrelated." + }, + { + "left": "issue:44355", + "right": "issue:44855", + "accept": false, + "reason": "Compiled-file import errors and Python 3.13 @torch.jit.script parsing/IndentationError have different causes." + }, + { + "left": "issue:43867", + "right": "issue:45375", + "accept": false, + "reason": "Qwen3.5 state_dict loading and missing deepstack_visual_indexes are different config/save issues." + }, + { + "left": "issue:41669", + "right": "issue:44246", + "accept": false, + "reason": "Import-time slowdown from removing star imports and a general 'import transformers takes long' report are not the same underlying bug." + }, + { + "left": "issue:36683", + "right": "issue:43064", + "accept": false, + "reason": "Gemma3 config field absence and Trainer optimizer-state corruption are unrelated." + }, + { + "left": "issue:44938", + "right": "issue:45071", + "accept": false, + "reason": "Python 3.14 load failure and PretrainedConfig type-checking regression are different breakages." + }, + { + "left": "issue:42890", + "right": "issue:45561", + "accept": false, + "reason": "Flaky integration tests from missing set_seed and xdist file races are different testing problems." + }, + { + "left": "issue:43010", + "right": "issue:45850", + "accept": false, + "reason": "A specific no_grad decoration request is not the same as a broad complaint that 'too many models' break." + }, + { + "left": "issue:43867", + "right": "issue:45357", + "accept": false, + "reason": "Qwen3.5 checkpoint load/save failure and incorrect visual encoder keys on save_pretrained are related only by model family, not by bug." + }, + { + "left": "issue:42490", + "right": "issue:44075", + "accept": false, + "reason": "Trailing-slash local model import warning and unused SGD args are unrelated." + }, + { + "left": "issue:43010", + "right": "issue:43976", + "accept": false, + "reason": "Cache update no_grad and Python 3.9/3.10 compatibility are unrelated." + }, + { + "left": "issue:43618", + "right": "issue:44077", + "accept": false, + "reason": "CLIP attentions assignment regression and PatchTSMixer post_init handling are unrelated." + }, + { + "left": "issue:43992", + "right": "issue:45478", + "accept": false, + "reason": "UMT5Encoder missing embeddings and Qwen3.5 MoE from_pretrained failures are different model-specific 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": 47, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:28282", + "issue:30333", + "issue:30990", + "issue:31795", + "issue:33453", + "issue:34689", + "issue:36296", + "issue:42548", + "issue:42757", + "issue:42831", + "issue:42890", + "issue:43010", + "issue:43065", + "issue:43232", + "issue:43299", + "issue:43502", + "issue:43575", + "issue:43576", + "issue:43618", + "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:44556", + "issue:44655", + "issue:44749", + "issue:44857", + "issue:44961", + "issue:44964", + "issue:44977", + "issue:45071", + "issue:45125", + "issue:45341", + "issue:45375", + "issue:45440", + "issue:45478", + "issue:45600", + "issue:46132" + ], + "soft_pairs": [ + "issue:36296|issue:43575", + "issue:28282|issue:33453", + "issue:43618|issue:44857", + "issue:44360|issue:45440", + "issue:43618|issue:44977", + "issue:42890|issue:44964", + "issue:43502|issue:44062", + "issue:42890|issue:44112", + "issue:42890|issue:45600", + "issue:43576|issue:46132", + "issue:43723|issue:44556", + "issue:44387|issue:44556", + "issue:42890|issue:45341", + "issue:44222|issue:45125", + "issue:43010|issue:43065", + "issue:42548|issue:44351", + "issue:44355|issue:44749", + "issue:43502|issue:44485", + "issue:45125|issue:45478", + "issue:30333|issue:33453", + "issue:43010|issue:43232", + "issue:45125|issue:45375", + "issue:30990|issue:31795", + "issue:43502|issue:44222", + "issue:43299|issue:44556", + "issue:42831|issue:43874", + "issue:43502|issue:44961", + "issue:44315|issue:44360", + "issue:43827|issue:44961", + "issue:44355|issue:45071", + "issue:30333|issue:36296", + "issue:44355|issue:44655", + "issue:33453|issue:34689", + "issue:42757|issue:43576", + "issue:44222|issue:44230", + "issue:43576|issue:45071", + "issue:33453|issue:36296", + "issue:43576|issue:43824" + ], + "prepared_review_unit_hash": "99993f86265dd9860150b26618c7ab2ba71d939eebe48c19d04bb38ac3fdfcc0", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 38, + "serialized_chars": 38489, + "estimated_input_tokens": 9623, + "estimated_eval_tokens": 19502 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items are mostly unrelated issues across imports, loading, tests, docs, FP8, and tensor-parallel behavior. The Qwen3.5 MoE reports (issue:45125 and issue:45478) look plausibly related at a high level, but the evidence here is not strong enough to treat them as the same bug or as one mergeable fix.", + "confidence": 0.78, + "canonical_issue_reason": "issue:45125 is the best anchor because it describes a concrete tensor-parallel failure with `_tp_plan`, making it the most specific and actionable Qwen3.5 MoE-related report in the set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45125 is the strongest representative issue overall: it is concrete, reproducible, and specific enough to serve as the anchor for the nearby Qwen3.5 MoE loading reports, even though that connection is only plausible rather than duplicate-level.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36296", + "right": "issue:43575", + "accept": false, + "reason": "Both involve tensor parallelism, but one is a generic training bug and the other is a model-load OOM; not the same concrete defect." + }, + { + "left": "issue:28282", + "right": "issue:33453", + "accept": false, + "reason": "Different failure classes: missing PyTorch import vs tokenizer loading regression." + }, + { + "left": "issue:43618", + "right": "issue:44857", + "accept": false, + "reason": "Unrelated model output attribute issue vs AMP/CUDA crash in a different loss path." + }, + { + "left": "issue:44360", + "right": "issue:45440", + "accept": false, + "reason": "Different code paths and symptoms; DSA indexer discussion is unrelated to DeepSeekV3MoE divergence." + }, + { + "left": "issue:43618", + "right": "issue:44977", + "accept": false, + "reason": "CLIPOutput attentions assignment and Qwen3.5 flash-attention generation are distinct problems." + }, + { + "left": "issue:42890", + "right": "issue:44964", + "accept": false, + "reason": "Test seeding flakiness is unrelated to loading a specific multimodal model." + }, + { + "left": "issue:43502", + "right": "issue:44062", + "accept": false, + "reason": "local_files_only network leak and AddedToken keyword collision are different bugs." + }, + { + "left": "issue:42890", + "right": "issue:44112", + "accept": false, + "reason": "Both are test failures, but on different models and causes; not the same bug." + }, + { + "left": "issue:42890", + "right": "issue:45600", + "accept": false, + "reason": "Different CI/test issues with different affected files and root causes." + }, + { + "left": "issue:43576", + "right": "issue:46132", + "accept": false, + "reason": "A broken env command is unrelated to AttentionInterface.register behavior changes." + }, + { + "left": "issue:43723", + "right": "issue:44556", + "accept": false, + "reason": "Both are loading regressions after v5 upgrades, but one is tokenizer-specific and the other is checkpoint reload; not concrete duplicates." + }, + { + "left": "issue:44387", + "right": "issue:44556", + "accept": false, + "reason": "Int4 CUDA memory OOM and checkpoint reload failure are separate issues." + }, + { + "left": "issue:42890", + "right": "issue:45341", + "accept": false, + "reason": "Test seeding flakiness and a small testing_utils bug are not the same underlying defect." + }, + { + "left": "issue:44222", + "right": "issue:45125", + "accept": false, + "reason": "FP8 save_pretrained/moe support and missing _tp_plan for tensor parallelism are different code paths." + }, + { + "left": "issue:43010", + "right": "issue:43065", + "accept": false, + "reason": "Cache update no_grad decoration and a dummy Conv2d in Sam3PixelDecoder are unrelated." + }, + { + "left": "issue:42548", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but for different symbols and likely different missing exports." + }, + { + "left": "issue:44355", + "right": "issue:44749", + "accept": false, + "reason": "Compiled Python file errors and slower filtering after upgrade are unrelated." + }, + { + "left": "issue:43502", + "right": "issue:44485", + "accept": false, + "reason": "local_files_only network behavior and GLM-5 RoPE implementation are different defects." + }, + { + "left": "issue:45125", + "right": "issue:45478", + "accept": false, + "reason": "Both are Qwen3.5 MoE / v5.4.0 regressions, but one is a specific tensor-parallel `_tp_plan` failure and the other is a broader `from_pretrained` error; related in theme, not strong enough to treat as the same bug." + }, + { + "left": "issue:30333", + "right": "issue:33453", + "accept": false, + "reason": "MLflow reporting on failed training jobs is unrelated to tokenizer loading regression." + }, + { + "left": "issue:43010", + "right": "issue:43232", + "accept": false, + "reason": "Generation kwargs sync behavior is a different code path from cache/layer no_grad decoration." + }, + { + "left": "issue:45125", + "right": "issue:45375", + "accept": false, + "reason": "Same model family, but one is tensor-parallel loading while the other is a missing config field; not the same bug." + }, + { + "left": "issue:30990", + "right": "issue:31795", + "accept": false, + "reason": "Sentence Transformers loading hang and forward() doc confusion are unrelated." + }, + { + "left": "issue:43502", + "right": "issue:44222", + "accept": false, + "reason": "Network request leakage and FP8 moe save_pretrained behavior are not the same issue." + }, + { + "left": "issue:43299", + "right": "issue:44556", + "accept": false, + "reason": "Both are v5 loading regressions, but one is specific to Qwen3VL MoE while the other is generic checkpoint reload." + }, + { + "left": "issue:42831", + "right": "issue:43874", + "accept": false, + "reason": "FP8 accuracy concerns and missing image processor method are unrelated." + }, + { + "left": "issue:44355", + "right": "issue:45071", + "accept": false, + "reason": "Compiled-file execution errors and PretrainedConfig type checking are different defects." + }, + { + "left": "issue:30333", + "right": "issue:36296", + "accept": false, + "reason": "MLflow job status reporting and tensor-parallel training bug are unrelated." + }, + { + "left": "issue:44355", + "right": "issue:44655", + "accept": false, + "reason": "Compiled Python errors and Pipeline.save_pretrained issues are different problems." + }, + { + "left": "issue:33453", + "right": "issue:34689", + "accept": false, + "reason": "Tokenizer loading regression and Llama model loading breakage are not the same concrete bug." + }, + { + "left": "issue:42757", + "right": "issue:43576", + "accept": false, + "reason": "huggingface_hub import breakage and transformers env command breakage are unrelated." + }, + { + "left": "issue:44222", + "right": "issue:44230", + "accept": false, + "reason": "Both concern FP8/moe, but one is save_pretrained and the other is inference support; not the same bug." + }, + { + "left": "issue:43576", + "right": "issue:45071", + "accept": false, + "reason": "env command breakage and PretrainedConfig type-checking regression are unrelated." + }, + { + "left": "issue:33453", + "right": "issue:36296", + "accept": false, + "reason": "Tokenizer loading regression and tensor-parallel training bug are different issues." + }, + { + "left": "issue:43576", + "right": "issue:43824", + "accept": false, + "reason": "Broken env command is unrelated to the missing Qwen2_5_VLForConditionalGeneration export." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The overall clustering is mostly conservative, but the positive soft-edge verdict for issue:45125 vs issue:45478 overstates the packet evidence. From the packet we only know one is a specific tensor-parallel `_tp_plan` failure and the other is a broader Qwen3.5 MoE `from_pretrained` error; that is enough for a plausible connection, not a strong duplicate conclusion or a clear single-bug merge. The summary and canonical reasons should be softened accordingly." + }, + "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": 48, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:31795", + "issue:36296", + "issue:38617", + "issue:41628", + "issue:41669", + "issue:42371", + "issue:42548", + "issue:42890", + "issue:43352", + "issue:43408", + "issue:43525", + "issue:43526", + "issue:43572", + "issue:43576", + "issue:43673", + "issue:43901", + "issue:43976", + "issue:44038", + "issue:44230", + "issue:44246", + "issue:44273", + "issue:44295", + "issue:44297", + "issue:44315", + "issue:44355", + "issue:44393", + "issue:44485", + "issue:44492", + "issue:44556", + "issue:44623", + "issue:44704", + "issue:44908", + "issue:44961", + "issue:45003", + "issue:45071", + "issue:45092", + "issue:45125", + "issue:45230", + "issue:45278", + "issue:45362", + "issue:45468", + "issue:45542", + "issue:45753", + "issue:45850", + "issue:46095", + "issue:46143", + "issue:46144", + "issue:46178" + ], + "soft_pairs": [ + "issue:31795|issue:38617", + "issue:41628|issue:42548", + "issue:44961|issue:45468", + "issue:38617|issue:43576", + "issue:44355|issue:46178", + "issue:46143|issue:46144", + "issue:44908|issue:44961", + "issue:44485|issue:44961", + "issue:43673|issue:44492", + "issue:36296|issue:43901", + "issue:36296|issue:43526", + "issue:45362|issue:45850", + "issue:44623|issue:45230", + "issue:44273|issue:45542", + "issue:44038|issue:45125", + "issue:44273|issue:45003", + "issue:44393|issue:45071", + "issue:44230|issue:46095", + "issue:44393|issue:45753", + "issue:43576|issue:44556", + "issue:43525|issue:45850", + "issue:41669|issue:43673", + "issue:44556|issue:45092", + "issue:43572|issue:45850", + "issue:44492|issue:45850", + "issue:42371|issue:44492", + "issue:45278|issue:45850", + "issue:44246|issue:44273", + "issue:42890|issue:44908", + "issue:43408|issue:44315", + "issue:44704|issue:44908", + "issue:43976|issue:44393", + "issue:43352|issue:44393", + "issue:44297|issue:45230", + "issue:43576|issue:44908", + "issue:44295|issue:45230", + "issue:44908|issue:45071" + ], + "prepared_review_unit_hash": "7057b1948095f019f5ec7802f7d57c6da9942d2516422bb56b09e1742a6cb247", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 37, + "serialized_chars": 38128, + "estimated_input_tokens": 9532, + "estimated_eval_tokens": 19320 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a loose collection of Transformers regressions and model-specific bugs, not a set of true duplicates. The closest shared theme is broad v5 breakage, so the most representative issue is a generic umbrella report rather than a precise defect.", + "confidence": 0.88, + "canonical_issue_reason": "issue:45850 is the broadest umbrella among the set (\u201cSince 5.0 version it breaks too many models\u201d), so it best represents the overall v5-regression theme even though it is very generic.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45850 is the best single representative for the cluster because it captures the widest scope of the repeated \u201cv5 breaks things\u201d reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:31795", + "right": "issue:38617", + "accept": false, + "reason": "Documentation confusion about forward arguments is unrelated to an ImportError for layer_type_validation." + }, + { + "left": "issue:41628", + "right": "issue:42548", + "accept": false, + "reason": "Both are import failures, but for different missing symbols and likely different root causes." + }, + { + "left": "issue:44961", + "right": "issue:45468", + "accept": false, + "reason": "The titles are unrelated; one is a nonsense/uninformative issue and the other is a Gemma-4 audio positional-encoding bug." + }, + { + "left": "issue:38617", + "right": "issue:43576", + "accept": false, + "reason": "A missing import name and a broken CLI command in v5 are different problems." + }, + { + "left": "issue:44355", + "right": "issue:46178", + "accept": false, + "reason": "Compiled Python file errors and a tensorflow_text backend mapping error are not the same bug." + }, + { + "left": "issue:46143", + "right": "issue:46144", + "accept": false, + "reason": "Both concern RoFormer, but one is kwargs propagation and the other is attention-interface usage; different code paths." + }, + { + "left": "issue:44908", + "right": "issue:44961", + "accept": false, + "reason": "A scheduler kwarg bug and an unrelated nonspecific issue do not match." + }, + { + "left": "issue:44485", + "right": "issue:44961", + "accept": false, + "reason": "RoPE implementation discussion is unrelated to the racoon issue." + }, + { + "left": "issue:43673", + "right": "issue:44492", + "accept": false, + "reason": "Cache missing in chunked prefill is not the same as a typo in cache strategy docs/code." + }, + { + "left": "issue:36296", + "right": "issue:43901", + "accept": false, + "reason": "Tensor parallel training bugs and text-classification pipeline docs mentioning return_all_scores are unrelated." + }, + { + "left": "issue:36296", + "right": "issue:43526", + "accept": false, + "reason": "Tensor parallel training and BeitImageProcessorFast label reduction are different subsystems and failures." + }, + { + "left": "issue:45362", + "right": "issue:45850", + "accept": false, + "reason": "A specific Qwen3.5-35B chat crash is not the same concrete bug as the generic \u201cv5 breaks too many models\u201d report." + }, + { + "left": "issue:44623", + "right": "issue:45230", + "accept": false, + "reason": "Missing files on processor.save_pretrained and a vague bug report are not the same