diff --git a/analysis/current/analysis-report-hybrid.json b/analysis/current/analysis-report-hybrid.json index 99211081567f6240017b8ed8528b7014e1fd37bb..b9c4e3be547ff6fa840830c80ecca31763b592f5 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": "20260510T120026Z", - "generated_at": "2026-05-10T12:08:00Z", + "snapshot_id": "20260510T180022Z", + "generated_at": "2026-05-10T18:06:40Z", "evidence_quality": "full", "llm_enrichment": true, "meta_bugs": [ @@ -1148,6 +1148,204 @@ } ] }, + { + "cluster_id": "cluster-43656-4", + "summary": "Cluster of 1 issues and 3 PRs centered on issue #43824.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 43824, + "canonical_pr_number": 43656, + "issue_numbers": [ + 43824 + ], + "pr_numbers": [ + 43656, + 43836, + 43842 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 43656, + "right_pr_number": 43836, + "code_similarity": 0.36, + "size_similarity": 0.176, + "file_overlap": 1.0, + "area_overlap": 0.051, + "patch_similarity": 0.048, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 30, + 36 + ], + [ + 315, + 323 + ], + [ + 665, + 671 + ], + [ + 931, + 937 + ], + [ + 1843, + 1849 + ], + [ + 1868, + 1874 + ] + ], + "right_ranges": [ + [ + 11, + 18 + ], + [ + 359, + 429 + ], + [ + 584, + 590 + ], + [ + 1892, + 1910 + ], + [ + 1917, + 1923 + ] + ] + } + ] + }, + { + "left_pr_number": 43656, + "right_pr_number": 43842, + "code_similarity": 0.405, + "size_similarity": 0.5, + "file_overlap": 1.0, + "area_overlap": 0.0, + "patch_similarity": 0.036, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 30, + 36 + ], + [ + 315, + 323 + ], + [ + 665, + 671 + ], + [ + 931, + 937 + ], + [ + 1843, + 1849 + ], + [ + 1868, + 1874 + ] + ], + "right_ranges": [ + [ + 54, + 61 + ], + [ + 587, + 593 + ] + ] + } + ] + }, + { + "left_pr_number": 43836, + "right_pr_number": 43842, + "code_similarity": 0.332, + "size_similarity": 0.088, + "file_overlap": 1.0, + "area_overlap": 0.033, + "patch_similarity": 0.017, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 359, + 429 + ], + [ + 584, + 590 + ], + [ + 1892, + 1910 + ], + [ + 1917, + 1923 + ] + ], + "right_ranges": [ + [ + 54, + 61 + ], + [ + 587, + 593 + ] + ] + } + ] + } + ] + }, { "cluster_id": "cluster-43240-3", "summary": "Cluster of 1 issues and 2 PRs centered on issue #43240.", @@ -1422,76 +1620,6 @@ } ] }, - { - "cluster_id": "cluster-43824-3", - "summary": "Cluster of 1 issues and 2 PRs centered on issue #43824.", - "status": "open", - "confidence": 0.75, - "canonical_issue_number": 43824, - "canonical_pr_number": 43836, - "issue_numbers": [ - 43824 - ], - "pr_numbers": [ - 43836, - 43842 - ], - "evidence_types": [ - "closing_reference", - "shared_issue_target" - ], - "pr_comparisons": [ - { - "left_pr_number": 43836, - "right_pr_number": 43842, - "code_similarity": 0.332, - "size_similarity": 0.088, - "file_overlap": 1.0, - "area_overlap": 0.033, - "patch_similarity": 0.017, - "shared_filenames": [ - "src/transformers/cli/serve.py" - ], - "shared_file_areas": [ - { - "filename": "src/transformers/cli/serve.py", - "left_ranges": [ - [ - 11, - 18 - ], - [ - 359, - 429 - ], - [ - 584, - 590 - ], - [ - 1892, - 1910 - ], - [ - 1917, - 1923 - ] - ], - "right_ranges": [ - [ - 54, - 61 - ], - [ - 587, - 593 - ] - ] - } - ] - } - ] - }, { "cluster_id": "cluster-45081-3", "summary": "Cluster of 1 issues and 2 PRs centered on issue #45081.", @@ -1989,6 +2117,16 @@ "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-43656-4", + "canonical_pr_number": 43656, + "duplicate_pr_numbers": [ + 43836, + 43842 + ], + "target_issue_number": 43824, + "reason": "PRs in cluster-43656-4 are treated as duplicates because they converge on issue #43824 with closing_reference, shared_issue_target, soft_similarity evidence." + }, { "cluster_id": "cluster-43698-3", "canonical_pr_number": 43779, @@ -1998,15 +2136,6 @@ "target_issue_number": 43698, "reason": "PRs in cluster-43698-3 are treated as duplicates because they converge on issue #43698 with closing_reference, shared_issue_target evidence." }, - { - "cluster_id": "cluster-43824-3", - "canonical_pr_number": 43836, - "duplicate_pr_numbers": [ - 43842 - ], - "target_issue_number": 43824, - "reason": "PRs in cluster-43824-3 are treated as duplicates because they converge on issue #43824 with closing_reference, shared_issue_target evidence." - }, { "cluster_id": "cluster-43979-11", "canonical_pr_number": 44007, diff --git a/analysis/current/analysis-report-hybrid.llm-reviews.json b/analysis/current/analysis-report-hybrid.llm-reviews.json index b5c6150e84ea28faaa865d6bfa33f9d950698400..f7c419e1d8dcacaa95e7a790530821b095afb83f 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": "20260510T120026Z", - "generated_at": "2026-05-10T12:08:00Z", + "snapshot_id": "20260510T180022Z", + "generated_at": "2026-05-10T18:06:40Z", "model": "gpt-5.4-mini?service_tier=flex", "reviews": [ { @@ -26,7 +26,7 @@ "issue:13244|issue:16618", "issue:15980|issue:16618" ], - "prepared_review_unit_hash": "33c647724a046cb82f8c07e404fdcd3910777b05e8d41a790ff5636a7e5d1424", + "prepared_review_unit_hash": "41162ca8966146067606c22430385a981dd11473ff1460afb248bed227e2be86", "component_budget": { "node_count": 3, "item_count": 3, @@ -48,24 +48,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These issues are not true duplicates. #16618 is a broad model-loading failure, while #15980 is specifically an authentication/error-message bug for private model downloads, and #13244 is about Tapas tokenization behavior versus TensorFlow code. The only plausible cluster anchor is #16618 by breadth, but it is not the same underlying problem as the others.", + "summary": "This cluster is heterogeneous: one tokenization discrepancy issue, one private-model auth/error-message issue, and one generic model-loading failure. None look like true duplicates of each other.", "confidence": 0.96, - "canonical_issue_reason": "#16618 is the broadest and most central-sounding issue in the set, but it still does not actually cover the other reports\u2019 distinct failure modes.", + "canonical_issue_reason": "Issue 16618 is the broadest of the three and the only one centered on model loading, so it is the least specific representative if a single canonical issue is needed.", "canonical_pr_reason": null, - "best_issue_reason": "#16618 is the best representative only because it is the most generic model-loading report; however, it should not be treated as a duplicate of the other two.", + "best_issue_reason": "16618 is the best cluster representative because it is the most general and closest to the apparent model-loading theme, whereas the other two are clearly narrower and unrelated.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:13244", "right": "issue:16618", "accept": false, - "reason": "Tapas tokenization mismatch is a different subsystem and symptom than a generic Bert model-loading failure; no clear shared code-path bug." + "reason": "Tapas tokenization mismatch is a tokenizer/behavior discrepancy, not the same underlying problem as being unable to load bert-base-uncased." }, { "left": "issue:15980", "right": "issue:16618", "accept": false, - "reason": "#15980 is about downloading a private model while logged out and the resulting error message, which is an auth/UX issue, not the same underlying load failure as #16618." + "reason": "Private-model unauthorized download error messaging is a specific auth/UX bug; 16618 is a separate generic model-loading failure." } ] }, @@ -81,7 +81,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 1, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -211,12 +211,12 @@ "issue:45800|issue:45823", "issue:41093|issue:41762" ], - "prepared_review_unit_hash": "86527d6645f7f52158d9fb70f3d41248df1b91bebc892599501571b5c47b9170", + "prepared_review_unit_hash": "ed47ed91a489038469a84da260f8a7bc40a1bb08d7bfa1c422098b31a263305e", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -224,423 +224,435 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 71, - "serialized_chars": 48867, - "estimated_input_tokens": 12217, - "estimated_eval_tokens": 24690 + "serialized_chars": 48871, + "estimated_input_tokens": 12218, + "estimated_eval_tokens": 24692 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is very noisy: most pairs are false positives across unrelated model, runtime, and docs issues. The only clear duplicate family is the DeepSpeed ZeRO-3/Bert index-0-out-of-bounds reports.", - "confidence": 0.61, - "canonical_issue_reason": "Issue 43638 is the clearest representative of the only true duplicate family here: the ZeRO-3/BertModel index-0-out-of-bounds failure. Its wording is broad enough to cover the paired report.", + "summary": "Most items are unrelated model-/docs-specific issues. The only clear duplicate-like pair is the DeepSpeed ZeRO-3 + BERT zero-dimension index error reports. The broadest reusable issue in this cluster is the generic mask/shape-mismatch report.", + "confidence": 0.78, + "canonical_issue_reason": "issue:44805 is the most generic and reusable issue in the set, with a broad error signature that can subsume nearby shape/mask failures.", "canonical_pr_reason": null, - "best_issue_reason": "Best overall representative of the cluster\u2019s only confirmed duplicate subtopic; the rest of the cluster is mostly unrelated or too loosely similar.", + "best_issue_reason": "issue:44805 best serves as the umbrella issue because its title is generic, symptom-focused, and likely to attract the most related duplicates.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44322", "right": "issue:45464", "accept": false, - "reason": "Different Qwen3.5 failures: config attribute missing vs streaming chat/completions issue." + "reason": "Different Qwen3.5 failures: missing config attribute vs streaming chat/completions failure." }, { "left": "issue:45237", "right": "issue:45685", "accept": false, - "reason": "Different MoE/runtime paths and different hardware backends; not the same bug." + "reason": "Different problems: AMD GPU model loading vs MPS histogram kernel failure." }, { "left": "issue:43716", "right": "issue:45237", "accept": false, - "reason": "Mistral-3 dtype mismatch is unrelated to GPT-OSS AMD GPU failure." + "reason": "Different code paths: image preprocessor dtype mismatch vs AMD GPU incompatibility." }, { "left": "issue:43828", "right": "issue:45237", "accept": false, - "reason": "Different models and different dtype/device error paths." + "reason": "Both are dtype/device-related, but they describe different models and failure modes." }, { "left": "issue:45237", "right": "issue:45507", "accept": false, - "reason": "GPU runtime failure vs invalid method call in a different MoE model." + "reason": "Different models and failures: AMD GPU load issue vs invalid method call in GraniteMoEHybrid." }, { "left": "issue:44292", "right": "issue:45237", "accept": false, - "reason": "Different model families and different NVFP4/GPU failure modes." + "reason": "Different Qwen3 NVFP4 runtime error vs AMD GPU support issue." }, { "left": "issue:30277", "right": "issue:35545", "accept": false, - "reason": "DeepSpeed collective mismatch is unrelated to ONNX export." + "reason": "Both are DeepSpeed/model-loading problems, but one is collective mismatch and the other is ONNX export." }, { "left": "issue:35545", "right": "issue:42915", "accept": false, - "reason": "ONNX export error vs FineGrainedFP8 model failure; unrelated." + "reason": "Different model/export failure vs FP8 checkpoint execution failure." }, { "left": "issue:35545", "right": "issue:41720", "accept": false, - "reason": "Different model/export path vs auto device mapping CUDA assert." + "reason": "ONNX export error and auto device-map CUDA assert are unrelated failures." }, { "left": "issue:44509", "right": "issue:44512", "accept": false, - "reason": "Both are docs regressions, but they cover different removed docs topics." + "reason": "Both are v5 docs updates, but they target different removed doc topics and are not the same change." }, { "left": "issue:35545", "right": "issue:36010", "accept": false, - "reason": "Export error vs import error for GenerationMixin; unrelated." + "reason": "ONNX export error vs GenerationMixin import regression are distinct issues." }, { "left": "issue:44805", "right": "issue:45823", "accept": false, - "reason": "Mask/index shape mismatch vs Gemma4 device-mapping mismatch; different bugs." + "reason": "Both mention tensor/device mismatch concepts, but the underlying bugs are different models and different failure modes." }, { "left": "issue:43638", "right": "issue:44805", "accept": false, - "reason": "Both are IndexError-like, but one is ZeRO-3/Bert loading and the other is a mask-shape mismatch." + "reason": "Similar index-style errors, but one is ZeRO-3 BERT loading and the other is a mask/tensor shape mismatch." }, { "left": "issue:43596", "right": "issue:44805", "accept": false, - "reason": "Different failure mode: ZeRO-3 Bert loading vs mask/tensor shape mismatch." + "reason": "Related by index/shape symptoms, but not clearly the same underlying bug." }, { "left": "issue:44805", "right": "issue:45161", "accept": false, - "reason": "Different problems: mask shape mismatch vs GPT-OSS tensor-parallel issue." + "reason": "Mask/tensor shape mismatch and GPT-OSS MoE TP issue are different problems." }, { "left": "issue:44805", "right": "issue:44918", "accept": false, - "reason": "Different models and different SFT/input-embedding failure paths." + "reason": "Different failures: mask shape mismatch vs Qwen3.5 embedding unpacking with TRL." }, { "left": "issue:34634", "right": "issue:35545", "accept": false, - "reason": "BarkProcessor voice_preset issue is unrelated to ModernBERT ONNX export." + "reason": "BarkProcessor voice_preset bug is unrelated to ModernBERT ONNX export." }, { "left": "issue:30277", "right": "issue:43638", "accept": false, - "reason": "Different DeepSpeed symptoms and different models; not the same bug." + "reason": "Both involve DeepSpeed, but collective mismatch is not the same as the ZeRO-3 Bert index error." }, { "left": "issue:43596", "right": "issue:43638", "accept": true, - "reason": "Same ZeRO-3/Bert index-0-out-of-bounds failure with only minor wording differences." + "reason": "Same ZeRO-3/BERT loading index-out-of-bounds failure, just reported with slightly different model wording." }, { "left": "issue:43039", "right": "issue:45161", "accept": false, - "reason": "Liger Kernel cross-entropy call issue vs GPT-OSS tensor-parallel failure; unrelated." + "reason": "Liger Kernel cross-entropy call issue is unrelated to GPT-OSS MoE TP failure." }, { "left": "issue:43975", "right": "issue:44457", "accept": false, - "reason": "Detokenization bug vs LoRA merge/save/load inconsistency; unrelated." + "reason": "Both involve detokenization/LoRA behavior, but they are not the same bug or code path." }, { "left": "issue:44292", "right": "issue:44457", "accept": false, - "reason": "Different model/runtime bug vs LoRA checkpoint consistency issue." + "reason": "Qwen3 NVFP4 runtime failure and LoRA save/reload output mismatch are unrelated." }, { "left": "issue:34928", "right": "issue:44805", "accept": false, - "reason": "FSDP checkpointing size mismatch is not the same as mask-index mismatch." + "reason": "Activation-checkpointing/FSDP tensor-size mismatch differs from the mask/index shape mismatch issue." }, { "left": "issue:24643", "right": "issue:30277", "accept": false, - "reason": "Different DeepSpeed errors and different code paths." + "reason": "Both mention DeepSpeed, but the errors are different: weight dimensionality vs collective mismatch." }, { "left": "issue:43638", "right": "issue:45161", "accept": false, - "reason": "ZeRO-3 Bert loading bug is unrelated to GPT-OSS tensor-parallel failure." + "reason": "ZeRO-3 BERT index error is unrelated to GPT-OSS TP failure." }, { "left": "issue:34928", "right": "issue:36331", "accept": false, - "reason": "Activation-checkpointing size mismatch is unrelated to CustomTrainer signature mismatch." + "reason": "Activation-checkpointing tensor mismatch is unrelated to CustomTrainer compute_loss signature regression." }, { "left": "issue:43596", "right": "issue:45161", "accept": false, - "reason": "Different model/load bug vs GPT-OSS TP issue." + "reason": "Different failure classes: ZeRO-3 BERT index error vs GPT-OSS MoE TP issue." }, { "left": "issue:43716", "right": "issue:45507", "accept": false, - "reason": "Different models and different dtype/method errors." + "reason": "Dtype mismatch in Mistral-3 preprocessing is unrelated to GraniteMoEHybrid invalid method call." }, { "left": "issue:39290", "right": "issue:45081", "accept": false, - "reason": "Gemma3/vLLM config attribute issue is unrelated to Mistral tokenizer regex crash." + "reason": "Gemma3 sliding-window/vLLM config error is unrelated to Mistral tokenizer regex patch crash." }, { "left": "issue:43828", "right": "issue:45161", "accept": false, - "reason": "Different models and different dtype/TP failures." + "reason": "Autocast dtype mismatch and GPT-OSS MoE TP failure are distinct." }, { "left": "issue:44918", "right": "issue:45161", "accept": false, - "reason": "TRL embedding unpacking issue is unrelated to GPT-OSS TP failure." + "reason": "TRL SFT embedding unpacking error is not the same as GPT-OSS MoE TP failure." }, { "left": "issue:34928", "right": "issue:41720", "accept": false, - "reason": "FSDP/activation-checkpointing mismatch is unrelated to CUDA assert on auto device mapping." + "reason": "FSDP checkpointing mismatch and Qwen3 auto device-map CUDA assert are different bugs." }, { "left": "issue:43716", "right": "issue:45685", "accept": false, - "reason": "Different model-specific dtype issue vs MPS histogram op problem." + "reason": "Different models and backends: Mistral-3 dtype mismatch vs MPS histogram op failure." }, { "left": "issue:43541", "right": "issue:43716", "accept": false, - "reason": "Grouped_mm tracing error vs dtype mismatch; not the same bug." + "reason": "Grouped_mm torch dynamo tracing failure is unrelated to image-preprocessor dtype mismatch." }, { "left": "issue:43828", "right": "issue:44292", "accept": false, - "reason": "Different MoE models and different dtype/runtime failures." + "reason": "Both are runtime mismatches, but they involve different models and different root causes." + }, + { + "left": "issue:44292", + "right": "issue:44918", + "accept": false, + "reason": "Qwen3 NVFP4 runtime error and TRL embedding unpacking issue are unrelated." }, { "left": "issue:43039", "right": "issue:44918", "accept": false, - "reason": "Cross-entropy/Liger Kernel issue is unrelated to TRL embedding unpacking." + "reason": "Liger Kernel cross-entropy call issue is not the same as Qwen3.5 embedding unpacking." }, { "left": "issue:41762", "right": "issue:43638", "accept": false, - "reason": "Same broad ZeRO-3 theme, but different model and load path; not clearly the same bug." + "reason": "Both are ZeRO-3 loading failures, but Gemma3 and Bert errors differ in symptom and likely cause." }, { "left": "issue:43827", "right": "issue:44512", "accept": false, - "reason": "Both are docs cleanups for v5, but they reference different removed content." + "reason": "Both are docs regressions after v5 removals, but they cover different removed entry points." }, { "left": "issue:43716", "right": "issue:44560", "accept": false, - "reason": "Different model/runtime issues with no shared code path." + "reason": "Mistral-3 dtype mismatch is unrelated to Qwen3-vl video StopIteration." }, { "left": "issue:43828", "right": "issue:45685", "accept": false, - "reason": "Different models, backends, and error types." + "reason": "Different backends and failures: autocast dtype mismatch vs MPS unsupported histogram on int." }, { "left": "issue:44560", "right": "issue:45685", "accept": false, - "reason": "Qwen3-vl StopIteration is unrelated to MPS histogram Int error." + "reason": "Video StopIteration in Qwen3-vl embedding is unrelated to the MPS histogram issue." }, { "left": "issue:43039", "right": "issue:43828", "accept": false, - "reason": "Different model/runtime issues despite both involving execution failures." + "reason": "Same broad dtype/runtime theme, but different concrete failures and code paths." }, { "left": "issue:30277", "right": "issue:36331", "accept": false, - "reason": "DeepSpeed collective mismatch is unrelated to CustomTrainer compute_loss signature." + "reason": "DeepSpeed collective mismatch and trainer signature regression are unrelated." }, { "left": "issue:34928", "right": "issue:36010", "accept": false, - "reason": "FSDP size mismatch is unrelated to GenerationMixin import failure." + "reason": "FSDP activation checkpointing mismatch is unrelated to GenerationMixin import failure." }, { "left": "issue:43039", "right": "issue:44805", "accept": false, - "reason": "Liger Kernel cross-entropy call issue is not the same as mask-shape IndexError." + "reason": "Liger Kernel cross-entropy use is unrelated to the mask/tensor shape mismatch bug." }, { "left": "issue:43901", "right": "issue:44512", "accept": false, - "reason": "Different docs issues: return_all_scores vs removed run command." + "reason": "Both are docs issues, but one is about pipeline task docs and the other about the run command." }, { "left": "issue:41762", "right": "issue:43596", "accept": false, - "reason": "Both are ZeRO-3/load related, but different models and error contexts." + "reason": "Both mention ZeRO-3, but Gemma3 loading and Bert loading are different concrete failures." }, { "left": "issue:39290", "right": "issue:41720", "accept": false, - "reason": "Gemma3/vLLM config bug is unrelated to Qwen3 device-mapping CUDA assert." + "reason": "Gemma3 sliding-window config error is unrelated to Qwen3 auto device-map CUDA assert." }, { "left": "issue:44841", "right": "issue:45823", "accept": false, - "reason": "Processor failure for Voxtral is unrelated to Gemma4 PLE device mismatch." + "reason": "Processor failure for Voxtral is unrelated to Gemma4 device-mapping mismatch." }, { "left": "issue:43039", "right": "issue:44560", "accept": false, - "reason": "Liger Kernel cross-entropy issue is unrelated to Qwen3-vl StopIteration." + "reason": "Liger Kernel cross-entropy issue and Qwen3-vl video StopIteration are unrelated." }, { "left": "issue:43866", "right": "issue:44863", "accept": false, - "reason": "Corrupted checkpoint vs implementation unable to load checkpoints; different root causes." + "reason": "Checkpoint corruption and NemotronH load failure are different problems." }, { "left": "issue:43854", "right": "issue:43866", "accept": false, - "reason": "Unit-test load failure for GLM-4.7 is unrelated to Ovis2 checkpoint corruption." + "reason": "Unable to load GLM-4.7-Flash in tests is not the same as a corrupted Ovis2 checkpoint." }, { "left": "issue:39290", "right": "issue:43531", "accept": false, - "reason": "Gemma3/vLLM config attribute issue is unrelated to Qwen3-MoE sliding_window bug." + "reason": "Gemma3 config error and Qwen3-MoE sliding_window issue are related only by model family, not the same bug." }, { "left": "issue:41093", "right": "issue:43638", "accept": false, - "reason": "Both are IndexErrors, but one is a mask/tensor shape mismatch and the other is ZeRO-3 Bert loading." + "reason": "Mask/index shape mismatch and ZeRO-3 Bert zero-dimension index error are different concrete failures." }, { "left": "issue:43425", "right": "issue:45070", "accept": false, - "reason": "Torch-version incompatibility vs pydantic PretrainedConfig field regression; unrelated." + "reason": "Torch version incompatibility and pydantic PretrainedConfig field regression are unrelated." }, { "left": "issue:43596", "right": "issue:45800", "accept": false, - "reason": "ZeRO-3 Bert loading bug is unrelated to torch/transformers version incompatibility." + "reason": "ZeRO-3 Bert index error is unrelated to torch/transformers version incompatibility." }, { "left": "issue:43792", "right": "issue:45070", "accept": false, - "reason": "Whisper run failure is unrelated to the pydantic model-field regression." + "reason": "Whisper cannot run and pydantic PretrainedConfig field breakage are unrelated." }, { "left": "issue:45362", "right": "issue:45464", "accept": false, - "reason": "Qwen3.5 chat crash vs streaming inference failure; different behavior and likely different bugs." + "reason": "Qwen3.5 chat crash and streaming inference API failure are different issues." }, { "left": "issue:43404", "right": "issue:43866", "accept": false, - "reason": "Mistral3 lm_head tying bug is unrelated to Ovis2 checkpoint corruption." + "reason": "Mistral3 lm_head tying bug is unrelated to a corrupted checkpoint." }, { - "left": "issue:43828", + "left": "issue:39290", + "right": "issue:45823", + "accept": false, + "reason": "Gemma3 sliding-window/vLLM error is unrelated to Gemma4 device_map mismatch." + }, + { + "left": "issue:45464", "right": "issue:45685", "accept": false, - "reason": "Different models and backends; not the same issue." + "reason": "Qwen3.5 streaming inference failure is unrelated to the MPS histogram op issue." }, { "left": "issue:43541", "right": "issue:45685", "accept": false, - "reason": "Grouped_mm tracing error is unrelated to MPS histogram Int error." + "reason": "Torch dynamo grouped_mm tracing failure is unrelated to the MPS histogram op issue." }, { "left": "issue:43541", "right": "issue:43828", "accept": false, - "reason": "Different MoE runtime failures and different models." + "reason": "Grouped_mm tracing failure and autocast dtype mismatch are different bugs." }, { "left": "issue:36010", "right": "issue:39290", "accept": false, - "reason": "GenerationMixin import failure is unrelated to Gemma3/vLLM config mismatch." + "reason": "GenerationMixin import regression and Gemma3 sliding-window config error are unrelated." }, { "left": "issue:44841", "right": "issue:45084", "accept": false, - "reason": "Processor failure for Voxtral is unrelated to template-node compilation error." + "reason": "Voxtral processor failure is unrelated to the template-node compile error." }, { "left": "issue:45800", "right": "issue:45823", "accept": false, - "reason": "Torch/transformers incompatibility is unrelated to Gemma4 device mismatch." + "reason": "Torch/transformers incompatibility and Gemma4 device mismatch are different problems." }, { "left": "issue:41093", "right": "issue:41762", "accept": false, - "reason": "Both are IndexErrors, but different models and different failure mechanisms." + "reason": "Both are tensor/indexing failures, but they occur in different model-loading paths and are not clearly the same bug." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative overall. The only accepted duplicate pair, issue:43596 \u2194 issue:43638, is well supported by the titles and descriptions. The rest of the soft-edge false verdicts are appropriately cautious. Minor caveat: issue:41762 is adjacent to the ZeRO-3 cluster, but treating it as non-duplicate is a defensible conservative call." + "feedback": "The summary is grounded in the packet and stays conservative overall. The chosen umbrella issue (44805) is generic enough to cover nearby shape/mask failures, and the only accepted soft-edge pair (43596/43638) looks like a plausible duplicate-class match based on nearly identical ZeRO-3/BERT index-error symptoms. I don\u2019t see any overstatement that would require rejection." }, "evaluator_used": true, "retried": false, @@ -653,7 +665,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 2, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -746,12 +758,12 @@ "issue:43828|issue:44928", "issue:43866|issue:44403" ], - "prepared_review_unit_hash": "0efb76dcc62da0164ea19bdb6b27457dcc36aea720855733fbfb3e1518716a4d", + "prepared_review_unit_hash": "8d78853ac7bb20e8ee5fbf85fd7c3ce0b005ca15fb6b22382827a0a496cce806", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -759,231 +771,231 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 34, - "serialized_chars": 37472, - "estimated_input_tokens": 9368, - "estimated_eval_tokens": 18992 + "serialized_chars": 37473, + "estimated_input_tokens": 9369, + "estimated_eval_tokens": 18994 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a set of loosely related Transformers/v5 regression reports, but only the non-persistent-buffer corruption reports form a true duplicate subcluster.", + "summary": "The cluster is mostly heterogeneous, but there is one clear duplicate subgroup around the Transformers 5.x non-persistent-buffer regression, plus a smaller custom-module cache/path collision pair. No PRs are present.", "confidence": 0.84, - "canonical_issue_reason": "issue:43950 is the clearest root report for the only exact duplicate subcluster here: non-persistent buffers being corrupted on `from_pretrained()` in v5, with direct matches in 43644 and 44534.", + "canonical_issue_reason": "Issue 43950 is the best canonical issue: it states the core v5 regression clearly, is broadly phrased, and matches the strongest duplicate subgroup with 43644 and 44534.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43950 is the best anchor issue because it states the regression most precisely and covers the other matching reports.", + "best_issue_reason": "43950 is the strongest representative of the shared bug because it describes the underlying non-persistent-buffer corruption most explicitly and in a way that can absorb the near-duplicate reports.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43296", "right": "issue:43366", "accept": false, - "reason": "Different problems: vLLM/PaddleOCR-VL loading failure versus GGUF gpt-oss architecture support." + "reason": "Different models and failures: PaddleOCR-VL load error vs gpt-oss GGUF support request." }, { "left": "issue:43572", "right": "issue:45070", "accept": false, - "reason": "Both are v5 config regressions, but one is missing `pad_token_idx` and the other is a pydantic `PretrainedConfig` field break; not the same bug." + "reason": "Different regressions: missing StableLmConfig field vs pydantic/PretrainedConfig incompatibility." }, { "left": "issue:44387", "right": "issue:45005", "accept": false, - "reason": "Related to v5 and weights, but one is int4 memory/OOM behavior and the other is tied-weights handling on translation models; different code paths." + "reason": "Different problems: int4 quantization OOM vs tied-weights handling on translation models." }, { "left": "issue:43541", "right": "issue:45161", "accept": false, - "reason": "Different symptoms and model paths: grouped_mm tracing failure versus GPT-OSS MoE tensor-parallel issue." + "reason": "Both involve MoE, but the concrete failures differ: torch dynamo grouped_mm tracing vs TP not working for GPT-OSS." }, { "left": "issue:43828", "right": "issue:45464", "accept": false, - "reason": "One is a torch autocast dtype mismatch, the other is a streaming chat/completions failure on Qwen3.5; not the same bug." + "reason": "Different code paths and symptoms: autocast dtype mismatch vs streaming chat/completions failure." }, { "left": "issue:44291", "right": "issue:45070", "accept": false, - "reason": "Both are v5 breakages, but init-empty-weights argument handling is distinct from the pydantic config-field regression." + "reason": "Different loading bugs: init_empty_weights/_is_hf_initialized TypeError vs pydantic field breakage." }, { "left": "issue:43366", "right": "issue:45464", "accept": false, - "reason": "Unrelated model support/report: gpt-oss GGUF versus Qwen3.5 chat streaming failure." + "reason": "Unrelated: gpt-oss GGUF architecture support vs Qwen3.5 streaming inference failure." }, { "left": "issue:45020", "right": "issue:45800", "accept": false, - "reason": "Broad compatibility issues, but one is remote_code regressions and the other is torch 2.4.1 / transformers 5.8.0 incompatibility; not the same concrete change." + "reason": "Broad version-regression labels, but not the same concrete bug or code path." }, { "left": "issue:43531", "right": "issue:45070", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior is unrelated to the PretrainedConfig/pydantic regression." + "reason": "Different issues: Qwen3-MoE sliding_window behavior vs PretrainedConfig/pydantic breakage." }, { "left": "issue:43541", "right": "issue:44589", "accept": false, - "reason": "Different runtime failures: torch dynamo grouped_mm tracing versus missing Float8 storage object." + "reason": "Different failures: grouped_mm tracing error vs missing Float8 storage object." }, { "left": "issue:41093", "right": "issue:43596", "accept": false, - "reason": "Both are IndexError-style reports, but they concern different tensors, models, and setup conditions." + "reason": "Both are IndexErrors, but in different subsystems and with different shapes/root causes." }, { "left": "issue:43054", "right": "issue:43994", "accept": false, - "reason": "Same model family, but one is a relative-quality complaint and the other is a loading/pipeline correctness report; root cause is not clearly the same." + "reason": "Same model family, but the reports describe different symptoms and do not clearly point to one concrete shared bug." }, { "left": "issue:45542", "right": "issue:45800", "accept": false, - "reason": "TensorBoard-without-TensorFlow backend error is unrelated to a torch/transformers version incompatibility." + "reason": "TensorBoard/TensorFlow backend issue is unrelated to torch/transformers version incompatibility." }, { "left": "issue:43716", "right": "issue:44918", "accept": false, - "reason": "Both mention Qwen-like multimodal models, but one is an image-preprocessor dtype mismatch and the other is a TRL SFT embedding unpacking failure." + "reason": "Different multimodal/training failures: Mistral-3 image-preprocessor dtype mismatch vs Qwen3.5 embedding unpacking in TRL." }, { "left": "issue:44918", "right": "issue:45685", "accept": false, - "reason": "Completely different failures: TRL embedding unpacking versus an MPS histogram kernel not implemented for int." + "reason": "Different model/backend problems: TRL embedding unpacking vs MPS histogram kernel not implemented for Int." }, { "left": "issue:45632", "right": "issue:45698", - "accept": false, - "reason": "Both involve custom code loading, but one is a cache-path collision and the other is loading the wrong custom module after save/load; not clearly the same bug." + "accept": true, + "reason": "Likely the same custom-module loading bug: cache/path collision or wrong module resolution causes from_pretrained to load the wrong code." }, { "left": "issue:43404", "right": "issue:45005", "accept": false, - "reason": "Related to tied weights, but the affected model classes and failure modes differ enough that they are not the same concrete issue." + "reason": "Different tied-weight bugs in different model families and usage scenarios." }, { "left": "issue:43645", "right": "issue:45399", "accept": false, - "reason": "Notebook/custom-model initialization breakage is unrelated to flash-attn2 