issue." + }, + { + "left": "issue:44273", + "right": "issue:45542", + "accept": false, + "reason": "Lazy loading malfunction and undefined tf backend from tensorboard-only installs are different bugs." + }, + { + "left": "issue:44038", + "right": "issue:45125", + "accept": false, + "reason": "A Qwen3-VL-Moe bug and missing _tp_plan for tensor parallelism are related only by model family, not by the same defect." + }, + { + "left": "issue:44273", + "right": "issue:45003", + "accept": false, + "reason": "Lazy loading problems and unsafe sys.modules access may overlap conceptually, but they are not the same concrete failure." + }, + { + "left": "issue:44393", + "right": "issue:45071", + "accept": false, + "reason": "Qwen3-VL bounding-box output errors are unrelated to PretrainedConfig type-checking regressions." + }, + { + "left": "issue:44230", + "right": "issue:46095", + "accept": false, + "reason": "FP8 inference support for Qwen3-VL/qwen3.5 moe is unrelated to a DeepSeek weight-conversion question." + }, + { + "left": "issue:44393", + "right": "issue:45753", + "accept": false, + "reason": "Both involve Qwen3-VL variants, but one is 2D bbox output and the other is an infinite loop on a specific image; different symptoms and fixes." + }, + { + "left": "issue:43576", + "right": "issue:44556", + "accept": false, + "reason": "A broken env command and checkpoint reload incompatibility after upgrade are different version-5 regressions." + }, + { + "left": "issue:43525", + "right": "issue:45850", + "accept": false, + "reason": "Missing pad_token_id in Llama4Config is a specific config bug, not the same as the broad model-breakage umbrella." + }, + { + "left": "issue:41669", + "right": "issue:43673", + "accept": false, + "reason": "Removing import * for performance and missing GenerationMixin cache in chunked_prefill are unrelated." + }, + { + "left": "issue:44556", + "right": "issue:45092", + "accept": false, + "reason": "Both are v5 incompatibilities, but one is checkpoint reload breakage and the other is remote-code/meta-init incompatibility for a specific model family." + }, + { + "left": "issue:43572", + "right": "issue:45850", + "accept": false, + "reason": "StableLmConfig missing pad_token_idx is a specific configuration regression, not the generic v5-breakage report." + }, + { + "left": "issue:44492", + "right": "issue:45850", + "accept": false, + "reason": "A typo in cache strategies is not the same defect as broad model breakage after v5." + }, + { + "left": "issue:42371", + "right": "issue:44492", + "accept": false, + "reason": "TF32 API settings guidance and a cache-strategy typo are unrelated." + }, + { + "left": "issue:45278", + "right": "issue:45850", + "accept": false, + "reason": "Many import errors after upgrade and generic model breakage are both broad v5 regressions, but not the same underlying bug." + }, + { + "left": "issue:44246", + "right": "issue:44273", + "accept": false, + "reason": "Import performance spikes and lazy-loading failure are related to loading, but not the same concrete issue." + }, + { + "left": "issue:42890", + "right": "issue:44908", + "accept": false, + "reason": "Missing set_seed in integration tests and inverse_sqrt scheduler kwargs handling are unrelated." + }, + { + "left": "issue:43408", + "right": "issue:44315", + "accept": false, + "reason": "A sam3_video/sam3_tracker model-type warning and Liger Kernel not applied with model_init are different problems." + }, + { + "left": "issue:44704", + "right": "issue:44908", + "accept": false, + "reason": "AutoProcessor kwargs not passed to cached_file and scheduler kwargs being ignored are separate kwargs bugs in different components." + }, + { + "left": "issue:43976", + "right": "issue:44393", + "accept": false, + "reason": "Python version compatibility issues and Qwen3-VL bbox hallucination/error are unrelated." + }, + { + "left": "issue:43352", + "right": "issue:44393", + "accept": false, + "reason": "Flash Attention 2 support for NemotronHForCausalLM is unrelated to Qwen3-VL bbox output errors." + }, + { + "left": "issue:44297", + "right": "issue:45230", + "accept": false, + "reason": "Tokenizer save_pretrained mismatch and a generic bug report are not the same defect." + }, + { + "left": "issue:43576", + "right": "issue:44908", + "accept": false, + "reason": "Broken env command and scheduler kwargs handling are unrelated version-5 regressions." + }, + { + "left": "issue:44295", + "right": "issue:45230", + "accept": false, + "reason": "Reading position_ids after buffer registration is unrelated to a generic bug report." + }, + { + "left": "issue:44908", + "right": "issue:45071", + "accept": false, + "reason": "Scheduler kwargs being ignored and PretrainedConfig type-checking regressions 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": 49, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:31515", + "issue:31795", + "issue:33453", + "issue:34689", + "issue:41628", + "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:43827", + "issue:43976", + "issue:44077", + "issue:44261", + "issue:44263", + "issue:44273", + "issue:44315", + "issue:44351", + "issue:44360", + "issue:44393", + "issue:44485", + "issue:44492", + "issue:44623", + "issue:44655", + "issue:44829", + "issue:44861", + "issue:44908", + "issue:44945", + "issue:44998", + "issue:45092", + "issue:45230", + "issue:45290", + "issue:45310", + "issue:45341", + "issue:45468", + "issue:45478", + "issue:45850", + "issue:46018", + "issue:46095", + "issue:46172" + ], + "soft_pairs": [ + "issue:41669|issue:44351", + "issue:41669|issue:45341", + "issue:44492|issue:44945", + "issue:43976|issue:45850", + "issue:44393|issue:45478", + "issue:44077|issue:44861", + "issue:43827|issue:44908", + "issue:41628|issue:41669", + "issue:31795|issue:33453", + "issue:44315|issue:44829", + "issue:43576|issue:44273", + "issue:44360|issue:45468", + "issue:44655|issue:44861", + "issue:45230|issue:45310", + "issue:44273|issue:44908", + "issue:46018|issue:46172", + "issue:43519|issue:44485", + "issue:43519|issue:44908", + "issue:41669|issue:43704", + "issue:31795|issue:34689", + "issue:31515|issue:31795", + "issue:44315|issue:45092", + "issue:43704|issue:44485", + "issue:44485|issue:45468", + "issue:43298|issue:46095", + "issue:42371|issue:43704", + "issue:43502|issue:43519", + "issue:43519|issue:44623", + "issue:43519|issue:43704", + "issue:43606|issue:45468", + "issue:44263|issue:45468", + "issue:44261|issue:45468", + "issue:42913|issue:43066", + "issue:44908|issue:44998", + "issue:44492|issue:44998", + "issue:43618|issue:44998", + "issue:44861|issue:45290", + "issue:44998|issue:45850", + "issue:44998|issue:45341", + "issue:43525|issue:44861", + "issue:43572|issue:44861" + ], + "prepared_review_unit_hash": "2bb45afb0272c6ab006ec22648266b5b07d655d5e724c370deb7ab88122a18bb", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 41, + "serialized_chars": 39192, + "estimated_input_tokens": 9798, + "estimated_eval_tokens": 19852 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items are mostly unrelated bug reports that only share broad keywords like loading, tokenizer, v5, or import. I would not merge any of the soft pairs as duplicates.", + "confidence": 0.93, + "canonical_issue_reason": "issue:41669 is the most concrete and broadly representative report in this set, but the set does not actually form a single duplicate cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:41669 is the best issue to anchor on if one must choose, because it is a specific, actionable bug report with the strongest superficial overlap to other import-related reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41669", + "right": "issue:44351", + "accept": false, + "reason": "Both mention imports, but one is about model import-star usage/performance and the other is a missing top-level symbol; different bugs and fixes." + }, + { + "left": "issue:41669", + "right": "issue:45341", + "accept": false, + "reason": "Unrelated: one is a library import/packaging concern, the other is a testing utility bug." + }, + { + "left": "issue:44492", + "right": "issue:44945", + "accept": false, + "reason": "Cache-strategy typo and pipeline-parallelism output error are not the same code-path or bug." + }, + { + "left": "issue:43976", + "right": "issue:45850", + "accept": false, + "reason": "One is a Python-version compatibility issue; the other is a broad complaint about many model regressions. Too generic to be the same bug." + }, + { + "left": "issue:44393", + "right": "issue:45478", + "accept": false, + "reason": "Both are Qwen-related, but they describe different model behaviors and likely different failure points." + }, + { + "left": "issue:44077", + "right": "issue:44861", + "accept": false, + "reason": "Optional post-init validation and tied-weight-key attribute handling are separate implementation issues." + }, + { + "left": "issue:43827", + "right": "issue:44908", + "accept": false, + "reason": "Documentation referencing removed pipeline APIs is unrelated to a scheduler kwarg bug." + }, + { + "left": "issue:41628", + "right": "issue:41669", + "accept": false, + "reason": "Both involve imports, but one is a missing exported class and the other is a model import-star refactor/performance issue." + }, + { + "left": "issue:31795", + "right": "issue:33453", + "accept": false, + "reason": "One is forward-API documentation confusion; the other is a tokenizer loading regression." + }, + { + "left": "issue:44315", + "right": "issue:44829", + "accept": false, + "reason": "Liger kernel application under model_init and flash-attention training degeneration are different training paths and failure modes." + }, + { + "left": "issue:43576", + "right": "issue:44273", + "accept": false, + "reason": "Broken env command and lazy loading failure are unrelated CLI/runtime issues." + }, + { + "left": "issue:44360", + "right": "issue:45468", + "accept": false, + "reason": "Different model components and different bugs; no shared concrete code-path." + }, + { + "left": "issue:44655", + "right": "issue:44861", + "accept": false, + "reason": "Saving pipeline objects and tied-weight-key attribute crashes are separate save/serialization problems." + }, + { + "left": "issue:45230", + "right": "issue:45310", + "accept": false, + "reason": "One is a placeholder bug report, the other is a specific from_pretrained failure for Qwen3.5 MoE." + }, + { + "left": "issue:44273", + "right": "issue:44908", + "accept": false, + "reason": "Lazy loading behavior and inverse_sqrt scheduler kwargs are unrelated." + }, + { + "left": "issue:46018", + "right": "issue:46172", + "accept": false, + "reason": "Shared-expert gating and a tensor transpose bug in deepseek-v4 are different defects." + }, + { + "left": "issue:43519", + "right": "issue:44485", + "accept": false, + "reason": "Timestamp calculation in Qwen3VL processor and GLM-5 RoPE implementation are different model-specific bugs." + }, + { + "left": "issue:43519", + "right": "issue:44908", + "accept": false, + "reason": "Processor timestamp math and scheduler kwargs handling are unrelated." + }, + { + "left": "issue:41669", + "right": "issue:43704", + "accept": false, + "reason": "Import-star cleanup/performance and VRAM leak in multi-threaded dataloading are unrelated." + }, + { + "left": "issue:31795", + "right": "issue:34689", + "accept": false, + "reason": "Documentation confusion for forward inputs is not the same as a model-loading regression for Llama 3.2 Vision." + }, + { + "left": "issue:31515", + "right": "issue:31795", + "accept": false, + "reason": "Checkpoint loading speed and forward-method documentation are unrelated issues." + }, + { + "left": "issue:44315", + "right": "issue:45092", + "accept": false, + "reason": "Both mention model initialization, but they concern different models and different failure mechanisms." + }, + { + "left": "issue:43704", + "right": "issue:44485", + "accept": false, + "reason": "A VRAM leak under dataloader threads and a RoPE implementation issue are not the same bug." + }, + { + "left": "issue:44485", + "right": "issue:45468", + "accept": false, + "reason": "Distinct model internals and distinct reported symptoms; no shared fix path." + }, + { + "left": "issue:43298", + "right": "issue:46095", + "accept": false, + "reason": "Continuous batching audio support and a weight conversion question are not duplicate bug reports." + }, + { + "left": "issue:42371", + "right": "issue:43704", + "accept": false, + "reason": "TF32 settings guidance and a VRAM leak are unrelated." + }, + { + "left": "issue:43502", + "right": "issue:43519", + "accept": false, + "reason": "Remote-file API calls despite local_files_only and Qwen3VL timestamp math are different subsystems." + }, + { + "left": "issue:43519", + "right": "issue:44623", + "accept": false, + "reason": "Processor timestamp calculation and processor.save_pretrained file omission are different bugs." + }, + { + "left": "issue:43519", + "right": "issue:43704", + "accept": false, + "reason": "No shared code-path: processor timestamp logic vs multi-thread VRAM leak." + }, + { + "left": "issue:43606", + "right": "issue:45468", + "accept": false, + "reason": "CPU offload device mismatch and Gemma audio positional encoding are unrelated." + }, + { + "left": "issue:44263", + "right": "issue:45468", + "accept": false, + "reason": "A torch.split return-value bug in one indexer and Gemma audio encoding are not the same issue." + }, + { + "left": "issue:44261", + "right": "issue:45468", + "accept": false, + "reason": "RMS norm epsilon precision discussion and Gemma audio positional encoding are different technical problems." + }, + { + "left": "issue:42913", + "right": "issue:43066", + "accept": false, + "reason": "Both are tokenizer-related v5 complaints, but one is generic behavior change and the other is a specific decoder-type bug; not enough to treat as the same underlying issue." + }, + { + "left": "issue:44908", + "right": "issue:44998", + "accept": false, + "reason": "Scheduler kwarg handling and an unrelated placeholder issue are not duplicates." + }, + { + "left": "issue:44492", + "right": "issue:44998", + "accept": false, + "reason": "A typo report and an irrelevant placeholder issue share no bug content." + }, + { + "left": "issue:43618", + "right": "issue:44998", + "accept": false, + "reason": "CLIP attentions assignment regression and an irrelevant placeholder issue are unrelated." + }, + { + "left": "issue:44861", + "right": "issue:45290", + "accept": false, + "reason": "Tied-weight key handling and chat-template tool-call crashes are different code paths." + }, + { + "left": "issue:44998", + "right": "issue:45850", + "accept": false, + "reason": "A placeholder issue cannot be merged with a broad regression complaint; no concrete overlap." + }, + { + "left": "issue:44998", + "right": "issue:45341", + "accept": false, + "reason": "Placeholder issue and testing_utils bug are unrelated." + }, + { + "left": "issue:43525", + "right": "issue:44861", + "accept": false, + "reason": "Missing pad_token_id on a config and an AttributeError in tied-weight key processing are different bugs." + }, + { + "left": "issue:43572", + "right": "issue:44861", + "accept": false, + "reason": "Missing pad_token_idx after v5 update and tied-weight-key crash are not the same failure." + } + ] + }, + "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": 50, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-429", + "nodes": [ + "issue:30333", + "issue:31515", + "issue:33453", + "issue:36296", + "issue:37934", + "issue:38617", + "issue:42936", + "issue:43240", + "issue:43298", + "issue:43668", + "issue:43717", + "issue:43813", + "issue:44031", + "issue:44230", + "issue:44623", + "issue:45310", + "issue:46018", + "issue:46144" + ], + "soft_pairs": [ + "issue:31515|issue:38617", + "issue:44230|issue:44623", + "issue:30333|issue:31515", + "issue:31515|issue:36296", + "issue:44230|issue:45310", + "issue:31515|issue:33453", + "issue:43298|issue:44230", + "issue:43717|issue:46144", + "issue:42936|issue:46018", + "issue:43668|issue:44031", + "issue:42936|issue:43240", + "issue:43240|issue:46144", + "issue:42936|issue:44031", + "issue:42936|issue:46144", + "issue:42936|issue:43813", + "issue:43240|issue:43668", + "issue:43668|issue:43813", + "issue:37934|issue:43668", + "issue:42936|issue:43668" + ], + "prepared_review_unit_hash": "86ac08ff22400010fe54bc67682f9a4d8ba89ecf1cd77ff6bdbfc96eae6008a8", + "component_budget": { + "node_count": 429, + "item_count": 429, + "soft_pair_count": 1585, + "serialized_chars": 820589, + "estimated_input_tokens": 205148, + "estimated_eval_tokens": 410552 + }, + "budget": { + "node_count": 18, + "item_count": 18, + "soft_pair_count": 19, + "serialized_chars": 15703, + "estimated_input_tokens": 3926, + "estimated_eval_tokens": 8108 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster looks over-grouped: the issues span unrelated models, configs, tokenizer warnings, training/runtime behavior, and one-off typos. None of the soft pairs appear to describe the same underlying bug or change.", + "confidence": 0.96, + "canonical_issue_reason": "Issue 31515 is the most connected hub in the soft-similarity graph, but the cluster is heterogeneous, so it is only a weak representative and not a true duplicate canonical.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 31515 is the closest to a cluster seed because it links to several other items by similarity, but its checkpoint-loading slowdown is still unrelated to the rest.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:31515", + "right": "issue:38617", + "accept": false, + "reason": "Checkpoint loading slowness vs an ImportError in configuration_utils: different failure modes and code paths." + }, + { + "left": "issue:44230", + "right": "issue:44623", + "accept": false, + "reason": "FP8 inference support for Qwen models vs missing files on processor.save_pretrained; not the same bug." + }, + { + "left": "issue:30333", + "right": "issue:31515", + "accept": false, + "reason": "MLflow status reporting on failed training vs from_pretrained checkpoint load speed." + }, + { + "left": "issue:31515", + "right": "issue:36296", + "accept": false, + "reason": "Checkpoint loading performance vs tensor-parallel training bug." + }, + { + "left": "issue:44230", + "right": "issue:45310", + "accept": false, + "reason": "Both mention Qwen3.5, but one is FP8 support and the other is a from_pretrained error; different concrete issues." + }, + { + "left": "issue:31515", + "right": "issue:33453", + "accept": false, + "reason": "Checkpoint loading slowdown vs tokenizer loading regression; not duplicates." + }, + { + "left": "issue:43298", + "right": "issue:44230", + "accept": false, + "reason": "Continuous batching support for audio models vs FP8 Qwen3-VL/Qwen3.5 support." + }, + { + "left": "issue:43717", + "right": "issue:46144", + "accept": false, + "reason": "Mamba init_weights behavior vs RoFormer attention interface usage; unrelated model implementation problems." + }, + { + "left": "issue:42936", + "right": "issue:46018", + "accept": false, + "reason": "Mask2Former ignore_value handling vs DeepSeek-V4 shared expert gating." + }, + { + "left": "issue:43668", + "right": "issue:44031", + "accept": false, + "reason": "ModernBERT config type hint issue vs tokenizer regex warning after upgrade; different artifacts." + }, + { + "left": "issue:42936", + "right": "issue:43240", + "accept": false, + "reason": "Both touch loss-related code, but one is ignore_value handling and the other is kwargs propagation; not the same bug." + }, + { + "left": "issue:43240", + "right": "issue:46144", + "accept": false, + "reason": "Loss kwargs forwarding vs RoFormer attention interface implementation." + }, + { + "left": "issue:42936", + "right": "issue:44031", + "accept": false, + "reason": "Mask2Former loss parameter handling vs tokenizer warning regression." + }, + { + "left": "issue:42936", + "right": "issue:46144", + "accept": false, + "reason": "Different model subsystems and different bugs." + }, + { + "left": "issue:42936", + "right": "issue:43813", + "accept": false, + "reason": "Mask2Former ignore_value handling vs a quantization typo; no underlying overlap." + }, + { + "left": "issue:43240", + "right": "issue:43668", + "accept": false, + "reason": "Loss kwargs not passed vs incorrect type hint; unrelated." + }, + { + "left": "issue:43668", + "right": "issue:43813", + "accept": false, + "reason": "ModernBERT type hint mismatch vs typo in a quantization symbol." + }, + { + "left": "issue:37934", + "right": "issue:43668", + "accept": false, + "reason": "Question about Llama4TextL2Norm being RMSNorm vs a ModernBERT config type-hint issue." + }, + { + "left": "issue:42936", + "right": "issue:43668", + "accept": false, + "reason": "Mask2Former ignore_value bug vs ModernBERT norm_eps annotation issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "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-10519-3", + "nodes": [ + "issue:10519", + "issue:11005", + "issue:11307" + ], + "soft_pairs": [ + "issue:10519|issue:11307", + "issue:10519|issue:11005", + "issue:11005|issue:11307" + ], + "prepared_review_unit_hash": "77810f68ceb91c8ccda0611d3fef63af16ec9cc6c4a8989715764263c21c4d6c", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 2876, + "estimated_input_tokens": 719, + "estimated_eval_tokens": 1694 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 2876, + "estimated_input_tokens": 719, + "estimated_eval_tokens": 1694 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These three issues are unrelated feature requests/questions in different areas (token truncation, learning-rate scheduling, and Wav2Vec2 word timestamps). They should not be deduplicated.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:10519", + "right": "issue:11307", + "accept": false, + "reason": "Different features and domains: truncation direction vs. word-level timing offsets in Wav2Vec2." + }, + { + "left": "issue:10519", + "right": "issue:11005", + "accept": false, + "reason": "No common underlying bug/change; one is about tokenizer truncation behavior, the other about scheduler functionality." + }, + { + "left": "issue:11005", + "right": "issue:11307", + "accept": false, + "reason": "Unrelated topics: ReduceLROnPlateau-like scheduler behavior versus extracting timestamps for words." + } + ] + }, + "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": "llm", + "cache_hit": false, + "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": "7c9e70f935bf4a9797a6c6ed144ea0a77edeb22d04c6511badbba524da29b174", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 2478, + "estimated_input_tokens": 620, + "estimated_eval_tokens": 1496 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 2478, + "estimated_input_tokens": 620, + "estimated_eval_tokens": 1496 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These three issues do not look like true duplicates: one is about Tapas tokenization mismatch, one about private-model auth/error messaging, and one about a generic model-load failure. The cluster appears to be soft-similarity only, not the same underlying bug.", + "confidence": 0.82, + "canonical_issue_reason": "Issue #16618 is the broadest and most central of the three, describing a model-loading failure, while the other two are narrower and about different topics.", + "canonical_pr_reason": null, + "best_issue_reason": "#16618 is the best representative issue for this cluster because it is the clearest user-facing loading problem and the most likely anchor for related reports; the others are not close enough to be merged into it as duplicates.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:13244", + "right": "issue:16618", + "accept": false, + "reason": "Tapas tokenization behavior is a different problem domain from failing to load bert-base-uncased; no evidence they describe the same code-path bug." + }, + { + "left": "issue:15980", + "right": "issue:16618", + "accept": false, + "reason": "Private-model download/auth error messaging is distinct from a generic model-load failure for bert-base-uncased; they do not clearly share the same underlying defect." + } + ] + }, + "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": "llm", + "cache_hit": false, + "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": "9b5cf9cbed794be0e538a6f10d2c87400a8b27f56725d3b8c675024e26732112", + "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 separate community feature requests: one for Flash Attention 2 support across more architectures, and one for GGUF support across more architectures. The shared wording is generic, but the underlying changes are different and there is no evidence they describe the same bug or code change.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:26350", + "right": "issue:33260", + "accept": false, + "reason": "Different feature areas (Flash Attention 2 vs GGUF) and different implementation targets; similar phrasing about \"more architectures\" is too broad to treat as 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": 5, + "component_count": 17, + "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-27088-6", + "nodes": [ + "issue:27088", + "issue:28936", + "issue:38435", + "issue:43834", + "issue:44365", + "issue:44370" + ], + "soft_pairs": [ + "issue:27088|issue:44370", + "issue:27088|issue:44365", + "issue:27088|issue:43834", + "issue:27088|issue:38435", + "issue:27088|issue:28936", + "issue:28936|issue:43834", + "issue:28936|issue:44365", + "issue:28936|issue:38435", + "issue:28936|issue:44370", + "issue:38435|issue:44370", + "issue:38435|issue:44365", + "issue:38435|issue:43834", + "issue:43834|issue:44370", + "issue:43834|issue:44365", + "issue:44365|issue:44370" + ], + "prepared_review_unit_hash": "d6eeee5d7913169dd58013da80c0f86b6c6c8cd697d89bbb7532a5efa2d1de59", + "component_budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 15, + "serialized_chars": 8793, + "estimated_input_tokens": 2199, + "estimated_eval_tokens": 4654 + }, + "budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 15, + "serialized_chars": 8793, + "estimated_input_tokens": 2199, + "estimated_eval_tokens": 4654 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster mixes three language-specific i18n doc translation issues (Turkish, Spanish, Romanian) with three near-identical generic template issues. The generic placeholder issues are duplicates of each other; the language-specific issues are not duplicates because they target different translations.", + "confidence": 0.96, + "canonical_issue_reason": "issue:43834 is the earliest generic placeholder issue and matches the same template wording as the other two placeholder issues, making it the best duplicate anchor.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43834 is the best representative of the duplicate template issues because it is the earliest and most canonical-looking copy of the generic i18n translation request.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:27088", + "right": "issue:44370", + "accept": false, + "reason": "Different target language (Turkish vs placeholder); same i18n theme but not the same underlying issue." + }, + { + "left": "issue:27088", + "right": "issue:44365", + "accept": false, + "reason": "Different target language (Turkish vs placeholder); not the same concrete request." + }, + { + "left": "issue:27088", + "right": "issue:43834", + "accept": false, + "reason": "Concrete Turkish translation request versus generic template issue; not duplicates." + }, + { + "left": "issue:27088", + "right": "issue:38435", + "accept": false, + "reason": "Different target languages (Turkish vs Romanian), so these are separate translation requests." + }, + { + "left": "issue:27088", + "right": "issue:28936", + "accept": false, + "reason": "Different target languages (Turkish vs Spanish); related topic but distinct issues." + }, + { + "left": "issue:28936", + "right": "issue:43834", + "accept": false, + "reason": "Concrete Spanish translation request versus generic template issue; not the same underlying issue." + }, + { + "left": "issue:28936", + "right": "issue:44365", + "accept": false, + "reason": "Concrete Spanish translation request versus generic template issue; not duplicates." + }, + { + "left": "issue:28936", + "right": "issue:38435", + "accept": false, + "reason": "Different target languages (Spanish vs Romanian), so they should stay separate." + }, + { + "left": "issue:28936", + "right": "issue:44370", + "accept": false, + "reason": "Concrete Spanish translation request versus generic template issue; not the same request." + }, + { + "left": "issue:38435", + "right": "issue:44370", + "accept": false, + "reason": "Concrete Romanian translation request versus generic template issue; not duplicates." + }, + { + "left": "issue:38435", + "right": "issue:44365", + "accept": false, + "reason": "Concrete Romanian translation request versus generic template issue; not the same underlying issue." + }, + { + "left": "issue:38435", + "right": "issue:43834", + "accept": false, + "reason": "Concrete Romanian translation request versus generic template issue; not duplicates." + }, + { + "left": "issue:43834", + "right": "issue:44370", + "accept": true, + "reason": "Both are the same generic placeholder i18n translation issue with identical wording and no language-specific content." + }, + { + "left": "issue:43834", + "right": "issue:44365", + "accept": true, + "reason": "Both are the same generic placeholder i18n translation issue; no substantive difference is visible." + }, + { + "left": "issue:44365", + "right": "issue:44370", + "accept": true, + "reason": "Both are identical generic placeholder issues for translating docs; effectively duplicates." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: the Turkish, Spanish, and Romanian issues are distinct by title, and the three placeholder issues are the closest match cluster with 43834 as the earliest. The soft-edge verdicts are conservative overall." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "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": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-36817-16", + "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", + "issue:46133" + ], + "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", + "issue:45322|issue:46133" + ], + "prepared_review_unit_hash": "1f542d67541bf73d6ab8ceae795d1f53a11b8d5fa6881cad85e1d6806318bebd", + "component_budget": { + "node_count": 16, + "item_count": 16, + "soft_pair_count": 36, + "serialized_chars": 21660, + "estimated_input_tokens": 5415, + "estimated_eval_tokens": 11086 + }, + "budget": { + "node_count": 16, + "item_count": 16, + "soft_pair_count": 36, + "serialized_chars": 21660, + "estimated_input_tokens": 5415, + "estimated_eval_tokens": 11086 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are all distinct model-request issues that share only a broad \"add support\" theme; I do not see true duplicates or a single underlying bug/change cluster.", + "confidence": 0.98, + "canonical_issue_reason": "No single canonical issue: each item requests a different model family, architecture, or modality, so the similarity is only topical.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:46133 is the most detailed and recent request, so it is the best representative of the theme, but it still is not a duplicate hub.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36817", + "right": "issue:41211", + "accept": false, + "reason": "EuroBert config support and DEIMv2 are unrelated model requests; only the generic \"add model\" pattern matches." + }, + { + "left": "issue:36817", + "right": "issue:43671", + "accept": false, + "reason": "EuroBert config support and Qwen3-TTS are different model families and modalities, not the same change." + }, + { + "left": "issue:36817", + "right": "issue:36879", + "accept": false, + "reason": "EuroBert and RF-DETR are separate model additions with no shared code-path bug." + }, + { + "left": "issue:36879", + "right": "issue:41211", + "accept": false, + "reason": "RF-DETR and DEIMv2 are different model requests, not one duplicated implementation task." + }, + { + "left": "issue:36879", + "right": "issue:43909", + "accept": false, + "reason": "RF-DETR and LFM2.5 Audio target different model domains and would not be merged as one PR." + }, + { + "left": "issue:36879", + "right": "issue:44121", + "accept": false, + "reason": "RF-DETR and the weight-sparse transformer request are unrelated architectures and use cases." + }, + { + "left": "issue:36879", + "right": "issue:43837", + "accept": false, + "reason": "RF-DETR and Qwen3-ASR are separate model support requests, not the same underlying change." + }, + { + "left": "issue:36879", + "right": "issue:43671", + "accept": false, + "reason": "RF-DETR (vision detection) and Qwen3-TTS (speech) are clearly different requests." + }, + { + "left": "issue:37015", + "right": "issue:43837", + "accept": false, + "reason": "NeoBERT and Qwen3-ASR are unrelated model additions with different code paths." + }, + { + "left": "issue:37015", + "right": "issue:44121", + "accept": false, + "reason": "NeoBERT and the sparse transformer request are different model families and concerns." + }, + { + "left": "issue:37015", + "right": "issue:43909", + "accept": false, + "reason": "NeoBERT and LFM2.5 Audio are distinct model support requests, not duplicates." + }, + { + "left": "issue:36879", + "right": "issue:37015", + "accept": false, + "reason": "RF-DETR and NeoBERT are separate model additions with no shared concrete bug." + }, + { + "left": "issue:37015", + "right": "issue:42503", + "accept": false, + "reason": "NeoBERT and ModernVBERT are different model families; the overlap is only that both are BERT-like." + }, + { + "left": "issue:41115", + "right": "issue:43837", + "accept": false, + "reason": "MiniCPM3 and Qwen3-ASR are different model requests and not the same fix." + }, + { + "left": "issue:41115", + "right": "issue:44121", + "accept": false, + "reason": "MiniCPM3 support and the sparse transformer request are unrelated changes." + }, + { + "left": "issue:41115", + "right": "issue:42503", + "accept": false, + "reason": "MiniCPM3 and ModernVBERT are distinct model-addition issues, not duplicates." + }, + { + "left": "issue:41115", + "right": "issue:45027", + "accept": false, + "reason": "MiniCPM3 and Voxtral-4B-TTS are different model families and modalities." + }, + { + "left": "issue:41211", + "right": "issue:43671", + "accept": false, + "reason": "DEIMv2 and Qwen3-TTS are unrelated model requests, sharing only a general support theme." + }, + { + "left": "issue:42503", + "right": "issue:43837", + "accept": false, + "reason": "ModernVBERT and Qwen3-ASR are different model support requests." + }, + { + "left": "issue:42503", + "right": "issue:43671", + "accept": false, + "reason": "ModernVBERT and Qwen3-TTS are distinct model requests with different modalities." + }, + { + "left": "issue:42503", + "right": "issue:42738", + "accept": false, + "reason": "ModernVBERT models and BERT-like models with RoPE are related in theme but not the same concrete request." + }, + { + "left": "issue:42738", + "right": "issue:45027", + "accept": false, + "reason": "BERT-like models with RoPE and Voxtral TTS are unrelated model additions." + }, + { + "left": "issue:43671", + "right": "issue:43837", + "accept": false, + "reason": "Qwen3-TTS and Qwen3-ASR are sibling requests but target different speech tasks and should not be merged." + }, + { + "left": "issue:43671", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-TTS and LFM2.5 Audio are different audio model requests, not one duplicated change." + }, + { + "left": "issue:43671", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3-TTS and the sparse transformer request address different model types and code paths." + }, + { + "left": "issue:43671", + "right": "issue:45027", + "accept": false, + "reason": "Qwen3-TTS and Voxtral-4B-TTS are separate TTS model support requests, not the same artifact." + }, + { + "left": "issue:43671", + "right": "issue:45177", + "accept": false, + "reason": "Qwen3-TTS and DeepSeek-OCR2 are unrelated model families and modalities." + }, + { + "left": "issue:43837", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-ASR and LFM2.5 Audio are different audio-model requests, not duplicates." + }, + { + "left": "issue:43837", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3-ASR and the sparse transformer request are unrelated changes." + }, + { + "left": "issue:43837", + "right": "issue:45027", + "accept": false, + "reason": "Qwen3-ASR and Voxtral-4B-TTS are different speech tasks and model families." + }, + { + "left": "issue:43837", + "right": "issue:45177", + "accept": false, + "reason": "Qwen3-ASR and DeepSeek-OCR2 are distinct model support requests." + }, + { + "left": "issue:43837", + "right": "issue:45322", + "accept": false, + "reason": "Qwen3-ASR and EUPE are separate model requests with no shared concrete implementation target." + }, + { + "left": "issue:43909", + "right": "issue:44205", + "accept": false, + "reason": "LFM2.5 Audio and SAM3-LiteText are different modality/model requests." + }, + { + "left": "issue:44121", + "right": "issue:45322", + "accept": false, + "reason": "The sparse transformer request and EUPE are unrelated model additions, not one code change." + }, + { + "left": "issue:45322", + "right": "issue:46133", + "accept": false, + "reason": "EUPE and TIPSv2 are distinct model requests from different authors and use cases." + } + ] + }, + "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": "llm", + "cache_hit": false, + "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": "010669a4ae6d9023b2f4a7a6a74aa588703e224df6a09cb9cf0c44e8f740e483", + "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 not duplicates: #41084 is about Set Block Decoding, while #43037 is a request for DeepSeek v3.2 support. They describe different features/problems with no shared targets or code paths.