fallback selection logic." + "reason": "Notebook custom-model initialization vs flash-attn fallback gating are unrelated." }, { "left": "issue:40990", "right": "issue:44960", "accept": false, - "reason": "Different model and symptom: perplexity regression on gpt-oss-20b versus a GLM5 issue." + "reason": "Unrelated model evaluation/perplexity problem vs a GLM5 issue with no matching concrete path." }, { "left": "issue:44530", "right": "issue:45005", "accept": false, - "reason": "PagedAttentionCache linear_attention crash is unrelated to tied-weights handling." + "reason": "PagedAttentionCache linear_attention crash is unrelated to tied-weight translation model issues." }, { "left": "issue:44360", "right": "issue:44512", "accept": false, - "reason": "DSA indexer/ReLU discussion is unrelated to docs mentioning the removed run command." + "reason": "DSA indexer discussion is unrelated to docs about the removed run command." }, { "left": "issue:42915", "right": "issue:45399", "accept": false, - "reason": "Qwen3-MoE FP8 failure and flash-attn2 fallback gating are different bugs." + "reason": "Qwen3Moe FP8 failure is unrelated to the flash-attn2 fallback checks." }, { "left": "issue:44863", "right": "issue:45005", "accept": false, - "reason": "NemotronH checkpoint loading failure is unrelated to tied-weights regressions." + "reason": "NemotronH checkpoint loading failure is unrelated to tied-weight translation issues." }, { "left": "issue:43873", "right": "issue:45005", "accept": false, - "reason": "Quantization/offloading behavior is a different issue from tied-weights handling." + "reason": "Quantization/offloading behavior is unrelated to tied-weights handling." }, { "left": "issue:39186", "right": "issue:44918", "accept": false, - "reason": "FSDP 2-D weight error and TRL embedding unpacking failure are unrelated." + "reason": "FSDP 2-D weight error and TRL embedding unpacking are different bugs." }, { "left": "issue:44492", "right": "issue:44512", "accept": false, - "reason": "A typo in cache strategies is not the same as stale docs for the removed transformers run command." + "reason": "A typo in cache strategies is unrelated to removed-command docs drift." }, { "left": "issue:44918", "right": "issue:45507", "accept": false, - "reason": "Different model families and failures: TRL embedding unpacking versus GraniteMoEHybrid invalid-method calls." + "reason": "Different failures: TRL embedding unpacking vs GraniteMoEHybrid invalid method call." }, { "left": "issue:43975", "right": "issue:44292", "accept": false, - "reason": "DeepSeek detokenization bug and Qwen-3 NVFP4 runtime failure are unrelated." + "reason": "Different model-specific failures: detokenization bug vs NVFP4 execution error." }, { "left": "issue:43950", "right": "issue:44534", "accept": true, - "reason": "Same underlying regression: v5 corrupts non-persistent buffers on load; 44534 is essentially a reworded duplicate of 43950." + "reason": "Exact same underlying regression: Transformers v5 corrupts non-persistent buffers during loading." }, { "left": "issue:43644", "right": "issue:43950", "accept": true, - "reason": "Same bug: both report v5 filling/corrupting non-persistent buffers, with 43950 giving the clearest root-cause description." + "reason": "Same non-persistent-buffer corruption regression in Transformers 5.x." }, { "left": "issue:44292", "right": "issue:45507", "accept": false, - "reason": "Different failures on different models; no shared concrete code-path is evident." + "reason": "Different model/runtime failures with no shared concrete code path." }, { "left": "issue:39692", "right": "issue:43054", "accept": false, - "reason": "Both concern SigLIP2, but one is a doc example/model-processor mismatch and quantization failure, while the other is a quality/regression report." + "reason": "SigLIP2 doc-example errors are not the same as the later text-embedding quality complaint." }, { "left": "issue:43828", "right": "issue:44928", "accept": false, - "reason": "Both involve dtype/precision concerns, but the runtime contexts and failure modes are different." + "reason": "Autocast dtype mismatch and SDPA/BF16 gradient explosion are different bugs." }, { "left": "issue:43866", "right": "issue:44403", "accept": false, - "reason": "Ovis2 checkpoint corruption and an unrelated loading-noise issue do not look like the same bug." + "reason": "Corrupted checkpoint vs loading-noise issue are not the same underlying bug." } ] }, "evaluator_result": { "accept": true, - "feedback": "Grounded overall. The anchor choice and canonical issue are well supported by the packet, and the only accepted pairings (43950/44534 and 43644/43950) look like the same non-persistent-buffer corruption regression. The negative pair verdicts are appropriately conservative and do not overstate evidence." + "feedback": "Grounded overall: the non-persistent-buffer regression cluster is well supported by the titles, the custom-module loading pair is a conservative match, and the negative pair verdicts stay cautious. No PR-pair issues to flag." }, "evaluator_used": true, "retried": false, @@ -996,7 +1008,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 3, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -1056,8 +1068,8 @@ "soft_pairs": [ "issue:36331|issue:41762", "issue:41628|issue:45800", - "issue:41553|issue:43883", "issue:43872|issue:44589", + "issue:41553|issue:43883", "issue:38175|issue:43054", "issue:43054|issue:45701", "issue:44910|issue:45859", @@ -1090,12 +1102,12 @@ "issue:42915|issue:45020", "issue:43638|issue:45823" ], - "prepared_review_unit_hash": "cec015b3ff7aed38c924280535f59102455495021ec23cf70845ee5056c18a7b", + "prepared_review_unit_hash": "eb3f48dd383c3bb29d2af30008a5983eb94a673720e5572b2ede3608207d0d22", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -1103,7 +1115,7 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 35, - "serialized_chars": 38227, + "serialized_chars": 38226, "estimated_input_tokens": 9557, "estimated_eval_tokens": 19370 }, @@ -1112,231 +1124,231 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Most pairs are distinct bugs across different models, loaders, and runtime paths. The two clear soft duplicates are the SigLIP2 implementation-mismatch pair (43054/43493) and the docs pipeline-removal pair (43827/44509). The earlier SigLIP2 quality-only pairing (38175/43054) is not strong enough to accept from titles alone.", - "confidence": 0.82, - "canonical_issue_reason": "issue:45020 is the best open umbrella for the current remote_code-related regression cluster, but it should be treated as a tracker rather than a duplicate of the more specific reports.", + "summary": "Most suggested pairs are broad text-similarity matches rather than true duplicates. Only the two documentation issues about removed pipeline tasks look like the same cleanup. No PRs were provided.", + "confidence": 0.74, + "canonical_issue_reason": "issue:45020 is the broadest open report in the set and best fits as an umbrella for recent transformers v5 remote_code/loading regressions.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45020 is the strongest global issue anchor because it is open, broad, and clearly positioned as a tracker for a recurring family of recent compatibility breakages.", + "best_issue_reason": "issue:45020 is the best single anchor for this cluster because it is open, explicitly about recent version breakage, and broad enough to absorb related loading regressions.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:36331", "right": "issue:41762", "accept": false, - "reason": "Different failures: trainer signature mismatch vs Gemma3 ZeRO-3 loading index error." + "reason": "Different failures: trainer API kwarg mismatch vs Gemma3 DeepSpeed ZeRO-3 loading index error." }, { "left": "issue:41628", "right": "issue:45800", "accept": false, - "reason": "Different subsystems: missing AutoImageProcessor import vs torch/transformers version incompatibility." + "reason": "Both are compatibility/loading complaints, but they point to different breakages and different root causes." }, { - "left": "issue:41553", - "right": "issue:43883", + "left": "issue:43872", + "right": "issue:44589", "accept": false, - "reason": "Different model paths and symptoms: Voxtral tokenizer error handling vs Molmo tied-weights attribute error." + "reason": "Both are library incompatibilities, but the underlying errors are unrelated Int8Params vs Float8 storage handling." }, { - "left": "issue:43872", - "right": "issue:44589", + "left": "issue:41553", + "right": "issue:43883", "accept": false, - "reason": "Both are compatibility errors, but the concrete bugs differ: bitsandbytes kwarg mismatch vs float8 storage lookup." + "reason": "Voxtral tokenizer error-message issue is unrelated to Molmo missing all_tied_weights_keys." }, { "left": "issue:38175", "right": "issue:43054", "accept": false, - "reason": "Same model family, but only related quality symptoms are shown; no shared concrete implementation bug is established." + "reason": "Different models and different symptom domains: zero probabilities vs text embedding quality regression." }, { "left": "issue:43054", "right": "issue:45701", "accept": false, - "reason": "SigLIP2 embedding quality regression is unrelated to a generic tokenization-change report." + "reason": "One is SigLIP2 embedding quality, the other is a generic tokenization version-change report; not the same bug." }, { "left": "issue:44910", "right": "issue:45859", "accept": false, - "reason": "Different code paths: Flash Attention packed-sequence crash vs CPU-offload rotary-embedding incompatibility." + "reason": "Both involve Qwen3.5, but one is flash-attn packed-sequence misinterpretation and the other is CPU offload incompatibility." }, { "left": "issue:41553", "right": "issue:43881", "accept": false, - "reason": "Different model/load failures: Voxtral tokenizer error vs glm-4v-9b loading failure." + "reason": "Different model-loading failures for different models; only a weak generic similarity." }, { "left": "issue:42947", "right": "issue:44387", "accept": false, - "reason": "LoRA gradient-checkpointing effectiveness and int4 OOM are separate training/memory issues." + "reason": "Both mention training/memory, but one is gradient checkpointing with LoRA and the other is int4 CUDA reserved memory growth." }, { "left": "issue:44403", "right": "issue:44451", "accept": false, - "reason": "Generic load-noise report vs a specific model failing to load." + "reason": "Generic loading-noise report vs a specific model load failure; not the same underlying bug." }, { "left": "issue:43643", "right": "issue:45020", "accept": false, - "reason": "AutoConfig missing-fields under trust_remote_code is a specific bug; 45020 is a broader tracker, not the same defect." + "reason": "Both touch recent v5 behavior, but one is missing fields from trust_remote_code config loading and the other is broader remote_code breakage." }, { "left": "issue:43975", "right": "issue:45520", "accept": false, - "reason": "Tokenizer detokenization regression and Python 3.13 flash_attn import failure are unrelated." + "reason": "Detokenization regression and Python 3.13 flash_attn import error are unrelated." }, { "left": "issue:43054", "right": "issue:43493", - "accept": true, - "reason": "Both describe the same SigLIP2 implementation discrepancy; 43493 explicitly frames it as HF vs original JAX mismatch." + "accept": false, + "reason": "Both concern SigLIP2, but one is text embedding quality and the other is HF vs JAX implementation discrepancy." }, { "left": "issue:43975", "right": "issue:45237", "accept": false, - "reason": "DeepSeek tokenization regression and AMD GPU runtime support issue are unrelated." + "reason": "Deepseek tokenizer/detokenization and GPT-OSS-on-AMD are unrelated." }, { "left": "issue:44403", "right": "issue:44488", "accept": false, - "reason": "One is about noisy load logs, the other is a concrete model load failure." + "reason": "Both are model-loading complaints, but they are separate model-specific failures." }, { "left": "issue:42947", "right": "issue:43856", "accept": false, - "reason": "Gradient checkpointing/LoRA and Qwen3 MoE memory inefficiency are different training concerns." + "reason": "Both mention Qwen/LoRA training, but one is ineffective checkpointing and the other is inefficient memory usage." }, { "left": "issue:43881", "right": "issue:43883", "accept": false, - "reason": "Different models and failures: glm-4v-9b load problem vs Molmo tied-weights attribute error." + "reason": "Both are model-loading failures, but one is glm-4v-9b loading and the other is Molmo missing tied-weights metadata." }, { "left": "issue:41762", "right": "issue:42915", "accept": false, - "reason": "Both involve model loading, but Gemma3 ZeRO-3 and Qwen3 MoE FP8 are distinct bugs." + "reason": "Different failures: Gemma3 ZeRO-3 loading vs Qwen3 Moe FineGrainedFP8Config." }, { "left": "issue:42491", "right": "issue:44368", "accept": false, - "reason": "Compatibility regression vs configuration warning; not the same concrete defect." + "reason": "LoRA compatibility on hf5.x and a config warning in Qwen3.5 are not the same bug." }, { "left": "issue:45685", "right": "issue:45823", "accept": false, - "reason": "MPS histogram-not-implemented error and Gemma4 device-mismatch forward error are unrelated." + "reason": "MPS histogram-int support in MoE and Gemma4 PLE device mismatch are different issues." }, { "left": "issue:43975", "right": "issue:44451", "accept": false, - "reason": "DeepSeek tokenizer regression and ScandiBERT load failure are not the same bug." + "reason": "Different model/tokenizer problems; no evidence they share a concrete code path." }, { "left": "issue:43824", "right": "issue:43872", "accept": false, - "reason": "Qwen2.5-VL import failure is unrelated to the bitsandbytes Int8Params incompatibility." + "reason": "Qwen2.5-VL import error and bitsandbytes Int8Params kwarg incompatibility are unrelated." }, { "left": "issue:45020", "right": "issue:45823", "accept": false, - "reason": "A broad remote_code tracker is too general to equate with a Gemma4 device-map forward mismatch." + "reason": "Broad remote_code breakage vs a Gemma4 device_map forward mismatch; different concrete bugs." }, { "left": "issue:44991", "right": "issue:45399", "accept": false, - "reason": "Tokenizer loading regression and flash-attn2 fallback gating are separate issues." + "reason": "Tokenizer loading failure for one model versus flash-attn fallback gating; unrelated." }, { "left": "issue:44661", "right": "issue:45020", "accept": false, - "reason": "Registry/add-new-model-like failure is a different bug class than the remote_code regression tracker." + "reason": "Model registration/add-new-model-like failure is not the same as remote_code loading regressions." }, { "left": "issue:43828", "right": "issue:45823", "accept": false, - "reason": "Autocast dtype mismatch in Phi-tiny-MoE is unrelated to Gemma4 device placement." + "reason": "Autocast dtype mismatch in Phi-tiny-MoE and Gemma4 PLE device mismatch are different forward-path bugs." }, { "left": "issue:45020", "right": "issue:45356", "accept": false, - "reason": "Kimi-K2.5 tokenizer regression is a specific tokenizer bug, not the same as the broader remote_code tracker." + "reason": "Remote_code breakage is broader; Kimi-K2.5 tokenizer codec/fix_mistral_regex regression is a separate tokenizer bug." }, { "left": "issue:43782", "right": "issue:44960", "accept": false, - "reason": "Qwen3VL weight_only loading error and GLM5 are different model-specific failures." + "reason": "Qwen3VL weight_only loading error and a generic GLM5 issue do not match." }, { "left": "issue:45081", "right": "issue:45399", "accept": false, - "reason": "Tokenizer regex crash and flash-attn2 fallback gating are unrelated." + "reason": "Tokenizer regex crash and flash-attn fallback gating are different code paths." }, { "left": "issue:43827", "right": "issue:44509", "accept": true, - "reason": "Both are the same docs regression: pipeline tasks removed in v5 but still referenced in documentation." + "reason": "Both report that v5 docs still reference removed pipeline tasks (summarization/translation/text2text-generation); same documentation cleanup." }, { "left": "issue:43404", "right": "issue:43950", "accept": false, - "reason": "Mistral3 tied-weight bug and non-persistent buffer corruption are separate loading issues." + "reason": "Untied lm_head weights in Mistral3 and non-persistent buffer corruption are different state/serialization bugs." }, { "left": "issue:43792", "right": "issue:44220", "accept": false, - "reason": "Whisper runtime failure is too underspecified here to confirm the same concrete bug as the fbank feature issue." + "reason": "Whisper runtime failure and fbank feature extraction issue are not the same underlying bug." }, { "left": "issue:43742", "right": "issue:45399", "accept": false, - "reason": "MobileLLM key error and flash-attn2 fallback blocking are unrelated." + "reason": "MobileLLM key error and flash-attn fallback checks are unrelated." }, { "left": "issue:42915", "right": "issue:45020", "accept": false, - "reason": "Qwen3 MoE FP8 loading failure is a specific model/config bug, not the same as the broad remote_code tracker." + "reason": "Qwen3Moe FineGrainedFP8Config failure is a specific quantization/config bug, not the broader remote_code loading regression." }, { "left": "issue:43638", "right": "issue:45823", "accept": false, - "reason": "ZeRO-3/BERT index error and Gemma4 device-mismatch are distinct failures." + "reason": "ZeRO-3 with non-pretrained Bert index error and Gemma4 device mismatch are unrelated." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The summary is mostly grounded, but it overstates one soft-edge duplicate claim: issue:38175 vs issue:43054 is not clearly supported by the packet. Both are in the SigLIP2 area, but the titles alone only show related model family/symptoms, not the same concrete bug or implementation mismatch. The 43054 vs 43493 pairing is more defensible, and the docs pair 43827 vs 44509 looks solid. Overall, the conservative verdicts are not consistent enough to accept as-is." + "accept": true, + "feedback": "The summary stays grounded in the packet and the soft-edge calls are conservative. The single accepted pair (43827/44509) is supported by the issue titles as the same docs cleanup around removed pipeline tasks. No PR-pair mergeability concerns apply because no PRs were provided." }, "evaluator_used": true, - "retried": true, + "retried": false, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -1346,7 +1358,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 4, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -1405,18 +1417,18 @@ "soft_pairs": [ "issue:43257|issue:43866", "issue:43872|issue:44291", - "issue:43940|issue:45313", "issue:45161|issue:45823", - "issue:41553|issue:44991", + "issue:43940|issue:45313", "issue:42915|issue:43872", "issue:43854|issue:44863", + "issue:41553|issue:44991", "issue:44928|issue:45588", "issue:36331|issue:41093", "issue:43257|issue:45305", - "issue:41553|issue:44488", "issue:43872|issue:45538", - "issue:44530|issue:44863", + "issue:41553|issue:44488", "issue:41093|issue:44805", + "issue:44530|issue:44863", "issue:44479|issue:44560", "issue:24643|issue:30064", "issue:43366|issue:43828", @@ -1436,12 +1448,12 @@ "issue:38175|issue:43994", "issue:43632|issue:45834" ], - "prepared_review_unit_hash": "96c7d10b6ea0fe2395abedec970d727ab1bf8d6b26b8332735261b4f73b78f73", + "prepared_review_unit_hash": "fd04d1498ee93c8bbfcdad2a69e81f962cef5df1d1806dd7f36164cac079099b", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -1449,7 +1461,7 @@ "node_count": 47, "item_count": 47, "soft_pair_count": 32, - "serialized_chars": 36776, + "serialized_chars": 36774, "estimated_input_tokens": 9194, "estimated_eval_tokens": 18644 }, @@ -1458,210 +1470,210 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is mostly heterogeneous issue reports with only two strong duplicate-like pairs: the Transformers 5 custom model init regression, and the `_is_hf_initialized` / `init_empty_weights` regression. I rejected the rest because they describe different model families, different symptoms, or only share a broad subsystem.", - "confidence": 0.72, - "canonical_issue_reason": "No single canonical issue cleanly spans the full set because the items are mostly unrelated; if a representative anchor is needed, issue 44291 is the clearest root-cause report for the `_is_hf_initialized` regression.", + "summary": "Mostly a heterogeneous cluster of unrelated Transformers bugs, with a few clear duplicate subgroups: the `_is_hf_initialized` regression, the custom model initialization regression, and the mask-shape IndexError report.", + "confidence": 0.8, + "canonical_issue_reason": "issue:43632 is the broadest and clearest statement of the shared `_is_hf_initialized` Transformers v5 regression that other nearby reports expand on.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 44291 is the strongest standalone issue: it states the concrete failure mode, ties it to the v5 regression, and gives the clearest actionable root cause.", + "best_issue_reason": "issue:43632 is the best representative issue for the cluster\u2019s main shared regression theme; it is general enough to anchor the close duplicates while staying concrete.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43257", "right": "issue:43866", "accept": false, - "reason": "Different problems: Qwen3 MoE weight conversion under accelerate+deepspeed vs a corrupted Ovis2 checkpoint." + "reason": "Different model families and failures: Qwen3 MoE weight conversion under accelerate/deepspeed vs an Ovis2 checkpoint corruption report." }, { "left": "issue:43872", "right": "issue:44291", "accept": true, - "reason": "Same underlying regression around `_is_hf_initialized` / `init_empty_weights` in Transformers 5, with bitsandbytes showing the same incompatibility symptom." - }, - { - "left": "issue:43940", - "right": "issue:45313", - "accept": false, - "reason": "Both involve DeepSpeed ZeRO-3 weight loading, but the models and failure details differ enough that this is not clearly the same bug." + "reason": "Same underlying `_is_hf_initialized` compatibility break during loading/init; one surfaces via bitsandbytes, the other via `init_empty_weights`." }, { "left": "issue:45161", "right": "issue:45823", "accept": false, - "reason": "Unrelated model-specific issues: GPT-OSS MoE tensor-parallel behavior vs Gemma4 PLE device placement." + "reason": "Both are model-loading/training problems, but they affect different models and code paths (GPT-OSS MoE TP vs Gemma4 PLE device mismatch)." }, { - "left": "issue:41553", - "right": "issue:44991", + "left": "issue:43940", + "right": "issue:45313", "accept": false, - "reason": "Both are tokenizer-loading failures, but they concern different models and different failure modes." + "reason": "Similar DeepSpeed ZeRO-3 weight-loading symptoms, but the model targets and reported failure details differ enough that the underlying bug is not established." }, { "left": "issue:42915", "right": "issue:43872", "accept": false, - "reason": "Different subsystems and symptoms: FineGrainedFP8Config on Qwen3Moe vs the `_is_hf_initialized`/bitsandbytes regression." + "reason": "Qwen3Moe FP8 failure is a different issue from the `_is_hf_initialized` bitsandbytes/loading incompatibility." }, { "left": "issue:43854", "right": "issue:44863", "accept": false, - "reason": "Different model-loading bugs for different architectures; only the broad theme of loading failure matches." + "reason": "Different models and failure modes: GLM-4.7-Flash test loading vs NemotronH checkpoint loading." + }, + { + "left": "issue:41553", + "right": "issue:44991", + "accept": false, + "reason": "Both mention tokenizer loading, but they are different models and distinct failure reports." }, { "left": "issue:44928", "right": "issue:45588", "accept": false, - "reason": "Qwen3.5 RLHF/SDPA NaN behavior is unrelated to the flash_attention `s_aux=None` crash." + "reason": "Different bugs: one is a Qwen3.5 training/SDPA/BF16 regression, the other is an `s_aux=None` crash in flash_attention integration." }, { "left": "issue:36331", "right": "issue:41093", "accept": false, - "reason": "Different error classes and different code paths: custom trainer API change vs mask/tensor shape mismatch." + "reason": "Completely different errors: trainer loss API mismatch vs tensor mask shape mismatch." }, { "left": "issue:43257", "right": "issue:45305", "accept": false, - "reason": "Both touch DeepSpeed training, but one is a Qwen MoE weight-conversion problem and the other is a gradient-averaging issue." - }, - { - "left": "issue:41553", - "right": "issue:44488", - "accept": false, - "reason": "Different tokenizer/loading issues for different models; not the same concrete bug." + "reason": "Different DeepSpeed-related regressions affecting different training semantics; not the same concrete bug." }, { "left": "issue:43872", "right": "issue:45538", "accept": false, - "reason": "bitsandbytes/_is_hf_initialized incompatibility is unrelated to CLIPTokenizer's max length default." + "reason": "`_is_hf_initialized`/bitsandbytes loading issue is unrelated to CLIPTokenizer's max length bug." }, { - "left": "issue:44530", - "right": "issue:44863", + "left": "issue:41553", + "right": "issue:44488", "accept": false, - "reason": "PagedAttentionCache linear_attention crash and NemotronH checkpoint loading are unrelated." + "reason": "Different tokenizer-loading reports for different models, with no shared concrete failure path shown." }, { "left": "issue:41093", "right": "issue:44805", + "accept": true, + "reason": "These appear to be the same mask-shape mismatch IndexError report, just with different concrete dimensions in the error text." + }, + { + "left": "issue:44530", + "right": "issue:44863", "accept": false, - "reason": "Both are index/shape errors, but they are distinct reports with no evidence of the same root cause." + "reason": "Qwen3.5 PagedAttention crash and NemotronH checkpoint loading are unrelated." }, { "left": "issue:44479", "right": "issue:44560", "accept": false, - "reason": "Both are video-related Qwen issues, but one is a broad v5.3.0 regression and the other is a specific StopIteration in embedding loading." + "reason": "Both are Qwen video-related, but one is a broad v5.3.0 regression and the other is a specific StopIteration report; same root cause is not clear enough." }, { "left": "issue:24643", "right": "issue:30064", "accept": false, - "reason": "Training with DeepSpeed and void segmentation-map processing are unrelated." + "reason": "Training with DeepSpeed and void segmentation map processing are unrelated issues." }, { "left": "issue:43366", "right": "issue:43828", "accept": false, - "reason": "GPT-OSS architecture support and Phi-tiny-MoE autocast dtype mismatch are separate bugs." + "reason": "GGUF gpt-oss support and Phi MoE autocast dtype mismatch are different features/bugs." }, { "left": "issue:45663", "right": "issue:45823", "accept": false, - "reason": "Gemma4 FSDP2 shared_kv_states issue is not the same as the device_map=\"auto\" PLE mismatch." + "reason": "Different Gemma4 failures: FSDP2 shared_kv_states logic vs device_map auto placement mismatch." }, { "left": "issue:43366", "right": "issue:43531", "accept": false, - "reason": "GPT-OSS support and Qwen3-MoE sliding_window behavior are different issues." + "reason": "Unrelated: GGUF gpt-oss support vs Qwen3-MoE sliding window behavior." }, { "left": "issue:43950", "right": "issue:45834", "accept": false, - "reason": "Non-persistent buffer corruption and Kosmos2.5 OCR index error are unrelated." + "reason": "Different regressions: non-persistent buffer corruption vs Kosmos2.5 long OCR input indexing." }, { "left": "issue:43550", "right": "issue:44910", "accept": false, - "reason": "Both mention attention/compile problems, but Bamba SDPA compile failure is unrelated to Qwen3.5 3D position_ids and flash-attention memory access." + "reason": "Different model/code-path issues: Bamba SDPA torch.compile crash vs Qwen3.5 flash-attention position_ids bug." }, { "left": "issue:43645", "right": "issue:43646", "accept": true, - "reason": "Same Transformers 5 custom-model initialization regression; one report is just a more specific notebook variant." + "reason": "Same custom model initialization regression in Transformers 5.0.0; the notebook wording is just a narrower reproduction." }, { "left": "issue:43366", "right": "issue:44589", "accept": false, - "reason": "GPT-OSS support request and Float8 storage import failure are unrelated." + "reason": "Unrelated failures: GPT-OSS support vs missing Float8 storage object." }, { "left": "issue:43950", "right": "issue:45325", "accept": false, - "reason": "Non-persistent buffer corruption is unrelated to the Qwen2.5-VL rope-index scaling bug." + "reason": "Non-persistent buffer corruption is unrelated to the Qwen2.5-VL rope index scaling bug." }, { "left": "issue:44560", "right": "issue:44918", "accept": false, - "reason": "Both involve Qwen3.5 video/input handling, but the reported failures and likely code paths differ." + "reason": "Both involve Qwen3.5-ish behavior, but video StopIteration and TRL SFT embedding unpacking are different concrete bugs." }, { "left": "issue:42617", "right": "issue:43366", "accept": false, - "reason": "3d_parallel execution failure and GPT-OSS architecture support are unrelated." + "reason": "3d_parallel.py runtime failure and GPT-OSS GGUF support are unrelated." }, { "left": "issue:43824", "right": "issue:43957", "accept": false, - "reason": "Missing Qwen2_5_VL export and `torch.device(\"meta\")` loading regressions are different bugs." + "reason": "Different issues: missing Qwen2.5-VL export vs meta-device model loading regression." }, { "left": "issue:42915", "right": "issue:43957", "accept": false, - "reason": "Qwen3Moe FP8 failure and meta-device loading regression do not share the same root cause." + "reason": "Qwen3Moe FP8 failure and meta-device loading breakage are different bugs." }, { "left": "issue:36010", "right": "issue:42915", "accept": false, - "reason": "GenerationMixin import failure and Qwen3Moe FP8 failure are unrelated." + "reason": "Import error for GenerationMixin is unrelated to Qwen3Moe FP8 loading." }, { "left": "issue:44661", "right": "issue:45823", "accept": false, - "reason": "Tokenizer-mapping registration bug and Gemma4 PLE device mismatch are different issues." + "reason": "Tokenizer mapping failure and Gemma4 device mismatch are unrelated." }, { "left": "issue:38175", "right": "issue:43994", "accept": false, - "reason": "Both mention SigLIP2, but one is zero probabilities and the other nonsensical AutoModel/pipeline outputs; not enough to treat as the same bug." + "reason": "Same model family, but the reports are too vague and not clearly the same underlying defect." }, { "left": "issue:43632", - "right": "issue:45834", - "accept": false, - "reason": "_is_hf_initialized flag regression and Kosmos2.5 OCR index error are unrelated." + "right": "issue:43872", + "accept": true, + "reason": "Same shared `_is_hf_initialized` regression; 43872 is a specific downstream symptom of the broader bug described in 43632." } ] }, "evaluator_result": { "accept": true, - "feedback": "Grounded and conservative overall. The two accepted soft pairs are plausible duplicate/regression matches, and the rejected pairs are appropriately cautious given the packet. Summary does not overstate the evidence." + "feedback": "The summary is grounded in the packet: it correctly treats the cluster as mostly heterogeneous while identifying the `_is_hf_initialized`, custom model initialization, and mask-shape duplicate subgroups. The accepted soft-edge pairs are conservative and well supported by the issue titles." }, "evaluator_used": true, "retried": false, @@ -1674,7 +1686,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 5, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -1748,12 +1760,12 @@ "issue:43854|issue:43931", "issue:41720|issue:42915", "issue:43708|issue:44075", - "issue:43257|issue:43854", "issue:42491|issue:45276", + "issue:43257|issue:43854", "issue:43856|issue:43873", "issue:42915|issue:44756", - "issue:42491|issue:43931", "issue:39692|issue:43994", + "issue:42491|issue:43931", "issue:43856|issue:44387", "issue:43644|issue:43645", "issue:44910|issue:45588", @@ -1763,12 +1775,12 @@ "issue:36010|issue:39404", "issue:45276|issue:45335" ], - "prepared_review_unit_hash": "87f2872331c988ef42b943937ff0372f82f64e6ea96041ad646db5fa51e88d3f", + "prepared_review_unit_hash": "c963d638300563b27247fde40aaf85fe7bebd0f7c18539b25793e477079d00b4", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -1776,7 +1788,7 @@ "node_count": 47, "item_count": 47, "soft_pair_count": 31, - "serialized_chars": 36407, + "serialized_chars": 36405, "estimated_input_tokens": 9102, "estimated_eval_tokens": 18460 }, @@ -1785,201 +1797,201 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Most items are unrelated bug reports. The clearest duplicate remains the non-persistent-buffer regression pair (43644/44534). The `resize_token_embeddings` issues (45276/45335) are plausibly the same propagation bug, but `43644/43645` should be treated conservatively as non-duplicate without body evidence.", - "confidence": 0.81, - "canonical_issue_reason": "Issue 43644 is the best canonical issue: it is a precise, well-scoped regression report and is an exact duplicate of 44534.", + "summary": "The cluster contains several small duplicate subgroups, mostly around Transformers v5 regressions in loading/tokenizer/config handling. I\u2019d keep the tokenizer-loading regression issue as the main issue, and reject most cross-model or cross-subsystem pairs as too loose to be true duplicates.", + "confidence": 0.78, + "canonical_issue_reason": "Issue 44488 is the best hub for the tokenizer-loading regression subgroup: it\u2019s broad, already has inbound references, and sits between the more specific model reports.", "canonical_pr_reason": null, - "best_issue_reason": "43644 is the strongest representative issue overall because it has the clearest duplicate evidence and the most specific regression framing.", + "best_issue_reason": "Issue 44991 is the clearest single statement of the underlying bug class: a Transformers >=5.0.0 tokenizer-loading regression. It best represents the shared failure mode across the related reports.