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "No single best issue for a duplicate cluster; the issues are unrelated and cover different user needs.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41084", + "right": "issue:43037", + "accept": false, + "reason": "Different topics and likely different code paths: block decoding behavior vs model compatibility/support. The weak textual similarity is not enough to indicate 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": 8, + "component_count": 17, + "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-43598-2", + "nodes": [ + "issue:43598", + "issue:43600" + ], + "soft_pairs": [ + "issue:43598|issue:43600" + ], + "prepared_review_unit_hash": "12e6cf905b6acf7c69e02097a412edd9acd245f67f3d2b6d03b2323e4de88cc0", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1584, + "estimated_input_tokens": 396, + "estimated_eval_tokens": 1048 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1584, + "estimated_input_tokens": 396, + "estimated_eval_tokens": 1048 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two closed issues are related only at a broad Trainer/customization level, but they describe different problems and fixes: one is about `remove_unused_column` behavior, the other about FLOPS estimation for custom trainers. They should not be treated as duplicates.", + "confidence": 0.89, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "issue:43598 is the more concrete and self-contained Trainer customization request, but it does not cover the FLOPS-estimation problem in issue:43600.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43598", + "right": "issue:43600", + "accept": false, + "reason": "Different underlying bugs: `remove_unused_column` customizability in Trainer versus accounting for custom trainers in FLOPS estimation. Same general subsystem, but not the same change or code path." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 9, + "component_count": 17, + "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-43684-2", + "nodes": [ + "issue:43684", + "issue:44405" + ], + "soft_pairs": [ + "issue:43684|issue:44405" + ], + "prepared_review_unit_hash": "9549391a400f2e89dfea51e0e9ba4ff1f33b00543dcfaa4aae5efa1af718f3cd", + "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 two closed enhancement requests for different Qwen variants and different model heads; they do not look like duplicate reports of the same underlying bug/change.", + "confidence": 0.97, + "canonical_issue_reason": "No canonical duplicate: issue 43684 is about registering Qwen3-Omni with AutoModel/AutoModelForConditionalGeneration, while issue 44405 is about adding AutoModelForSequenceClassification support for Qwen3.5 (Qwen3_5Config).", + "canonical_pr_reason": null, + "best_issue_reason": "If a representative issue is needed, 43684 is the broader library-registration request, but it still does not cover the distinct sequence-classification support asked for in 44405.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43684", + "right": "issue:44405", + "accept": false, + "reason": "Different model families and different task heads; this is a soft similarity only, not the same underlying 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": 10, + "component_count": 17, + "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-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": "a440aaab826acf4ff33297c9c812c136713014c7245bbea0d81dce2219bbfb3d", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4264, + "estimated_input_tokens": 1066, + "estimated_eval_tokens": 2388 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4264, + "estimated_input_tokens": 1066, + "estimated_eval_tokens": 2388 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Three issues titled \"huggingface \" look like the same duplicate report; the \"Fett\" issue appears unrelated. I\u2019d keep the earliest huggingface issue as canonical.", + "confidence": 0.72, + "canonical_issue_reason": "Issue 43845 is the earliest of the near-identical \"huggingface \" reports, so it is the best canonical representative among the likely duplicates.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43845 is the best cluster anchor because it matches the repeated huggingface title pattern and is the earliest of that group.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43835", + "right": "issue:43845", + "accept": false, + "reason": "Different titles and no supporting description or targets; no evidence they are the same underlying issue." + }, + { + "left": "issue:43835", + "right": "issue:43846", + "accept": false, + "reason": "Different titles and no supporting description or targets; too little evidence to treat as duplicates." + }, + { + "left": "issue:43835", + "right": "issue:43859", + "accept": false, + "reason": "Different titles and no supporting description or targets; not enough to connect them as the same issue." + }, + { + "left": "issue:43845", + "right": "issue:43846", + "accept": true, + "reason": "Exact same title pattern and nearly identical metadata, with no sign of a different underlying problem." + }, + { + "left": "issue:43845", + "right": "issue:43859", + "accept": true, + "reason": "Same title pattern and very similar duplicate-looking reports; no evidence of a distinct issue." + }, + { + "left": "issue:43846", + "right": "issue:43859", + "accept": true, + "reason": "Same title pattern and very similar duplicate-looking reports; no evidence of a distinct issue." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The anchor choice is grounded: 43845 is the earliest of the three near-identical \"huggingface \" issues. The rejection of 43835 as unrelated is conservative and supported by the title mismatch. The soft-edge accepts are also reasonably cautious given the matching titles and soft-similarity evidence, so I don't see an overstatement that would require rejection." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "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": "llm", + "cache_hit": false, + "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": "bc490bef964e203c83282dcb8bfae6ac9d8cf26112d00e39c2dd0cd6335186a5", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 9, + "serialized_chars": 5788, + "estimated_input_tokens": 1447, + "estimated_eval_tokens": 3150 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 9, + "serialized_chars": 5788, + "estimated_input_tokens": 1447, + "estimated_eval_tokens": 3150 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is dominated by low-signal/spam issues with unrelated titles; there is no clear shared bug or change to unify.", + "confidence": 0.92, + "canonical_issue_reason": "Issue #44418 is the only one with a somewhat descriptive, non-spam title, so it is the least ambiguous representative of the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "#44418 is the best issue representative because it is the most readable and specific title, even though it still looks generic and low-value.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44371", + "right": "issue:44572", + "accept": false, + "reason": "Both are titled '', but there is no evidence they describe the same underlying bug or request beyond identical spam labeling." + }, + { + "left": "issue:44371", + "right": "issue:44573", + "accept": false, + "reason": "Identical spam titles are not enough to treat them as the same issue; no shared details or target are provided." + }, + { + "left": "issue:44371", + "right": "issue:44418", + "accept": false, + "reason": "One is spam and the other is a generic documentation suggestion; they do not look like the same issue." + }, + { + "left": "issue:44371", + "right": "issue:44937", + "accept": false, + "reason": "'Check out \"Google LLC\"' is unrelated to the spam placeholder title and gives no basis for duplication." + }, + { + "left": "issue:44418", + "right": "issue:44572", + "accept": false, + "reason": "A documentation enhancement request is not the same underlying item as a spam placeholder issue." + }, + { + "left": "issue:44418", + "right": "issue:44573", + "accept": false, + "reason": "Generic documentation feedback and spam placeholder content do not indicate the same bug or change." + }, + { + "left": "issue:44572", + "right": "issue:44573", + "accept": false, + "reason": "Although both are spam-titled, there is no concrete evidence they refer to the same report or change." + }, + { + "left": "issue:44572", + "right": "issue:44937", + "accept": false, + "reason": "Spam placeholder and 'Check out \"Google LLC\"' are unrelated; no shared code-path or request is visible." + }, + { + "left": "issue:44573", + "right": "issue:44937", + "accept": false, + "reason": "The titles do not match in subject matter, and there is no supporting detail to justify a duplicate merge." + } + ] + }, + "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": "llm", + "cache_hit": false, + "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": "a10feab0ec3d1a67b9ba5c56a695376c0afd547f73d2c65a399523973c3fdd3f", + "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 are very likely duplicates or closely related: they have the exact same title and moderate textual similarity, but the evidence stops short of proving they are exact duplicates. #45145 remains the best canonical issue because it has the inbound reference.", + "confidence": 0.86, + "canonical_issue_reason": "#45145 is the better canonical issue because it has the same title as #45151 and already has an inbound reference, so it is the more natural anchor for the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "#45145 is the best issue overall for the cluster because it is the most referenced instance of the same titled report and is a reasonable canonical representative.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45145", + "right": "issue:45151", + "accept": true, + "reason": "These look like a likely duplicate/closely related issue pair: the titles match exactly and the body similarity is moderate, but the available evidence does not conclusively establish perfect duplication." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The packet supports that the issues have the same title and a soft-similarity signal, but it does not establish that they are exact duplicates or that the text is highly overlapping beyond the similarity metric. The canonical choice based on the inbound reference is reasonable, but the summary and soft-edge language overstate the evidence. Please downgrade the verdict to a more conservative formulation (e.g., likely duplicate / closely related)." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "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": "llm", + "cache_hit": false, + "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": "c447b4349d721d84f02dec5299d3b357e15038f781560b4e91162f632061bfce", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1669, + "estimated_input_tokens": 418, + "estimated_eval_tokens": 1092 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1669, + "estimated_input_tokens": 418, + "estimated_eval_tokens": 1092 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are two separate 4-bit inference regressions: one in Gemma4 audio-module dtype handling (torch.finfo on uint8 weights), and one in BitsAndBytesConfig skip-module defaults affecting lm_head exclusion. They should not be merged as duplicates.", + "confidence": 0.97, + "canonical_issue_reason": "No canonical duplicate: 45672 is a Gemma4 audio-module uint8/torch.finfo failure, while 45674 is a BitsAndBytesConfig skip_modules/lm_head assertion regression.", + "canonical_pr_reason": null, + "best_issue_reason": "Neither issue fully represents the other; 45674 is the broader configuration regression, but it should not absorb 45672.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45672", + "right": "issue:45674", + "accept": false, + "reason": "Different bugs and code paths: Gemma4 audio-module finfo/uint8 handling vs BitsAndBytesConfig clearing the default lm_head exclusion. Shared 4-bit inference context is too broad to treat as one fix." + } + ] + }, + "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": "llm", + "cache_hit": false, + "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": "50f64a7c4a18e923f16dc354cafee6fb7e1946f5be38162119d9226d64fee02d", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1477, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1477, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two issues are unrelated closed items with only name/date-like titles; there is no evidence they describe the same bug or request.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45762", + "right": "issue:45763", + "accept": false, + "reason": "Similar surface structure in the titles, but they refer to different people and dates and contain no shared bug/report context; not the same underlying issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 16, + "component_count": 17, + "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-45764-2", + "nodes": [ + "issue:45764", + "issue:45765" + ], + "soft_pairs": [ + "issue:45764|issue:45765" + ], + "prepared_review_unit_hash": "66ff4ecda68211c661ff54be8e5e511735db1f9db61c8ca9885393c707a1e022", + "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 both empty, closed, and only share a weak name/date pattern; there is no evidence they describe the same bug or request.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "Neither issue is a good canonical representative: both have no body, no references, and look like unrelated low-signal entries rather than a real duplicate cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45764", + "right": "issue:45765", + "accept": false, + "reason": "Only soft text similarity is present; the titles are different names with different dates and there is no shared problem statement or linkage indicating the same underlying issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 17, + "component_count": 17, + "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-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": "1b1c0988e3e8bb2e6f2cb1b792d5f8eef001797f065277a9940f230e10b2f459", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 8, + "serialized_chars": 5728, + "estimated_input_tokens": 1432, + "estimated_eval_tokens": 3120 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 8, + "serialized_chars": 5728, + "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 a single duplicate set: it contains two exact duplicate issue pairs (45870/45871 and 45872/45873) plus one separate dataset-related issue (45869). There is no one global canonical issue for all five items.", + "confidence": 0.96, + "canonical_issue_reason": "No single canonical issue for the whole cluster; it splits into two unrelated exact-duplicate pairs, with 45870/45871 and 45872/45873 each representing separate underlying issues.", + "canonical_pr_reason": null, + "best_issue_reason": "No single best issue across the full cluster; if forced to pick within the duplicate pairs, the earliest and slightly more active copy in 45870/45871 is the strongest representative for that pair.