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44155", "right": "issue:45584", "accept": false, - "reason": "Different audio/model bugs: batched inference track leakage vs Whisper empty-transcription behavior." + "reason": "Different bugs and different models: batched embedding/token leakage vs Whisper empty-transcription generation failure." }, { "left": "issue:44877", "right": "issue:45030", - "accept": false, - "reason": "Both involve config loading, but the models and failure modes differ; no clear shared code path." + "accept": true, + "reason": "Both describe the same underlying v5 config-validation regression blocking model/config loading for different model families." }, { "left": "issue:44560", "right": "issue:44805", "accept": false, - "reason": "Unrelated symptoms and models: video StopIteration in Qwen3-VL vs a mask shape IndexError." + "reason": "Unrelated failures: Qwen3-VL video StopIteration vs a mask/tensor shape mismatch." }, { "left": "issue:43638", "right": "issue:44661", "accept": false, - "reason": "Deepspeed/BERT zero3 init bug is unrelated to tokenizer-mapping registration failure." + "reason": "Different code paths: DeepSpeed ZeRO-3 Bert init vs tokenizer-mapping logic for adding a model-like entry." }, { "left": "issue:43317", "right": "issue:44756", "accept": false, - "reason": "Both touch offloading/memory, but one is a dequantized load failure and the other is a Strix Halo mmap OOM fix." + "reason": "Both involve loading/offload/memory, but the concrete failure modes are different (dequantized offload load failure vs mmap OOM)." }, { "left": "issue:43596", "right": "issue:44661", "accept": false, - "reason": "Different root causes: zero3/BertModel IndexError vs `add-new-model-like` tokenizer-mapping logic." + "reason": "Distinct issues: BertModel ZeRO-3 index error vs tokenizer-mapping add-new-model failure." }, { "left": "issue:44661", "right": "issue:44805", "accept": false, - "reason": "Tokenizer-mapping registration problem vs a tensor mask shape mismatch are not the same bug." + "reason": "No shared bug: tokenizer mapping registration vs a tensor-mask indexing mismatch." }, { "left": "issue:38175", "right": "issue:39692", "accept": false, - "reason": "Same model family, but one is bad output probabilities and the other is a docs/example mismatch plus quantization failure." + "reason": "Related SigLIP2 area, but not the same bug: zero probabilities vs doc-example/model-processor mismatch and quantization errors." }, { "left": "issue:43644", "right": "issue:44534", "accept": true, - "reason": "Near-identical titles describing the same non-persistent-buffer junk regression; clearly the same underlying bug." + "reason": "Same duplicate: Transformers v5 fills non-persistent buffers with junk." }, { "left": "issue:45313", "right": "issue:45357", "accept": false, - "reason": "Load-time ZeRO-3 weight issue and save_pretrained visual-encoder key regression are different code paths." + "reason": "Different concrete problems: ZeRO-3 language_model loading vs incorrect visual-encoder keys saved by pretrained export." }, { "left": "issue:44960", "right": "issue:44977", "accept": false, - "reason": "Different models and different flash-attention failures; not the same concrete issue." + "reason": "Different models and failure modes: GLM5 issue vs Qwen3.5 flash-attention generation problem." }, { "left": "issue:45488", "right": "issue:45812", "accept": false, - "reason": "Both are tokenizer regressions, but they affect different tokenization layers and different model families." + "reason": "Both are tokenizer regressions, but they affect different model families and look like separate bugs." }, { "left": "issue:44451", "right": "issue:44488", - "accept": false, - "reason": "Both are model-loading failures, but the titles point to different repos and no shared concrete bug is evident." + "accept": true, + "reason": "Same underlying regression: current Transformers version fails to load BERT-like tokenizer/model checkpoints for multiple repositories." }, { "left": "issue:42491", "right": "issue:43720", "accept": false, - "reason": "Both involve loading/compatibility, but one is Qwen3 MoE LoRA cross-version use and the other is BitNet packed-weight handling." + "reason": "Both touch loading/quantization, but the concrete bugs are different: Qwen3 MoE LoRA compatibility vs BitNet packed-weight unpacking." }, { "left": "issue:43854", "right": "issue:43931", "accept": false, - "reason": "Different model loading failures with different symptoms and likely different fixes." + "reason": "Different models and root causes: GLM-4.7-Flash test loading vs Qwen3-VL weight-shape mismatch." }, { "left": "issue:41720", "right": "issue:42915", "accept": false, - "reason": "Qwen3 auto device mapping CUDA assert is not the same as Qwen3Moe FineGrainedFP8Config failure." + "reason": "Both are Qwen3-family issues, but the failures are unrelated: auto device mapping CUDA assert vs FineGrainedFP8Config failure." }, { "left": "issue:43708", "right": "issue:44075", "accept": false, - "reason": "Trainer checkpoint resume step calculation and SGD optimizer args being ignored are unrelated." + "reason": "Trainer checkpoint math and optimizer argument handling are unrelated bugs." }, { - "left": "issue:43257", - "right": "issue:43854", + "left": "issue:42491", + "right": "issue:45276", "accept": false, - "reason": "Different models and different loading paths; no evidence of a common bug." + "reason": "Different scope and failure mode: Qwen3 MoE HF5 compatibility vs Gemma4 resize_token_embeddings behavior." }, { - "left": "issue:42491", - "right": "issue:45276", + "left": "issue:43257", + "right": "issue:43854", "accept": false, - "reason": "LoRA compatibility across versions is unrelated to `resize_token_embeddings` not updating embeddings." + "reason": "Separate problems: Qwen3 MoE accelerate+deepspeed weight conversion vs GLM-4.7-Flash loading in tests." }, { "left": "issue:43856", "right": "issue:43873", "accept": false, - "reason": "Training memory inefficiency and quantized offload behavior are different problems." + "reason": "Both mention memory/offload, but one is Qwen3 MoE training memory usage and the other is quantization offloading behavior." }, { "left": "issue:42915", "right": "issue:44756", "accept": false, - "reason": "Qwen3Moe FP8 failure on one side and Strix Halo mmap OOM on the other are unrelated." + "reason": "Different issues: Qwen3Moe FineGrainedFP8Config failure vs mmap/OOM on Strix Halo." }, { - "left": "issue:42491", - "right": "issue:43931", + "left": "issue:39692", + "right": "issue:43994", "accept": false, - "reason": "Different models, different mechanisms, and no shared concrete code-path issue." + "reason": "Both are SigLIP2-related, but one is doc-example errors and the other is nonsensical outputs in AutoModel/pipeline." }, { - "left": "issue:39692", - "right": "issue:43994", + "left": "issue:42491", + "right": "issue:43931", "accept": false, - "reason": "Same SigLIP2 family, but one is docs/example misuse plus quantization failure while the other is an inference regression." + "reason": "Different bugs: Qwen3 MoE HF5 compatibility vs Qwen3-VL shape mismatch on load." }, { "left": "issue:43856", "right": "issue:44387", "accept": false, - "reason": "Both mention memory, but the causes differ: MoE training efficiency vs increased CUDA reserved memory under int4 quantization." + "reason": "Both are memory-related, but the actual regressions differ: training memory inefficiency vs increased reserved CUDA memory under int4 quantization." }, { "left": "issue:43644", "right": "issue:43645", "accept": false, - "reason": "The titles both mention Transformers 5.0.0 regressions, but one is about non-persistent buffers and the other is about custom models in Jupyter notebooks; the packet does not show the same underlying bug." + "reason": "Related v5 breakage theme, but one is non-persistent buffers junk and the other is custom model initialization in notebooks." }, { "left": "issue:44910", "right": "issue:45588", "accept": false, - "reason": "Both are flash-attention crashes, but one is a packed-sequence misinterpretation and the other is an `s_aux=None` attribute error." + "reason": "Both involve flash attention, but the concrete failures differ: packed-sequence position_ids crash vs s_aux=None AttributeError." }, { "left": "issue:45362", "right": "issue:45406", "accept": false, - "reason": "Different crash points: Qwen3.5 chat generation vs Gemma4Processor missing `_tokenizer`." + "reason": "Different components and failures: Qwen3.5 chat crash vs Gemma4Processor missing _tokenizer in serve." }, { "left": "issue:44488", "right": "issue:44991", - "accept": false, - "reason": "Both are tokenizer/model loading failures in v5, but the specific repos and failure modes are too different to call duplicates." + "accept": true, + "reason": "Same tokenizer-loading regression in Transformers v5; the two issues are model-specific reports of the same underlying failure." }, { "left": "issue:36010", "right": "issue:39404", "accept": false, - "reason": "Importing `GenerationMixin` and Whisper `return_language` pipeline behavior are unrelated." + "reason": "Unrelated problems: GenerationMixin import error vs Whisper return_language pipeline behavior." }, { "left": "issue:45276", "right": "issue:45335", "accept": true, - "reason": "Both report the same `resize_token_embeddings` propagation bug to model-specific embedding/output modules; one fix could plausibly cover both." + "reason": "Same resize_token_embeddings regression affecting output embeddings across different model variants." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The cluster summary is mostly grounded, but one soft-edge acceptance is too strong: `issue:43644` vs `issue:43645` is not supported by the packet. `43644`/`44534` clearly match on the non-persistent-buffer junk regression, but `43645` is titled about custom models in Jupyter notebooks and does not obviously describe the same bug. That pair should stay conservative/rejected unless there is direct evidence in the issue bodies. The `resize_token_embeddings` pair looks plausibly related, but the `43644`/`43645` acceptance overstates the evidence." + "accept": true, + "feedback": "The summary is grounded in the packet and stays mostly conservative on the soft edges. The main cluster call around Transformers v5 tokenizer/config-loading regressions is supported, 44488 is a reasonable hub choice given its breadth and inbound refs, and the accepted duplicate pairs are plausible from the issue titles. I don\u2019t see an overstatement severe enough to reject." }, "evaluator_used": true, - "retried": true, + "retried": false, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -1989,7 +2001,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 6, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -2067,8 +2079,8 @@ "issue:43381|issue:44928", "issue:44164|issue:44756", "issue:44479|issue:44877", - "issue:41720|issue:44155", "issue:43646|issue:43708", + "issue:41720|issue:44155", "issue:45588|issue:45663", "issue:43854|issue:44960", "issue:43957|issue:44756", @@ -2076,18 +2088,18 @@ "issue:44402|issue:44451", "issue:43828|issue:43957", "issue:43645|issue:44164", - "issue:43257|issue:44863", "issue:43425|issue:43828", + "issue:43257|issue:44863", "issue:44589|issue:44756", "issue:44683|issue:45823", "issue:39404|issue:45701" ], - "prepared_review_unit_hash": "0090eedf181c34281bdbe70ecdf4f93a763a26e3850d31d49547d1f25a16289b", + "prepared_review_unit_hash": "fec8c9366a638da6d3772f5adfcf3b494983aec474afee3c9f0d8938ee329678", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -2095,237 +2107,237 @@ "node_count": 47, "item_count": 47, "soft_pair_count": 35, - "serialized_chars": 37609, - "estimated_input_tokens": 9403, - "estimated_eval_tokens": 19062 + "serialized_chars": 37606, + "estimated_input_tokens": 9402, + "estimated_eval_tokens": 19060 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous model-loading / quantization / training bugs. Only the resize_token_embeddings issues look like true duplicates; most other soft edges are same subsystem at best, but not the same concrete bug.", - "confidence": 0.93, - "canonical_issue_reason": "issue:45292 is the broadest, most generic representative of the only clear duplicate set (`resize_token_embeddings` not updating output/decoder embeddings).", + "summary": "This cluster is mostly heterogeneous, but there is a small duplicate subgroup around `resize_token_embeddings` not propagating to output/decoder embeddings. Most other pairs are related only at a broad subsystem level and should not be merged.", + "confidence": 0.46, + "canonical_issue_reason": "`issue:45292` is the cleanest, most generic report of the shared `resize_token_embeddings` regression and best matches the strongest duplicate subgroup.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45292 best represents the cluster\u2019s one real duplicate thread and is the most general formulation of that bug.", + "best_issue_reason": "`issue:45292` is the broadest and most reusable anchor for the accepted resize-token-embedding duplicates, with a concise title that captures the common failure mode.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43404", "right": "issue:43454", "accept": false, - "reason": "Same symptom class (lm_head tying) but different model families and likely separate fixes." + "reason": "Both mention tied `lm_head` behavior, but they affect different model implementations and do not clearly describe the same code-path bug." }, { "left": "issue:44164", "right": "issue:44291", "accept": false, - "reason": "Both touch loading/saving paths, but one is extra_state handling and the other is init_empty_weights argument compatibility." + "reason": "`extra_state` save/load handling and `init_empty_weights` argument errors are different serialization/loading failures." }, { "left": "issue:44402", "right": "issue:44488", "accept": false, - "reason": "Both report load failures for different BERT models, but the titles point to separate model/tokenizer mismatches rather than one bug." + "reason": "Both are BERT load problems, but the models and stated failure modes differ; not enough evidence of one shared bug." }, { "left": "issue:43425", "right": "issue:43957", "accept": false, - "reason": "Unrelated failures: Torch version incompatibility vs meta-device loading regression." + "reason": "One is torch 2.10 incompatibility and the other is meta-device loading breakage; unrelated regressions." }, { "left": "issue:39692", "right": "issue:44960", "accept": false, - "reason": "Documentation example errors versus a GLM5 loading issue; no shared underlying bug." + "reason": "Documentation example errors and a generic GLM5 issue are not the same underlying bug." }, { "left": "issue:42947", "right": "issue:45704", "accept": false, - "reason": "Gradient checkpointing/LoRA behavior is unrelated to the T5 apex RMSNorm memory leak." + "reason": "Gradient checkpointing with PEFT LoRA and an apex RMSNorm memory leak are different problems." }, { "left": "issue:43335", "right": "issue:45663", "accept": false, - "reason": "SwitchTransformers sparse-layer creation bug is unrelated to Gemma4 FSDP shared_kv_states handling." + "reason": "Sparse-layer config creation and Gemma4 FSDP2 attention state rebuilding are unrelated code paths." }, { "left": "issue:43873", "right": "issue:44387", "accept": false, - "reason": "Both involve quantization/OOM, but one is offloading behavior and the other is reserved-memory growth under int4; different code paths." + "reason": "Both are quantization memory issues, but the causes differ (`offloading` vs increased reserved memory/OOM regression)." }, { "left": "issue:45663", "right": "issue:45759", "accept": false, - "reason": "Gemma4 FSDP attention state rebuild is unrelated to Qwen multimodal from_config text_config unwrapping." + "reason": "FSDP2 `shared_kv_states` rebuilding and `from_config` not unwrapping `text_config` are distinct bugs." }, { "left": "issue:45663", "right": "issue:45859", "accept": false, - "reason": "Different models and failures: Gemma4 FSDP KeyError vs Qwen3_5MoE CPU-offload incompatibility." + "reason": "The Gemma4 FSDP2 error and the Qwen3_5 MoE rotary offload incompatibility are different failures." }, { "left": "issue:44155", "right": "issue:45823", "accept": false, - "reason": "AudioFlamingo batched inference token leak is unrelated to Gemma4 device-mapping mismatch." + "reason": "AudioFlamingo3 batched-token leakage and Gemma4 PLE device mismatch are unrelated." }, { "left": "issue:43854", "right": "issue:45216", "accept": false, - "reason": "Different model-loading regressions with no shared concrete failure mode." + "reason": "A model-loading failure in tests and a `save_pretrained` regression are different issues." }, { "left": "issue:44387", "right": "issue:44756", "accept": false, - "reason": "OOM-related, but one is int4 quantization memory reservation and the other is mmap on Strix Halo." + "reason": "Both involve memory pressure, but one is an int4 quantization regression and the other is mmap/OOM on Strix Halo." }, { "left": "issue:44291", "right": "issue:44756", "accept": false, - "reason": "init_empty_weights compatibility issue is unrelated to mmap/OOM behavior." + "reason": "Unexpected `_is_hf_initialized` handling and mmap-related OOM are not the same bug." }, { "left": "issue:44292", "right": "issue:44912", "accept": false, - "reason": "Both are quantization-related, but they involve different quantization formats and different models." + "reason": "NVFP4 load errors and MXFP4 fallback behavior are different quantization/load problems." }, { "left": "issue:42947", "right": "issue:43381", "accept": false, - "reason": "Both mention gradient checkpointing, but one is ineffective LoRA behavior and the other is an eval-mode restriction." + "reason": "These are both checkpointing-related, but one is ineffective LoRA checkpointing and the other is an eval-mode limitation." }, { "left": "issue:45684", "right": "issue:45698", "accept": false, - "reason": "Custom-model save/load issues, but permissions propagation and wrong-module loading are distinct bugs." + "reason": "Custom-model file permissions and wrong custom-module loading after save/load are separate save/load bugs." }, { "left": "issue:45276", "right": "issue:45292", "accept": true, - "reason": "Same underlying resize_token_embeddings bug: output embeddings are not updated, with 45276 being a model-specific variant." + "reason": "These describe the same `resize_token_embeddings` regression: resized embeddings are not propagated to the output path, with `45276` adding Gemma4-specific detail." }, { "left": "issue:43381", "right": "issue:44928", "accept": false, - "reason": "Gradient checkpointing eval-mode limitation is unrelated to Qwen3.5 RLHF gradient explosion." + "reason": "Gradient checkpointing in eval mode and RLHF NaN explosions from 3D position IDs are unrelated." }, { "left": "issue:44164", "right": "issue:44756", "accept": false, - "reason": "save/from_pretrained extra_state handling is unrelated to Strix Halo mmap OOM." + "reason": "`extra_state` serialization and mmap/OOM on Strix Halo do not share a concrete root cause." }, { "left": "issue:44479", "right": "issue:44877", "accept": false, - "reason": "Video-input regression across Qwen variants versus strict config loading for granite_speech; different problems." + "reason": "Video-input regression in Qwen models and strict config blocking `granite_speech` are different failures." }, { - "left": "issue:41720", - "right": "issue:44155", + "left": "issue:43646", + "right": "issue:43708", "accept": false, - "reason": "Auto device mapping cudaErrorAssert and cross-track token leak are unrelated." + "reason": "Custom model initialization in notebooks and incorrect `max_steps` on resume are separate trainer/model-init issues." }, { - "left": "issue:43646", - "right": "issue:43708", + "left": "issue:41720", + "right": "issue:44155", "accept": false, - "reason": "Custom model initialization breakage is unrelated to Trainer max_steps recomputation on resume." + "reason": "Qwen3 auto-device-map CUDA asserts and AudioFlamingo3 batched inference leakage are unrelated." }, { "left": "issue:45588", "right": "issue:45663", "accept": false, - "reason": "Flash-attention s_aux=None crash is unrelated to Gemma4 FSDP state rebuilding." + "reason": "A flash-attention `s_aux=None` crash and the Gemma4 FSDP2 shared-state bug are different code paths." }, { "left": "issue:43854", "right": "issue:44960", "accept": false, - "reason": "Different GLM-related failures with no evidence they are the same bug." + "reason": "These are different model-loading issues with different targets and symptoms." }, { "left": "issue:43957", "right": "issue:44756", "accept": false, - "reason": "Meta-device loading regression is unrelated to the Strix Halo mmap workaround." + "reason": "Meta-device loading breakage and mmap-induced OOM are not the same problem." }, { "left": "issue:45292", "right": "issue:45335", "accept": true, - "reason": "Same resize_token_embeddings bug: output_embeddings and decoder.embed_tokens are both not refreshed." + "reason": "Both report the same underlying `resize_token_embeddings` bug: the resized weights do not update the model's embedding/output path, just on different model variants." }, { "left": "issue:44402", "right": "issue:44451", "accept": false, - "reason": "Both are model load failures, but the titles indicate distinct model-specific issues." + "reason": "A tokenizer vocab-size mismatch and a later model-load failure for a specific checkpoint are not clearly the same bug." }, { "left": "issue:43828", "right": "issue:43957", "accept": false, - "reason": "Autocast dtype mismatch for Phi MoE is unrelated to meta-device loading failures." + "reason": "Autocast dtype mismatch and meta-device loading failures are unrelated." }, { "left": "issue:43645", "right": "issue:44164", "accept": false, - "reason": "Notebook custom-model initialization and extra_state save/load handling are different failures." + "reason": "Notebook custom-model initialization and `extra_state` save/load handling are different issues." }, { - "left": "issue:43257", - "right": "issue:44863", + "left": "issue:43425", + "right": "issue:43828", "accept": false, - "reason": "Qwen3 MOE deepspeed conversion issue is unrelated to NemotronH checkpoint loading." + "reason": "Torch version incompatibility and an autocast dtype mismatch are distinct regressions." }, { - "left": "issue:43425", - "right": "issue:43828", + "left": "issue:43257", + "right": "issue:44863", "accept": false, - "reason": "Torch version incompatibility is unrelated to Phi-tiny-MoE autocast dtype mismatch." + "reason": "Qwen3 MoE conversion under accelerate+deepspeed and NemotronH checkpoint loading are different model-loading failures." }, { "left": "issue:44589", "right": "issue:44756", "accept": false, - "reason": "Float8 storage lookup failure is unrelated to Strix Halo mmap OOM." + "reason": "Missing Float8 storage support and Strix Halo mmap/OOM are unrelated." }, { "left": "issue:44683", "right": "issue:45823", "accept": false, - "reason": "Compiled flex_attention on torch>=2.9 is unrelated to Gemma4 PLE device mismatch." + "reason": "Compiled flex_attention failing on torch>=2.9 and Gemma4 PLE device mismatch are not the same bug." }, { "left": "issue:39404", "right": "issue:45701", "accept": false, - "reason": "Whisper pipeline return_language regression is unrelated to tokenization changes in a different issue." + "reason": "Whisper pipeline `return_language` regression and tokenizer-version-dependent tokenization changes are different issues." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays appropriately conservative. The only clear duplicate cluster is the resize_token_embeddings set (45276/45292/45335), and the other soft-edge rejections are justified by the titles being model- or bug-specific rather than clearly mergeable into one PR." + "feedback": "The summary is grounded in the packet: the only clearly supported duplicate subgroup is the resize_token_embeddings trio (45276/45292/45335), and the other pairings are conservatively rejected. No pair is overstated as mergeable, and the reasoning stays within the evidence shown in titles/body signals." }, "evaluator_used": true, "retried": false, @@ -2338,7 +2350,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 7, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -2409,8 +2421,8 @@ "issue:44479|issue:44805", "issue:43425|issue:44918", "issue:44589|issue:45084", - "issue:43856|issue:44756", "issue:40990|issue:42947", + "issue:43856|issue:44756", "issue:39404|issue:44671", "issue:44164|issue:45759", "issue:43994|issue:44079", @@ -2426,15 +2438,15 @@ "issue:43582|issue:43632", "issue:40990|issue:43421", "issue:43611|issue:43644", - "issue:44206|issue:44220", - "issue:43716|issue:45084" + "issue:43716|issue:45084", + "issue:44206|issue:44220" ], - "prepared_review_unit_hash": "1860ce3a02a5bc3e021b404266db3628f7bbf43aad00c44fcbdd0c99c57769fb", + "prepared_review_unit_hash": "21b5560eae18a2d8736b63f1f28c1ec0746fcd03a91114734bac35151a68d40d", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -2442,219 +2454,219 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 32, - "serialized_chars": 37316, - "estimated_input_tokens": 9329, - "estimated_eval_tokens": 18914 + "serialized_chars": 37318, + "estimated_input_tokens": 9330, + "estimated_eval_tokens": 18916 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly a grab bag of unrelated Transformers regressions and docs bugs. Only the audio feature-extraction pair looks plausibly duplicate; otherwise the soft edges are too broad or only share a subsystem. I\u2019d anchor the cluster on the generic v5 model-loading regression around `base_model_prefix`.", - "confidence": 0.46, - "canonical_issue_reason": "issue:43611 is the cleanest representative of the v5 loading regressions: generic, concrete, and closer to the common model-initialization/loading failure mode than the more specialized neighboring reports.", + "summary": "This cluster is mostly heterogeneous Transformers regressions and docs issues, not a tight duplicate set. The only clear duplicate-like pair is the audio feature-extraction crash (44206/44220).", + "confidence": 0.58, + "canonical_issue_reason": "Issue 44206 is the clearest representative of the only true duplicate pair here: it states the regression, the failing component, and the crash mode more fully than 44220.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43611 is the best overall issue to keep as the canonical issue because it is broad enough to represent the cluster\u2019s main v5 model-loading breakage without being overly model-specific.", + "best_issue_reason": "44206 is the best issue anchor because it is the most explicit, reproducible report among the actual duplicate candidates; the rest of the cluster is too mixed to serve as a single canonical bug.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43906", "right": "issue:44530", "accept": false, - "reason": "Both involve Qwen-related behavior, but one is an isolated reproduction of a prior issue and the other is a PagedAttentionCache crash on Qwen3.5; different failures and code paths." + "reason": "Different bugs: one is Whisper pipeline behavior, the other is Qwen3.5 cache/template parsing." }, { "left": "issue:43425", "right": "issue:45823", "accept": false, - "reason": "Torch version incompatibility vs a Gemma4 PLE device-mismatch forward bug; unrelated symptoms and fixes." + "reason": "Torch-version incompatibility vs Gemma4 PLE device-map mismatch are unrelated failures." }, { "left": "issue:43611", "right": "issue:43645", "accept": false, - "reason": "Both are v5 regressions, but `base_model_prefix` loading failure and custom-model-in-Jupyter initialization are distinct underlying problems." + "reason": "Both are v5 regressions, but they affect different code paths and symptoms." }, { "left": "issue:43425", "right": "issue:43716", "accept": false, - "reason": "Torch 2.10 incompatibility is unrelated to the Mistral-3 image preprocessor dtype mismatch." + "reason": "Different issues: torch compatibility in general vs image preprocessor/model dtype mismatch." }, { "left": "issue:42915", "right": "issue:44863", "accept": false, - "reason": "Different model families and failures: FineGrainedFP8Config on Qwen3Moe vs checkpoint-loading failure in NemotronH." + "reason": "Different model families and different failure modes; not the same underlying bug." }, { "left": "issue:44530", "right": "issue:45084", "accept": false, - "reason": "Qwen3.5 cache crash vs template compilation error; no shared underlying bug." + "reason": "Qwen3.5 linear-attention cache crash is unrelated to template-node compilation errors." }, { "left": "issue:43901", "right": "issue:44509", "accept": false, - "reason": "Both are docs-related, but one is about `return_all_scores` and the other is about removed pipeline task docs; not the same issue." + "reason": "Both are docs-related, but they document different removed/deprecated pipeline behaviors." }, { "left": "issue:39404", "right": "issue:44912", "accept": false, - "reason": "Whisper pipeline language return regression and gpt-oss quantization/perplexity are unrelated." + "reason": "Whisper return_language regression and GPT-OSS quantization fallback are unrelated." }, { "left": "issue:44265", "right": "issue:44898", "accept": false, - "reason": "`torch.export`/`torch_compilable_check` failure and Perceiver resolution/interpolation failure are different bugs." + "reason": "torch.export/torch_compilable_check is unrelated to Perceiver non-default-resolution masking." }, { "left": "issue:43299", "right": "issue:43931", "accept": false, - "reason": "Both concern Qwen3-VL loading, but one is a dev-version breakage for MoE models and the other is a weight-shape mismatch on a specific checkpoint; not enough to treat as the same bug." + "reason": "Both concern Qwen3-VL loading, but one is a version breakage and the other is a checkpoint shape mismatch." }, { "left": "issue:44479", "right": "issue:44805", "accept": false, - "reason": "Video-input regression across Qwen VL variants vs a generic mask-shape IndexError; different failure modes." + "reason": "Video-input regression for specific VL models is not the same as a generic mask shape IndexError." }, { "left": "issue:43425", "right": "issue:44918", "accept": false, - "reason": "Torch compatibility and TRL SFT input-embedding unpacking are unrelated." + "reason": "Torch compatibility and Qwen3.5 embedding unpacking under TRL are different problems." }, { "left": "issue:44589", "right": "issue:45084", "accept": false, - "reason": "Float8 storage lookup failure is not the same as the template-node compilation error." + "reason": "Float8 storage lookup failure is unrelated to non-template-node compilation." }, { - "left": "issue:43856", - "right": "issue:44756", + "left": "issue:40990", + "right": "issue:42947", "accept": false, - "reason": "Both mention memory/OOM, but one is Qwen3 MoE training memory inefficiency and the other is mmap behavior on Strix Halo; different root causes." + "reason": "Perplexity anomaly and LoRA gradient-checkpointing behavior are distinct issues." }, { - "left": "issue:40990", - "right": "issue:42947", + "left": "issue:43856", + "right": "issue:44756", "accept": false, - "reason": "Perplexity regression on gpt-oss-20b and gradient-checkpointing ineffectiveness with LoRA are separate issues." + "reason": "Qwen3 MoE training memory usage and mmap OOM on Strix Halo are not the same bug." }, { "left": "issue:39404", "right": "issue:44671", "accept": false, - "reason": "Whisper pipeline language return regression vs CamemBERT masked-LM prediction regression; unrelated model paths." + "reason": "Whisper pipeline regression and CamemBERT masked-LM prediction regression are unrelated." }, { "left": "issue:44164", "right": "issue:45759", "accept": false, - "reason": "`extra_state` serialization/loading and `text_config` unwrapping for composite Qwen configs are distinct loader issues." + "reason": "Both involve model loading/serialization, but they hit different APIs and failure modes." }, { "left": "issue:43994", "right": "issue:44079", "accept": false, - "reason": "SigLIP2 bad outputs with AutoModel/pipeline and ModelOutput key assignment when a value was previously None are different bugs." + "reason": "SigLIP2 nonsensical outputs and ModelOutput key assignment are different defects." }, { "left": "issue:36032", "right": "issue:43452", "accept": false, - "reason": "T5 tokenizer special-token method conflict and gguf-related from_pretrained breakage are unrelated loading failures." + "reason": "Tokenizer special-token conflict is unrelated to gguf_file loading failures." }, { "left": "issue:43596", "right": "issue:44683", "accept": false, - "reason": "DeepSpeed ZeRO3/BertModel index error and compiled flex_attention failure on newer torch versions do not share the same root cause." + "reason": "DeepSpeed ZeRO3 BertModel init error is unrelated to compiled flex_attention on newer torch." }, { "left": "issue:44671", "right": "issue:44991", "accept": false, - "reason": "CamemBERT incorrect predictions and tokenizer loading failure for EMBEDDIA/est-roberta are different issues." + "reason": "CamemBERT masked-LM regression and tokenizer loading failure for est-roberta are different issues." }, { "left": "issue:44991", "right": "issue:45081", "accept": false, - "reason": "Both are tokenizer-loading regressions, but one is model-specific tokenizer loading for EMBEDDIA/est-roberta and the other is Mistral regex patching; not the same bug." + "reason": "Different tokenizers/models and different failure causes; not mergeable into one bug." }, { "left": "issue:44737", "right": "issue:45859", "accept": false, - "reason": "Both involve device placement/offload concerns, but XLNet CPU `arange` work and Qwen3_5Moe rotary embedding CPU-offload incompatibility are separate code paths." + "reason": "CPU-device placement bug in XLNet is unrelated to Qwen3.5 MoE rotary embedding offload issues." }, { "left": "issue:32090", "right": "issue:39404", "accept": false, - "reason": "Trainer GPU broadcast TypeError and Whisper `return_language` regression are unrelated." + "reason": "Trainer broadcast TypeError and Whisper return_language regression are unrelated." }, { "left": "issue:44164", "right": "issue:44479", "accept": false, - "reason": "Serialization/loading of extra state is unrelated to Qwen VL video-input regression." + "reason": "Serialization extra_state handling and video-input regression are different code paths." }, { "left": "issue:44488", "right": "issue:45081", "accept": false, - "reason": "Loading `cjvt/sleng-bert` and the Mistral regex patch crash are different tokenizer issues." + "reason": "sleng-bert tokenizer load failure is unrelated to the Mistral regex patch crash." }, { "left": "issue:44661", "right": "issue:44683", "accept": false, - "reason": "`add-new-model-like`/mapping-name handling and compiled flex_attention are unrelated." + "reason": "Tokenizer mapping bug and flex_attention compilation bug are unrelated." }, { "left": "issue:43582", "right": "issue:43632", "accept": false, - "reason": "Apple Silicon allocator warmup TypeError and `_is_hf_initialized` flag breakage are different regressions." + "reason": "AppleSilicon warmup TypeError and _is_hf_initialized flag regression are different problems." }, { "left": "issue:40990", "right": "issue:43421", "accept": false, - "reason": "Perplexity regression and runtime special-token post-processor update behavior are not the same bug." + "reason": "Perplexity issue and runtime special-token post-processor update are unrelated." }, { "left": "issue:43611", "right": "issue:43644", "accept": false, - "reason": "Both are v5 model-loading regressions, but `base_model_prefix` handling and non-persistent buffer initialization are separate underlying defects." - }, - { - "left": "issue:44206", - "right": "issue:44220", - "accept": true, - "reason": "These both point at the same audio feature-extraction path: a regression in `LasrFeatureExtractor`/`_torch_extract_fbank_features` around the same internal function call and crash mode." + "reason": "Both are Transformers v5 regressions, but they affect different mechanisms and symptoms." }, { "left": "issue:43716", "right": "issue:45084", "accept": false, - "reason": "Mistral-3 image preprocessor dtype mismatch and template-node compilation errors are unrelated." + "reason": "Multimodal dtype mismatch is unrelated to template-node compilation failure." + }, + { + "left": "issue:44206", + "right": "issue:44220", + "accept": true, + "reason": "Both point to the same audio feature-extraction failure around `_torch_extract_fbank_features`; 44220 looks like the lower-level duplicate." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is well grounded in the packet and stays conservative on the soft edges. The only accepted pair, issue:44206 and issue:44220, looks plausibly like the same audio feature-extraction bug and mergeable into one fix. Anchoring on issue:43611 as the canonical v5 loading regression is also reasonable given the surrounding reports are mostly model-specific or unrelated." + "feedback": "The summary is grounded in the packet: it treats the cluster as mostly heterogeneous, and the only accepted pair (44206/44220) is supported by closely related audio feature-extraction titles. The rejected soft pairs are phrased conservatively and do not overclaim duplicate status." }, "evaluator_used": true, "retried": false, @@ -2667,7 +2679,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 8, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -2725,10 +2737,10 @@ "issue:45584" ], "soft_pairs": [ - "issue:43883|issue:44488", "issue:44488|issue:44987", - "issue:34567|issue:40444", + "issue:43883|issue:44488", "issue:43643|issue:44530", + "issue:34567|issue:40444", "issue:44811|issue:45584", "issue:43644|issue:43646", "issue:44451|issue:44987", @@ -2762,12 +2774,12 @@ "issue:42915|issue:44291", "issue:36032|issue:43742" ], - "prepared_review_unit_hash": "453af618e3a203eec6efd592b0bf03a1d19af376cdcd30578caa3e95087322f8", + "prepared_review_unit_hash": "e131a590db60c5c88ffd87097fa9dbd320ada125279ce5cdf6a34747b7b189ff", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -2775,243 +2787,249 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 36, - "serialized_chars": 38525, - "estimated_input_tokens": 9632, - "estimated_eval_tokens": 19520 + "serialized_chars": 38522, + "estimated_input_tokens": 9631, + "estimated_eval_tokens": 19518 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Most pairs are unrelated model-specific regressions, not true duplicates. The only clear duplicate-like thread is the Qwen3.5 `save_pretrained` serialization bug, where one issue is the broader report and the other is a narrower symptom.", - "confidence": 0.39, - "canonical_issue_reason": "issue:45216 is the broadest description of the Qwen3.5 `save_pretrained` regression; issue:45357 looks like a narrower symptom about incorrect visual encoder keys.", + "summary": "This cluster is mostly heterogeneous and centered on separate Transformers v5/model-loading regressions. Only one soft duplicate looks strong enough to merge: the Qwen3.5 save_pretrained checkpoint serialization regression.", + "confidence": 0.66, + "canonical_issue_reason": "Issue 45216 is the clearest duplicate anchor: it reports a concrete Qwen3.5 save_pretrained regression, and 45357 describes the same incorrect checkpoint serialization for visual encoder keys.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45216 is the best umbrella issue for the one clearly duplicate-like thread in this set.", + "best_issue_reason": "45216 is the most suitable representative issue because it is concrete, versioned, and has a direct near-duplicate in 45357 with the same save_pretrained checkpoint bug.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:43883", - "right": "issue:44488", - "accept": false, - "reason": "Different bugs: Molmo tied-weights metadata vs loading a specific checkpoint." - }, { "left": "issue:44488", "right": "issue:44987", "accept": false, - "reason": "Both are load failures, but for different models and different failure modes." + "reason": "Both are model-loading failures, but for different checkpoints and likely different root causes." }, { - "left": "issue:34567", - "right": "issue:40444", + "left": "issue:43883", + "right": "issue:44488", "accept": false, - "reason": "Trainer token counting bug vs Qwen2.5-VL iterable dataset/multi-image training bug." + "reason": "Different bugs: tied-weights attribute error vs. model loading failure." }, { "left": "issue:43643", "right": "issue:44530", "accept": false, - "reason": "Missing fields from `AutoConfig` with `trust_remote_code` is unrelated to Qwen3.5 cache group-type errors." + "reason": "Different code paths: AutoConfig field loss vs. PagedAttentionCache group-type crash." + }, + { + "left": "issue:34567", + "right": "issue:40444", + "accept": false, + "reason": "Trainer token accounting and multimodal iterable dataset failures are unrelated." }, { "left": "issue:44811", "right": "issue:45584", "accept": false, - "reason": "Both involve Whisper, but one is `batch_decode` special-token handling and the other is empty-transcription generation after alignment." + "reason": "Both involve Whisper, but one is batch_decode token skipping and the other is empty-transcription generation failure." }, { "left": "issue:43644", "right": "issue:43646", "accept": false, - "reason": "Both are v5 regressions, but one is non-persistent buffers and the other is custom model initialization." + "reason": "Both are v5 regressions, but one is non-persistent buffer corruption and the other is custom model initialization." }, { "left": "issue:44451", "right": "issue:44987", "accept": false, - "reason": "Different checkpoints with no shared code-path evidence." + "reason": "Different models and load failures; no clear shared bug." }, { "left": "issue:43541", "right": "issue:45084", "accept": false, - "reason": "Torch dynamo grouped_mm tracing error is unrelated to template-node compilation." + "reason": "Unrelated failures: torch dynamo grouped_mm tracing vs. template-node compilation." }, { "left": "issue:36032", "right": "issue:42915", "accept": false, - "reason": "Tokenizer method conflict vs Qwen3Moe FP8 config loading failure." + "reason": "Tokenizer attribute conflict and Qwen3Moe FP8 failure are unrelated." }, { "left": "issue:43452", "right": "issue:43482", "accept": false, - "reason": "Both mention GGUF loading, but one is a general `gguf_file` API regression and the other is a Qwen2.5-GGUF-specific v5 failure." + "reason": "Both mention GGUF, but one is a generic gguf_file loader breakage and the other is a specific Qwen2.5-GGUF v5 loading failure." }, { "left": "issue:42915", "right": "issue:44530", "accept": false, - "reason": "Qwen3Moe FP8 config issue and Qwen3.5 linear-attention cache crash are different bugs." + "reason": "Different model families and failure modes." }, { "left": "issue:43317", "right": "issue:43482", "accept": false, - "reason": "Device-map/offload dequantized-model loading issue is not the same as Qwen2.5-GGUF v5 loading failure." + "reason": "Different loading paths: device_map/offload dequantization vs. GGUF/v5 failure." }, { "left": "issue:44849", "right": "issue:45325", "accept": false, - "reason": "Different Qwen family regressions: hidden-states output vs RoPE position-id scaling." + "reason": "Different Qwen bugs: hidden-state handling vs. RoPE position scaling." }, { "left": "issue:43883", "right": "issue:44991", "accept": false, - "reason": "Different problems: missing tied-weight keys vs tokenizer loading for another model." + "reason": "Different model-loading errors with different underlying causes." }, { "left": "issue:43404", "right": "issue:44466", "accept": false, - "reason": "Both concern tied weights, but one is a model-specific untied `lm_head` and the other is save serialization differing by device." + "reason": "Related to tied weights, but one is untied lm_head in a model class and the other is device-dependent serialization." }, { "left": "issue:36032", "right": "issue:43645", "accept": false, - "reason": "Tokenizer attribute conflict is unrelated to custom model initialization in notebooks." + "reason": "Tokenizer load conflict and custom model initialization are unrelated." }, { "left": "issue:45084", "right": "issue:45507", "accept": false, - "reason": "Template-node compilation error is unrelated to GraniteMoEHybrid invalid-method calls." + "reason": "Different failures in different subsystems; no shared bug." }, { "left": "issue:43262", "right": "issue:43377", "accept": false, - "reason": "Audio chat-template sampling-rate bug vs MIMI padding-mask batch inconsistency are different issues." + "reason": "Audio processor sampling-rate defaulting and MIMI padding-mask mismatch are different issues." }, { "left": "issue:43646", "right": "issue:44534", "accept": false, - "reason": "Custom model initialization and non-persistent buffer junk are separate regressions." + "reason": "Both are v5 init-related regressions, but the concrete bugs differ: custom model init vs. non-persistent buffer junk." }, { "left": "issue:44987", "right": "issue:44991", "accept": false, - "reason": "Different model-loading failures with no shared concrete bug." + "reason": "Both are loader failures, but for different model/tokenizer packages and different symptoms." }, { "left": "issue:43994", "right": "issue:44610", "accept": false, - "reason": "SigLIP2 nonsense outputs vs OmDet-Turbo image-size mismatch are unrelated." + "reason": "Different multimodal models and mismatched preprocessing expectations." + }, + { + "left": "issue:44265", + "right": "issue:44683", + "accept": false, + "reason": "Different export/compile failures with different triggers." }, { "left": "issue:44403", "right": "issue:45081", "accept": false, - "reason": "Generic loading noise is not the same as the Mistral regex patch crash." + "reason": "Noise on loading vs. a specific tokenizer regex patch crash are not the same bug." }, { "left": "issue:43322", "right": "issue:43540", "accept": false, - "reason": "Llava Next loading segfault and Qwen3OmniMoe video-input ValueError are different code paths." + "reason": "Different multimodal failures: Llava Next load segfault vs. Qwen3OmniMoe video processing error." }, { "left": "issue:43377", "right": "issue:43819", "accept": false, - "reason": "Both are model-consistency bugs, but for different models and different mechanisms." + "reason": "Both are audio-related, but one is padding-mask batching and the other is DAC STE behavior." }, { "left": "issue:43645", "right": "issue:44534", "accept": false, - "reason": "Jupyter custom-model initialization issue is distinct from buffer serialization junk." + "reason": "Custom model initialization in notebooks is not the same as buffer initialization corruption." }, { "left": "issue:42915", "right": "issue:45084", "accept": false, - "reason": "Qwen3Moe FP8 config and template compilation are unrelated." + "reason": "Unrelated model/config problems." }, { "left": "issue:44451", "right": "issue:45081", "accept": false, - "reason": "Different models and different failure modes." + "reason": "Different model-loading bugs with different failure modes." }, { "left": "issue:45216", "right": "issue:45357", "accept": true, - "reason": "Same underlying Qwen3.5 `save_pretrained` serialization regression; the second issue is a narrower symptom about incorrect visual encoder keys." + "reason": "Same save_pretrained checkpoint regression for Qwen3.5, with 45357 explicitly describing the same incorrect visual encoder keys." }, { "left": "issue:44987", "right": "issue:45081", "accept": false, - "reason": "Loading a specific model vs Mistral tokenizer regex patch crash are unrelated." + "reason": "Different failure surfaces: loading a model vs. tokenizer regex patch crash." }, { "left": "issue:44220", "right": "issue:44683", "accept": false, - "reason": "Audio feature extraction bug vs flex_attention compile failure are unrelated." + "reason": "Different low-level feature/export issues." }, { "left": "issue:44265", "right": "issue:44610", "accept": false, - "reason": "`torch.export`/`torch_compilable_check` failure is unrelated to the OmDet-Turbo processor size mismatch." + "reason": "torch.export checker failure and image-size preprocessing mismatch are unrelated." }, { "left": "issue:43404", "right": "issue:45127", "accept": false, - "reason": "Both mention tied embeddings, but one is untied weights in a model class and the other is LoRA merge collapse." + "reason": "Both mention tied weights, but the underlying bugs differ: missing tying vs. LoRA merge collapse." }, { "left": "issue:43296", "right": "issue:43531", "accept": false, - "reason": "PaddleOCR-VL load failure in vLLM is unrelated to Qwen3-MoE sliding window behavior." + "reason": "PaddleOCR-VL load failure and Qwen3-MoE sliding_window issue are unrelated." }, { "left": "issue:43632", "right": "issue:44756", "accept": false, - "reason": "`_is_hf_initialized` flag regression is unrelated to Strix Halo mmap OOM behavior." + "reason": "Different regressions: _is_hf_initialized flag handling vs. mmap OOM on Strix Halo." }, { "left": "issue:42915", "right": "issue:44291", "accept": false, - "reason": "Different regressions: Qwen3Moe FP8 config vs generic `init_empty_weights` argument error." + "reason": "Different FP8/init issues; no shared underlying change." }, { "left": "issue:36032", "right": "issue:43742", "accept": false, - "reason": "Tokenizer method-name collision is unrelated to a key error loading MobileLLM-125M." + "reason": "Tokenizer method conflict and MobileLLM load key error are unrelated." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet, and the one accepted soft-edge pair is supported by the issue titles: 45216 is the broader Qwen3.5 `save_pretrained` regression, while 45357 is a narrower symptom about visual encoder keys. The rejected pairs are phrased conservatively and do not overclaim duplication based on the available evidence." + "feedback": "The summary is grounded in the packet, and the only accepted soft pair (45216/45357) is well supported as the same Qwen3.5 save_pretrained serialization bug. The rejected soft pairs are stated conservatively, with no clear overclaiming beyond what the titles and packet text support." }, "evaluator_used": true, "retried": false, @@ -3024,7 +3042,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 9, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -3084,13 +3102,13 @@ "soft_pairs": [ "issue:44062|issue:44987", "issue:42915|issue:44589", - "issue:43611|issue:44534", "issue:43531|issue:44877", - "issue:41553|issue:43582", + "issue:43611|issue:44534", "issue:43317|issue:43856", "issue:43425|issue:44403", "issue:44479|issue:45325", "issue:40990|issue:44811", + "issue:41553|issue:43582", "issue:42175|issue:45542", "issue:43818|issue:45357", "issue:44462|issue:45812", @@ -3113,12 +3131,12 @@ "issue:43531|issue:44291", "issue:43611|issue:43646" ], - "prepared_review_unit_hash": "ce5136055948fe3fb3a5892ba2a69985498d5ed612770c1672f6f579c2fdda02", + "prepared_review_unit_hash": "9ec3342a576e5ba4fb5095e8c3df47a53d8ae4ff3eabc407f727ffabc048a4e0", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -3126,7 +3144,7 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 36777, + "serialized_chars": 36778, "estimated_input_tokens": 9195, "estimated_eval_tokens": 18646 }, @@ -3135,201 +3153,198 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly heterogeneous. The closest-looking pairs are related regressions, but from titles alone they are not confirmed to be the same concrete bug or change, so I would not merge any soft edges.", - "confidence": 0.61, - "canonical_issue_reason": "No single canonical issue stands out: the cluster is mixed, and the nearest matches are only loosely related from titles alone.", + "summary": "This cluster is mostly a grab bag of Transformers regression reports across unrelated models/subsystems. The soft pairs are thematically similar in places, but none look like the same concrete bug/change; I would not merge any of them.", + "confidence": 0.86, + "canonical_issue_reason": "issue:45020 is the broadest umbrella report here: it captures the general class of recent-version regressions breaking model loading/behavior for remote-code/custom-model cases, which best matches the cluster\u2019s overall theme.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45479 is the best standalone representative because it describes a concrete, broadly applicable classification failure more precisely than most other items.", + "best_issue_reason": "issue:45020 is the strongest single representative because it is broad, open, and describes the overarching regression pattern rather than one model-specific symptom.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44062", "right": "issue:44987", "accept": false, - "reason": "Both are tokenizer/loading regressions, but the titles describe different failure modes and do not establish the same bug." + "reason": "Both are loading regressions in recent Transformers, but they describe different failure modes and models; not the same concrete tokenizer/model bug." }, { "left": "issue:42915", "right": "issue:44589", "accept": false, - "reason": "Both mention FP8-related breakage, but one is a config failure and the other is a storage-object TypeError; not the same issue." - }, - { - "left": "issue:43611", - "right": "issue:44534", - "accept": false, - "reason": "Both are Transformers v5 regressions, but the titles point to different concrete failures and likely different code paths." + "reason": "Qwen3MoE FP8 failure vs missing Float8 storage class are different low-level errors and likely different code paths." }, { "left": "issue:43531", "right": "issue:44877", "accept": false, - "reason": "Different models and different symptoms; the titles do not show a shared underlying bug." + "reason": "One is a Qwen3-MoE sliding-window bug, the other is strict config handling for granite_speech; unrelated subsystems." }, { - "left": "issue:41553", - "right": "issue:43582", + "left": "issue:43611", + "right": "issue:44534", "accept": false, - "reason": "Unrelated subsystems: tokenizer loading/error messaging versus Apple Silicon allocator warmup." + "reason": "Base-model-prefix loading breakage and non-persistent-buffer corruption are distinct issues." }, { "left": "issue:43317", "right": "issue:43856", "accept": false, - "reason": "Both involve memory/device behavior, but one is device-map/offload loading and the other is MoE training memory usage." + "reason": "Device-map/offload loading failure and Qwen3 MoE memory inefficiency are not the same bug." }, { "left": "issue:43425", "right": "issue:44403", "accept": false, - "reason": "Version compatibility and loading-noise complaints are not the same concrete bug." + "reason": "Torch 2.10 compatibility and noisy model-loading output are unrelated." }, { "left": "issue:44479", "right": "issue:45325", "accept": false, - "reason": "These are related Qwen VL/video-position regressions, but the titles alone do not confirm the same root cause or code path." + "reason": "Both involve Qwen VL/video behavior, but one is a video-input regression and the other is a rope-index scaling bug for still images." }, { "left": "issue:40990", "right": "issue:44811", "accept": false, - "reason": "Different models and different behaviors: perplexity evaluation versus Whisper decoding options." + "reason": "Perplexity regression on gpt-oss and Whisper batch_decode skip_special_tokens are unrelated." + }, + { + "left": "issue:41553", + "right": "issue:43582", + "accept": false, + "reason": "AutoTokenizer/Voxtral error handling and an Apple Silicon allocator TypeError are different problems." }, { "left": "issue:42175", "right": "issue:45542", "accept": false, - "reason": "Both touch backend packaging, but the reported breakages are not the same concrete failure." + "reason": "Both touch TF packaging/backend handling, but one is missing TensorFlow in a torch extra and the other is an undefined backend when only tensorboard is installed." }, { "left": "issue:43818", "right": "issue:45357", "accept": false, - "reason": "Different model families and distinct bugs: missing temporal attention versus incorrect saved key mapping." + "reason": "Video-LLaVA tower/temporal-attention bug and Qwen3.5 save_pretrained key regression are different model-specific defects." }, { "left": "issue:44462", "right": "issue:45812", "accept": false, - "reason": "Both involve AutoTokenizer, but one is repository tokenizer precedence and the other is a Granite token-ID regression." + "reason": "Both are AutoTokenizer regressions, but one ignores tokenizer.json while the other miscomputes Granite token IDs; not the same fix." }, { "left": "issue:36032", "right": "issue:41720", "accept": false, - "reason": "Tokenizer loading conflict versus CUDA assertion during device mapping; unrelated." + "reason": "Tokenizer method-name conflict and Qwen3 auto-device-map cuda assert are unrelated." }, { "left": "issue:44079", "right": "issue:45663", "accept": false, - "reason": "A ModelOutput key assignment bug and a Gemma-4 FSDP2 KeyError are different issues." + "reason": "ModelOutput key assignment and Gemma4 shared_kv_states rebuilding are unrelated code paths." }, { "left": "issue:43421", "right": "issue:44568", "accept": false, - "reason": "Both mention special tokens, but one is runtime post-processor updates and the other is BOS/EOS emission for a specific tokenizer." + "reason": "Runtime special-token post-processing update and add_special_tokens not adding BOS/EOS are different tokenizer behaviors." }, { "left": "issue:43792", "right": "issue:44589", "accept": false, - "reason": "A Whisper runtime failure and a missing Float8 storage object are unrelated." + "reason": "Whisper runtime failure and missing Float8 storage support are different failures." }, { "left": "issue:43632", "right": "issue:44534", "accept": false, - "reason": "Distinct v5 regressions affecting different initialization/buffer mechanisms." + "reason": "_is_hf_initialized flag breakage and junk-filled non-persistent buffers are separate regressions." }, { "left": "issue:44403", "right": "issue:44991", "accept": false, - "reason": "A noise/logging issue and a tokenizer loading failure are not the same bug." + "reason": "Noisy load messages and tokenizer loading failure for EMBEDDIA/est-roberta are unrelated." }, { "left": "issue:44683", "right": "issue:45020", "accept": false, - "reason": "Compiled flex attention on torch>=2.9 and remote_code loading are separate problems." + "reason": "Compiled flex_attention on torch>=2.9 is a torch/kernel compatibility issue, not the remote_code loading regression described in 45020." }, { "left": "issue:43482", "right": "issue:45538", "accept": false, - "reason": "GGUF loading under v5 and CLIPTokenizer model_max_length are unrelated." + "reason": "GGUF loading with transformers v5 and CLIPTokenizer max-length misuse are different tokenizer/model bugs." }, { "left": "issue:44829", "right": "issue:45479", "accept": false, - "reason": "These are related degenerate-training reports, but the titles do not confirm the same failure path or code change." + "reason": "Flash-attention training degeneration and zero-loss classification behavior are both training problems but not the same concrete defect." }, { "left": "issue:33666", "right": "issue:40444", "accept": false, - "reason": "Both are Qwen VL training issues, but they affect different workflows and are not the same bug." + "reason": "Qwen2-VL multi-GPU training and iterable-dataset multi-image prompting are different training scenarios and failures." }, { "left": "issue:44291", "right": "issue:44589", "accept": false, - "reason": "Different TypeErrors caused by different v5 changes; no shared code-path evidence." + "reason": "init_empty_weights unexpected argument and missing Float8 storage are different initialization/storage issues." }, { "left": "issue:43482", "right": "issue:43525", "accept": false, - "reason": "Different model-loading failures with different symptoms and likely different causes." + "reason": "GGUF loading failure and missing pad_token_id in Llama4Config are unrelated." }, { "left": "issue:40444", "right": "issue:45325", "accept": false, - "reason": "Both are Qwen2.5-VL-related, but one is multi-image training and the other is temporal position scaling." + "reason": "Multi-image iterable dataset failure and Qwen2.5-VL still-image position-id scaling are different multimodal bugs." }, { "left": "issue:43377", "right": "issue:45491", "accept": false, - "reason": "Both involve batching/masking behavior, but they are separate models and separate bugs." + "reason": "Batched-vs-single MIMI output mismatch from missing padding mask and Gemma3 NaNs from sliding-window all-padding windows are different issues." }, { "left": "issue:41720", "right": "issue:45081", "accept": false, - "reason": "CUDA assertion during device mapping and a Mistral tokenizer regex crash are unrelated." + "reason": "Qwen3 device-map assert and Mistral tokenizer regex patch crash are unrelated." }, { "left": "issue:42175", "right": "issue:43296", "accept": false, - "reason": "A packaging/backend install issue and a vLLM model-loading failure are different problems." + "reason": "TF backend packaging and PaddleOCR-VL load failure in vLLM are different problems." }, { "left": "issue:43531", "right": "issue:44291", "accept": false, - "reason": "Sliding-window Qwen3-MoE behavior and an init_empty_weights argument regression are unrelated." + "reason": "Qwen3-MoE sliding-window behavior and init_empty_weights argument handling are unrelated." }, { "left": "issue:43611", "right": "issue:43646", "accept": false, - "reason": "Both are broad Transformers v5 regressions, but the titles describe different concrete failures and not one mergeable fix." + "reason": "Both are Transformers v5 loading regressions, but one is specifically base_model_prefix handling and the other is generic custom model initialization; not enough evidence of the same bug." } ] }, - "evaluator_result": { - "accept": false, - "feedback": "The cluster-level summary is directionally plausible, but a few claims go beyond what the packet supports. In particular, the two accepted soft pairs are asserted too strongly from titles alone: 44479/45325 is described as the same regression with 45325 as the root cause, and 44829/45479 is called the same zero-loss bug. The packet only gives issue titles, so these should be framed more cautiously as related, possibly overlapping regressions rather than confirmed duplicates or shared code paths." - }, - "evaluator_used": true, - "retried": true, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null @@ -3339,7 +3354,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 10, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -3407,12 +3422,12 @@ "issue:42915|issue:43482", "issue:44079|issue:45072", "issue:40444|issue:45381", - "issue:45325|issue:45381", "issue:43644|issue:44079", + "issue:45325|issue:45381", "issue:44387|issue:44617", - "issue:43881|issue:44488", "issue:43296|issue:45800", "issue:44479|issue:45823", + "issue:43881|issue:44488", "issue:35707|issue:40444", "issue:44291|issue:44877", "issue:43317|issue:43873", @@ -3422,21 +3437,21 @@ "issue:43606|issue:43819", "issue:43262|issue:43746", "issue:41720|issue:45823", - "issue:43526|issue:43883", "issue:43454|issue:43550", "issue:43377|issue:44610", "issue:43377|issue:44898", "issue:43454|issue:45072", "issue:40990|issue:45584", "issue:43572|issue:45759", - "issue:39692|issue:40444" + "issue:39692|issue:40444", + "issue:43526|issue:43883" ], - "prepared_review_unit_hash": "5b3dcbb3bb817f96037c2dd072d87cd443171bfe63d5680526bc0e933dfe659a", + "prepared_review_unit_hash": "9f9e616372c5fe7ea2b6e7c39740c8e65212cc8e0bd531526cecc16f6656a11c", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -3444,225 +3459,228 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 33, - "serialized_chars": 37582, - "estimated_input_tokens": 9396, - "estimated_eval_tokens": 19048 + "serialized_chars": 37587, + "estimated_input_tokens": 9397, + "estimated_eval_tokens": 19050 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a grab-bag of distinct model-loading, multimodal, quantization, and device-mapping regressions. None of the soft edges look like true duplicates, and there are no PRs to consolidate.", - "confidence": 0.62, - "canonical_issue_reason": "issue:43644 is the broadest systemic regression in the set, centered on a Transformers v5 state/buffer behavior break that is representative of the wider v5-related failures here.", + "summary": "Mostly unrelated issue reports across different models/code paths. The Qwen2.5-VL position-id reports are the only close pair, but they look related rather than a confirmed duplicate; I\u2019d keep 45325 as the cluster anchor.", + "confidence": 0.78, + "canonical_issue_reason": "issue:45325 is the best anchor because it is earlier and more specific about the likely root path (`get_rope_index` / temporal position-id scaling), while 45381 reads as a related video-input symptom rather than a clearly identical bug.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43644 is the best umbrella issue candidate because it describes a concrete, cross-cutting v5 regression with broad downstream impact and is likely to be the most reusable reference point.", + "best_issue_reason": "issue:45325 is the strongest representative for the Qwen2.5-VL position-id regression cluster: it is concrete, root-cause oriented, and precedes the later video report.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44265", "right": "issue:45072", "accept": false, - "reason": "Different code paths and symptoms: torch.export support for torch_compilable_check versus bfloat16 dtype mismatches during inference." + "reason": "Different failures: torch.export/torch_compilable_check vs bfloat16 dtype mismatch." }, { "left": "issue:43632", "right": "issue:45072", "accept": false, - "reason": "One is an initialization flag regression; the other is a dtype-mismatch issue under bfloat16 inference. Not the same bug." + "reason": "Unrelated bugs: `_is_hf_initialized` breakage vs bfloat16 inference dtype mismatch." }, { "left": "issue:43454", "right": "issue:44466", "accept": false, - "reason": "Both involve tied weights, but one is a missing weight-tying bug and the other is inconsistent serialization behavior; distinct underlying failures." + "reason": "Both mention tied weights, but one is missing lm_head tying and the other is device-dependent serialization; different code paths." }, { "left": "issue:43994", "right": "issue:44898", "accept": false, - "reason": "Different models and failure modes: SigLIP2 pipeline/AutoModel mismatch versus Perceiver non-default-resolution classification." + "reason": "Different vision-model issues with different symptoms and mechanisms." }, { "left": "issue:44079", "right": "issue:44534", "accept": false, - "reason": "ModelOutput key assignment logic is unrelated to non-persistent buffer initialization/serialization." + "reason": "ModelOutput key assignment is unrelated to non-persistent-buffer junk serialization." }, { "left": "issue:45325", "right": "issue:45834", "accept": false, - "reason": "Both are multimodal indexing bugs, but one is a Qwen2.5-VL temporal RoPE scaling issue and the other is a Kosmos2.5 long-OCR index error." + "reason": "Both are multimodal indexing bugs, but the concrete models and failure modes differ (Qwen2.5-VL position IDs vs Kosmos2.5 OCR long-input indexing)." }, { "left": "issue:43792", "right": "issue:43957", "accept": false, - "reason": "Different failure classes: Whisper model runtime failure versus meta-device loading breakage across some models." + "reason": "Whisper runtime failure is unrelated to meta-device loading breakage in other models." }, { "left": "issue:42915", "right": "issue:43482", "accept": false, - "reason": "Different models and mechanisms: FineGrainedFP8Config failure versus GGUF loading failure in v5." + "reason": "Different issues: FineGrainedFP8Config failure vs GGUF loading failure under v5." }, { "left": "issue:44079", "right": "issue:45072", "accept": false, - "reason": "ModelOutput key handling is not the same as dtype mismatches in bf16 inference." + "reason": "ModelOutput key handling is unrelated to dtype mismatches under bfloat16." }, { "left": "issue:40444", "right": "issue:45381", "accept": false, - "reason": "Both are Qwen2.5-VL related, but one is training with multiple images per prompt and the other is video vision_position_ids; not the same concrete bug." - }, - { - "left": "issue:45325", - "right": "issue:45381", - "accept": false, - "reason": "Closely related family, but still different symptoms: still-image temporal position scaling versus video vision_position_id computation." + "reason": "Same family (Qwen2.5-VL) but different concrete bugs: multi-image finetuning vs video vision_position_ids." }, { "left": "issue:43644", "right": "issue:44079", "accept": false, - "reason": "Buffer initialization junk and ModelOutput key assignment are unrelated regressions." + "reason": "Non-persistent-buffer junk and ModelOutput key assignment are distinct regressions." }, { - "left": "issue:44387", - "right": "issue:44617", + "left": "issue:45325", + "right": "issue:45381", "accept": false, - "reason": "Both can end in OOM, but one is a Transformers int4 memory regression and the other is a model-specific video OOM." + "reason": "Related Qwen2.5-VL position-id regressions, but the packet only supports plausible relatedness; the surfaces differ (still-image temporal scaling vs video `vision_position_ids`)." }, { - "left": "issue:43881", - "right": "issue:44488", + "left": "issue:44387", + "right": "issue:44617", "accept": false, - "reason": "Separate model-loading failures for different models; no shared concrete code-path shown." + "reason": "Different resource problems: int4 quantization memory regression vs video OOM." }, { "left": "issue:43296", "right": "issue:45800", "accept": false, - "reason": "Different compatibility problems: vLLM/PaddleOCR-VL loading versus a torch 2.4.1 / Transformers 5.8.0 incompatibility." + "reason": "Different problems: PaddleOCR-VL loading failure vs torch/transformers version incompatibility." }, { "left": "issue:44479", "right": "issue:45823", "accept": false, - "reason": "Different multimodal/device issues: Qwen VL video regression versus Gemma4 PLE device mismatch in forward." + "reason": "Device-related, but not the same concrete bug: Qwen VL video regression vs Gemma4 PLE forward mismatch." + }, + { + "left": "issue:43881", + "right": "issue:44488", + "accept": false, + "reason": "Different models and different loading failures." }, { "left": "issue:35707", "right": "issue:40444", "accept": false, - "reason": "Progressive generation with inputs_embeds/past_key_values is unrelated to Qwen2.5-VL multi-image finetuning failures." + "reason": "Progressive generation with inputs_embeds/past_key_values is unrelated to Qwen2.5-VL multi-image finetuning." }, { "left": "issue:44291", "right": "issue:44877", "accept": false, - "reason": "One is an unexpected _is_hf_initialized argument during init_empty_weights; the other is strict config validation blocking granite_speech config loading." + "reason": "Both are loading/config issues, but the specific failures are different (`init_empty_weights` argument vs strict granite_speech config)." }, { "left": "issue:43317", "right": "issue:43873", "accept": false, - "reason": "Both mention offloading/quantization, but one is dequantized model loading with auto device maps and the other is a broader offloading complaint; not clearly the same bug." + "reason": "Both involve offload/quantization, but the reported failures are not the same code-path bug." }, { "left": "issue:43606", "right": "issue:44265", "accept": false, - "reason": "CPU offload device mismatch and torch.export support for torch_compilable_check are unrelated." + "reason": "CPU offload device mismatch in bark-small is unrelated to torch.export failures in detection models." }, { "left": "issue:43701", "right": "issue:45325", "accept": false, - "reason": "Checkpoint resume key mismatch is unrelated to Qwen2.5-VL RoPE position-id scaling." + "reason": "Checkpoint resume key mismatch is unrelated to Qwen2.5-VL position-id scaling." }, { "left": "issue:44186", "right": "issue:44265", "accept": false, - "reason": "Tokenizer crashes on NER padding/truncation are unrelated to torch.export failures on compilable checks." + "reason": "Tokenizer crashes on NER padding/truncation are unrelated to torch.export/torch_compilable_check." }, { "left": "issue:43606", "right": "issue:43819", "accept": false, - "reason": "CPU offload device mismatch is unrelated to DAC.from_latents versus forward-pass mismatch." + "reason": "Different audio-model bugs: CPU-offload device mismatch vs DAC latent/STE mismatch." }, { "left": "issue:43262", "right": "issue:43746", "accept": false, - "reason": "Audio chat-template sampling-rate defaults and GraniteSpeech PEFT checkpoint loading are different issues." + "reason": "Audio processor sample-rate defaulting is unrelated to GraniteSpeech PEFT checkpoint loading." }, { "left": "issue:41720", "right": "issue:45823", "accept": false, - "reason": "Both are device_map=auto issues, but they affect different models and failures; not the same code-path bug." - }, - { - "left": "issue:43526", - "right": "issue:43883", - "accept": false, - "reason": "BEiT label reduction and missing all_tied_weights_keys are unrelated." + "reason": "Different device-mapping failures in different models; no shared concrete bug." }, { "left": "issue:43454", "right": "issue:43550", "accept": false, - "reason": "Tied-weight loading/serialization versus torch.compile SDPA failure are different bugs." + "reason": "Weight-tying failure is unrelated to Bamba torch.compile SDPA failure." }, { "left": "issue:43377", "right": "issue:44610", "accept": false, - "reason": "Missing padding mask support in MIMI encoder is unrelated to OmDet-Turbo processor/model resolution mismatch." + "reason": "Missing padding-mask support in MIMI encoder is unrelated to OmDet processor resolution mismatch." }, { "left": "issue:43377", "right": "issue:44898", "accept": false, - "reason": "Different models and different failures: MIMI batching discrepancy versus Perceiver resolution handling." + "reason": "Different models and symptoms; no shared underlying bug." }, { "left": "issue:43454", "right": "issue:45072", "accept": false, - "reason": "A tied-weights bug is not the same as bf16 dtype mismatch during inference." + "reason": "Weight-tying bug is unrelated to bfloat16 dtype mismatch under CI inference." }, { "left": "issue:40990", "right": "issue:45584", "accept": false, - "reason": "High perplexity on WikiText-2 is unrelated to Whisper empty-transcription generation after align_special_tokens." + "reason": "GPT-OSS perplexity regression is unrelated to Whisper empty-transcription generation failure." }, { "left": "issue:43572", "right": "issue:45759", "accept": false, - "reason": "StableLm pad_token_idx regression and Qwen multimodal config unwrapping are different failures." + "reason": "Missing pad_token_idx in StableLmConfig is unrelated to AutoModelForCausalLM.from_config text_config unwrapping." }, { "left": "issue:39692", "right": "issue:40444", "accept": false, - "reason": "SigLIP2 documentation errors are unrelated to Qwen2.5-VL finetuning with multiple images per prompt." + "reason": "SigLIP2 doc-example errors are unrelated to Qwen2.5-VL multi-image finetuning failures." + }, + { + "left": "issue:43526", + "right": "issue:43883", + "accept": false, + "reason": "BEiT Fast label reduction bug is unrelated to Molmo tied-weights attribute failure." } ] }, - "evaluator_result": null, - "evaluator_used": false, - "retried": false, + "evaluator_result": { + "accept": false, + "feedback": "The overall framing is mostly grounded, but the accepted 45325/45381 edge is a bit too strong for the packet alone. The titles show the same model/version and both mention position IDs, yet they describe different surfaces of the bug (still-image temporal scaling vs video `vision_position_ids`) and the packet does not provide explicit duplicate evidence. I would treat that pair as plausible/related rather than a definite duplicate; the rest of the soft-edge rejections look conservative." + }, + "evaluator_used": true, + "retried": true, "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null @@ -3672,7 +3690,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 11, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -3689,10 +3707,10 @@ "issue:43296", "issue:43316", "issue:43317", + "issue:43322", "issue:43404", "issue:43450", "issue:43454", - "issue:43526", "issue:43550", "issue:43577", "issue:43606", @@ -3730,8 +3748,8 @@ "issue:45823" ], "soft_pairs": [ - "issue:43881|issue:44991", "issue:44466|issue:45357", + "issue:43881|issue:44991", "issue:43792|issue:44683", "issue:43296|issue:44877", "issue:43454|issue:43720", @@ -3742,10 +3760,10 @@ "issue:43404|issue:45357", "issue:34634|issue:35707", "issue:44423|issue:45406", - "issue:44186|issue:45072", "issue:43577|issue:43708", - "issue:43873|issue:44756", + "issue:44186|issue:45072", "issue:35707|issue:41720", + "issue:43873|issue:44756", "issue:44877|issue:44991", "issue:42617|issue:42915", "issue:43749|issue:44534", @@ -3756,19 +3774,19 @@ "issue:36331|issue:42617", "issue:44186|issue:44610", "issue:44387|issue:45704", - "issue:43526|issue:43881", "issue:44479|issue:44918", "issue:42915|issue:43317", - "issue:43316|issue:44913", "issue:43550|issue:43606", - "issue:45081|issue:45812" + "issue:43316|issue:44913", + "issue:45081|issue:45812", + "issue:41720|issue:43322" ], - "prepared_review_unit_hash": "787f72bbe02d5f4636fa9028e04a7835af16275847bf28f5c847fd25762d9b80", + "prepared_review_unit_hash": "480ab5f688ebfa18db4c56a4ed1f88c85378d2bfc88c05e1895bd9ade11d1eb2", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -3776,207 +3794,213 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 32, - "serialized_chars": 37407, - "estimated_input_tokens": 9352, - "estimated_eval_tokens": 18960 + "serialized_chars": 37355, + "estimated_input_tokens": 9339, + "estimated_eval_tokens": 18934 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly heterogeneous: many items are model-specific loading/runtime regressions, and the soft pairs share broad themes but not the same concrete bug. I\u2019d use the broad offloading/quantization issue as the cluster representative.", - "confidence": 0.61, - "canonical_issue_reason": "issue:43873 is the most general and central representative of the cluster\u2019s recurring offloading/quantization/device-loading failures, and it has broader linkage than the more model-specific reports.", + "summary": "These issues are mostly unrelated model-specific regressions and loading/runtime failures, with no strong duplicate cluster. I did not find any soft-edge pair that looks like the same underlying bug or change.", + "confidence": 0.9, + "canonical_issue_reason": "issue:43873 is the broadest and most central representative here, covering offloading/quantization behavior that overlaps the cluster\u2019s general loading/runtime theme.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43873 is the best single issue anchor because it is broad, still open, and closest to the repeated loading/offload failure pattern seen across the cluster.", + "best_issue_reason": "issue:43873 is the best single issue representative because it is open, broadly phrased, and has the strongest evidence of ongoing impact among the set.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43881", - "right": "issue:44991", + "left": "issue:44466", + "right": "issue:45357", "accept": false, - "reason": "Different models and different failure surfaces: GLM-4V load failure vs tokenizer regression for EMBEDDIA/est-roberta." + "reason": "Different bugs: lm_head tying/serialization by device vs incorrect visual encoder keys in Qwen3.5 save_pretrained." }, { - "left": "issue:44466", - "right": "issue:45357", + "left": "issue:43881", + "right": "issue:44991", "accept": false, - "reason": "Both involve serialization, but one is tied lm_head handling on device-dependent save, the other is incorrect visual encoder keys in Qwen3.5." + "reason": "Different models and failure points: glm-4v-9b load failure vs tokenizer loading regression for EMBEDDIA/est-roberta." }, { "left": "issue:43792", "right": "issue:44683", "accept": false, - "reason": "Whisper loading failure and compiled flex_attention on torch>=2.9 are unrelated code paths." + "reason": "Whisper model runtime failure is unrelated to the torch>=2.9 compiled flex_attention regression." }, { "left": "issue:43296", "right": "issue:44877", "accept": false, - "reason": "PaddleOCR-VL/vLLM load compatibility and strict config loading for granite_speech are distinct issues." + "reason": "Different config-loading problems for different models; no shared underlying bug is clear." }, { "left": "issue:43454", "right": "issue:43720", "accept": false, - "reason": "Mistral3 weight tying and BitNet packed-weight unpacking are different loader/model-conversion bugs." + "reason": "One is a weight-tying bug, the other is packed-weight unpacking during accelerate loading." }, { "left": "issue:43873", "right": "issue:45701", "accept": false, - "reason": "Quantization/offloading behavior and tokenization differences are not the same underlying bug." + "reason": "Quantization/offload behavior and tokenizer changes are different code paths and symptoms." }, { "left": "issue:41720", "right": "issue:44977", "accept": false, - "reason": "Qwen3 auto device-mapping cuda assert is a different failure from Qwen3.5 flash-attention generation regressions." + "reason": "Both are Qwen family, but one is device-mapping CUDA assert and the other is flash-attention generation regression." }, { "left": "issue:44008", "right": "issue:45823", "accept": false, - "reason": "Gemma3n forward variable collision and Gemma4 PLE device mismatch are separate model-specific bugs." + "reason": "Different Gemma bugs: variable-name collision in forward vs device mismatch with auto device map." }, { "left": "issue:45632", "right": "issue:45684", "accept": false, - "reason": "Cache-path collisions and read-only permission propagation are unrelated save/load issues." + "reason": "Cache-path collisions and permission propagation are unrelated save/load issues." }, { "left": "issue:43404", "right": "issue:45357", "accept": false, - "reason": "Mistral3 lm_head tying and Qwen3.5 visual encoder key serialization affect different models and mechanisms." + "reason": "Mistral3 lm_head weight tying issue is unrelated to Qwen3.5 visual encoder key serialization." }, { "left": "issue:34634", "right": "issue:35707", "accept": false, - "reason": "BarkProcessor voice_preset failure and progressive generation with inputs_embeds/past_key_values are unrelated." + "reason": "BarkProcessor voice_preset bug and progressive generation with inputs_embeds/past_key_values are different problems." }, { "left": "issue:44423", "right": "issue:45406", "accept": false, - "reason": "Continuous-batching multimodal crash and missing _tokenizer on Gemma4Processor are different serve-time failures." - }, - { - "left": "issue:44186", - "right": "issue:45072", - "accept": false, - "reason": "LayoutLMv2Tokenizer NER/padding crash and bfloat16 dtype mismatch are not the same bug." + "reason": "Both crash in serve, but with different processors, attributes, and likely different root causes." }, { "left": "issue:43577", "right": "issue:43708", "accept": false, - "reason": "Blip2 dtype propagation and Trainer resume/max_steps calculation are different subsystems." + "reason": "BLIP2 dtype loading and trainer resume/max_steps calculation are unrelated." }, { - "left": "issue:43873", - "right": "issue:44756", + "left": "issue:44186", + "right": "issue:45072", "accept": false, - "reason": "Both mention memory/offload concerns, but one is quantization/offloading behavior and the other is a Strix Halo mmap OOM fix." + "reason": "Tokenizer NER/padding crash and bf16 dtype mismatch are different failure classes." }, { "left": "issue:35707", "right": "issue:41720", "accept": false, - "reason": "Input-embedding generation handling is unrelated to Qwen3 device-map cuda asserts." + "reason": "Generation with inputs_embeds/past_key_values is unrelated to a Qwen3 device-mapping CUDA assert." + }, + { + "left": "issue:43873", + "right": "issue:44756", + "accept": false, + "reason": "Quantization offloading problems are not the same as disabling mmap to avoid OOM on Strix Halo." }, { "left": "issue:44877", "right": "issue:44991", "accept": false, - "reason": "Strict config loading and tokenizer loading regression are separate problems." + "reason": "Strict config loading for granite_speech and tokenizer loading regression for est-roberta are unrelated." }, { "left": "issue:42617", "right": "issue:42915", "accept": false, - "reason": "3d_parallel.py startup/runtime failure and Qwen3Moe FineGrainedFP8Config failure are different concrete bugs." + "reason": "A 3d_parallel.py runtime problem is unrelated to Qwen3Moe failing with FineGrainedFP8Config." }, { "left": "issue:43749", "right": "issue:44534", "accept": false, - "reason": "FSDP CPU RAM efficient loading and non-persistent buffer junk are both load/init related but not the same code-path problem." + "reason": "FSDP CPU-efficient loading and non-persistent buffer junk are different loading bugs." }, { "left": "issue:43450", "right": "issue:45701", "accept": false, - "reason": "Video processor batching shape bug and tokenizer version-dependent tokenization are unrelated." + "reason": "Batched video processor shape mismatch is unrelated to tokenizer changes across versions." }, { "left": "issue:43550", - "right": "issue:43720", + "right": "issue:43606", "accept": false, - "reason": "Bamba SDPA torch.compile failure and BitNet packed-weight unpacking are different model/runtime bugs." + "reason": "torch.compile+SDPA failure for Bamba is unrelated to Bark CPU-offload device mismatch." }, { "left": "issue:36331", "right": "issue:42915", "accept": false, - "reason": "CustomTrainer compute_loss signature mismatch and Qwen3Moe FP8 load failure are unrelated." + "reason": "Trainer compute_loss signature breakage is unrelated to Qwen3Moe FP8 config loading." }, { "left": "issue:44610", "right": "issue:44898", "accept": false, - "reason": "Both are vision-processing/resolution issues, but they hit different models and different mismatch logic." + "reason": "Both involve vision input sizing, but they affect different models and different root causes." }, { "left": "issue:36331", "right": "issue:42617", "accept": false, - "reason": "Trainer API mismatch and 3d_parallel.py failure are different concrete issues." + "reason": "Unexpected compute_loss argument and 3d_parallel.py execution failure are unrelated." }, { "left": "issue:44186", "right": "issue:44610", "accept": false, - "reason": "Tokenizer crash on NER/batched padding and processor output-size mismatch are different preprocessing bugs." + "reason": "Tokenizer crash and processor image-size mismatch do not indicate the same bug." }, { "left": "issue:44387", "right": "issue:45704", "accept": false, - "reason": "Int4 quantization OOM and apex FusedRMSNorm memory leak are both memory-related but not the same defect." - }, - { - "left": "issue:43526", - "right": "issue:43881", - "accept": false, - "reason": "BeitImageProcessorFast label reduction bug and GLM-4V loading failure are unrelated." + "reason": "Int4 quantization OOM from reserved memory growth is unrelated to apex RMSNorm memory leak." }, { "left": "issue:44479", "right": "issue:44918", "accept": false, - "reason": "Qwen VL video regression and TRL SFT embedding unpack failure are distinct multimodal/training bugs." + "reason": "Video-input regression in Qwen models and trl SFT unpacking of input embeddings are different bugs." }, { "left": "issue:42915", "right": "issue:43317", "accept": false, - "reason": "Qwen3Moe FP8 config failure and dequantized model offload loading failure are different failure modes." + "reason": "Both mention loading/offload, but one is FP8 config failure and the other is gpu+cpu offload with dequantized models." + }, + { + "left": "issue:43550", + "right": "issue:43606", + "accept": false, + "reason": "These are different offload/compile/device-mismatch issues and not the same code-path problem." }, { "left": "issue:43316", "right": "issue:44913", "accept": false, - "reason": "Gemma3TextConfig API discrepancy and GPTNeoX rotary_pct reload regression are unrelated config issues." + "reason": "Config API discrepancy for Gemma3TextConfig is unrelated to GPTNeoX rotary_pct reload behavior." }, { - "left": "issue:43550", - "right": "issue:43606", + "left": "issue:45081", + "right": "issue:45812", "accept": false, - "reason": "Bamba SDPA compile failure and Bark CPU-offload device mismatch are different runtime paths." + "reason": "Mistral tokenizer regex patch crash and Granite token-id regression are different tokenizer bugs." + }, + { + "left": "issue:41720", + "right": "issue:43322", + "accept": false, + "reason": "Qwen3 device-map CUDA assert and Llava Next segfault are unrelated model-loading failures." } ] }, @@ -3992,7 +4016,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 12, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -4013,6 +4037,7 @@ "issue:43322", "issue:43388", "issue:43421", + "issue:43526", "issue:43531", "issue:43540", "issue:43550", @@ -4020,9 +4045,9 @@ "issue:43606", "issue:43653", "issue:43720", - "issue:43746", "issue:43782", "issue:43873", + "issue:43881", "issue:43927", "issue:44186", "issue:44361", @@ -4035,10 +4060,8 @@ "issue:44671", "issue:44743", "issue:44779", - "issue:44898", "issue:44991", "issue:45059", - "issue:45072", "issue:45161", "issue:45357", "issue:45406", @@ -4050,9 +4073,9 @@ "issue:45859" ], "soft_pairs": [ - "issue:41720|issue:43322", "issue:43295|issue:45701", "issue:40990|issue:45701", + "issue:43526|issue:43881", "issue:41720|issue:45161", "issue:43531|issue:43572", "issue:43421|issue:45812", @@ -4068,8 +4091,8 @@ "issue:44779|issue:45812", "issue:42915|issue:43322", "issue:43606|issue:43720", - "issue:43388|issue:45059", "issue:43550|issue:43653", + "issue:43388|issue:45059", "issue:44514|issue:44545", "issue:43531|issue:45759", "issue:43606|issue:43653", @@ -4078,182 +4101,180 @@ "issue:44368|issue:45357", "issue:44451|issue:44991", "issue:43873|issue:45704", - "issue:45759|issue:45859", - "issue:44898|issue:45072", - "issue:41720|issue:43746" + "issue:45759|issue:45859" ], - "prepared_review_unit_hash": "523ca39b6cbd7183aecce575cefe8df0ed2b7f1e51f2a89b419e84e09c0e330e", + "prepared_review_unit_hash": "4afc43e7ac7ba007b388b47616ff9143510ebc042bea816ba83c0b296a2412b4", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 31, - "serialized_chars": 36984, - "estimated_input_tokens": 9246, - "estimated_eval_tokens": 18748 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 35702, + "estimated_input_tokens": 8926, + "estimated_eval_tokens": 18108 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a set of unrelated transformer/model bugs. Only one pair is a clear duplicate: the two Qwen2_5_VLProcessor.apply_chat_template padding=False crashes. All other soft pairs differ in model, subsystem, or failure mode.", - "confidence": 0.95, - "canonical_issue_reason": "issue:44545 is the best canonical representative for the only true duplicate pair; it has the same exact bug report as 44514 and slightly more discussion/inbound references.", + "summary": "The cluster is mostly heterogeneous: many unrelated model-specific bugs and regressions were grouped by broad tokenizer/processor similarity. The only clear duplicate pair is the Qwen2_5_VLProcessor batching crash (issues 44514/44545).", + "confidence": 0.93, + "canonical_issue_reason": "issue:44545 is the best canonical choice because it is an exact duplicate of 44514, has slightly higher activity, and the title/body are the cleaner target for consolidation.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44545 is the strongest issue to keep as the canonical cluster item because it is the clearest, most engaged report for the duplicated Qwen2_5_VLProcessor.apply_chat_template crash.", + "best_issue_reason": "issue:44545 is the only strong duplicate anchor in this cluster; the rest of the items are not the same underlying bug, so it is the safest representative issue.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:41720", - "right": "issue:43322", - "accept": false, - "reason": "Different failures in different models: Qwen3 device-mapping cuda assert vs Llava Next load segfault." - }, { "left": "issue:43295", "right": "issue:45701", "accept": false, - "reason": "One is a processor/tokenizer API regression; the other is a broad tokenization-version complaint." + "reason": "Both mention tokenization-related regressions, but one is a processor/tokenizer API regression and the other is a broad tokenization behavior change; not the same bug." }, { "left": "issue:40990", "right": "issue:45701", "accept": false, - "reason": "Perplexity regression on GPT-OSS is not the same bug as version-dependent tokenization changes." + "reason": "High perplexity on a specific model is not the same as a general tokenization change regression." + }, + { + "left": "issue:43526", + "right": "issue:43881", + "accept": false, + "reason": "Different models and failure modes: BeitImageProcessor label reduction vs glm-4v loading failure." }, { "left": "issue:41720", "right": "issue:45161", "accept": false, - "reason": "Different Qwen/MoE issues with unrelated symptoms: cudaErrorAssert vs tensor-parallel not working." + "reason": "Both involve Qwen3/MoE and device mapping, but one is a CUDA assert and the other is a tensor-parallel-only issue; different code paths." }, { "left": "issue:43531", "right": "issue:43572", "accept": false, - "reason": "Sliding-window behavior in Qwen3-MoE and missing pad_token_idx in StableLmConfig are unrelated." + "reason": "Sliding-window behavior in Qwen3-MoE is unrelated to a missing pad_token_idx in StableLmConfig." }, { "left": "issue:43421", "right": "issue:45812", "accept": false, - "reason": "Both involve tokenizers, but one is runtime special-token post-processing; the other is Granite token IDs regression." + "reason": "Both concern tokenizers, but one is runtime post-processor updates and the other is wrong token IDs for Granite models; not the same defect." }, { "left": "issue:44671", "right": "issue:44743", "accept": false, - "reason": "CamemBERT masked-LM outputs and Qwen3.5 recurrent cache-state resets are different code paths." + "reason": "CamemBERT masked-LM prediction errors and Qwen recurrent-state reset are different model internals and bugs." }, { "left": "issue:41720", "right": "issue:42617", "accept": false, - "reason": "Qwen3 auto device mapping crash and a 3d_parallel.py execution failure are unrelated." + "reason": "Qwen3 auto device mapping CUDA assert is unrelated to a 3d_parallel.py execution failure." }, { "left": "issue:36010", "right": "issue:42617", "accept": false, - "reason": "ImportError for GenerationMixin is not the same as a parallel script runtime failure." + "reason": "Importing GenerationMixin and running 3d_parallel.py are unrelated failures." }, { "left": "issue:43540", "right": "issue:43782", "accept": false, - "reason": "Video-input processing error and Qwen3VL weight_only load error are different bugs." + "reason": "Video input processing in Qwen3OmniMoe is not the same as a weight_only loading error in Qwen3VL." }, { "left": "issue:44186", "right": "issue:44361", "accept": false, - "reason": "Different tokenizer failures on different models and tasks; not the same underlying defect." + "reason": "Both are tokenizer/task issues, but they affect different tokenizers and failure modes; not a shared underlying bug." }, { "left": "issue:45406", "right": "issue:45464", "accept": false, - "reason": "Gemma4Processor missing _tokenizer in serve is unrelated to Qwen3.5 streaming inference failure." + "reason": "Gemma4Processor missing _tokenizer in serve is unrelated to Qwen3.5 streaming inference failures." }, { "left": "issue:30064", "right": "issue:34634", "accept": false, - "reason": "Image segmentation map processing and BarkProcessor voice_preset are unrelated." + "reason": "Image processor void segmentation maps and BarkProcessor voice_preset are unrelated processor bugs." }, { "left": "issue:43421", "right": "issue:45701", "accept": false, - "reason": "Runtime post-processor update bug is different from a general tokenization regression report." + "reason": "Runtime special-token/post-processor updates do not match a broad tokenization regression across versions." }, { "left": "issue:44492", "right": "issue:44509", "accept": false, - "reason": "A typo in cache strategies and outdated docs for removed pipeline tasks are unrelated." + "reason": "A typo in cache strategy docs is unrelated to removed pipeline-task documentation." }, { "left": "issue:44779", "right": "issue:45812", "accept": false, - "reason": "Both are tokenizer regressions, but they affect different models and likely different fixes." + "reason": "Deepseek tokenizer regression and Granite tokenizer regression are separate model-specific bugs." }, { "left": "issue:42915", "right": "issue:43322", "accept": false, - "reason": "Qwen3Moe FP8 failure and Llava Next loading segfault are unrelated." + "reason": "Qwen3Moe FP8 config failure and Llava Next segmentation fault are different failures in different subsystems." }, { "left": "issue:43606", "right": "issue:43720", "accept": false, - "reason": "CPU offload device mismatch and BitNet packed-weight unloading are different accelerate/loading bugs." + "reason": "CPU offload device mismatch in Bark is unrelated to BitNet packed-weight unpacking during accelerate loading." }, { - "left": "issue:43388", - "right": "issue:45059", + "left": "issue:43550", + "right": "issue:43653", "accept": false, - "reason": "Metrics label truncation and SAM3 text/bbox weirdness are different problems." + "reason": "Bamba torch.compile SDPA failure and BigBird tokenizer special-token registration are unrelated." }, { - "left": "issue:43550", - "right": "issue:43653", + "left": "issue:43388", + "right": "issue:45059", "accept": false, - "reason": "torch.compile/SDPA failure and tokenizer special-token registration are unrelated." + "reason": "Metric gathering label truncation and SAM3 text/bounding-box behavior are different bugs." }, { "left": "issue:44514", "right": "issue:44545", "accept": true, - "reason": "Same exact Qwen2_5_VLProcessor.apply_chat_template padding=False crash; these are clear duplicates." + "reason": "Same title and same crash scenario; 44545 is a clear duplicate of 44514." }, { "left": "issue:43531", "right": "issue:45759", "accept": false, - "reason": "Qwen3-MoE sliding_window bug and composite-config unwrap behavior are different model/config issues." + "reason": "Qwen3-MoE sliding-window behavior and unwrapping text_config for composite configs are distinct generation/model-construction bugs." }, { "left": "issue:43606", "right": "issue:43653", "accept": false, - "reason": "CPU offload mismatch and tokenizer mask-token registration are unrelated CI bugs." + "reason": "Bark CPU offload device mismatch and BigBird mask-token registration are unrelated issues." }, { "left": "issue:43421", "right": "issue:43927", "accept": false, - "reason": "Special-token post-processing and DiaConfig token ID persistence are different tokenizer/config defects." + "reason": "Updating post-processors when special tokens change is different from saving/loading DiaConfig custom token IDs." }, { "left": "issue:34567", @@ -4265,43 +4286,31 @@ "left": "issue:44368", "right": "issue:45357", "accept": false, - "reason": "Warning about tie_word_embeddings is not the same as incorrect visual encoder keys in save_pretrained." + "reason": "A config warning about tie_word_embeddings is not the same as saving incorrect visual encoder keys." }, { "left": "issue:44451", "right": "issue:44991", "accept": false, - "reason": "General model-loading failure for one checkpoint and tokenizer loading regression for another checkpoint are not the same bug." + "reason": "Both are tokenizer-loading regressions, but they affect different models and likely different tokenizer files/code paths." }, { "left": "issue:43873", "right": "issue:45704", "accept": false, - "reason": "Quantization offloading behavior and apex FusedRMSNorm memory leak are unrelated." + "reason": "Quantization/offloading problems are unrelated to a T5 apex RMSNorm memory leak." }, { "left": "issue:45759", "right": "issue:45859", "accept": false, - "reason": "Composite Qwen config unwrapping and CPU-offload incompatibility in rotary embedding are different issues." - }, - { - "left": "issue:44898", - "right": "issue:45072", - "accept": false, - "reason": "Perceiver non-default resolution failure and dtype mismatches in other models are unrelated." - }, - { - "left": "issue:41720", - "right": "issue:43746", - "accept": false, - "reason": "Qwen3 device-mapping assert and GraniteSpeech PEFT checkpoint loading are different code paths." + "reason": "Composite-config unwrapping and CPU-offload incompatibility in rotary embedding are different bugs." } ] }, "evaluator_result": { "accept": true, - "feedback": "The canonical choice for issue:44545 is well grounded: it is effectively the same report as 44514 and has slightly more inbound attention. The soft-edge rejections are conservative and supported by the titles/body metadata; no pair is overstated as a duplicate or same-bug merge. The summary stays within the packet evidence." + "feedback": "Grounded and conservative. The cluster summary matches the packet: most items are clearly heterogeneous by title/body, and the 44514/44545 pair is the only obvious duplicate with near-identical titles and consistent activity. The soft-edge rejections are appropriately cautious and do not overclaim beyond the packet." }, "evaluator_used": true, "retried": false, @@ -4314,7 +4323,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 13, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -4331,7 +4340,6 @@ "issue:41720", "issue:42886", "issue:42915", - "issue:43335", "issue:43381", "issue:43421", "issue:43525", @@ -4341,7 +4349,7 @@ "issue:43618", "issue:43653", "issue:43697", - "issue:43756", + "issue:43746", "issue:43782", "issue:43844", "issue:43873", @@ -4357,12 +4365,13 @@ "issue:44661", "issue:44671", "issue:44843", + "issue:44898", "issue:44918", "issue:44936", "issue:44987", "issue:45042", + "issue:45072", "issue:45081", - "issue:45183", "issue:45356", "issue:45381", "issue:45479", @@ -4372,6 +4381,8 @@ "issue:45859" ], "soft_pairs": [ + "issue:44898|issue:45072", + "issue:41720|issue:43746", "issue:44062|issue:44451", "issue:44987|issue:45042", "issue:43531|issue:44589", @@ -4380,8 +4391,8 @@ "issue:45588|issue:45759", "issue:42886|issue:44843", "issue:43381|issue:43844", - "issue:44918|issue:44936", "issue:39692|issue:44610", + "issue:44918|issue:44936", "issue:43421|issue:44186", "issue:43525|issue:43531", "issue:44625|issue:45479", @@ -4397,16 +4408,14 @@ "issue:43540|issue:44008", "issue:43618|issue:43697", "issue:44220|issue:44661", - "issue:30064|issue:36010", - "issue:45183|issue:45479", - "issue:43335|issue:43756" + "issue:30064|issue:36010" ], - "prepared_review_unit_hash": "e960158f57910d53a8df1181808acf90b31086782bf4da8ba055c45ce06e878f", + "prepared_review_unit_hash": "d8a87b8a179bbee28fc05bdbf7c2a672e66c418ecea1e494b2d6fef9378def78", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -4414,189 +4423,189 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 28, - "serialized_chars": 36240, - "estimated_input_tokens": 9060, - "estimated_eval_tokens": 18376 + "serialized_chars": 36230, + "estimated_input_tokens": 9058, + "estimated_eval_tokens": 18372 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is highly heterogeneous: tokenizer, multimodal, training, quantization, and docs regressions with no convincing duplicate pairs. The strongest anchor is the Mistral tokenizer regex/offline-loading regression, but it is not a clear duplicate hub for the rest.", - "confidence": 0.91, - "canonical_issue_reason": "Best anchor in this mixed set: explicit tokenizer code-path regression with a concrete crash surface and multiple references.", + "summary": "The set is a heterogeneous collection of unrelated issues. Several pairs share broad themes like tokenizers, multimodal models, or offloading, but none look like the same concrete bug/change.", + "confidence": 0.94, + "canonical_issue_reason": "issue:43873 is the most broadly scoped and most actively discussed item in the set (offloading/quantization with the highest inbound attention), so it is the least bad representative if one must be chosen. It is not, however, a true duplicate umbrella for the cluster.", "canonical_pr_reason": null, - "best_issue_reason": "Most actionable standalone bug here: precise repro, narrow fix surface, and a clear runtime failure in a core tokenizer-loading path.", + "best_issue_reason": "issue:43873 is the strongest global representative because it has the broadest impact and most discussion, but the cluster is too mixed to treat it as a real canonical duplicate target.