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45869", + "right": "issue:45870", + "accept": false, + "reason": "Different artifact: dataset listing vs example issue; only broad financial theme overlaps." + }, + { + "left": "issue:45869", + "right": "issue:45871", + "accept": false, + "reason": "Different artifact: dataset listing vs example issue; only broad financial theme overlaps." + }, + { + "left": "issue:45870", + "right": "issue:45871", + "accept": true, + "reason": "Exact duplicate: same title and matching body length/topic." + }, + { + "left": "issue:45870", + "right": "issue:45872", + "accept": false, + "reason": "Related finance/DataForge wording, but different underlying request: example prediction vs scraping-service topic." + }, + { + "left": "issue:45870", + "right": "issue:45873", + "accept": false, + "reason": "Related finance/DataForge wording, but different underlying request: example prediction vs scraping-service topic." + }, + { + "left": "issue:45871", + "right": "issue:45872", + "accept": false, + "reason": "Related finance/DataForge wording, but different underlying request: example prediction vs scraping-service topic." + }, + { + "left": "issue:45871", + "right": "issue:45873", + "accept": false, + "reason": "Related finance/DataForge wording, but different underlying request: example prediction vs scraping-service topic." + }, + { + "left": "issue:45872", + "right": "issue:45873", + "accept": true, + "reason": "Exact duplicate: same title and matching body length/topic." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Grounded and conservative overall. The summary correctly identifies two exact-duplicate pairs (45870/45871 and 45872/45873) and treats 45869 as separate. The soft-edge false verdicts are appropriately cautious, and there is no evidence of overclaiming beyond what the packet supports." + }, + "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:46048" + ], + "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:44827", + "pull_request:43995|pull_request:45213", + "pull_request:44827|pull_request:45170", + "pull_request:44827|pull_request:46048", + "pull_request:44827|pull_request:45655", + "pull_request:44827|pull_request:45213", + "pull_request:43823|pull_request:45213", + "pull_request:43251|pull_request:43254" + ], + "prepared_review_unit_hash": "c9abc291c4e2dad75880798294a9aeb51e022dfa5bb47b37d6d430113a8bb9a9", + "component_budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 18, + "serialized_chars": 34775, + "estimated_input_tokens": 8694, + "estimated_eval_tokens": 17644 + }, + "budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 18, + "serialized_chars": 34775, + "estimated_input_tokens": 8694, + "estimated_eval_tokens": 17644 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The cluster is mostly heterogeneous and does not form one duplicate set. The only true duplicate-like pair is the two `fixed_cross_entropy` PRs (#43251 and #43254), which patch the same loss helper for the same underlying kwargs-handling bug. All other pairs are unrelated by code path despite broad topical overlap.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #43251 is the best canonical PR because it directly fixes the tracked `cross_entropy` kwargs bug in `loss_utils.py` with an explicit issue link, and PR #43254 is just a narrower variant of the same fix.", + "best_issue_reason": null, + "best_pr_reason": "PR #43251 is the strongest representative of the only real duplicate cluster in this set: it addresses the same `fixed_cross_entropy` bug as #43254 and has the clearest issue linkage and implementation.", + "soft_edge_verdicts": [ + { + "left": "pull_request:39895", + "right": "pull_request:43424", + "accept": false, + "reason": "VideoPrism model integration vs executorch dynamic-shape export test; different subsystems and no shared bug/change." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43823", + "accept": false, + "reason": "Mistral tokenizer helper methods vs adding MobileLLM model support; unrelated changes." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43424", + "accept": false, + "reason": "Tokenizer API additions and an executorch export test are not the same underlying change." + }, + { + "left": "pull_request:42668", + "right": "pull_request:43823", + "accept": false, + "reason": "Processor auto-loading robustness vs new MobileLLM model support; broad overlap in modeling infra but not the same fix." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43823", + "accept": false, + "reason": "Loss-function kwargs bugfix vs MobileLLM model addition; no common code-path problem." + }, + { + "left": "pull_request:43251", + "right": "pull_request:44827", + "accept": false, + "reason": "Both touch different areas of training/testing; the loss-helper fix and Mistral4 test changes are not mergeable as one bug fix." + }, + { + "left": "pull_request:43424", + "right": "pull_request:44827", + "accept": false, + "reason": "Executorch dynamic-shape export test vs Mistral4 test fixes; different concrete issues." + }, + { + "left": "pull_request:43424", + "right": "pull_request:43823", + "accept": false, + "reason": "Executorch exportability test and MobileLLM model addition are unrelated." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45655", + "accept": false, + "reason": "Adding MobileLLM vs config-resolution ordering fix; no shared underlying defect." + }, + { + "left": "pull_request:43823", + "right": "pull_request:43995", + "accept": false, + "reason": "MobileLLM model addition vs Falcon output-collection refactor; different code paths and goals." + }, + { + "left": "pull_request:43995", + "right": "pull_request:44827", + "accept": false, + "reason": "Falcon refactor and Mistral4 test fix are separate model-specific changes." + }, + { + "left": "pull_request:43995", + "right": "pull_request:45213", + "accept": false, + "reason": "Falcon model refactor vs model-creation skill/docs PR; unrelated." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45170", + "accept": false, + "reason": "Mistral4 test fixes vs CLIP-family weight-renaming cleanup; different model families and bugs." + }, + { + "left": "pull_request:44827", + "right": "pull_request:46048", + "accept": false, + "reason": "Mistral4 tests vs TDT loss kernel integration; unrelated functionality." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45655", + "accept": false, + "reason": "Mistral4 test fixes and config-resolution ordering fix are not the same code-path issue." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45213", + "accept": false, + "reason": "A model test fix and a model-creation skill/docs PR are clearly unrelated." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45213", + "accept": false, + "reason": "New MobileLLM model code vs a model-creation skill/draft PR; not the same underlying change." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43254", + "accept": true, + "reason": "Both modify `src/transformers/loss/loss_utils.py` to pass extra `cross_entropy` kwargs and address the same `fixed_cross_entropy` bug, so they could plausibly be merged into one PR." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The evaluation is grounded in the packet and stays conservative. The only clearly mergeable duplicate pair is PR #43251/#43254: both edit `src/transformers/loss/loss_utils.py`, both target issue 43240, and both implement the same `fixed_cross_entropy` kwargs bugfix. The remaining pairs are reasonably judged unrelated despite superficial topic overlap." + }, + "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": "aec7bfddbca0e814bbf51260271bc4632f757cf152f6ab510e7e6ca051c78664", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 7225, + "estimated_input_tokens": 1807, + "estimated_eval_tokens": 3870 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 7225, + "estimated_input_tokens": 1807, + "estimated_eval_tokens": 3870 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs work on VibeVoice, but they are not the same change: #40546 is the core VibeVoice implementation, while #42781 is a draft for VibeVoice Realtime plus the acoustic tokenizer and additional generation/feature-extraction plumbing. They overlap in shared model files, but the concrete scope differs enough that they should not be merged as duplicates.", + "confidence": 0.9, + "canonical_issue_reason": null, + "canonical_pr_reason": "#40546 is the best canonical PR because it is the original, non-draft VibeVoice implementation and provides the core model/docs/auto-registry changes that the later work builds on.", + "best_issue_reason": null, + "best_pr_reason": "#40546 is the better global representative: it is broader, more complete, and non-draft, whereas #42781 is a narrower realtime follow-up with extra tokenizer and generation changes.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40546", + "right": "pull_request:42781", + "accept": false, + "reason": "Shared VibeVoice files alone are not enough: #40546 implements the base model, while #42781 adds realtime support and an acoustic tokenizer, so they target different concrete functionality and could not be cleanly merged 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": 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": "40dfb802ec76acaff4be9386ef635883d9cd98a1573a0add6f664ec8c9dd3dad", + "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: TimesFM covariate forecasting versus DINOv3 image-classification support. They do not appear to fix the same bug or implement the same change, so this cluster should not be merged.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: the PRs target different model families, different code paths, and different user-facing features.", + "best_issue_reason": null, + "best_pr_reason": "PR #41224 is the more self-contained and better-reviewed change, but it is not a duplicate of #40755.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40755", + "right": "pull_request:41224", + "accept": false, + "reason": "Different features in different subsystems: TimesFM covariate forecasting versus DINOv3 image classification. They do not share the same underlying bug or change and could not plausibly be merged into one PR." + } + ] + }, + "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": "890774250e31b9e74bcfb49a34e99daa4d87826b1a46009ed9015f796742dc1a", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 10436, + "estimated_input_tokens": 2609, + "estimated_eval_tokens": 5474 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 10436, + "estimated_input_tokens": 2609, + "estimated_eval_tokens": 5474 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are three separate model-addition PRs for different architectures (DeepSeek OCR, Isaac, and Kimi2-6). They share repository scaffolding, but not the same model or concrete code-path change, so they should not be merged as duplicates.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: each PR adds a different model family and touches distinct model implementations, configs, and tests.", + "best_issue_reason": null, + "best_pr_reason": "PR 45630 is the strongest standalone candidate by activity and breadth, but it is still not a duplicate of the others.", + "soft_edge_verdicts": [ + { + "left": "pull_request:41797", + "right": "pull_request:45186", + "accept": false, + "reason": "Different additions: DeepSeek OCR vs Isaac. Shared auto-registry/docs scaffolding is expected for new-model PRs, but the model code, files, and purpose are unrelated." + }, + { + "left": "pull_request:45186", + "right": "pull_request:45630", + "accept": false, + "reason": "Different model families: Isaac vs Kimi2-6. Overlap is limited to generic framework registration and docs; they do not fix the same code-path problem." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 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": "f32dc76a2fc3cf1effd70d8a7abde57d60dafea87f8690eaf059b22edd1f3e23", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5935, + "estimated_input_tokens": 1484, + "estimated_eval_tokens": 3224 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5935, + "estimated_input_tokens": 1484, + "estimated_eval_tokens": 3224 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two open PRs that both update GitHub Actions versions, but they target different action families and different workflow sets. They overlap only at a broad maintenance level, not the same concrete change.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": "PR 42975 is the more representative GitHub Actions maintenance PR because its scope is clearly centered on Node 24-compatible core actions across many workflows, while 42976 is a separate update focused mainly on docker/build-push-action and other latest-version bumps.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42975", + "right": "pull_request:42976", + "accept": false, + "reason": "Reject: both are workflow dependency upgrades, but they touch different actions and different code paths (core workflow actions vs docker build actions). The overlap is too broad to treat as 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": 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-42978-5", + "nodes": [ + "pull_request:42978", + "pull_request:43448", + "pull_request:43451", + "pull_request:45490", + "pull_request:46162" + ], + "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:45490|pull_request:46162" + ], + "prepared_review_unit_hash": "f3ef85915c8a699c1f27337dcab06a0b20115d7c7688e00a857e071d47ce971e", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 7, + "serialized_chars": 16553, + "estimated_input_tokens": 4139, + "estimated_eval_tokens": 8534 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 7, + "serialized_chars": 16553, + "estimated_input_tokens": 4139, + "estimated_eval_tokens": 8534 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is heterogeneous: four independent model-addition PRs (ViT NEPA, Molmo, Molmo2, CTSM) plus one small test-only XPU expectation PR. They target different models and code paths, so there is no duplicate/canonical change here.", + "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:42978", + "right": "pull_request:43448", + "accept": false, + "reason": "Different model integrations: ViT NEPA vs Molmo. Shared docs/auto-registration files are expected for new-model PRs and do not indicate the same underlying change." + }, + { + "left": "pull_request:42978", + "right": "pull_request:43451", + "accept": false, + "reason": "Different model additions: ViT NEPA vs Molmo2. The overlap is only in generic registration/docs files, not a shared bug or code-path fix." + }, + { + "left": "pull_request:42978", + "right": "pull_request:45490", + "accept": false, + "reason": "ViT NEPA and CTSM are unrelated model implementations. Similar auto/docs updates are boilerplate for adding a model, not duplicate work." + }, + { + "left": "pull_request:43448", + "right": "pull_request:43451", + "accept": false, + "reason": "Molmo and Molmo2 are separate model families with distinct files and functionality. They are not the same concrete feature or fix." + }, + { + "left": "pull_request:43448", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo vs CTSM are unrelated model additions; shared framework registration files are too broad to merge as duplicates." + }, + { + "left": "pull_request:43451", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo2 and CTSM implement different models and code paths. This is not the same underlying change despite similar integration patterns." + }, + { + "left": "pull_request:45490", + "right": "pull_request:46162", + "accept": false, + "reason": "CTSM is a model-addition PR, while 46162 is a narrow test-only change adding XPU expectations. Different scope and code path, so 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": 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-43291-4", + "nodes": [ + "pull_request:43291", + "pull_request:43665", + "pull_request:44815", + "pull_request:46102" + ], + "soft_pairs": [ + "pull_request:43291|pull_request:43665", + "pull_request:43291|pull_request:44815", + "pull_request:43665|pull_request:46102", + "pull_request:43665|pull_request:44815" + ], + "prepared_review_unit_hash": "fa2328e4fdf4fd6d7845b67a52189f5928e7386b7763836d3bfaaf8ab88b51fd", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 4, + "serialized_chars": 9390, + "estimated_input_tokens": 2348, + "estimated_eval_tokens": 4952 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 4, + "serialized_chars": 9390, + "estimated_input_tokens": 2348, + "estimated_eval_tokens": 4952 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are not duplicates: they cover unrelated areas (Whisper decoding/tests, CLIP/ViT test placeholders, FP8 dequantization, and FSDP tied-weights). The one soft-similarity edge is not strong enough to merge into a single change.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44815 is the strongest standalone candidate: it has a coherent code-path fix in model loading / FP8 quantization with supporting tests. The others are either test-only or address different subsystems.", + "best_issue_reason": null, + "best_pr_reason": "PR 44815 is the best representative of the cluster because it is an actual functional fix rather than a test-only edit, and it has the clearest end-to-end bug/fix relationship.