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44898", + "right": "issue:45072", + "accept": false, + "reason": "Both involve vision/image-processing behavior, but one is a Perceiver resolution bug and the other is a bfloat16 dtype mismatch in different models/code paths." + }, + { + "left": "issue:41720", + "right": "issue:43746", + "accept": false, + "reason": "These are unrelated model-loading/runtime failures: Qwen3 device-mapping CUDA asserts versus GraniteSpeech PEFT local checkpoint loading." + }, { "left": "issue:44062", "right": "issue:44451", "accept": false, - "reason": "Tokenizer constructor error vs model-loading failure; no shared underlying bug." + "reason": "Both are loading-related, but one is an AddedToken argument clash and the other is a model-specific failure to load ScandiBERT. Different root causes." }, { "left": "issue:44987", "right": "issue:45042", "accept": false, - "reason": "Different subsystems: specific model load issue vs PIL/torchvision backend dependency regression." + "reason": "One is a failure loading a specific model on newer transformers, the other is an image processor backend dependency regression. Not the same bug." }, { "left": "issue:43531", "right": "issue:44589", "accept": false, - "reason": "Unrelated Qwen sliding-window config bug vs PyTorch storage-type import/runtime error." + "reason": "These are different issues: a Qwen3-MoE sliding-window problem versus a Float8 storage lookup error." }, { "left": "issue:33666", "right": "issue:35707", "accept": false, - "reason": "Multi-GPU training problem and generation with inputs_embeds/past_key_values are different failure modes." + "reason": "Multi-GPU training for Qwen2-VL is unrelated to progressive generation with inputs_embeds/past_key_values." }, { "left": "issue:43421", "right": "issue:43653", "accept": false, - "reason": "Both involve tokenizers, but one is runtime post-processor updates and the other is mask-token registration/empty decode behavior." + "reason": "Both touch special tokens, but one is runtime post-processor updating and the other is BigBirdTokenizer mask-token registration. Similar area, different bug." }, { "left": "issue:45588", "right": "issue:45759", "accept": false, - "reason": "Different code paths and symptoms: flash-attention sink handling vs composite Qwen config unwrapping." + "reason": "Flash-attention sink handling and composite Qwen config unwrapping are unrelated code paths." }, { "left": "issue:42886", "right": "issue:44843", "accept": false, - "reason": "Both touch offline loading, but 44843 is a specific mistral-regex model_info call; 42886 is a broader cache-load failure." + "reason": "Both mention offline tokenization, but 44843 is specifically the Mistral regex patch calling model_info(), while 42886 is a broader cache-load failure." }, { "left": "issue:43381", "right": "issue:43844", "accept": false, - "reason": "Checkpointing-in-eval issue vs ZeRO-3 gradient anomaly; unrelated bugs." + "reason": "Gradient checkpointing in eval mode is not the same as gradients increasing under DeepSpeed ZeRO-3." }, { - "left": "issue:44918", - "right": "issue:44936", + "left": "issue:39692", + "right": "issue:44610", "accept": false, - "reason": "Different trainer issues: SFT embedding unpacking vs train/evaluate lifecycle failure." + "reason": "Both involve vision processor/model mismatch, but one is a SigLIP2 doc example/quantization issue and the other is OmDet-Turbo input-size mismatch." }, { - "left": "issue:39692", - "right": "issue:44610", + "left": "issue:44918", + "right": "issue:44936", "accept": false, - "reason": "Both are processor/model mismatches, but for different models and different root causes." + "reason": "Training with Qwen3.5 embeddings/trainer unpacking is unrelated to trainer.evaluate() failing after train()." }, { "left": "issue:43421", "right": "issue:44186", "accept": false, - "reason": "Different tokenizer bugs: post-processor refresh vs NER padding/truncation crash." + "reason": "Both are tokenizer-related, but NER padding/truncation crashes and runtime special-token post-processing are different concrete failures." }, { "left": "issue:43525", "right": "issue:43531", "accept": false, - "reason": "Missing config attribute vs sliding_window behavior; not the same defect." + "reason": "Llama4Config missing pad_token_id and Qwen3-MoE sliding_window behavior are unrelated configuration bugs." }, { "left": "issue:44625", "right": "issue:45479", "accept": false, - "reason": "Shared num_labels wording, but one is config propagation and the other is classification-loss behavior." + "reason": "One is propagation of num_labels into text config; the other is degenerate zero loss for single-label classification. Same broad area, different bug." }, { "left": "issue:45704", "right": "issue:45859", "accept": false, - "reason": "Different models and mechanisms: apex RMSNorm leak vs CPU-offload incompatibility in rotary embedding." + "reason": "T5 apex RMSNorm memory leak and Qwen3_5Moe CPU-offload incompatibility are unrelated." }, { "left": "issue:45081", "right": "issue:45356", "accept": false, - "reason": "Same broad regex-patching area, but one is a tokenizer-load crash and the other is a Kimi codec regression; not clearly one bug." + "reason": "Both involve fix_mistral_regex, but one is an AttributeError crash and the other is a tokenizer regression with codec handling/warning issues. Not the same concrete fix." }, { "left": "issue:43782", "right": "issue:45381", "accept": false, - "reason": "Different Qwen VL issues: weight-only loading error vs video vision_position_ids mismatch." + "reason": "Qwen3VL weight_only loading and Qwen2.5-VL video vision_position_ids are distinct multimodal failures." }, { "left": "issue:34634", "right": "issue:41720", "accept": false, - "reason": "Bark voice preset bug and Qwen3 auto-device-map CUDA assert are unrelated." + "reason": "BarkProcessor voice_preset and Qwen3 auto device mapping are unrelated model/processor bugs." }, { "left": "issue:43994", "right": "issue:44671", "accept": false, - "reason": "Different model regressions with no shared code path." + "reason": "SigLIP2 inference nonsense and CamemBERT masked-LM predictions in v5 are different model-specific regressions." }, { "left": "issue:43381", "right": "issue:45704", "accept": false, - "reason": "Eval-mode checkpointing bug vs T5 RMSNorm memory leak; unrelated." + "reason": "Gradient checkpointing eval-mode behavior and T5 RMSNorm memory leak do not share the same underlying code path." }, { "left": "issue:39692", "right": "issue:43873", "accept": false, - "reason": "Docs/example mismatch vs quantization offloading behavior; not the same underlying issue." + "reason": "SigLIP2 example/model mismatch and offloading-with-quantization are unrelated issues." }, { "left": "issue:42915", "right": "issue:45759", "accept": false, - "reason": "Different Qwen issues: FP8 config failure vs composite-config unwrapping." + "reason": "Qwen3Moe FineGrainedFP8Config failure is not the same as composite Qwen config text_config unwrapping." }, { "left": "issue:43596", "right": "issue:44220", "accept": false, - "reason": "Deepspeed/Bert init error vs audio fbank feature extraction; unrelated." + "reason": "DeepSpeed ZeRO-3/BertModel index error and _torch_extract_fbank_features() are different runtime failures." }, { "left": "issue:43540", "right": "issue:44008", "accept": false, - "reason": "Both are multimodal, but they fail in different modalities and from different root causes." + "reason": "Video processing ValueError in Qwen3OmniMoe and Gemma 3n audio_mel_mask tensor/name collision are unrelated." }, { "left": "issue:43618", "right": "issue:43697", "accept": false, - "reason": "Different model regressions; only both are output-related at a very high level." + "reason": "CLIPOutput attentions assignment and RTDetrV2 output differences in v5 are separate model behavior changes." }, { "left": "issue:44220", "right": "issue:44661", "accept": false, - "reason": "Audio feature extraction bug vs tokenizer-mapping extension bug." + "reason": "Audio feature extraction and add-new-model-like failing inside TOKENIZER_MAPPING_NAMES are unrelated tokenizer/model registry issues." }, { "left": "issue:30064", "right": "issue:36010", "accept": false, - "reason": "Image segmentation processing bug vs GenerationMixin import regression; unrelated." - }, - { - "left": "issue:45183", - "right": "issue:45479", - "accept": false, - "reason": "Input-validation XOR error vs single-label classification loss bug; different code paths." - }, - { - "left": "issue:43335", - "right": "issue:43756", - "accept": false, - "reason": "Sparse-layer config bug vs RoPE-layer dropping mismatch; not the same issue." + "reason": "Void segmentation map processing and GenerationMixin import failure are completely different subsystems and failures." } ] }, @@ -4612,7 +4621,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 14, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -4620,12 +4629,10 @@ "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ - "issue:30064", - "issue:36331", - "issue:39692", "issue:42915", "issue:43295", "issue:43322", + "issue:43335", "issue:43421", "issue:43531", "issue:43540", @@ -4636,6 +4643,7 @@ "issue:43716", "issue:43720", "issue:43746", + "issue:43756", "issue:43782", "issue:43818", "issue:43819", @@ -4647,7 +4655,6 @@ "issue:44077", "issue:44186", "issue:44448", - "issue:44479", "issue:44485", "issue:44488", "issue:44509", @@ -4664,21 +4671,25 @@ "issue:45072", "issue:45081", "issue:45084", + "issue:45183", "issue:45381", + "issue:45479", "issue:45584", "issue:45685", "issue:45834" ], "soft_pairs": [ + "issue:43335|issue:43756", "issue:43720|issue:43819", + "issue:45183|issue:45479", "issue:44077|issue:44625", "issue:43653|issue:43720", "issue:43716|issue:44008", "issue:42915|issue:43746", "issue:43295|issue:45834", "issue:43746|issue:45381", - "issue:43550|issue:45072", "issue:43746|issue:43873", + "issue:43550|issue:45072", "issue:43550|issue:43819", "issue:44186|issue:44898", "issue:44843|issue:45081", @@ -4692,223 +4703,214 @@ "issue:44448|issue:44671", "issue:43782|issue:44977", "issue:45584|issue:45834", + "issue:44821|issue:45084", "issue:43322|issue:45685", "issue:43825|issue:43994", - "issue:44821|issue:45084", "issue:44561|issue:45020", - "issue:44485|issue:44509", - "issue:30064|issue:36331", - "issue:39692|issue:45834", - "issue:44479|issue:45834" + "issue:44485|issue:44509" ], - "prepared_review_unit_hash": "5556f93240bfdb776111a24644ea8792bc4371cb0b8413fc464f09618ec9e96e", + "prepared_review_unit_hash": "6100093784cf24e124a8a400cb4b226df7eb428dbce863945a71bce820e991e3", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 30, - "serialized_chars": 36855, - "estimated_input_tokens": 9214, - "estimated_eval_tokens": 18684 + "soft_pair_count": 29, + "serialized_chars": 36668, + "estimated_input_tokens": 9167, + "estimated_eval_tokens": 18590 }, "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 many unrelated bugs across tokenizers, multimodal processors, quantization/loading, and version regressions. The soft links are mostly title-level similarity, not the same concrete code-path failure.", - "confidence": 0.95, - "canonical_issue_reason": "No single canonical issue fits well; the items are heterogeneous and do not describe one underlying bug.", + "summary": "This cluster is mostly a set of unrelated model-specific regressions. I found no convincing duplicate issue/PR pairs; the only broadly representative issue is the open remote_code regression umbrella.", + "confidence": 0.89, + "canonical_issue_reason": "Issue 45020 is the broadest umbrella in the set (\u201cremote_code\u201d regressions) and is the closest thing to a cluster anchor, though most items are not true duplicates.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45020 is the broadest umbrella complaint in the set (recent transformers versions breaking remote_code models), but it still does not subsume the rest as duplicates.", + "best_issue_reason": "Issue 45020 is the best representative anchor because it captures the only cross-cutting theme in the cluster; the rest are separate model or tokenizer bugs.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43335", + "right": "issue:43756", + "accept": false, + "reason": "Different model families and failures: sparse-layer config bug vs RoPE-layer mismatch." + }, { "left": "issue:43720", "right": "issue:43819", "accept": false, - "reason": "BitNet accelerate-loading failure vs DAC latent/STE mismatch; unrelated model paths." + "reason": "Different code paths: packed-weight loading in BitNet vs DAC latent decoding/STE mismatch." + }, + { + "left": "issue:45183", + "right": "issue:45479", + "accept": false, + "reason": "Input validation error handling vs single-label loss degeneracy are unrelated bugs." }, { "left": "issue:44077", "right": "issue:44625", "accept": false, - "reason": "PatchTSMixer post-init policy vs Qwen3.5 num_labels propagation; different subsystems." + "reason": "PatchTSMixer post-init policy and Qwen3.5 num_labels propagation are unrelated model config issues." }, { "left": "issue:43653", "right": "issue:43720", "accept": false, - "reason": "BigBird tokenizer special-token decode bug vs BitNet weight loading bug; not the same issue." + "reason": "Tokenizer special-token registration bug vs BitNet packed-weight loading bug; different subsystems." }, { "left": "issue:43716", "right": "issue:44008", "accept": false, - "reason": "Mistral image dtype mismatch vs Gemma3n audio variable collision; different code paths and modalities." + "reason": "Both are multimodal, but one is a dtype mismatch and the other is a variable-name collision causing AttributeError." }, { "left": "issue:42915", "right": "issue:43746", "accept": false, - "reason": "Qwen3Moe FP8 config failure vs GraniteSpeech PEFT/local checkpoint loading; unrelated failures." + "reason": "Qwen3Moe FP8 loading failure and GraniteSpeech PEFT local-checkpoint loading are unrelated." }, { "left": "issue:43295", "right": "issue:45834", "accept": false, - "reason": "Processor/tokenizer regression vs Kosmos2.5 OCR index error; only broad multimodal overlap." + "reason": "Processor/tokenizer regression and Kosmos2.5 long-OCR index error are different failure modes." }, { "left": "issue:43746", "right": "issue:45381", "accept": false, - "reason": "GraniteSpeech adapter loading vs Qwen2.5-VL video position ids; different models and bugs." + "reason": "GraniteSpeech PEFT loading and Qwen2.5-VL video position IDs are unrelated issues." }, { - "left": "issue:43550", - "right": "issue:45072", + "left": "issue:43746", + "right": "issue:43873", "accept": false, - "reason": "torch.compile SDPA issue vs bf16 dtype mismatch; not the same concrete problem." + "reason": "PEFT checkpoint loading is unrelated to quantization/offloading behavior." }, { - "left": "issue:43746", - "right": "issue:43873", + "left": "issue:43550", + "right": "issue:45072", "accept": false, - "reason": "PEFT checkpoint loading vs quantization offloading behavior; distinct failure modes." + "reason": "Different models and bugs: torch.compile+SDPA failure vs dtype mismatch in bfloat16 inference." }, { "left": "issue:43550", "right": "issue:43819", "accept": false, - "reason": "Bamba SDPA/compile bug vs DAC from_latents mismatch; unrelated." + "reason": "No shared concrete code path; Bamba compile/SDPA issue is unrelated to DAC latent mismatch." }, { "left": "issue:44186", "right": "issue:44898", "accept": false, - "reason": "Tokenizer padding/truncation crash vs image classification/interpolation failure; different components." + "reason": "Tokenizer NER/padding crash and Perceiver interpolation issue are different subsystems." }, { "left": "issue:44843", "right": "issue:45081", "accept": false, - "reason": "Same helper function area, but different bugs: offline model_info call vs backend_tokenizer AttributeError." + "reason": "Both touch _patch_mistral_regex, but one is an offline model_info call and the other is an AttributeError on tokenizer backend; distinct bugs." }, { "left": "issue:44062", "right": "issue:44488", "accept": false, - "reason": "AddedToken special-arg conflict vs model loading failure; no concrete duplicate evidence." + "reason": "AddedToken keyword duplication is unrelated to loading cjvt/sleng-bert." }, { "left": "issue:43577", "right": "issue:43818", "accept": false, - "reason": "Blip2 dtype propagation bug vs Video-LLaVA tower architecture issue; unrelated." + "reason": "BLIP2 dtype propagation and Video-LLaVA temporal-attention/weight-sharing are unrelated." }, { "left": "issue:43531", "right": "issue:43643", "accept": false, - "reason": "Qwen3-MoE sliding window bug vs trust_remote_code config field loss; distinct areas." + "reason": "Sliding-window Qwen3-MoE bug and trust_remote_code AutoConfig field loss are unrelated." }, { "left": "issue:43643", "right": "issue:44877", "accept": false, - "reason": "Both involve config loading, but one is missing fields and the other is strict GraniteSpeech config rejection." + "reason": "Both involve config loading, but one is missing fields from trust_remote_code and the other is strict config rejection; not the same bug." }, { "left": "issue:43421", "right": "issue:44811", "accept": false, - "reason": "Tokenizer backend post-processor sync issue vs Whisper batch_decode skip_special_tokens behavior; not the same bug." + "reason": "Runtime special-token post-processing update and Whisper batch_decode skip_special_tokens behavior are different tokenizer bugs." }, { "left": "issue:43540", "right": "issue:45381", "accept": false, - "reason": "Different video-input regressions in different Qwen model families; not mergeable as one fix." + "reason": "Qwen3OmniMoe video-input ValueError and Qwen2.5-VL vision_position_ids are different model-specific issues." }, { "left": "issue:43653", "right": "issue:43819", "accept": false, - "reason": "BigBird special-token registration bug vs DAC latent mismatch; unrelated." + "reason": "Tokenizer special-token decode bug and DAC latent conversion mismatch are unrelated." }, { "left": "issue:44448", "right": "issue:44671", "accept": false, - "reason": "Different models and outputs (Pegasus vs CamemBERT); no shared concrete code-path." + "reason": "Both are regression reports, but on different models and different output paths." }, { "left": "issue:43782", "right": "issue:44977", "accept": false, - "reason": "Qwen3VL from_pretrained weight_only error vs Qwen3.5 flash-attention generation issue; distinct failures." + "reason": "Qwen3VL weight_only loading error and Qwen3.5 flash-attention generation issue are different code paths." }, { "left": "issue:45584", "right": "issue:45834", "accept": false, - "reason": "Whisper empty-transcription generation bug vs Kosmos2.5 OCR long-input index error; unrelated." + "reason": "Whisper empty-transcription failure and Kosmos2.5 long OCR input error are unrelated." + }, + { + "left": "issue:44821", + "right": "issue:45084", + "accept": false, + "reason": "AutoImageProcessor URL loading and template-node compilation errors are unrelated." }, { "left": "issue:43322", "right": "issue:45685", "accept": false, - "reason": "Llava Next load segfault vs MPS histogram Int limitation; completely different areas." + "reason": "Llava Next segmentation fault and MPS histogram-on-Int error are unrelated." }, { "left": "issue:43825", "right": "issue:43994", "accept": false, - "reason": "Pipeline docs/error-message issue vs SigLIP2 bad predictions; not the same bug." - }, - { - "left": "issue:44821", - "right": "issue:45084", - "accept": false, - "reason": "AutoImageProcessor URL loading vs template-node compilation error; unrelated." + "reason": "Pipeline error messaging and SigLIP2 output quality are unrelated issues." }, { "left": "issue:44561", "right": "issue:45020", "accept": false, - "reason": "Related broad theme around remote_code regressions, but these are not the same concrete breakage." + "reason": "Issue 44561 is one specific remote_code regression cause; 45020 is a broad umbrella and not the same concrete bug." }, { "left": "issue:44485", "right": "issue:44509", "accept": false, - "reason": "GLM-5 RoPE implementation discussion vs documentation task-name mismatch; no duplicate overlap." - }, - { - "left": "issue:30064", - "right": "issue:36331", - "accept": false, - "reason": "Image segmentation-map processing bug vs CustomTrainer compute_loss signature change; unrelated." - }, - { - "left": "issue:39692", - "right": "issue:45834", - "accept": false, - "reason": "SigLIP2 docs/model mismatch and quantization failure vs Kosmos2.5 OCR indexing bug; different issues." - }, - { - "left": "issue:44479", - "right": "issue:45834", - "accept": false, - "reason": "Qwen video-input regression vs Kosmos2.5 OCR long-input index error; only generic multimodal similarity." + "reason": "GLM-5 RoPE implementation discussion and stale v5 docs are unrelated." } ] }, @@ -4924,7 +4926,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 15, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -4932,8 +4934,11 @@ "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ + "issue:30064", "issue:34634", "issue:36010", + "issue:36331", + "issue:39692", "issue:42175", "issue:43262", "issue:43329", @@ -4943,14 +4948,11 @@ "issue:43577", "issue:43582", "issue:43606", - "issue:43638", "issue:43644", "issue:43650", - "issue:43653", "issue:43697", "issue:43720", "issue:43742", - "issue:43746", "issue:43749", "issue:43782", "issue:43819", @@ -4961,12 +4963,11 @@ "issue:44186", "issue:44368", "issue:44442", + "issue:44479", "issue:44610", "issue:44671", "issue:44805", - "issue:44811", "issue:44857", - "issue:44912", "issue:44936", "issue:44991", "issue:45020", @@ -4978,9 +4979,13 @@ "issue:45538", "issue:45600", "issue:45701", - "issue:45803" + "issue:45803", + "issue:45834" ], "soft_pairs": [ + "issue:30064|issue:36331", + "issue:39692|issue:45834", + "issue:44479|issue:45834", "issue:43825|issue:43827", "issue:44186|issue:44442", "issue:43606|issue:45072", @@ -5003,17 +5008,14 @@ "issue:45084|issue:45538", "issue:43644|issue:43749", "issue:43329|issue:45600", - "issue:43742|issue:45020", - "issue:43653|issue:44912", - "issue:43638|issue:44936", - "issue:43746|issue:44811" + "issue:43742|issue:45020" ], - "prepared_review_unit_hash": "ceb51bba412330ce799f5e96eb586fb67791c88f7b9984d44673c40e03202c3f", + "prepared_review_unit_hash": "cd5d33c9e4f3c900ea0af7244a23dd49df8a6dd488f43f1723d891277377e330", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -5021,177 +5023,177 @@ "node_count": 47, "item_count": 47, "soft_pair_count": 26, - "serialized_chars": 35264, - "estimated_input_tokens": 8816, - "estimated_eval_tokens": 17888 + "serialized_chars": 35160, + "estimated_input_tokens": 8790, + "estimated_eval_tokens": 17836 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a grab bag of distinct Transformers regressions across tokenizers, processors, loading paths, dtype/device issues, and training/runtime errors. I found no true duplicate pair among the soft edges; the closest matches are only topic-level overlaps, not the same underlying bug.", - "confidence": 0.9, - "canonical_issue_reason": "Use issue 45020 as the canonical issue: it is the broadest umbrella report about recent Transformers versions breaking model behavior, and it best represents the general regression theme in this otherwise heterogeneous cluster.", + "summary": "The candidate pairs are largely false positives: they span unrelated bugs, models, and code paths. No PR pairs are present. If a single issue must anchor this heterogeneous set, the broadest regression report is issue 45020.", + "confidence": 0.71, + "canonical_issue_reason": "Issue 45020 is the broadest, most umbrella-like report in the set and the only one framed as a general recent-version regression affecting remote_code models; it is the closest thing to a cluster anchor, though the cluster itself is heterogeneous.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45020 is the best representative because it is open, high-level, and covers the widest slice of version-related breakage; the rest are narrower, model-specific bugs that do not collapse cleanly into one concrete root cause.", + "best_issue_reason": "Issue 45020 is the best representative of the set because its scope is broader than the model-specific tokenizer/processor bugs and it captures a version-regression theme that could plausibly subsume nearby reports, even if it is not a true duplicate of them.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:30064", + "right": "issue:36331", + "accept": false, + "reason": "Different failures in different components: image processor segmentation-map handling vs trainer custom loss kwargs." + }, + { + "left": "issue:39692", + "right": "issue:45834", + "accept": false, + "reason": "Unrelated models and symptoms: SigLIP2 doc example errors vs Kosmos2.5 long-OCR index error." + }, + { + "left": "issue:44479", + "right": "issue:45834", + "accept": false, + "reason": "Both are vision/multimodal regressions, but one is a video-input regression and the other is an OCR long-input index error." + }, { "left": "issue:43825", "right": "issue:43827", "accept": false, - "reason": "Both involve pipeline/translation deprecation fallout, but one is an error message bug and the other is outdated docs; different artifacts and fixes." + "reason": "Related to pipeline deprecations, but one is an error-message wording bug and the other is stale documentation; not the same underlying issue." }, { "left": "issue:44186", "right": "issue:44442", "accept": false, - "reason": "Different tokenizer failures on different models and code paths; only broad tokenizer-loading similarity." + "reason": "Both are tokenizer-related, but they concern different tokenizers and different failure modes." }, { "left": "issue:43606", "right": "issue:45072", "accept": false, - "reason": "Device mismatch in Bark CPU offload vs dtype mismatch in other models; unrelated concrete bugs." + "reason": "Device-mismatch during CPU offload vs dtype mismatches in bfloat16 inference are distinct code paths and bugs." }, { "left": "issue:43577", "right": "issue:43582", "accept": false, - "reason": "BLIP2 dtype propagation vs Apple Silicon allocator TypeError; no shared underlying defect." + "reason": "Blip2 dtype-loading bug is unrelated to an Apple Silicon TypeError in caching allocator warmup." }, { "left": "issue:34634", "right": "issue:36010", "accept": false, - "reason": "BarkProcessor voice_preset bug is unrelated to a transformers.GenerationMixin import error." + "reason": "BarkProcessor voice preset behavior and a GenerationMixin import error are unrelated." }, { "left": "issue:44805", "right": "issue:44936", "accept": false, - "reason": "Different failures: mask/index shape mismatch vs trainer lifecycle failure after train()." + "reason": "Generic mask-shape IndexError vs trainer.evaluate() failing after train() are not the same failure." }, { "left": "issue:43452", "right": "issue:44991", "accept": false, - "reason": "Both are loading/tokenizer issues, but the models and root causes differ; not the same bug." + "reason": "Both are loading failures, but one is gguf_file handling and the other is a tokenizer compatibility regression." }, { "left": "issue:42175", "right": "issue:45081", "accept": false, - "reason": "Backend dependency packaging issue vs tokenizer regex patch crash; unrelated." + "reason": "Backend-install packaging issue vs Mistral tokenizer regex crash; no shared underlying bug." }, { "left": "issue:44610", "right": "issue:45072", "accept": false, - "reason": "Processor image size mismatch vs inference dtype mismatch; different code paths." + "reason": "Processor input-size mismatch is unrelated to dtype mismatch inference failures." }, { "left": "issue:43720", "right": "issue:45072", "accept": false, - "reason": "Packed-weight loading bug in BitNet vs dtype mismatch in inference; not mergeable as one fix." + "reason": "Packed-weight loading bug in BitNet is unrelated to dtype mismatches." }, { "left": "issue:45081", "right": "issue:45406", "accept": false, - "reason": "Both are attribute errors during loading, but one is Mistral tokenizer regex patching and the other is Gemma4 serve processor state." + "reason": "Both are attribute errors in loading/serving, but they involve different models, different missing attributes, and different code paths." }, { "left": "issue:43404", "right": "issue:43782", "accept": false, - "reason": "Mistral lm_head tying bug vs Qwen3VL weight_only load error; different models and mechanisms." + "reason": "Mistral weight tying and Qwen3VL weight_only loading are distinct model bugs." }, { "left": "issue:44060", "right": "issue:44368", "accept": false, - "reason": "Both mention tied-weights warnings, but the underlying models and behavior are different warning/reporting issues." + "reason": "Both mention tied-weights warnings, but one is an incorrect internal tying bug and the other is a config warning during fine-tuning." }, { "left": "issue:43650", "right": "issue:43906", "accept": false, - "reason": "Placeholder/irrelevant issue vs isolated reproduction of another issue; no duplication." + "reason": "Placeholder issue title and a reproduction of another issue are not the same underlying bug." }, { "left": "issue:44671", "right": "issue:45701", "accept": false, - "reason": "CamemBERT masked LM regression vs a general tokenization-change report; only loose version-related similarity." + "reason": "Masked-LM prediction regression and tokenization changes are different symptoms and likely different fixes." }, { "left": "issue:43582", "right": "issue:44857", "accept": false, - "reason": "Allocator warmup TypeError and AMP crash are separate runtime failures." + "reason": "Apple Silicon allocator TypeError vs CUDA AMP loss crash are unrelated." }, { "left": "issue:43262", "right": "issue:43819", "accept": false, - "reason": "Audio sampling-rate defaulting bug vs DAC latent reconstruction mismatch; unrelated." + "reason": "Sampling-rate defaulting in audio chat templates is unrelated to DAC latent reconstruction mismatch." }, { "left": "issue:43526", "right": "issue:43697", "accept": false, - "reason": "BEiT label reduction bug vs RTDetrV2 output drift; different models and fixes." + "reason": "BEiT label reduction bug and RTDetrV2 output divergence are different model-specific regressions." }, { "left": "issue:45459", "right": "issue:45803", "accept": false, - "reason": "Both involve overly broad exception handling, but they are different functions and failure modes." + "reason": "Both involve exception handling, but they are separate code paths and separate bugs." }, { "left": "issue:45084", "right": "issue:45538", "accept": false, - "reason": "Template compilation TypeError vs tokenizer max_length constant misuse; not the same bug." + "reason": "Template compilation TypeError and CLIPTokenizer max length are unrelated." }, { "left": "issue:43644", "right": "issue:43749", "accept": false, - "reason": "Non-persistent buffer corruption in v5 vs FSDP CPU RAM efficient loading breakage; different subsystems." + "reason": "Non-persistent buffer junk-fill vs FSDP CPU RAM-efficient loading are different loading issues." }, { "left": "issue:43329", "right": "issue:45600", "accept": false, - "reason": "Undefined multimodal-token helper bug vs stale auto_mappings references; unrelated maintenance issues." + "reason": "Multimodal token counting video-branch bug is unrelated to stale auto_mappings config references." }, { "left": "issue:43742", "right": "issue:45020", "accept": false, - "reason": "MobileLLM key error may be version-related, but it is a distinct loading failure from the broad remote_code regression report." - }, - { - "left": "issue:43653", - "right": "issue:44912", - "accept": false, - "reason": "BigBird tokenizer special-token bug vs MXFP4 quantization fallback; no shared root cause." - }, - { - "left": "issue:43638", - "right": "issue:44936", - "accept": false, - "reason": "Deepspeed zero3 indexing error vs trainer evaluate-after-train failure; separate training bugs." - }, - { - "left": "issue:43746", - "right": "issue:44811", - "accept": false, - "reason": "PEFT/local checkpoint loading issue vs Whisper batch_decode skip_special_tokens bug; different code paths." + "reason": "Specific KeyError for one model load is not the same as a broad remote_code regression." } ] }, @@ -5207,7 +5209,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 16, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -5222,24 +5224,23 @@ "issue:38175", "issue:39692", "issue:40990", - "issue:42915", "issue:43257", "issue:43262", "issue:43329", "issue:43450", - "issue:43452", "issue:43454", "issue:43526", "issue:43531", "issue:43550", "issue:43577", - "issue:43582", "issue:43606", + "issue:43638", "issue:43643", "issue:43645", + "issue:43653", "issue:43697", "issue:43720", - "issue:43742", + "issue:43746", "issue:43749", "issue:43819", "issue:43854", @@ -5254,6 +5255,7 @@ "issue:44811", "issue:44849", "issue:44912", + "issue:44936", "issue:44977", "issue:45042", "issue:45356", @@ -5265,6 +5267,9 @@ "issue:45859" ], "soft_pairs": [ + "issue:43653|issue:44912", + "issue:43638|issue:44936", + "issue:43746|issue:44811", "issue:44589|issue:45042", "issue:43854|issue:44977", "issue:38175|issue:44610", @@ -5281,8 +5286,8 @@ "issue:43749|issue:44291", "issue:43531|issue:45042", "issue:43262|issue:44811", - "issue:44568|issue:45356", "issue:36010|issue:36331", + "issue:44568|issue:45356", "issue:43643|issue:45759", "issue:44849|issue:45701", "issue:43329|issue:43450", @@ -5292,228 +5297,229 @@ "issue:43257|issue:43931", "issue:43697|issue:45357", "issue:45823|issue:45859", - "issue:44291|issue:45042", - "issue:43452|issue:43582", - "issue:42915|issue:43742" + "issue:44291|issue:45042" ], - "prepared_review_unit_hash": "db3ecc0d08eadbf788e6b89d0c5c92bc06d6036cfc67a6a90f1178f0f33fcc0c", + "prepared_review_unit_hash": "0f6e3641d6d29dd4134af980150bc92d1c8a6d098e8b8c3036144cadec304e0e", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 30, - "serialized_chars": 36974, - "estimated_input_tokens": 9244, - "estimated_eval_tokens": 18744 + "soft_pair_count": 31, + "serialized_chars": 37392, + "estimated_input_tokens": 9348, + "estimated_eval_tokens": 18952 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a set of unrelated closed issues from the same repo; only one soft pair looks like the same underlying regression in the video multimodal path.", - "confidence": 0.77, - "canonical_issue_reason": "issue:45701 is the broadest and most reusable issue in the set: it is open, has inbound references, and describes a general tokenization regression that can plausibly anchor related tokenizer behavior reports.", + "summary": "This cluster is a loose grab-bag of Transformers bug reports, mostly around model loading, tokenization, multimodal processors, and trainer behavior. The soft edges look like topical similarity rather than true duplicates, so I would reject them all.", + "confidence": 0.91, + "canonical_issue_reason": "issue:44912 is the most connected issue in the set and has the broadest relevance to a shared code path (model loading/quantization), making it the best cluster anchor even though it is not a true duplicate hub.