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43291", + "right": "pull_request:43665", + "accept": false, + "reason": "Both are test-related, but they target different models and different changes (Whisper tokenizer behavior vs. CLIP/ViT test edits). Not the same underlying bug or mergeable into one PR." + }, + { + "left": "pull_request:43291", + "right": "pull_request:44815", + "accept": false, + "reason": "Whisper decoding/tokenization changes are unrelated to FP8 dequantization and model loading logic." + }, + { + "left": "pull_request:43665", + "right": "pull_request:46102", + "accept": false, + "reason": "CLIP/ViT test placeholders are unrelated to the FSDP tied-weights fix; they do not share a concrete code-path problem." + }, + { + "left": "pull_request:43665", + "right": "pull_request:44815", + "accept": false, + "reason": "Despite superficial similarity as fixes, one is only test edits while the other is a quantization/model-loading bug fix; not the same change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 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-43488-5", + "nodes": [ + "pull_request:43488", + "pull_request:43532", + "pull_request:45932", + "pull_request:46100", + "pull_request:46114" + ], + "soft_pairs": [ + "pull_request:43488|pull_request:46114", + "pull_request:43488|pull_request:43532", + "pull_request:43532|pull_request:46114", + "pull_request:45932|pull_request:46100", + "pull_request:46100|pull_request:46114" + ], + "prepared_review_unit_hash": "3a40b3ef80670fd1722af77b2fea6ae70a362aeb7c8b30aa851aab8de93b1361", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 5, + "serialized_chars": 11339, + "estimated_input_tokens": 2835, + "estimated_eval_tokens": 5926 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 5, + "serialized_chars": 11339, + "estimated_input_tokens": 2835, + "estimated_eval_tokens": 5926 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Only the two ViT test-migration PRs are true duplicates; the other soft links are superficial filename overlaps or unrelated CI/test scaffolding changes.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #46100 is the cleanest representative of the duplicated ViT test-migration change; #46114 appears to be the forked copy with the same patch.", + "best_issue_reason": null, + "best_pr_reason": "PR #46100 is the best global PR candidate because it is the canonical version of the only real duplicate pair and has the clearest title for the shared change.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43488", + "right": "pull_request:46114", + "accept": false, + "reason": "Both touch tests/models/vit/test_modeling_vit.py, but #43488 is a repo-bot/version/dependency stub and #46114 is a test-migration/OTEL PR; they are not the same underlying change." + }, + { + "left": "pull_request:43488", + "right": "pull_request:43532", + "accept": false, + "reason": "Shared ViT test file is incidental; #43488 is setup/version/dependency plumbing while #43532 is workflow/notification/testing-utils changes. Different PR goals and code paths." + }, + { + "left": "pull_request:43532", + "right": "pull_request:46114", + "accept": false, + "reason": "Both mention ViT tests only tangentially; #43532 centers on CI workflows and utilities, while #46114 is a forked test-migration PR. Not the same fix/change." + }, + { + "left": "pull_request:45932", + "right": "pull_request:46100", + "accept": false, + "reason": "Despite the similarity signal, #45932 is a broad Grafana/testing/integration PR across many models and workflows, while #46100 is a tiny ViT test assertion change. Not mergeable as one PR." + }, + { + "left": "pull_request:46100", + "right": "pull_request:46114", + "accept": true, + "reason": "These are effectively identical: same file, same added failing assertions, and the titles indicate the same test-migration intent. They look like forked duplicates of one underlying change." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The duplicate judgement for 46100/46114 is grounded by the identical diff preview and titles. The other soft-edge rejections are conservative and supported by the packet: they share at most a filename or broad testing/CI context, but not the same underlying bugfix or a mergeable single PR change. The summary stays within the evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "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": "b52d527be0d0325bb742fec92c54ab31c42561426b3e40306685bf584ea3ca7a", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6083, + "estimated_input_tokens": 1521, + "estimated_eval_tokens": 3298 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6083, + "estimated_input_tokens": 1521, + "estimated_eval_tokens": 3298 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two separate feature PRs: one adds Promptable Concept Segmentation, the other adds Promptable Visual Segmentation. They share framework/docs scaffolding but target different pipelines, models, and tests, so they are not duplicates.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single canonical PR for a duplicate set here; these are distinct pipeline additions rather than two implementations of the same change.", + "best_issue_reason": null, + "best_pr_reason": "If a representative is needed, #43613 is slightly broader/more integrated, but it is still a separate feature from #43612 rather than a duplicate counterpart.", + "soft_edge_verdicts": [ + { + "left": "Add Promptable Concept Segmentation pipeline", + "right": "Add Promptable Visual Segmentation pipeline", + "accept": false, + "reason": "Different underlying tasks and code paths: concept segmentation vs visual segmentation use different model integrations and tests, so shared docs/pipeline plumbing does not make them the same change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 11, + "component_count": 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": "7e149a7f484b9678838fb92c4c141f85dd32c0c30dc4ec4083a4cf7df4dd60ef", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4293, + "estimated_input_tokens": 1074, + "estimated_eval_tokens": 2404 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4293, + "estimated_input_tokens": 1074, + "estimated_eval_tokens": 2404 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two open PRs touch `trainer.py` and both add override points for custom trainers, but they address different behaviors: gradient-accumulation loss scaling vs. signature-column filtering. They are not the same underlying change.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: PR #43651 changes training loss scaling logic, while PR #43663 changes dataloader column filtering/signature inspection; they are unrelated extension points.", + "best_issue_reason": null, + "best_pr_reason": "PR #43651 is the more self-contained trainer behavior change, but the cluster does not have a single best representative because the PRs solve different problems.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43651", + "right": "pull_request:43663", + "accept": false, + "reason": "Different code paths and goals: #43651 adds `_loss_is_scaled_for_ga` for gradient accumulation loss normalization, while #43663 adds `_get_signature_columns` for column filtering. Same file, but not the same 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": 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-43656-2", + "nodes": [ + "pull_request:43656", + "pull_request:43842" + ], + "soft_pairs": [ + "pull_request:43656|pull_request:43842" + ], + "prepared_review_unit_hash": "07657b337baabeb8089f43a15e3470e19ca7706371ab31be477f23bd9ccb2324", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 3664, + "estimated_input_tokens": 916, + "estimated_eval_tokens": 2088 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 3664, + "estimated_input_tokens": 916, + "estimated_eval_tokens": 2088 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs touch the same CLI file and both mention a TypeAdapter NameError, but they address different fixes: one is broader annotation/postponement cleanup, the other is a targeted pydantic-absent runtime import issue. I would not merge them as duplicates.", + "confidence": 0.83, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #43842 is the more precise fix: it directly addresses the TypeAdapter NameError when pydantic is not installed, with a minimal change in the exact validation path.", + "best_issue_reason": null, + "best_pr_reason": "PR #43842 is the best standalone PR because it targets a concrete runtime failure with a narrow, plausible merge surface and clear dependency-related behavior.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43656", + "right": "pull_request:43842", + "accept": false, + "reason": "They share a file and a loosely related NameError theme, but the fixes are not the same code-path problem: #43656 is broader typing/annotations cleanup, while #43842 specifically handles TypeAdapter when pydantic is absent." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "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:44116", + "pull_request:44068|pull_request:44722", + "pull_request:44018|pull_request:44116", + "pull_request:44071|pull_request:44722", + "pull_request:44018|pull_request:44086", + "pull_request:44018|pull_request:44085", + "pull_request:44068|pull_request:44086", + "pull_request:44071|pull_request:44085", + "pull_request:44059|pull_request:44086", + "pull_request:44085|pull_request:44086", + "pull_request: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:43997|pull_request:44073", + "pull_request:44071|pull_request:44086", + "pull_request:44073|pull_request:44101", + "pull_request:44017|pull_request:44071", + "pull_request:44056|pull_request:44101", + "pull_request:44059|pull_request:44071", + "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:44010|pull_request:44073", + "pull_request:44018|pull_request:44129", + "pull_request:43997|pull_request:44074", + "pull_request:44071|pull_request:44129", + "pull_request:43997|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": "1674e09279a5d1448f9588266b336f51a49ca32e467ce8b2c3ac64291350709e", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 78, + "serialized_chars": 84893, + "estimated_input_tokens": 21224, + "estimated_eval_tokens": 42704 + }, + "budget": { + "node_count": 27, + "item_count": 27, + "soft_pair_count": 72, + "serialized_chars": 75089, + "estimated_input_tokens": 18773, + "estimated_eval_tokens": 37802 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a theme cluster of output-tracing refactors across many unrelated models, not one single duplicate chain. Only the same-model GPT-Neo and GPT-J pairs look like true overlaps; the rest are separate model-specific refactors that should stay distinct.", + "confidence": 0.83, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical issue is present. As a representative PR, 44066 is the strongest anchor because it has an explicit issue link, covers the core GPT-J/CodeGen output-tracing refactor, and overlaps with later GPT-J follow-ups.", + "best_issue_reason": null, + "best_pr_reason": "44066 is the best representative for the cluster\u2019s central refactor theme: it is broad, explicit about the tracking issue, and closest to the repeated GPT-J/CodeGen duplicate stream.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43996", + "right": "pull_request:44085", + "accept": false, + "reason": "Different model families (FNet/CVT vs GPT-J) with only a shared refactor theme." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44044", + "accept": false, + "reason": "Different model families and different code paths; same broad output-tracing motif is not enough." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44085", + "accept": true, + "reason": "Both target GPT-J output tracing in the same code path and are plausibly mergeable into one PR." + }, + { + "left": "pull_request:44007", + "right": "pull_request:44072", + "accept": false, + "reason": "ResNet/RT-DETR ResNet vs EfficientNet are separate model implementations, not the same change." + }, + { + "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 vs EfficientNet are different models and different fixes." + }, + { + "left": "pull_request:44013", + "right": "pull_request:44044", + "accept": false, + "reason": "MobileNetV2 vs DeBERTa-V2 are unrelated model-specific refactors." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J/CodeGen vs MGP-STR are unrelated implementations." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-J/CodeGen and MPT are different model code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44068", + "accept": true, + "reason": "Both refactor GPT-Neo output tracing in the same file and appear to be the same underlying change." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44068", + "accept": false, + "reason": "GPT-J/CodeGen and GPT-Neo are different model families." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44066", + "accept": false, + "reason": "GPT-Neo and GPT-J/CodeGen are separate model implementations." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44722", + "accept": false, + "reason": "ResNet vs GPT-J/CodeGen are unrelated." + }, + { + "left": "pull_request:44086", + "right": "pull_request:44722", + "accept": false, + "reason": "MGP-STR vs GPT-J/CodeGen are unrelated model changes." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44085", + "accept": false, + "reason": "ResNet and GPT-J are different code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44019", + "accept": false, + "reason": "GPT-Neo and ResNet are different models; shared refactor pattern is not duplicate evidence." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44071", + "accept": false, + "reason": "ResNet vs MPT are unrelated model-specific changes." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo and Flaubert are unrelated implementations." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT-Neo vs GPT-J/CodeGen are different model families." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo and Flaubert are unrelated code paths." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44722", + "accept": false, + "reason": "MPT and GPT-J/CodeGen are different models." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo vs MGP-STR are unrelated model changes." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44085", + "accept": false, + "reason": "GPT-Neo vs GPT-J are different code paths." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo vs MGP-STR are unrelated." + }, + { + "left": "pull_request:44098", + "right": "pull_request:44101", + "accept": false, + "reason": "ViLT and XLM are distinct model families." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT-2 and GPT-J/CodeGen are separate implementations." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-Neo and MPT are different models." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44722", + "accept": false, + "reason": "SegFormer and GPT-J/CodeGen are unrelated." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44161", + "accept": false, + "reason": "SegFormer and LongT5 are unrelated model-specific refactors." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44073", + "accept": false, + "reason": "SegFormer and VisualBERT are different code paths." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-Neo and MPT are different models." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44073", + "accept": false, + "reason": "RegNet and VisualBERT are unrelated." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44076", + "accept": false, + "reason": "MPT and ImageGPT are separate model implementations." + }, + { + "left": "pull_request:44074", + "right": "pull_request:44101", + "accept": false, + "reason": "TextNet and XLM are unrelated models." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44161", + "accept": false, + "reason": "MPNet and LongT5 are unrelated code paths." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44018", + "accept": false, + "reason": "RegNet and GPT-Neo are different model families." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44161", + "accept": false, + "reason": "RegNet and LongT5 are unrelated." + }, + { + "left": "pull_request:44074", + "right": "pull_request:44161", + "accept": false, + "reason": "TextNet and LongT5 are unrelated model changes." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44161", + "accept": false, + "reason": "GPT-Neo and LongT5 are unrelated." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44071", + "accept": false, + "reason": "RegNet and MPT are different code paths." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44071", + "accept": false, + "reason": "SqueezeBERT and MPT are unrelated models." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44073", + "accept": false, + "reason": "SqueezeBERT and VisualBERT are separate implementations." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44129", + "accept": false, + "reason": "GPT-Neo and SpeechT5 are unrelated model-specific refactors." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44161", + "accept": false, + "reason": "MPNet and LongT5 are unrelated." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44018", + "accept": false, + "reason": "RegNet and GPT-Neo are different model families." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44161", + "accept": false, + "reason": "RegNet and LongT5 are unrelated." + }, + { + "left": "pull_request:44074", + "right": "pull_request:44161", + "accept": false, + "reason": "TextNet and LongT5 do not share the same code-path change." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44161", + "accept": false, + "reason": "GPT-Neo and LongT5 are unrelated model changes." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44071", + "accept": false, + "reason": "RegNet and MPT are unrelated." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44071", + "accept": false, + "reason": "SqueezeBERT and MPT are different models." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44073", + "accept": false, + "reason": "SqueezeBERT and VisualBERT are unrelated." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44044", + "accept": false, + "reason": "SqueezeBERT and DeBERTa-V2 are unrelated." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44074", + "accept": false, + "reason": "DeBERTa-V2 and TextNet are different model implementations." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44722", + "accept": true, + "reason": "Same GPT-J output-tracing refactor on the same concrete code path; these could plausibly be one PR." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44722", + "accept": true, + "reason": "Both touch GPT-J output tracing in the same file and look like overlapping refactor variants." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44129", + "accept": false, + "reason": "GPT-J vs SpeechT5 are unrelated model code paths." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44007", + "accept": false, + "reason": "FNet/CVT and RegNet/ResNet are different models; same architectural theme is insufficient." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44129", + "accept": false, + "reason": "FNet/CVT and SpeechT5 are unrelated." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44129", + "accept": false, + "reason": "DeBERTa-V2 and SpeechT5 are unrelated model-specific changes." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44154", + "accept": false, + "reason": "DeBERTa-V2 and VITS are different code paths and model families." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The evaluation is grounded in the packet and stays conservative on soft-edge calls. The accepted pairs are plausible same-code-path overlaps (GPT-Neo and GPT-J/CodeGen), and the rejected pairs correctly separate different model families and unrelated fixes. The canonical/representative PR choice is also reasonable given the explicit issue link and breadth of 44066." + }, + "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": "136ed919d772830ba6c128a5b872bfc04b3dca0a8fc1df190421eb966601441d", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 78, + "serialized_chars": 84893, + "estimated_input_tokens": 21224, + "estimated_eval_tokens": 42704 + }, + "budget": { + "node_count": 8, + "item_count": 8, + "soft_pair_count": 6, + "serialized_chars": 17125, + "estimated_input_tokens": 4282, + "estimated_eval_tokens": 8820 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These PRs all refactor model-specific output tracing toward the same library-wide decorator pattern, but they are separate per-model changes and not true duplicates of one another.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single PR is the obvious duplicate canonical: each PR targets a different model file and code path. If one representative must be chosen, PR 44129 is the strongest anchor because it has an explicit issue target and a concrete SpeechT5 refactor.", + "best_issue_reason": null, + "best_pr_reason": "PR 44129 is the best representative because it is the most concretely scoped, has an explicit linked issue, and clearly describes the standardized output capture refactor for one model.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44024", + "right": "pull_request:44076", + "accept": false, + "reason": "Same broad migration theme, but FocalNet and ImageGPT are different model implementations with separate forward paths; not the same underlying change." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44074", + "accept": false, + "reason": "Both are output-tracing refactors, but they touch different models (VisualBert vs TextNet) and distinct code paths, so they are not mergeable as one PR." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44073", + "accept": false, + "reason": "MPNet and VisualBert are unrelated model-specific refactors; shared decorator usage alone is too broad to treat as the same change." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44074", + "accept": false, + "reason": "Different models and different forward/tracing implementations; this is the same migration pattern, not the same bug or fix." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44010", + "accept": false, + "reason": "RegNet and SqueezeBert changes are model-specific output-tracing migrations, not the same concrete code-path problem." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44129", + "accept": false, + "reason": "SqueezeBert and SpeechT5 affect different architectures and output flows; they share a refactor goal but not a single duplicate fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 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-43998-14", + "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", + "pull_request:46106" + ], + "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", + "pull_request:44027|pull_request:46106", + "pull_request:44026|pull_request:46106", + "pull_request:44001|pull_request:46106", + "pull_request:44002|pull_request:46106", + "pull_request:43998|pull_request:46106" + ], + "prepared_review_unit_hash": "8b96f7a3020a11410d6ab5619e79c193b8a56cdbf2e84b0cb7d2a2d1309733e2", + "component_budget": { + "node_count": 14, + "item_count": 14, + "soft_pair_count": 45, + "serialized_chars": 43771, + "estimated_input_tokens": 10943, + "estimated_eval_tokens": 22142 + }, + "budget": { + "node_count": 14, + "item_count": 14, + "soft_pair_count": 45, + "serialized_chars": 43771, + "estimated_input_tokens": 10943, + "estimated_eval_tokens": 22142 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This is a loose similarity cluster of parallel \"refactor output tracing\" PRs across different model implementations, plus one unrelated docs toctree edit. They share a pattern and vocabulary, but not the same concrete change or code path, so there is no true duplicate PR set here.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single canonical PR: the PRs are independent, model-specific output-tracing refactors rather than duplicate fixes for one shared code path.", + "best_issue_reason": null, + "best_pr_reason": "44003 is the broadest representative of the pattern, but it still only covers Mamba/Falcon-Mamba and is not a mergeable duplicate of the other PRs.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43998", + "right": "pull_request:44002", + "accept": false, + "reason": "Same refactor theme, but different model files and code paths; not the same underlying change." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44000", + "accept": false, + "reason": "Both are output-tracing refactors, but they target unrelated model implementations." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44001", + "accept": false, + "reason": "Different models with separate forward paths; too broad a similarity to count as a duplicate." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44003", + "accept": false, + "reason": "Timm backbone vs Mamba/Falcon-Mamba are unrelated code paths, so these are not mergeable as one PR." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44029", + "accept": false, + "reason": "Same naming pattern, but separate model code and different behavior; not a duplicate fix." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44001", + "accept": false, + "reason": "MobileNetV1 and UnivNet are unrelated model implementations; this is only a shared refactor style." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44002", + "accept": false, + "reason": "They both modernize output handling, but in different models with different forward logic." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44025", + "accept": false, + "reason": "Different model families and files; not the same concrete bug or change." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44026", + "accept": false, + "reason": "Same broad output-tracing cleanup, but the code paths are distinct encoder-decoder vs MobileNetV1." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44027", + "accept": false, + "reason": "These touch unrelated models; similarity is only at the refactor pattern level." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44001", + "accept": false, + "reason": "Vision-text dual encoder and UnivNet are separate implementations; not one shared fix." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44002", + "accept": false, + "reason": "Same refactor theme, but different model classes and output paths." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44003", + "accept": false, + "reason": "Different subsystems and model families; not plausibly merged into one PR." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44025", + "accept": false, + "reason": "Both are output-tracing refactors, but for unrelated model code paths." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44002", + "accept": false, + "reason": "UnivNet and UperNet are unrelated models; only the refactor pattern matches." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44003", + "accept": false, + "reason": "Different model stacks and forward implementations; not a duplicate." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44025", + "accept": false, + "reason": "These are separate model-specific refactors, not the same underlying change." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44029", + "accept": false, + "reason": "UperNet and RWKV are unrelated code paths; similarity is only conceptual." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44003", + "accept": false, + "reason": "Different model families and files; not the same fix." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44028", + "accept": false, + "reason": "Mamba/Falcon-Mamba and SuperPoint are unrelated code paths, so this is not a duplicate." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44004", + "accept": false, + "reason": "Both refactor outputs, but CodeGen and Mamba address different model internals and cannot be one PR." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44004", + "accept": false, + "reason": "Timm backbone and CodeGen are unrelated models; not the same concrete change." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44004", + "accept": false, + "reason": "UnivNet and CodeGen have different forward logic and output semantics." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44004", + "accept": false, + "reason": "UperNet segmentation and CodeGen are unrelated implementations; not a duplicate." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44004", + "accept": false, + "reason": "Vision-text dual encoder and CodeGen are separate code paths; only the refactor style is shared." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44026", + "accept": false, + "reason": "Depth Anything and Vision-Encoder-Decoder are different model families; same theme, different change." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44027", + "accept": false, + "reason": "Different encoder-decoder models with distinct forward paths; not mergeable as one fix." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44028", + "accept": false, + "reason": "Depth Anything and SuperPoint are unrelated model implementations." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44029", + "accept": false, + "reason": "Different models and output structures; only the refactor motif matches." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44030", + "accept": false, + "reason": "Depth Anything and DPR are separate code paths, so this is not a duplicate PR." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44029", + "accept": false, + "reason": "Vision-Encoder-Decoder and RWKV are unrelated models; not the same underlying change." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44027", + "accept": false, + "reason": "Both are model refactors, but for different encoder-decoder stacks and code paths." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44028", + "accept": false, + "reason": "Different model families and forward methods; not a duplicate." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44030", + "accept": false, + "reason": "Vision-Encoder-Decoder and DPR do not share the same code path or fix." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44028", + "accept": false, + "reason": "Speech-Encoder-Decoder and SuperPoint are unrelated implementations; similarity is only superficial." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44029", + "accept": false, + "reason": "Different model stacks; not the same concrete bug or change." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44030", + "accept": false, + "reason": "Speech-Encoder-Decoder and DPR are separate code paths, so not a duplicate." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44029", + "accept": false, + "reason": "SuperPoint and RWKV are unrelated models; this is only a shared refactor pattern." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44030", + "accept": false, + "reason": "Different model domains and forward logic; not mergeable as one PR." + }, + { + "left": "pull_request:44029", + "right": "pull_request:44030", + "accept": false, + "reason": "RWKV and DPR are distinct model implementations, not the same underlying fix." + }, + { + "left": "pull_request:44027", + "right": "pull_request:46106", + "accept": false, + "reason": "Model output-tracing refactor vs docs toctree edit; completely different change." + }, + { + "left": "pull_request:44026", + "right": "pull_request:46106", + "accept": false, + "reason": "A docs navigation tweak is unrelated to encoder-decoder output tracing." + }, + { + "left": "pull_request:44001", + "right": "pull_request:46106", + "accept": false, + "reason": "UnivNet model refactor and docs toctree change are unrelated." + }, + { + "left": "pull_request:44002", + "right": "pull_request:46106", + "accept": false, + "reason": "UperNet output tracing and docs navigation changes are not the same issue." + }, + { + "left": "pull_request:43998", + "right": "pull_request:46106", + "accept": false, + "reason": "Timm backbone refactor vs docs toctree edit; no shared 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": 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": "9ce3da2c82805116caba8aeb7667de2017c21ecf7fa607735fe439e7600f1810", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 10914, + "estimated_input_tokens": 2729, + "estimated_eval_tokens": 5714 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 10914, + "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 pull requests are separate model-onboarding changes for different architectures (PenguinVL, DeepSeek-OCR-2, and Voxtral TTS). They share framework boilerplate and auto-registration updates, but they do not fix the same code-path problem and should not be merged as duplicates.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: these are distinct model-addition PRs for different models, with different configs, model files, processors, and tests.", + "best_issue_reason": null, + "best_pr_reason": "PR #45075 is the strongest representative only in the sense of being the most complete model onboarding patch (includes conversion script, image processing variants, and broad integration work), but it is not a duplicate of the others.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44662", + "right": "pull_request:45401", + "accept": false, + "reason": "Different models and different functionality: PenguinVL implementation vs Voxtral TTS support. Shared auto-registration/docs scaffolding is generic boilerplate, not the same underlying change." + }, + { + "left": "pull_request:44662", + "right": "pull_request:45075", + "accept": false, + "reason": "Both are model additions, but for unrelated models (PenguinVL vs DeepSeek-OCR-2) with different model code, processors, and tests; not the same bug or change." + }, + { + "left": "pull_request:45075", + "right": "pull_request:45401", + "accept": false, + "reason": "DeepSeek-OCR-2 and Voxtral TTS are distinct model ports with different code paths and file sets. Overlap in shared Transformers registry files is expected and not sufficient for duplication." + } + ] + }, + "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": "ddb908bc2c2ad10573767698cff54a4cc09e4bfeab13b0514437cdbbc937f8e1", + "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": "These are related fusion-feature PRs, but they target different layers of the stack: one adds a generic module-fusion API, while the other wires KernelConfig-driven n-to-1 kernel fusion into model loading/integration code. They are not the same underlying change and would not plausibly be merged into one PR as duplicates.", + "confidence": 0.88, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45363 is the broader, more user-facing feature work: it threads KernelConfig-based fusion through loading/integration paths and adds an example, making it the better representative PR for this cluster.", + "best_issue_reason": null, + "best_pr_reason": "PR #45363 is the strongest standalone PR in the cluster because it covers the end-to-end kernel-fusion flow, not just the lower-level fusion primitive.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44979", + "right": "pull_request:45363", + "accept": false, + "reason": "Related fusion infrastructure, but not the same concrete change: #44979 introduces a generic module fusion API, while #45363 implements KernelConfig-based n-to-1 kernel fusion and model integration. Different code paths and different deliverables." + } + ] + }, + "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": "0318b8c1f01b668dbf8de1b6494e3f882a32eee2de79063bfd6c92196d92ff02", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4414, + "estimated_input_tokens": 1104, + "estimated_eval_tokens": 2464 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4414, + "estimated_input_tokens": 1104, + "estimated_eval_tokens": 2464 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both pull requests fix the same concrete Mistral regex patching AttributeError in the same code path, and the later PR 45317 appears to be the more complete version with tests.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45317 is the better canonical PR because it implements the same fix as 45086 and adds test coverage in the same area.", + "best_issue_reason": null, + "best_pr_reason": "PR 45317 is the strongest representative of the cluster since it contains the same code fix plus validation tests.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45086", + "right": "pull_request:45317", + "accept": true, + "reason": "Same underlying bug and same file-level fix: both replace backend_tokenizer.pre_tokenizer access with tokenizer.pre_tokenizer to avoid the AttributeError in _patch_mistral_regex; the later PR adds tests and looks like the merged-into-one version." + } + ] + }, + "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": "a0d32dbf900967b20dd8a2eb632d3209833b81316aed3f16ba8f00e1ef6ea8d1", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6066, + "estimated_input_tokens": 1517, + "estimated_eval_tokens": 3290 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6066, + "estimated_input_tokens": 1517, + "estimated_eval_tokens": 3290 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two related NemotronH pull requests, but they address different changes: one is a conversion/refactor PR for NemotronH-to-GraniteMoeHybrid style mapping, while the other splits NemotronH into dense and sparse model variants with docs/tests updates.", + "confidence": 0.9, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45569 is the better canonical PR because it is the broader, more complete architecture change and includes the user-facing docs/test surface; PR 45115 is a narrower conversion-mapping refactor.", + "best_issue_reason": null, + "best_pr_reason": "PR 45569 best represents the cluster since it introduces the new dense/sparse NemotronH model family and associated documentation, which is the larger end-state change in this set.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45115", + "right": "pull_request:45569", + "accept": false, + "reason": "They share NemotronH files, but the concrete changes differ: 45115 updates checkpoint conversion and internal inheritance/mapping, while 45569 introduces separate dense/sparse model packages, docs, and tests. These are distinct code paths and not the same 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": 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": "b84a21632379376bce376ce6126e669c3411561e3490420576a181c29c99c5c8", + "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 heterogeneous per-layer config support, the other adds heterogeneous modeling/runtime support that consumes that config. They overlap in files and theme, but they are not duplicates of the same change.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45332 is the broader, more end-to-end change: it adds heterogeneous model/runtime support across cache, masking, modeling, and GPT-OSS code paths, building on the config primitives. It is the better representative of the feature cluster.", + "best_issue_reason": null, + "best_pr_reason": "PR #45332 is the stronger anchor for the cluster because it exercises the new heterogeneous config in concrete model execution paths and spans the larger user-facing change set.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45332", + "right": "pull_request:45333", + "accept": false, + "reason": "Related feature work, but not the same underlying change. #45333 introduces per-layer heterogeneous config plumbing; #45332 adds heterogeneous modeling/runtime support that consumes such configs. They touch the same subsystem, but they would not be duplicates or a single fix for one concrete code-path bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 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": "cf1f79e3ab618fd6f9e346372674f383ad58c36bb39b1e0283e58d96130fc486", + "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 target different changes: one is a broad type-checking sweep across many transformer files, while the other adds specific typing helpers/protocols for modeling-related code. They do not look like the same underlying fix.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single canonical PR: 45415 is a broad type-checking cleanup, while 45425 is a focused typing-helper/refactor PR; they are related but not duplicates.", + "best_issue_reason": null, + "best_pr_reason": "45425 is the more self-contained and concrete PR, with a narrower code change centered on new typing protocols and helpers.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45415", + "right": "pull_request:45425", + "accept": false, + "reason": "Both are typing work, but the scopes differ materially: 45415 is a broad mypy/type-checking sweep across many files, whereas 45425 adds targeted typing abstractions and support in modeling_utils/peft. They do not fix the same concrete problem and would not reasonably merge into one duplicate PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 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-45487-4", + "nodes": [ + "pull_request:45487", + "pull_request:46109", + "pull_request:46135", + "pull_request:46151" + ], + "soft_pairs": [ + "pull_request:45487|pull_request:46151", + "pull_request:46109|pull_request:46151", + "pull_request:46135|pull_request:46151" + ], + "prepared_review_unit_hash": "fe9c0b0fd9318120df780bce51a1aa4c2753f406d4fcee51f397fb7b1d11d3cb", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 3, + "serialized_chars": 9912, + "estimated_input_tokens": 2478, + "estimated_eval_tokens": 5212 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 3, + "serialized_chars": 9912, + "estimated_input_tokens": 2478, + "estimated_eval_tokens": 5212 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are four unrelated open PRs: one model-parallel fix for AltCLIP/ChineseCLIP, one distributed trainer test generalization, one Kosmos2.5 XPU integration-test adjustment, and one token-classification pipeline expectation update. The soft similarity is only broad testing/accelerator overlap, not the same underlying change.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "No true canonical duplicate exists in this cluster; PR 46151 is the cleanest representative only because it is the most self-contained test-expectation update, but it does not match the others\u2019 concrete change.", + "best_issue_reason": null, + "best_pr_reason": "PR 46151 is the most focused and understandable single change in the set, but it is not a duplicate of the others and should not be used to merge the cluster.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45487", + "right": "pull_request:46151", + "accept": false, + "reason": "Different targets and bugs: model-parallel token_type_ids/device handling in AltCLIP/ChineseCLIP vs token-classification pipeline test expectations." + }, + { + "left": "pull_request:46109", + "right": "pull_request:46151", + "accept": false, + "reason": "Both touch tests, but one generalizes distributed trainer device assertions while the other adds pipeline token-classification expectations; not the same concrete change." + }, + { + "left": "pull_request:46135", + "right": "pull_request:46151", + "accept": false, + "reason": "Both adjust accelerator-specific test expectations, but for different models and behaviors (Kosmos2.5 integration vs token classification pipeline); not mergeable 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": 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-45513-3", + "nodes": [ + "pull_request:45513", + "pull_request:46084", + "pull_request:46098" + ], + "soft_pairs": [ + "pull_request:45513|pull_request:46084", + "pull_request:46084|pull_request:46098" + ], + "prepared_review_unit_hash": "7e593779429368ea08183ccdd6f6978b31c7cc2b25eb36fa4f337e24e44dfe61", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 7427, + "estimated_input_tokens": 1857, + "estimated_eval_tokens": 3970 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 7427, + "estimated_input_tokens": 1857, + "estimated_eval_tokens": 3970 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The cluster contains two unrelated PRs for cached-forward bugs: one in Qwen/Olmo hybrid attention and one in Mamba2. Only the two Mamba2 PRs appear to target the same underlying seq_len>1 cache bug; the Qwen/Olmo PR is separate.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 46098 is the best representative of the Mamba2 fix: it addresses the seq_len>1 use_cache bug directly, includes regression coverage, and documents the behavior change. PR 46084 is a narrower implementation-only slice of the same underlying fix.", + "best_issue_reason": null, + "best_pr_reason": "PR 46098 is the strongest global representative because its title and diff align most clearly with the full Mamba2 cached-forward bug, while 46084 looks like a partial/smaller patch to the same code path.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45513", + "right": "pull_request:46084", + "accept": false, + "reason": "Different models and different bugs: 45513 is about Qwen3.5/related hybrid cached multi-token forward behavior, while 46084 fixes Mamba2 use_cache when seq_len>1." + }, + { + "left": "pull_request:46084", + "right": "pull_request:46098", + "accept": true, + "reason": "Same underlying Mamba2 cache bug in the same code path (use_cache with seq_len>1); 46098 appears to be a fuller version with docs/tests around the same fix, so they could plausibly be merged into one PR." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: PR 45513 is a separate model family and bug from the Mamba2 fixes, while 46084 and 46098 share the same issue target (46032), filenames, and seq_len>1 use_cache bug. The soft-edge verdicts are conservative enough, and the 46084/46098 pair looks mergeable into a single 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": 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-45548-2", + "nodes": [ + "pull_request:45548", + "pull_request:45662" + ], + "soft_pairs": [ + "pull_request:45548|pull_request:45662" + ], + "prepared_review_unit_hash": "1d670eb6bd04fb8d8cc38bdcbbfa9e16321f3d257ee580ded6ea7fa2547a0921", + "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": "Both PRs concern expert-parallel loading paths, but they target different failure modes and distributed backends: one fixes EP + DeepSpeed ZeRO-3 loading via accelerate launch, the other fixes EP + FSDP2 where experts are overwritten by rank-0 broadcast. Related area, not the same underlying change.", + "confidence": 0.88, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45662 is the more concrete and self-contained fix: it addresses a specific expert-parallel parameter loading corruption path and touches the loader where the bug occurs.", + "best_issue_reason": null, + "best_pr_reason": "PR 45662 is the better representative of the cluster because it fixes the more explicit code-path bug and has a clearer, narrower technical scope than the configuration/property tweak in 45548.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45548", + "right": "pull_request:45662", + "accept": false, + "reason": "They share the EP/distributed-loading theme, but the bugs differ: 45548 is about EP + DeepSpeed ZeRO-3/accelerate config handling, while 45662 is about EP + FSDP2 parameter overwrites during sharded loading. Not the same concrete fix and not safely mergeable 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": 25, + "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": "ead192a85047a3a477fc0df20f2d0255c49773304ee9a686e495f2a787800c14", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4590, + "estimated_input_tokens": 1148, + "estimated_eval_tokens": 2552 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4590, + "estimated_input_tokens": 1148, + "estimated_eval_tokens": 2552 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs target the same captured_info/xdist collision problem, but PR 45645 is the broader, more complete fix: it includes the xdist-safe testing_utils change plus CI workflow updates to preserve and print multiple captured_info files. PR 45639 is a narrower subset of that same change.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45645 is the best canonical PR because it covers the core xdist-safe artifact fix and the downstream CI/reporting changes needed to consume the new per-worker captured_info files.", + "best_issue_reason": null, + "best_pr_reason": "PR 45645 is the strongest representative of the cluster: same underlying bug, same shared testing_utils/test changes, and additional workflow handling that makes the fix complete.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45639", + "right": "pull_request:45645", + "accept": true, + "reason": "They fix the same concrete captured_info xdist collision path; 45645 appears to incorporate 45639\u2019s core testing_utils/test changes and adds CI log aggregation, so they could plausibly be merged 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-46069-4", + "nodes": [ + "pull_request:46069", + "pull_request:46073", + "pull_request:46154", + "pull_request:46196" + ], + "soft_pairs": [ + "pull_request:46069|pull_request:46073", + "pull_request:46069|pull_request:46154", + "pull_request:46069|pull_request:46196", + "pull_request:46073|pull_request:46154", + "pull_request:46073|pull_request:46196", + "pull_request:46154|pull_request:46196" + ], + "prepared_review_unit_hash": "a788a403e1fccb6d7fbe8637de0167202813b8cfcfed3f459c0a402edd9c8e53", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 10496, + "estimated_input_tokens": 2624, + "estimated_eval_tokens": 5504 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 10496, + "estimated_input_tokens": 2624, + "estimated_eval_tokens": 5504 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "All four PRs are about adding SDPA/attention-dispatch support, but each targets a different model family and code path, so they are related theme-wise rather than duplicates.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single canonical duplicate PR: these are separate model-specific implementations (ShieldGemma2, CTRL, T5, SeamlessM4T/v2) rather than one change that could be merged into a single PR.", + "best_issue_reason": null, + "best_pr_reason": "PR 46196 is the best representative of the cluster because it is the most complete model-family update, covering both SeamlessM4T and SeamlessM4T v2 plus tests.", + "soft_edge_verdicts": [ + { + "left": "pull_request:46069", + "right": "pull_request:46073", + "accept": false, + "reason": "Same general SDPA theme, but they modify different model implementations (ShieldGemma2 vs CTRL) and cannot plausibly be merged as one fix." + }, + { + "left": "pull_request:46069", + "right": "pull_request:46154", + "accept": false, + "reason": "Both add attention-dispatch support, but they target unrelated model code paths (ShieldGemma2 vs T5) with different implementation details." + }, + { + "left": "pull_request:46069", + "right": "pull_request:46196", + "accept": false, + "reason": "These are separate model-family changes; ShieldGemma2 image-classification attention dispatch is not the same underlying change as SeamlessM4T/v2 seq2seq attention dispatch." + }, + { + "left": "pull_request:46073", + "right": "pull_request:46154", + "accept": false, + "reason": "CTRL and T5 are different architectures and model files; this is a shared feature theme, not the same concrete bug or change." + }, + { + "left": "pull_request:46073", + "right": "pull_request:46196", + "accept": false, + "reason": "Different model families and code paths; support for CTRL sdpa dispatch is not duplicate work with SeamlessM4T/v2 dispatch support." + }, + { + "left": "pull_request:46154", + "right": "pull_request:46196", + "accept": false, + "reason": "Both are sdpa-dispatch PRs, but they fix distinct model implementations (T5-related vs SeamlessM4T/v2), so they should stay separate." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + } + ] +} diff --git a/snapshots/20260525T180030Z/analysis-runs/hybrid-model-20260525t180030z/manifest.json b/snapshots/20260525T180030Z/analysis-runs/hybrid-model-20260525t180030z/manifest.json new file mode 100644 index 0000000000000000000000000000000000000000..263e20e410d8e8c2fff4f0a771b1f2990a6ae1aa --- /dev/null +++ b/snapshots/20260525T180030Z/analysis-runs/hybrid-model-20260525t180030z/manifest.json @@ -0,0 +1,14 @@ +{ + "analysis_id": "hybrid-model-20260525t180030z", + "artifacts": { + "hybrid": "snapshots/20260525T180030Z/analysis-runs/hybrid-model-20260525t180030z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260525T180030Z/analysis-runs/hybrid-model-20260525t180030z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "model": null, + "published_at": "2026-05-25T18:21:08Z", + "repo": "huggingface/transformers", + "schema_version": 1, + "snapshot_id": "20260525T180030Z", + "variant": "hybrid" +} diff --git a/snapshots/20260525T180030Z/manifest.json b/snapshots/20260525T180030Z/manifest.json index 71500769cd6793161db9aef5bb739c470661815a..237ae23d66f6ee8a6aabb798c0901ea75adf9937 100644 --- a/snapshots/20260525T180030Z/manifest.json +++ b/snapshots/20260525T180030Z/manifest.json @@ -32,6 +32,24 @@ "timeline_events": 1358 }, "extracted_at": "2026-05-25T18:00:30Z", + "published_analysis": { + "canonical_analysis_id": "hybrid-model-20260525t180030z", + "runs": { + "hybrid-model-20260525t180030z": { + "analysis_id": "hybrid-model-20260525t180030z", + "artifacts": { + "hybrid": "snapshots/20260525T180030Z/analysis-runs/hybrid-model-20260525t180030z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260525T180030Z/analysis-runs/hybrid-model-20260525t180030z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "manifest_path": "snapshots/20260525T180030Z/analysis-runs/hybrid-model-20260525t180030z/manifest.json", + "model": null, + "published_at": "2026-05-25T18:21:08Z", + "variant": "hybrid" + } + }, + "schema_version": 1 + }, "repo": "huggingface/transformers", "snapshot_id": "20260525T180030Z", "watermark": {