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45701 is the best overall issue candidate because it is broad, still open, and likely to attract/organize follow-up reports around tokenizer behavior changes.", + "best_issue_reason": "issue:44912 is the strongest single representative of the cluster\u2019s recurring loading/quantization regression theme and has multiple soft links, so it is the best issue to anchor triage.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43653", + "right": "issue:44912", + "accept": false, + "reason": "Different bugs: tokenizer special-token registration/decoding vs MXFP4 quantization fallback during model loading." + }, + { + "left": "issue:43638", + "right": "issue:44936", + "accept": false, + "reason": "Unrelated failure modes: DeepSpeed ZeRO-3/non-pretrained BERT index error vs trainer.evaluate() breaking after train()." + }, + { + "left": "issue:43746", + "right": "issue:44811", + "accept": false, + "reason": "Different code paths: PEFT adapter loading from local checkpoints vs Whisper batch_decode skip_special_tokens behavior." + }, { "left": "issue:44589", "right": "issue:45042", "accept": false, - "reason": "Different failures: one is a storage/backend type error, the other is an image-processor dependency regression." + "reason": "Both are loader/backend issues, but one is a missing storage object for float8 tensors and the other is PIL image processors wrongly requiring torchvision." }, { "left": "issue:43854", "right": "issue:44977", "accept": false, - "reason": "Different models and code paths: GLM loading/unit-test failure vs Qwen3.5 flash-attention generation behavior." + "reason": "Different symptoms: GLM-4.7 model-loading test failure vs Qwen3.5 flash-attention generation regression." }, { "left": "issue:38175", "right": "issue:44610", "accept": false, - "reason": "Unrelated subsystems: SigLIP2 probability output issue vs OmDet-Turbo image size mismatch." + "reason": "Different model families and bugs: SIGLIP2 zero probabilities vs OmDet-Turbo processor/model input-size mismatch." }, { "left": "issue:39692", "right": "issue:44912", "accept": false, - "reason": "Docs/example errors for SigLIP2 are not the same bug as MXFP4 quantization fallback for git-oss-20b." + "reason": "SigLIP2 doc example errors are about model/processor mismatch and quantization example failures, not the same MXFP4 loading fallback bug." }, { "left": "issue:43526", "right": "issue:44554", "accept": false, - "reason": "Different components: Beit image label reduction vs an MPS attention correctness issue." + "reason": "Unrelated issues: BeitImageProcessorFast label reduction bug vs MPS attention correctness when value head dim differs from query." }, { "left": "issue:36010", "right": "issue:43645", "accept": false, - "reason": "Both are import/model-init regressions in v5, but they affect different mechanisms and are not the same code-path bug." + "reason": "Both mention GenerationMixin/custom model loading, but one is an import path regression and the other is a Jupyter custom-model initialization regression." }, { "left": "issue:34634", "right": "issue:36331", "accept": false, - "reason": "BarkProcessor voice preset handling is unrelated to CustomTrainer.compute_loss signature changes." + "reason": "BarkProcessor voice_preset and CustomTrainer.compute_loss are distinct APIs and unrelated failures." }, { "left": "issue:43819", "right": "issue:43927", "accept": false, - "reason": "Different model behaviors: DAC latent reconstruction mismatch vs DiaConfig losing custom token IDs on save/load." + "reason": "Different mechanisms: DAC from_latents/STE mismatch vs DiaConfig losing custom token IDs after save/load." }, { "left": "issue:43454", "right": "issue:43577", "accept": false, - "reason": "Different model families and failures: weight tying in AyaVision vs dtype propagation in Blip2." + "reason": "AyaVision lm_head tying and BLIP2 dtype propagation are separate model-specific initialization bugs." }, { "left": "issue:43257", "right": "issue:43329", "accept": false, - "reason": "Qwen3 MoE weight conversion/loading is unrelated to the multimodal token-counting video-branch undefined-variable bug." + "reason": "Qwen3 MoE accelerate/deepspeed weight conversion and multimodal token counting in the video branch are different problems." }, { "left": "issue:43720", "right": "issue:44610", "accept": false, - "reason": "Packed-weight loading for BitNet is unrelated to the OmDet-Turbo processor input-size regression." + "reason": "BitNet packed-weight unpacking during accelerate loading is unrelated to OmDet-Turbo processor image \u0906\u0915\u093e\u0930 mismatch." }, { "left": "issue:43550", "right": "issue:44912", "accept": false, - "reason": "torch.compile + SDPA failure in Bamba is a different issue than MXFP4 quantization fallback in git-oss-20b." + "reason": "Bamba torch.compile SDPA failure is an execution-time attention issue, not the same as MXFP4 quantized loading fallback." }, { "left": "issue:44568", "right": "issue:45488", "accept": false, - "reason": "Both are tokenizer regressions, but they involve different tokenizers and different failure modes." + "reason": "Tokenizer special-token addition bug and LlamaTokenizer ByteLevel/Metaspace override are related to tokenization broadly, but they are not the same concrete regression." }, { "left": "issue:43749", "right": "issue:44291", "accept": false, - "reason": "Related loading stack, but not the same bug: FSDP CPU RAM efficient loading vs init_empty_weights passing an unexpected argument." + "reason": "Both are loading-related, but FSDP CPU RAM efficient loading and init_empty_weights/_is_hf_initialized are distinct loading paths with different breakages." }, { "left": "issue:43531", "right": "issue:45042", "accept": false, - "reason": "Qwen3-MoE sliding-window behavior is unrelated to PIL backend torchvision requirements." + "reason": "Qwen3-MoE sliding_window behavior and PIL backend torchvision dependency are unrelated." }, { "left": "issue:43262", "right": "issue:44811", "accept": false, - "reason": "Both are audio processor issues, but one is chat-template sampling rate and the other is batch_decode skip_special_tokens handling." + "reason": "Audio apply_chat_template sampling-rate default and Whisper batch_decode skip_special_tokens are different audio-processing bugs." }, { - "left": "issue:44568", - "right": "issue:45356", + "left": "issue:36010", + "right": "issue:36331", "accept": false, - "reason": "Different tokenizer regressions affecting different models; not the same underlying bug." + "reason": "ImportError for GenerationMixin and compute_loss unexpected kwarg are separate trainer/model API regressions." }, { - "left": "issue:36010", - "right": "issue:36331", + "left": "issue:44568", + "right": "issue:45356", "accept": false, - "reason": "Importing GenerationMixin and CustomTrainer.compute_loss keyword handling are unrelated failures." + "reason": "Both involve tokenization, but mdeberta BOS/EOS handling and Kimi-K2.5 codec/fix_mistral_regex regression are different tokenizer implementations and failures." }, { "left": "issue:43643", "right": "issue:45759", "accept": false, - "reason": "AutoConfig remote-code field loss is not the same issue as unwrapping text_config in composite multimodal configs." + "reason": "AutoConfig trust_remote_code missing fields and AutoModelForCausalLM.from_config text_config unwrapping are related only at a high level; different objects and failure points." }, { "left": "issue:44849", "right": "issue:45701", "accept": false, - "reason": "Qwen3.5 output_hidden_states behavior is a model forward bug, not the broader tokenization regression." + "reason": "Qwen3.5 output_hidden_states regression and general tokenization changes are not the same bug." }, { "left": "issue:43329", "right": "issue:43450", "accept": false, - "reason": "Both involve video, but one is token counting with undefined vars and the other is batched processor output shape; different bugs." + "reason": "Undefined video token-count helpers vs batched video processor output shape are both video-related but not the same underlying defect." }, { "left": "issue:34567", "right": "issue:40990", "accept": false, - "reason": "TrainerState token counters and GPT-OSS perplexity are unrelated." + "reason": "TrainerState token-count tracking and GPT-OSS perplexity are unrelated training metrics vs model evaluation issues." }, { "left": "issue:43329", "right": "issue:44479", - "accept": true, - "reason": "Both describe the same video-input regression in Qwen VLM paths, centered on the video multimodal code path used by several Qwen variants." + "accept": false, + "reason": "Both concern video inputs, but one is an undefined helper path in token counting and the other is a v5.3.0 video-input regression across specific models." }, { "left": "issue:43606", "right": "issue:45859", "accept": false, - "reason": "Both mention CPU offload, but they affect different models and different failure points." + "reason": "Both involve CPU offload/device handling in Bark/Qwen3.5-MoE, but they are different models and different failing code paths." }, { "left": "issue:43257", "right": "issue:43931", "accept": false, - "reason": "Qwen3 MoE loading/conversion and Qwen3-VL weight-shape mismatch are different model-loading problems." + "reason": "Qwen3 MoE deepspeed weight conversion and Qwen3-VL weight-shape mismatch are separate model-loading bugs." }, { "left": "issue:43697", "right": "issue:45357", "accept": false, - "reason": "RTDetrV2 output changes and Qwen3.5 save_pretrained key naming are unrelated regressions." + "reason": "RTDetrV2 output differences in v5 and Qwen3.5 save_pretrained visual-encoder key issues are unrelated regressions." }, { "left": "issue:45823", "right": "issue:45859", "accept": false, - "reason": "Different offload/device-mapping failures in different models; not the same concrete bug." + "reason": "Gemma4 PLE device mismatch during forward and Qwen3_5MoeTextRotaryEmbedding CPU-offload incompatibility are different runtime device-placement bugs." }, { "left": "issue:44291", "right": "issue:45042", "accept": false, - "reason": "Unexpected init argument during empty-weight loading is unrelated to the torchvision dependency regression." - }, - { - "left": "issue:43452", - "right": "issue:43582", - "accept": false, - "reason": "gguf_file tokenizer/model loading and Apple Silicon allocator warmup are unrelated." - }, - { - "left": "issue:42915", - "right": "issue:43742", - "accept": false, - "reason": "Fine-grained FP8 loading for Qwen3Moe is unrelated to the MobileLLM key error." + "reason": "init_empty_weights/_is_hf_initialized handling and PIL backend torchvision dependency are unrelated loading vs image-processing regressions." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet, and the only accepted soft pair (issue:43329 with issue:44479) is a conservative match: both point to the same Qwen video-input regression area and could plausibly be fixed together. The canonical issue choice is also reasonable because issue:45701 is open, broad, and has inbound references. A minor caveat is that the cluster is not entirely \u2018closed,\u2019 since several open issues are present, but that does not undermine the overall conclusion." - }, - "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 }, @@ -5522,7 +5528,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 17, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -5544,6 +5550,7 @@ "issue:43493", "issue:43540", "issue:43577", + "issue:43582", "issue:43643", "issue:43646", "issue:43696", @@ -5579,6 +5586,8 @@ "issue:45823" ], "soft_pairs": [ + "issue:43452|issue:43582", + "issue:42915|issue:43742", "issue:41720|issue:43540", "issue:43317|issue:45538", "issue:33357|issue:34567", @@ -5595,8 +5604,8 @@ "issue:45137|issue:45405", "issue:38175|issue:44898", "issue:44737|issue:45588", - "issue:44062|issue:44991", "issue:43742|issue:44291", + "issue:44062|issue:44991", "issue:43540|issue:45823", "issue:43906|issue:45381", "issue:43646|issue:43749", @@ -5611,226 +5620,238 @@ "issue:43452|issue:44488", "issue:44792|issue:44964" ], - "prepared_review_unit_hash": "499a1faa77392d06b864adeca38057a338435625c404c8fb93dd0034d81112ab", + "prepared_review_unit_hash": "c932c38ed6589a841fe45a92655e87052943d4644b52ea44cee1d952aff279fd", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 31, - "serialized_chars": 36473, - "estimated_input_tokens": 9119, - "estimated_eval_tokens": 18494 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37633, + "estimated_input_tokens": 9409, + "estimated_eval_tokens": 19074 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is largely heterogeneous and contains several unrelated issue families. The only strong duplicate candidates are the Qwen video-input regression pair and the SigLIP2 correctness pair; the rest are not the same underlying bug/change.", - "confidence": 0.78, - "canonical_issue_reason": "No single issue cleanly represents the cluster: it spans unrelated topics (trainer API, tokenizers, model loading, device_map, multimodal video regressions, dtype issues, etc.).", + "summary": "The set is mostly heterogeneous and does not form one duplicate cluster. Only two soft pairs look like true duplicates: the Qwen video-input regression pair and the SigLIP2 discrepancy pair. The rest are related by broad subsystem or model family only, so they should stay separate.", + "confidence": 0.86, + "canonical_issue_reason": "No single issue cleanly represents the whole mixed set; if a representative is needed, issue 44479 is the best umbrella for the clearest duplicate subcluster (the v5.3.0 Qwen video-input regression), and it is broader than its specific report 45381.", "canonical_pr_reason": null, - "best_issue_reason": "None of these issues is a reliable global canonical for the cluster; the set is too mixed for one issue to represent all others.", + "best_issue_reason": "Issue 44479 is the strongest global representative because it captures a broad, concrete regression with a likely duplicate (45381) and describes an actionable code-path bug rather than a model-specific symptom.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43452", + "right": "issue:43582", + "accept": false, + "reason": "Different subsystems and failure modes: gguf loading vs Apple Silicon warmup TypeError." + }, + { + "left": "issue:42915", + "right": "issue:43742", + "accept": false, + "reason": "Different models and bugs: Qwen3MoE FP8 conversion vs MobileLLM key error." + }, { "left": "issue:41720", "right": "issue:43540", "accept": false, - "reason": "Different Qwen models and failures: CUDA assert during auto device mapping vs video-processing ValueError. Same broad area, not the same bug." + "reason": "Both involve Qwen3, but one is auto device mapping on A800 and the other is video input processing in Qwen3OmniMoe; not the same bug." }, { "left": "issue:43317", "right": "issue:45538", "accept": false, - "reason": "Device-map/offload loading failure and CLIPTokenizer max_length bug are unrelated." + "reason": "Unrelated issues: dequantized model loading/offload vs CLIPTokenizer max length." }, { "left": "issue:33357", "right": "issue:34567", "accept": false, - "reason": "Completely different subsystems: MacOS CLIP bus error vs TrainerState token counting." + "reason": "Completely different areas: Mac bus error on CLIP model vs TrainerState token counting." }, { "left": "issue:42915", "right": "issue:44821", "accept": false, - "reason": "Qwen3Moe FP8 loading failure vs AutoImageProcessor URL loading; no shared code path." + "reason": "Different model-loading problems in different code paths; not the same underlying defect." }, { "left": "issue:44987", "right": "issue:45538", "accept": false, - "reason": "Model-loading regression for physical-intelligence/fast vs CLIP tokenizer length issue; unrelated." + "reason": "One is a model-loading regression for a specific model; the other is tokenizer max-length behavior." }, { "left": "issue:42915", "right": "issue:45538", "accept": false, - "reason": "FP8 Qwen3Moe load failure is not the same as CLIPTokenizer model_max_length behavior." + "reason": "Different bugs with no shared concrete code path." }, { "left": "issue:43927", "right": "issue:44912", "accept": false, - "reason": "DiaConfig save/load token ID loss and git-oss quantization fallback are different bugs." + "reason": "Dia config save/load token IDs bug is unrelated to MXFP4 quantization fallback." }, { "left": "issue:44479", "right": "issue:45381", "accept": true, - "reason": "Both describe the same Qwen2.5-VL / related Qwen video-input regression in v5.3.0, centered on incorrect video position handling." + "reason": "Both describe the same Qwen video-input regression; 45381 is a specific manifestation of the broader v5.3.0 video-input bug covered by 44479." }, { "left": "issue:43257", "right": "issue:43756", "accept": false, - "reason": "Qwen3 MoE weight conversion and Smollm3 RoPE-layer dropping are unrelated model-specific issues." + "reason": "Different model-specific issues: Qwen3 MoE weight conversion vs SmolLM3 RoPE layer mismatch." }, { "left": "issue:43540", "right": "issue:44560", "accept": false, - "reason": "Both are video-input failures, but in different Qwen model lines with different errors; not clearly one bug." + "reason": "Both are video-input issues, but in different Qwen model families with different errors; too broad to merge." }, { "left": "issue:43540", "right": "issue:44479", "accept": false, - "reason": "Different model families; 44479 is a broader Qwen2.5-VL/Qwen3-VL regression, while 43540 is Qwen3OmniMoe-specific." + "reason": "Related to video inputs, but the concrete models and failure modes differ; not clearly one bug." }, { "left": "issue:43257", "right": "issue:43696", "accept": false, - "reason": "Qwen3 MoE weight conversion vs GPT-oss OOM are unrelated." + "reason": "Qwen3 MoE conversion bug is unrelated to GPT-oss OOM." }, { "left": "issue:43577", "right": "issue:45072", "accept": false, - "reason": "Both mention dtype mismatches, but in different models and code paths; not the same concrete bug." + "reason": "Both mention dtype, but one is BLIP2 load-time dtype propagation and the other is CI inference mismatches in different models." }, { "left": "issue:45137", "right": "issue:45405", "accept": false, - "reason": "DeepSpeed ZeRO3 deque error and PEFT version bump are unrelated." + "reason": "DeepSpeed ZeRO3 deque error and MIN_PEFT_VERSION bump are unrelated." }, { "left": "issue:38175", "right": "issue:44898", "accept": false, - "reason": "Different vision-model correctness problems (SigLIP2 zero probs vs Perceiver non-default resolution failure)." + "reason": "Different model architectures and symptoms: SigLIP2 zero probabilities vs Perceiver non-default resolution failure." }, { "left": "issue:44737", "right": "issue:45588", "accept": false, - "reason": "XLNet CPU arange bug and flash_attention sink-less crash are unrelated." + "reason": "CPU arange placement bug in XLNet is unrelated to flash_attention s_aux handling." }, { - "left": "issue:44062", - "right": "issue:44991", + "left": "issue:43742", + "right": "issue:44291", "accept": false, - "reason": "Tokenizer AddedToken argument error and est-roberta tokenizer loading failure are not the same bug." + "reason": "Both are loading-time errors, but one is a specific model key issue and the other is an init_empty_weights API change." }, { - "left": "issue:43742", - "right": "issue:44291", + "left": "issue:44062", + "right": "issue:44991", "accept": false, - "reason": "Different model-loading failures with different root causes: key error vs unexpected init_empty_weights argument." + "reason": "Both involve tokenizers, but the reported failures and code paths are not clearly the same bug." }, { "left": "issue:43540", "right": "issue:45823", "accept": false, - "reason": "Both involve device-related inference issues, but on different models and code paths." + "reason": "Different models and different device-mismatch paths." }, { "left": "issue:43906", "right": "issue:45381", "accept": false, - "reason": "The isolated reproduction points to another issue, but it is not clearly the same as the qwen2.5-vl video-position-id regression." + "reason": "No shared concrete bug is evident; one is just a reproduction of another issue." }, { "left": "issue:43646", "right": "issue:43749", "accept": false, - "reason": "Custom model initialization breakage and FSDP CPU RAM efficient loading are unrelated." + "reason": "Generic custom-model initialization breakage is not the same as FSDP CPU RAM efficient loading." }, { "left": "issue:44062", "right": "issue:45081", "accept": false, - "reason": "AddedToken duplication and Mistral regex backend_tokenizer crash are different tokenizer problems." + "reason": "Different tokenizer regression paths: AddedToken special-arg conflict vs Mistral regex patch on a missing backend_tokenizer." }, { "left": "issue:43749", "right": "issue:44756", "accept": false, - "reason": "Both concern loading/memory, but one is an FSDP bug and the other is mmap/OOM on Strix Halo; not the same issue." + "reason": "Both relate to memory/loading, but one is FSDP loading and the other is mmap behavior on Strix Halo." }, { "left": "issue:34567", "right": "issue:36331", "accept": false, - "reason": "Both are Trainer-related, but one is token accounting and the other is compute_loss signature incompatibility." + "reason": "TrainerState token counting and CustomTrainer.compute_loss signature changes are unrelated." }, { "left": "issue:36010", "right": "issue:42175", "accept": false, - "reason": "GenerationMixin import failure and missing TensorFlow backend are unrelated packaging/import issues." + "reason": "Import surface breakage and packaging backend contents are different issues." }, { "left": "issue:43493", "right": "issue:43994", "accept": true, - "reason": "Both are about SigLIP2 producing wrong outputs; one is the concrete HF-vs-JAX discrepancy and the other is the user-visible nonsensical-results symptom." + "reason": "Both point to the same SigLIP2 implementation discrepancy; 43994 is a user-facing symptom of the underlying HF-vs-JAX mismatch in 43493." }, { "left": "issue:43643", "right": "issue:45375", "accept": false, - "reason": "Both mention missing fields, but one is trust_remote_code AutoConfig serialization and the other is a specific Qwen3_5MoeVisionConfig field-loss bug." + "reason": "Both involve config fields, but one is trust_remote_code return completeness and the other is a specific config field being dropped by strict handling." }, { "left": "issue:42175", "right": "issue:43824", "accept": false, - "reason": "Package backend composition and a missing Qwen2_5_VL import are unrelated." + "reason": "Packaging TensorFlow omission and missing Qwen2.5-VL import are unrelated." }, { "left": "issue:44291", "right": "issue:44821", "accept": false, - "reason": "init_empty_weights/_is_hf_initialized and AutoImageProcessor URL loading are different failures." + "reason": "init_empty_weights argument handling and AutoImageProcessor URL loading are different code paths." }, { "left": "issue:43452", "right": "issue:44488", "accept": false, - "reason": "gguf_file/from_pretrained breakage and sleng-bert loading failure are not the same underlying bug." + "reason": "Different loading issues: gguf support vs a specific model failing to load." }, { "left": "issue:44792", "right": "issue:44964", "accept": false, - "reason": "Different multimodal model failures; one is a failed janus test, the other is Phi-4-multimodal-instruct loading." + "reason": "Different multimodal model failures and different symptoms; not the same underlying bug." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative: it characterizes the cluster as heterogeneous, and the only accepted soft edges are the two pairs that have clear textual alignment (Qwen video regression and SigLIP2 correctness). The remaining rejections are appropriately cautious and do not overstate duplicate evidence." + "feedback": "The summary is grounded in the packet and stays appropriately conservative overall. The two accepted duplicate pairs (44479/45381 and 43493/43994) are plausible from the titles, and the rest of the false verdicts avoid overclaiming similarity. No mergeability or single-PR issue is overstated." }, "evaluator_used": true, "retried": false, @@ -5843,7 +5864,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 18, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -5910,13 +5931,13 @@ "issue:43697|issue:45216", "issue:28282|issue:29127", "issue:44514|issue:45381", - "issue:44484|issue:44704", "issue:43582|issue:44977", + "issue:44484|issue:44704", "issue:43643|issue:44561", "issue:44625|issue:44877", "issue:43720|issue:44898", - "issue:42175|issue:44938", "issue:43452|issue:43577", + "issue:42175|issue:44938", "issue:41762|issue:44936", "issue:44514|issue:45290", "issue:43452|issue:44843", @@ -5927,12 +5948,12 @@ "issue:44936|issue:45823", "issue:24643|issue:29127" ], - "prepared_review_unit_hash": "27eb51972404d92118598cd891b8b3ddd7c4b3f0c8b693a232f5ccc615f3078d", + "prepared_review_unit_hash": "d99a9826a9fd44fed77c1a238e27a2ce9caa0b1de668dee9e5711558969390f8", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -5940,17 +5961,17 @@ "node_count": 47, "item_count": 47, "soft_pair_count": 26, - "serialized_chars": 35357, - "estimated_input_tokens": 8840, - "estimated_eval_tokens": 17936 + "serialized_chars": 35353, + "estimated_input_tokens": 8839, + "estimated_eval_tokens": 17934 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These items are mostly unrelated Transformers bug reports that only share broad themes like loading, tokenization, config handling, or version regressions. None of the soft pairs looks like the same underlying bug/change, so this cluster should not be deduplicated as one issue set.", - "confidence": 0.92, + "summary": "This cluster is highly heterogeneous: the soft-similarity pairs are all false positives spanning unrelated tokenizer, model-loading, config, training, and vision issues. No safe duplicate merge candidate stands out.", + "confidence": 0.97, "canonical_issue_reason": null, "canonical_pr_reason": null, "best_issue_reason": null, @@ -5960,157 +5981,157 @@ "left": "issue:43526", "right": "issue:45479", "accept": false, - "reason": "Both concern labels/classification, but one is an image-processor bug and the other is a sequence-classification loss issue; different code paths." + "reason": "Different bugs: BeitImageProcessorFast reduce_labels vs sequence-classification zero-loss behavior across models." }, { "left": "issue:28282", "right": "issue:34689", "accept": false, - "reason": "Missing PyTorch installation is an environment error; Llama 3.2 Vision loading is a regression in model loading behavior." + "reason": "Unrelated loading problems: missing PyTorch dependency vs Llama 3.2 Vision model loading regression." }, { "left": "issue:45042", "right": "issue:45081", "accept": false, - "reason": "One is about PIL backend requiring torchvision; the other is a Mistral regex/tokenizer attribute crash." + "reason": "Different code paths: PIL image processors requiring torchvision vs Mistral tokenizer regex crash." }, { "left": "issue:43756", "right": "issue:45325", "accept": false, - "reason": "Both mention vision/rope ideas, but they affect different models and different positional-index logic." + "reason": "Both touch RoPE-related behavior, but one is about Smollm3 layer drops and the other about Qwen2.5-VL still-image temporal position ids; not the same bug." }, { "left": "issue:43742", "right": "issue:44589", "accept": false, - "reason": "Different failures: a key error while loading MobileLLM versus a Float8 storage lookup TypeError." + "reason": "Different failure modes: loading facebook/MobileLLM-125M key error vs Float8 storage deserialization error." }, { "left": "issue:45405", "right": "issue:45600", "accept": false, - "reason": "One is a dependency version bump, the other is a stale auto_mappings reference to removed configs." + "reason": "One is a dependency version pin issue, the other is stale auto-mapping references breaking CI." }, { "left": "issue:43531", "right": "issue:44821", "accept": false, - "reason": "Qwen3-MoE sliding-window behavior and AutoImageProcessor URL loading are unrelated issues." + "reason": "Both are loading-related, but Qwen3-MoE sliding_window and AutoImageProcessor-from-URL are unrelated." }, { "left": "issue:43697", "right": "issue:45216", "accept": false, - "reason": "RTDetrV2 output differences and Qwen3.5 save_pretrained regression are separate bugs." + "reason": "Different regressions: RTDetrV2 output drift in v5 vs Qwen3.5 save_pretrained checkpoint corruption." }, { "left": "issue:28282", "right": "issue:29127", "accept": false, - "reason": "ImportError for missing PyTorch is not the same as LayoutLMv3 box-validation messaging." + "reason": "Missing PyTorch install vs LayoutLMv3 box-validation error; different root causes." }, { "left": "issue:44514", "right": "issue:45381", "accept": false, - "reason": "Both involve chat/template or VL inputs, but they fail in different shapes and model-specific position handling." + "reason": "Both are Qwen2.5-VL chat/vision issues, but one is batched apply_chat_template with padding=False and the other is incorrect video vision_position_ids." }, { - "left": "issue:44484", - "right": "issue:44704", + "left": "issue:43582", + "right": "issue:44977", "accept": false, - "reason": "Save-pretrained shard-size behavior and AutoProcessor kwarg forwarding are unrelated." + "reason": "Different subsystems: Apple Silicon caching_allocator_warmup TypeError vs Qwen3.5 flash-attention generation failure." }, { - "left": "issue:43582", - "right": "issue:44977", + "left": "issue:44484", + "right": "issue:44704", "accept": false, - "reason": "Apple Silicon warmup TypeError and Qwen3.5 flash-attention generation are different runtime problems." + "reason": "save_pretrained shard-size question vs AutoProcessor not forwarding kwargs to cached_file; not duplicates." }, { "left": "issue:43643", "right": "issue:44561", "accept": false, - "reason": "One is missing fields in AutoConfig with trust_remote_code; the other is removal of a helper breaking remote-code models." + "reason": "Different breakages: missing fields with trust_remote_code in AutoConfig vs removal of is_torch_fx_available breaking remote-code models." }, { "left": "issue:44625", "right": "issue:44877", "accept": false, - "reason": "Num-label propagation in Qwen3.5 and strict config rejection for granite_speech are not the same bug." + "reason": "Both involve config handling, but Qwen3.5 num_labels propagation and granite_speech strict-config loading are different bugs." }, { "left": "issue:43720", "right": "issue:44898", "accept": false, - "reason": "BitNet packed-weight loading and Perceiver non-default-resolution behavior are unrelated." + "reason": "BitNet packed-weights loading failure is unrelated to Perceiver interpolation at non-default resolution." }, { - "left": "issue:42175", - "right": "issue:44938", + "left": "issue:43452", + "right": "issue:43577", "accept": false, - "reason": "TensorFlow extra dependency packaging and Python 3.14 load failure are different issues." + "reason": "Different model-loading issues: gguf_file breaks tokenizer/model loading vs Blip2 dtype not propagating to qformer/model." }, { - "left": "issue:43452", - "right": "issue:43577", + "left": "issue:42175", + "right": "issue:44938", "accept": false, - "reason": "GGUF loading failure and Blip2 dtype propagation do not share the same failing code path." + "reason": "TensorFlow missing from a torch install extra vs Python 3.14 transformers import/load failure; not the same bug." }, { "left": "issue:41762", "right": "issue:44936", "accept": false, - "reason": "Gemma3 ZeRO-3 loading IndexError and trainer.evaluate() after train are unrelated runtime failures." + "reason": "Different training/loading paths: Gemma3ForConditionalGeneration ZeRO-3 load IndexError vs trainer.evaluate() failing after train()." }, { "left": "issue:44514", "right": "issue:45290", "accept": false, - "reason": "Both are apply_chat_template crashes, but one is batched padding=False and the other is assistant tool-call handling; not the same bug." + "reason": "Both hit apply_chat_template, but one is batched padding=False and the other is assistant tool-call messages with no content; distinct defects." }, { "left": "issue:43452", "right": "issue:44843", "accept": false, - "reason": "GGUF tokenizer/model loading and offline mistral regex patching are distinct problems." + "reason": "gguf_file loading regression is unrelated to offline HF_HUB_OFFLINE failure in _patch_mistral_regex." }, { "left": "issue:44466", "right": "issue:45005", "accept": false, - "reason": "Both mention tied weights, but one is a serialization inconsistency and the other is a broader translation-model regression." + "reason": "Both concern tied weights, but one is inconsistent lm_head serialization and the other is translation-model tied-weight issues in v5; not clearly the same concrete bug." }, { "left": "issue:43295", "right": "issue:45356", "accept": false, - "reason": "Processor.tokenizer regression and Kimi-K2.5 codec/fix_mistral_regex issues are different tokenizer bugs." + "reason": "Different regressions: processor.tokenizer / image passing breakage vs Kimi-K2.5 tokenizer codec handling and warning behavior." }, { "left": "issue:43819", "right": "issue:44811", "accept": false, - "reason": "DAC latent reconstruction mismatch and Whisper batch_decode skipping special tokens are unrelated." + "reason": "Different audio/model behaviors: DAC.from_latents vs forward mismatch and Whisper batch_decode skip_special_tokens handling." }, { "left": "issue:43653", "right": "issue:44568", "accept": false, - "reason": "BigBird special-token registration and mdeberta BOS/EOS handling are separate tokenizer special-token bugs." + "reason": "BigBirdTokenizer special-token registration bug is unrelated to mdeberta-v3 BOS/EOS not being added." }, { "left": "issue:44936", "right": "issue:45823", "accept": false, - "reason": "Trainer evaluation failure and Gemma4 PLE device mismatch are different layers of the stack." + "reason": "Trainer lifecycle failure vs Gemma4 PLE device mismatch during forward; different code paths and symptoms." }, { "left": "issue:24643", "right": "issue:29127", "accept": false, - "reason": "DeepSpeed weight-shape RuntimeError and LayoutLMv3 box-info error are not the same underlying issue." + "reason": "DeepSpeed training weight-dimension RuntimeError is unrelated to LayoutLMv3 box-information validation." } ] }, @@ -6126,7 +6147,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 19, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -6185,8 +6206,8 @@ "soft_pairs": [ "issue:30064|issue:33666", "issue:38175|issue:43295", - "issue:43653|issue:44361", "issue:44361|issue:44442", + "issue:43653|issue:44361", "issue:43577|issue:43697", "issue:44464|issue:44743", "issue:44843|issue:44991", @@ -6195,8 +6216,8 @@ "issue:43688|issue:45440", "issue:43531|issue:43742", "issue:43653|issue:43927", - "issue:43550|issue:43927", "issue:44464|issue:44977", + "issue:43550|issue:43927", "issue:43577|issue:45588", "issue:43550|issue:44361", "issue:32090|issue:34567", @@ -6213,16 +6234,16 @@ "issue:33666|issue:36010", "issue:41720|issue:44464", "issue:43329|issue:45325", - "issue:43756|issue:44913", "issue:43525|issue:43572", + "issue:43756|issue:44913", "issue:43688|issue:43749" ], - "prepared_review_unit_hash": "60a0de3a9b98b15a138e0f22a5356a8693905288e89a2aeabebdddfca6049dbb", + "prepared_review_unit_hash": "ae60b74bc6bc23e12d521a9c4095741d160f892db2e08a7ffe645dfd10289b67", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -6230,81 +6251,81 @@ "node_count": 47, "item_count": 47, "soft_pair_count": 33, - "serialized_chars": 37184, - "estimated_input_tokens": 9296, - "estimated_eval_tokens": 18848 + "serialized_chars": 37180, + "estimated_input_tokens": 9295, + "estimated_eval_tokens": 18846 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly a loose semantic group of unrelated Transformers bugs, especially tokenizer/model-loading regressions plus several separate training/inference and vision issues. None of the soft-edge pairs look like true duplicates, so I would not merge any of them.", - "confidence": 0.94, - "canonical_issue_reason": "Issue 45812 is the broadest and most user-impactful recent tokenizer regression in the set: it affects all Granite models and describes a silent v4\u2192v5 ID change, making it a strong representative issue for the cluster\u2019s tokenizer-regression slice.", + "summary": "This cluster is mostly heterogeneous: the soft pairs point to different models, APIs, and failure modes, so I would not merge any of them as duplicates. The strongest standalone issue is the open Granite AutoTokenizer regression, which is concrete and broadly impactful.", + "confidence": 0.74, + "canonical_issue_reason": "issue:45812 is the best representative issue here because it is a concrete, user-facing tokenizer regression with broad model impact and active inbound references.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45812 is the best single representative because it is specific enough to be actionable yet broad enough to capture the most important common theme in the cluster (tokenizer regressions).", + "best_issue_reason": "issue:45812 is the strongest issue to anchor on: it is open, clearly scoped, and describes a likely cross-model regression affecting token IDs.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:30064", "right": "issue:33666", "accept": false, - "reason": "Different subsystems: image processor void segmentation-map handling vs Qwen2-VL multi-GPU training." + "reason": "Different subsystems: image processor segmentation-map handling vs Qwen2-VL multi-GPU training." }, { "left": "issue:38175", "right": "issue:43295", "accept": false, - "reason": "Unrelated bugs: SIGLIP2 zero probabilities vs a regression around processor.tokenizer and image passing." + "reason": "Both are regressions, but they concern different code paths: SigLIP2 zero probabilities vs processor/tokenizer API breakage." }, { - "left": "issue:43653", - "right": "issue:44361", + "left": "issue:44361", + "right": "issue:44442", "accept": false, - "reason": "Different tokenizer failures: BigBird special-token decode issue vs MLukeTokenizer attribute error." + "reason": "Both are tokenizer/loading failures, but for different tokenizers and unrelated error modes." }, { - "left": "issue:44361", - "right": "issue:44442", + "left": "issue:43653", + "right": "issue:44361", "accept": false, - "reason": "Both are tokenizer-related, but one is an MLukeTokenizer task error and the other is AutoTokenizer failing on a different tokenizer class." + "reason": "BigBird special-token decoding issue is unrelated to MLukeTokenizer task errors." }, { "left": "issue:43577", "right": "issue:43697", "accept": false, - "reason": "Different model behavior bugs: BLIP2 dtype propagation vs RTDetrV2 output drift in v5." + "reason": "Different model families and bugs: dtype propagation in BLIP2 vs divergent outputs in RTDetrV2." }, { "left": "issue:44464", "right": "issue:44743", "accept": false, - "reason": "Different code paths: compiled chunked generation inconsistency vs Qwen3.5 modular recurrent-state reset." + "reason": "Both affect generation, but the concrete failures are different: compiled forward inconsistency vs cache/state reset in Qwen3.5 modular code." }, { "left": "issue:44843", "right": "issue:44991", "accept": false, - "reason": "Different tokenizer regressions: offline hub regex patch side effect vs EMBEDDIA/est-roberta loading failure." + "reason": "Both involve tokenizer loading, but one is offline model_info misuse and the other is a specific tokenizer regression for EMBEDDIA/est-roberta." }, { "left": "issue:41720", "right": "issue:43906", "accept": false, - "reason": "Qwen3 auto device mapping CUDA assert is unrelated to an isolated reproduction of another issue." + "reason": "The titles suggest different manifestations; there is not enough evidence they are the same underlying device-mapping bug." }, { "left": "issue:44977", "right": "issue:45356", "accept": false, - "reason": "Both involve Qwen/Kimi generation/tokenization, but the concrete failures are flash-attention generation vs codec/regex tokenizer regression." + "reason": "Different failures: flash-attention generation bug vs tokenizer codec/regex regression." }, { "left": "issue:43688", "right": "issue:45440", "accept": false, - "reason": "Different MoE/model-implementation bugs: auxiliary-loss normalization vs DeepseekV3 native divergence." + "reason": "Both are MoE-related, but one is auxiliary-loss normalization and the other is DeepSeekV3 implementation divergence." }, { "left": "issue:43531", @@ -6316,133 +6337,133 @@ "left": "issue:43653", "right": "issue:43927", "accept": false, - "reason": "BigBird mask-token decode bug and DiaConfig custom token ID loss are separate tokenizer/config issues." + "reason": "BigBird mask-token decode failure and DiaConfig custom token-ID loss are different bug classes." }, { - "left": "issue:43550", - "right": "issue:43927", + "left": "issue:44464", + "right": "issue:44977", "accept": false, - "reason": "Different failures: Bamba torch.compile SDPA vs DiaConfig save/load token-ID corruption." + "reason": "Both mention generation, but the model families and failure mechanisms differ." }, { - "left": "issue:44464", - "right": "issue:44977", + "left": "issue:43550", + "right": "issue:43927", "accept": false, - "reason": "Both are generation bugs, but compiled forward inconsistency is not the same concrete issue as Qwen3.5 flash-attention generation failure." + "reason": "torch.compile/SDPA failure in Bamba is unrelated to DiaConfig save/load token ID corruption." }, { "left": "issue:43577", "right": "issue:45588", "accept": false, - "reason": "BLIP2 dtype loading and flash_attention.py crashing on s_aux=None are unrelated." + "reason": "BLIP2 dtype propagation and flash-attention s_aux=None crash are unrelated bugs." }, { "left": "issue:43550", "right": "issue:44361", "accept": false, - "reason": "No shared bug path: Bamba compile/SDPA issue vs MLukeTokenizer task AttributeError." + "reason": "Different areas: compiled attention failure vs tokenizer AttributeError on tasks." }, { "left": "issue:32090", "right": "issue:34567", "accept": false, - "reason": "Trainer NoneType broadcast error is distinct from TrainerState.num_input_tokens_seen not updating." + "reason": "Trainer distributed broadcast error is unrelated to TrainerState token-count tracking." }, { "left": "issue:43504", "right": "issue:43550", "accept": false, - "reason": "Beit pretrained-loading legacy field bug is unrelated to Bamba compile/SDPA behavior." + "reason": "Legacy-field loading in BeitForSemanticSegmentation is unrelated to Bamba torch.compile failures." }, { "left": "issue:43122", "right": "issue:43906", "accept": false, - "reason": "Tokenizer output differences across versions are not the same as an isolated reproduction of another issue." + "reason": "Different tokenizer regressions with no evidence of the same underlying cause." }, { "left": "issue:43504", "right": "issue:43720", "accept": false, - "reason": "Different loading issues: legacy field in Beit vs BitNet packed-weight unpacking during accelerate loading." + "reason": "Pretrained-model legacy-field loading and BitNet packed-weight unpacking are different code paths." }, { "left": "issue:28282", "right": "issue:35141", "accept": false, - "reason": "AutoModel missing PyTorch import and token-embedding resizing/post_init reinitialization are unrelated." + "reason": "PyTorch-missing import error and embedding reinitialization bug are unrelated." }, { "left": "issue:32090", "right": "issue:33666", "accept": false, - "reason": "Trainer broadcast NoneType error is a different failure mode from Qwen2-VL multi-GPU training." + "reason": "Both touch training, but one is a NoneType broadcast error and the other is a multi-GPU Qwen2-VL training request." }, { "left": "issue:43504", "right": "issue:44610", "accept": false, - "reason": "Beit legacy-field loading bug and OmDet-Turbo processor/model image-size mismatch are different problems." + "reason": "Different model-loading/processor issues with no shared failure mechanism." }, { "left": "issue:43452", "right": "issue:44451", "accept": false, - "reason": "gguf_file breaks specific AutoTokenizer/AutoModel loading paths, while ScandiBERT loading failure is a separate model/tokenizer compatibility issue." + "reason": "gguf_file loading breakage is not the same as ScandiBERT tokenizer loading failure." }, { "left": "issue:44849", "right": "issue:45357", "accept": false, - "reason": "Qwen3.5 hidden-states bug and incorrect visual-encoder keys on save_pretrained are different regressions." + "reason": "Qwen3.5 hidden-states bug and save_pretrained visual-key regression are different defects." }, { "left": "issue:43742", "right": "issue:44821", "accept": false, - "reason": "MobileLLM key error on load is unrelated to AutoImageProcessor loading from URL." + "reason": "Key error loading MobileLLM-125M is unrelated to loading AutoImageProcessor from URL." }, { "left": "issue:44568", "right": "issue:45812", "accept": false, - "reason": "mdeberta-v3 special-token addition bug is not the same regression as Granite token-ID changes; different tokenizer families and behaviors." + "reason": "Both are tokenizer regressions, but they affect different model families and different tokenization behaviors." }, { "left": "issue:33666", "right": "issue:36010", "accept": false, - "reason": "Qwen2-VL multi-GPU training and GenerationMixin import failure are unrelated." + "reason": "Multi-GPU Qwen2-VL training issue is unrelated to a GenerationMixin import error." }, { "left": "issue:41720", "right": "issue:44464", "accept": false, - "reason": "CUDA assert on auto device mapping is a different failure from compiled-forward generation inconsistency." + "reason": "Different bug types: device-mapping CUDA assert vs chunked-generation inconsistency under compiled forward." }, { "left": "issue:43329", "right": "issue:45325", "accept": false, - "reason": "Undefined helper/merge_size in video multimodal token counting is distinct from Qwen2.5-VL rope-index scaling for still images." + "reason": "Both involve multimodal token calculations, but one is an undefined-video-branch bug and the other is still-image position scaling." }, { - "left": "issue:43756", - "right": "issue:44913", + "left": "issue:43525", + "right": "issue:43572", "accept": false, - "reason": "Smollm3 RoPE layer mismatch and GPTNeoX rotary_pct reload bug are separate configuration issues." + "reason": "Both are config-field problems, but the missing attributes differ and the affected models are unrelated." }, { - "left": "issue:43525", - "right": "issue:43572", + "left": "issue:43756", + "right": "issue:44913", "accept": false, - "reason": "Both are config attribute regressions, but they concern different fields and model families (pad_token_id vs pad_token_idx)." + "reason": "RoPE/rotary-related issues, but one is a model-architecture discrepancy and the other is config reload behavior." }, { "left": "issue:43688", "right": "issue:43749", "accept": false, - "reason": "Aux-loss normalization in MoE models and FSDP_CPU_RAM_EFFICIENT_LOADING are unrelated." + "reason": "MoE auxiliary-loss normalization is unrelated to FSDP CPU RAM efficient loading." } ] }, @@ -6458,7 +6479,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 20, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -6527,8 +6548,8 @@ "issue:39692|issue:43493", "issue:43720|issue:44361", "issue:43688|issue:45704", - "issue:43334|issue:43572", "issue:44964|issue:45405", + "issue:43334|issue:43572", "issue:43540|issue:44977", "issue:44479|issue:44625", "issue:43493|issue:43844", @@ -6538,8 +6559,8 @@ "issue:44488|issue:44843", "issue:43257|issue:43299", "issue:43824|issue:44589", - "issue:43278|issue:43844", "issue:43646|issue:44466", + "issue:43278|issue:43844", "issue:45229|issue:45823", "issue:44589|issue:45520", "issue:43688|issue:45701", @@ -6550,12 +6571,12 @@ "issue:44423|issue:44734", "issue:43927|issue:44361" ], - "prepared_review_unit_hash": "a1b233fedade9e9f596428ccc25679fa4f7c7264a9ec36dcc800c2653271f51c", + "prepared_review_unit_hash": "ad43c99914c644be17580e6487fa7d3c1ca1a05c2a54e8e030784177d515307d", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -6563,219 +6584,219 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 33, - "serialized_chars": 37975, - "estimated_input_tokens": 9494, - "estimated_eval_tokens": 19244 + "serialized_chars": 37977, + "estimated_input_tokens": 9495, + "estimated_eval_tokens": 19246 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is highly heterogeneous: most items are distinct Transformers bugs/regressions across unrelated models, loaders, and runtime paths. I found no true duplicate pairs among the soft edges.", - "confidence": 0.94, - "canonical_issue_reason": "Issue 43646 is the broadest, most representative regression report in the set (\u201cTransformers 5.0.0 breaks custom model initialization\u201d) and is phrased as a concrete framework-level breakage rather than a model-specific symptom.", + "summary": "The cluster is mostly heterogeneous, with a small Qwen/multimodal-loading subgroup and many unrelated standalone bugs. No soft edge pair looks like the same underlying bug/change, so all candidate merges are rejected.", + "confidence": 0.27, + "canonical_issue_reason": "issue:44479 is the broadest and most representative item in the only clearly related subgroup: a cross-model Qwen multimodal/video-input regression affecting multiple variants.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43646 is the best global exemplar because it describes a clear, high-level compatibility regression with direct impact and a well-scoped failure mode.", + "best_issue_reason": "issue:44479 is the best global representative because it spans several Qwen model families and reflects a concrete regression with a likely shared code path.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43493", "right": "issue:43825", "accept": false, - "reason": "Different bugs: SigLIP2 implementation mismatch vs an incorrect pipeline error message about translation tasks." + "reason": "SigLIP2 implementation discrepancies are unrelated to a pipeline error-message regression." }, { "left": "issue:43262", "right": "issue:43295", "accept": false, - "reason": "Unrelated regressions: audio sampling-rate defaulting vs processor.tokenizer / image passthrough breakage." + "reason": "Audio processor sampling-rate defaulting and processor.tokenizer regression are different code paths." }, { "left": "issue:43606", "right": "issue:43927", "accept": false, - "reason": "Different code paths: CPU offload device mismatch in Bark vs DiaConfig losing custom token IDs on save/load." + "reason": "CPU offload device mismatch in Bark is unrelated to DiaConfig token-id persistence." }, { "left": "issue:43720", "right": "issue:43927", "accept": false, - "reason": "Different models and failures: BitNet packed-weight loading vs DiaConfig token-id persistence." + "reason": "Packed-weight loading for BitNet is unrelated to custom token ID loss in DiaConfig." }, { "left": "issue:28282", "right": "issue:32090", "accept": false, - "reason": "ImportError for missing PyTorch is unrelated to Trainer's NoneType broadcast failure." + "reason": "Missing PyTorch import and NoneType GPU broadcast errors are unrelated failures." }, { "left": "issue:28282", "right": "issue:33357", "accept": false, - "reason": "Different underlying problems: missing PyTorch installation vs MacOS bus error loading a CLIP model." + "reason": "PyTorch import failure and MacOS bus error in CLIP are unrelated." }, { "left": "issue:43577", "right": "issue:44554", "accept": false, - "reason": "BLIP2 dtype mismatch is not the same as the MPS attention correctness issue." + "reason": "BLIP2 dtype persistence and MPS attention correctness are different bugs." }, { "left": "issue:33666", "right": "issue:36331", "accept": false, - "reason": "Multi-GPU training for Qwen2-VL is unrelated to CustomTrainer.compute_loss signature breakage." + "reason": "Qwen2-VL multi-GPU training and CustomTrainer loss signature mismatch are unrelated." }, { "left": "issue:39692", "right": "issue:43493", "accept": false, - "reason": "Docs/example errors are separate from a SigLIP2 HF-vs-JAX implementation discrepancy." + "reason": "Documentation example errors and SigLIP2 HF-vs-JAX implementation divergence are not the same issue." }, { "left": "issue:43720", "right": "issue:44361", "accept": false, - "reason": "BitNet packed-weight loading and MLukeTokenizer task attribute errors are different bugs." + "reason": "BitNet accelerate-loading bug and MLukeTokenizer task AttributeError are unrelated." }, { "left": "issue:43688", "right": "issue:45704", "accept": false, - "reason": "Auxiliary-loss normalization and T5 apex memory leak are unrelated issues." + "reason": "Aux-loss normalization and T5 apex memory leak affect different subsystems." }, { - "left": "issue:43334", - "right": "issue:43572", + "left": "issue:44964", + "right": "issue:45405", "accept": false, - "reason": "Both involve missing config fields, but for different models and different attributes (pad_token_id vs pad_token_idx)." + "reason": "Phi-4 multimodal loading regression and an out-of-date PEFT version pin are unrelated." }, { - "left": "issue:44964", - "right": "issue:45405", + "left": "issue:43334", + "right": "issue:43572", "accept": false, - "reason": "Model loading failure for Phi-4 multimodal is unrelated to a dependency version bump for PEFT." + "reason": "Qwen3-VL pad_token_id loading bug and StableLm pad_token_idx regression are different model/config issues." }, { "left": "issue:43540", "right": "issue:44977", "accept": false, - "reason": "Video-input processing failure in Qwen3OmniMoe is unrelated to flash-attention generation behavior in Qwen3.5." + "reason": "Qwen3OmniMoe video processing failure and Qwen3.5 flash-attention generation bug do not share the same failure mode." }, { "left": "issue:44479", "right": "issue:44625", "accept": false, - "reason": "Video regression across Qwen variants is different from num_labels propagation in Qwen3.5 configs." + "reason": "Video-input regression and num_labels propagation are separate config bugs." }, { "left": "issue:43493", "right": "issue:43844", "accept": false, - "reason": "SigLIP2 implementation discrepancy is unrelated to ZeRO-3 gradient growth." + "reason": "SigLIP2 implementation mismatch and DeepSpeed gradient growth are unrelated." }, { "left": "issue:43756", "right": "issue:45083", "accept": false, - "reason": "Smollm3 RoPE-layer dropping and a helper length function behaving unexpectedly are different failures." + "reason": "RoPE-layer dropout in Smollm3 and feat-extract length behavior in qwen3_omni_moe are different bugs." }, { "left": "issue:43334", "right": "issue:45759", "accept": false, - "reason": "Both are multimodal config issues, but they affect different fields and initialization paths." + "reason": "Missing pad_token_id and text_config unwrapping problems are distinct Qwen config-loading issues." }, { "left": "issue:45200", "right": "issue:45229", "accept": false, - "reason": "Text-only token-type defaults are unrelated to Gemma 4 multi-GPU CUDA OOM." + "reason": "Missing mm_token_type_ids for fine-tuning and multi-GPU OOM are not the same underlying bug." }, { "left": "issue:44488", "right": "issue:44843", "accept": false, - "reason": "Model-loading failure for a specific checkpoint is not the same as an offline-mode tokenizer patch bug." + "reason": "Model load failure for a specific checkpoint and offline model_info lookup bug have different root causes." }, { "left": "issue:43257", "right": "issue:43299", "accept": false, - "reason": "Qwen3 MoE weight conversion under accelerate/deepspeed is distinct from a general Qwen3VL MoE loading regression." + "reason": "Qwen3 MOE weight conversion and Qwen3VL MOE loading are related only broadly by model family, not by the same bug." }, { "left": "issue:43824", "right": "issue:44589", "accept": false, - "reason": "Missing Qwen2.5-VL import and missing Float8 storage support are unrelated import/runtime issues." + "reason": "Import error for Qwen2.5-VL class and missing Float8 storage type are unrelated." }, { - "left": "issue:43278", - "right": "issue:43844", + "left": "issue:43646", + "right": "issue:44466", "accept": false, - "reason": "A dtype change in embeddings is not the same bug as exploding gradients under ZeRO-3." + "reason": "Custom model initialization breakage and device-dependent lm_head serialization are different issues." }, { - "left": "issue:43646", - "right": "issue:44466", + "left": "issue:43278", + "right": "issue:43844", "accept": false, - "reason": "Custom model initialization breakage is different from device-dependent serialization of lm_head.weight." + "reason": "Embedding dtype drift and DeepSpeed gradient growth are unrelated training problems." }, { "left": "issue:45229", "right": "issue:45823", "accept": false, - "reason": "OOM during multi-GPU inference is not the same as a device mismatch in PLE with device_map=\"auto\"." + "reason": "Gemma4 OOM and Gemma4 PLE device mismatch are different inference failures." }, { "left": "issue:44589", "right": "issue:45520", "accept": false, - "reason": "Float8 storage lookup failure and Python 3.13 flash_attn KeyError are separate compatibility issues." + "reason": "Float8 storage lookup failure and flash_attn KeyError on Python 3.13 are unrelated environment bugs." }, { "left": "issue:43688", "right": "issue:45701", "accept": false, - "reason": "Aux-loss normalization and tokenization changes are unrelated." + "reason": "Aux-loss normalization and tokenization changes across versions are not the same defect." }, { "left": "issue:39692", "right": "issue:43295", "accept": false, - "reason": "Documentation example mistakes do not match the processor/tokenizer regression in custom model code." + "reason": "Documentation example errors and processor.tokenizer regression are unrelated." }, { "left": "issue:43572", "right": "issue:44291", "accept": false, - "reason": "Missing pad_token_idx in StableLmConfig is unrelated to init_empty_weights passing an unexpected argument." + "reason": "StableLm pad_token_idx regression and init_empty_weights unexpected argument are different config/init bugs." }, { "left": "issue:33357", "right": "issue:33666", "accept": false, - "reason": "MacOS bus error on CLIP and Qwen2-VL multi-GPU training are different problems." + "reason": "MacOS bus error in a community CLIP model and Qwen2-VL multi-GPU training are unrelated." }, { "left": "issue:43504", "right": "issue:43606", "accept": false, - "reason": "Legacy-field pretrained loading failure is unrelated to a CPU-offload device mismatch." + "reason": "Legacy field load failure in BEiT and Bark CPU-offload device mismatch are different model-loading bugs." }, { "left": "issue:44423", "right": "issue:44734", "accept": false, - "reason": "Continuous-batching multimodal crash and KV-cache continuation indexing bug are distinct serve-path failures." + "reason": "Continuous-batching multimodal crash and KV-cache continuation indexing bug are separate serve-path issues." }, { "left": "issue:43927", "right": "issue:44361", "accept": false, - "reason": "DiaConfig token-id persistence and MLukeTokenizer task attribute errors do not share the same root cause." + "reason": "DiaConfig custom token IDs and MLukeTokenizer task failure are unrelated." } ] }, @@ -6791,7 +6812,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 21, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -6858,8 +6879,8 @@ "issue:44521|issue:45290", "issue:29942|issue:30333", "issue:44464|issue:45584", - "issue:43844|issue:44964", "issue:28218|issue:34567", + "issue:43844|issue:44964", "issue:45084|issue:45520", "issue:44554|issue:45446", "issue:43688|issue:43873", @@ -6877,12 +6898,12 @@ "issue:43295|issue:44610", "issue:44466|issue:45127" ], - "prepared_review_unit_hash": "847b47c86ca43776114df3781461d17c53d64f6629760b84f5df2960691a68ea", + "prepared_review_unit_hash": "f3405d36ae18623239229e8124c5dbb2d893d444363bdc6efb4535c3b9b8259d", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -6890,183 +6911,183 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 27, - "serialized_chars": 35873, - "estimated_input_tokens": 8969, - "estimated_eval_tokens": 18194 + "serialized_chars": 35870, + "estimated_input_tokens": 8968, + "estimated_eval_tokens": 18192 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This is a mixed cluster of unrelated issues across tokenization, generation, multimodal preprocessing, training state, quantization, and CI. None of the soft pairs look like the same underlying defect, so I would not collapse any of them as duplicates.", - "confidence": 0.92, - "canonical_issue_reason": "No single canonical issue fits the cluster: the items are heterogeneous and do not describe one shared bug.", + "summary": "This cluster is not a duplicate set: the soft pairs are only superficially similar by keywords, but they describe different models, different subsystems, and different failure modes.", + "confidence": 0.98, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "If a representative issue is needed, issue:44521 is the most active and clearly scoped, but it only represents one narrow multimodal chat-template bug and does not subsume the rest.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43504", "right": "issue:43653", "accept": false, - "reason": "Legacy field loading for Beit segmentation is unrelated to BigBirdTokenizer special-token registration and empty decode output." + "reason": "Different tokenization/loading bugs on different models: BEiT legacy-field loading vs BigBirdTokenizer special-token registration." }, { "left": "issue:43575", "right": "issue:45405", "accept": false, - "reason": "Tensor-parallel OOM on Qwen2-57B-A14B is unrelated to a PEFT minimum-version bump not yet on PyPI." + "reason": "One is a tensor-parallel OOM on Qwen2 loading; the other is a packaging/version requirement issue for PEFT." }, { "left": "issue:44625", "right": "issue:45759", "accept": false, - "reason": "Qwen3.5 num_labels propagation and Qwen 3.5/3.6 text_config unwrapping are different config bugs with different failure modes." + "reason": "Both mention Qwen multimodal configs, but one is num_labels propagation and the other is AutoModelForCausalLM unwrapping text_config." }, { "left": "issue:43606", "right": "issue:44112", "accept": false, - "reason": "CPU offload device mismatch in bark-small is unrelated to a stale GraniteSpeech CI test." + "reason": "Different problems: a real CPU offload device mismatch in bark-small vs a stale GraniteSpeech CI test." }, { "left": "issue:44792", "right": "issue:45405", "accept": false, - "reason": "Janus image-generation test failures are not the same as a PEFT version availability issue." + "reason": "Janus image-generation test failure is unrelated to a minimum PEFT version bump." }, { "left": "issue:43994", "right": "issue:44493", "accept": false, - "reason": "SigLIP2 nonsensical outputs are unrelated to unexpected position-id key handling." + "reason": "Different symptoms and code paths: SigLIP2 nonsensical outputs vs a position-id key warning across many models." }, { "left": "issue:44521", "right": "issue:45290", "accept": false, - "reason": "All-zero assistant masks for multimodal inputs are a different bug from crashing on assistant tool-call messages with no content." + "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 with no content." }, { "left": "issue:29942", "right": "issue:30333", "accept": false, - "reason": "Flash Attention 2 CI failures and MLflow not reporting failed jobs are unrelated subsystems and symptoms." + "reason": "Flash Attention 2 CI failures are unrelated to MLFlow reporting after training-job failure." }, { "left": "issue:44464", "right": "issue:45584", "accept": false, - "reason": "Chunked generation inconsistency with compiled forward is unrelated to empty-transcription generation after align_special_tokens." + "reason": "Different generation bugs: compiled-forward chunked generation inconsistency vs Whisper empty-transcription failure after token alignment." }, { - "left": "issue:43844", - "right": "issue:44964", + "left": "issue:28218", + "right": "issue:34567", "accept": false, - "reason": "Gradient inflation under ZeRO-3 is not the same as failing to load a multimodal Phi-4 model." + "reason": "Tokenizer spacing after added tokens is unrelated to TrainerState not updating num_input_tokens_seen." }, { - "left": "issue:28218", - "right": "issue:34567", + "left": "issue:43844", + "right": "issue:44964", "accept": false, - "reason": "Tokenizer extra-space insertion and TrainerState num_input_tokens_seen not updating are unrelated bugs." + "reason": "ZeRO-3 gradient growth during training is unrelated to loading Phi-4 multimodal configs in latest transformers." }, { "left": "issue:45084", "right": "issue:45520", "accept": false, - "reason": "Compilation of non-template nodes is unrelated to a flash_attn import KeyError on Python 3.13." + "reason": "Non-template-node compilation error is unrelated to the flash_attn import KeyError on Python 3.13." }, { "left": "issue:44554", "right": "issue:45446", "accept": false, - "reason": "An MPS attention correctness issue is unrelated to an incorrect PyTorch version check for AuxRequest import." + "reason": "Both touch attention-related code, but one is an MPS correctness bug and the other is a PyTorch version gate in flex_attention." }, { "left": "issue:43688", "right": "issue:43873", "accept": false, - "reason": "Incorrect auxiliary-loss normalization and offloading/quantization behavior are different code paths and defects." + "reason": "Aux-loss normalization in MoE models is unrelated to offloading not working with quantization." }, { "left": "issue:44568", "right": "issue:45701", "accept": false, - "reason": "A specific add_special_tokens regression for mdeberta-v3-base is not the same as a broad report that tokenization changes across versions." + "reason": "A specific mdeberta tokenizer special-token regression is not the same as a broad report that transformers version changes tokenization." }, { "left": "issue:15354", "right": "issue:38175", "accept": false, - "reason": "TorchScript generator-expression export failure is unrelated to SigLIP2 producing zero probabilities." + "reason": "TorchScript GeneratorExp export failure for ViT is unrelated to SigLIP2 producing zero probabilities." }, { "left": "issue:43232", "right": "issue:44849", "accept": false, - "reason": "Generation kwargs updates after sync_gpus are unrelated to Qwen3.5 output_hidden_states behavior." + "reason": "Generation kwarg update after sync_gpus is a different bug from Qwen3.5 hidden-states output handling." }, { "left": "issue:43540", "right": "issue:45200", "accept": false, - "reason": "Qwen3OmniMoe video-input processing errors are unrelated to Gemma 4 mm_token_type_ids defaults." + "reason": "Video-input processing in Qwen3OmniMoe is unrelated to Gemma 4 mm_token_type_ids defaulting to zeros." }, { "left": "issue:45200", "right": "issue:45823", "accept": false, - "reason": "Defaulting mm_token_type_ids to zeros is a different issue from Gemma4 PLE device mismatch during forward." + "reason": "Gemma 4 token-type defaults and a device mismatch under device_map=auto are different forward-path bugs." }, { "left": "issue:45072", "right": "issue:45198", "accept": false, - "reason": "bfloat16 inference dtype mismatches are unrelated to Wav2Vec2 save_pretrained/tokenization failures." + "reason": "bfloat16 dtype mismatches in inference are unrelated to Wav2Vec2 save_pretrained/tokenization failures." }, { "left": "issue:44315", "right": "issue:44849", "accept": false, - "reason": "Liger Kernel not applied with model_init is unrelated to Qwen3.5 output_hidden_states bugs." + "reason": "Liger Kernel not applied with model_init has no overlap with Qwen3.5 output_hidden_states behavior." }, { "left": "issue:43278", "right": "issue:43701", "accept": false, - "reason": "Embedding dtype changing between train/eval is unrelated to resume_from_checkpoint key mismatch." + "reason": "BF16-to-FP32 embedding dtype drift during eval is unrelated to resume_from_checkpoint key mismatch." }, { "left": "issue:28218", "right": "issue:33357", "accept": false, - "reason": "Added-token spacing is not the same defect as a MacOS bus error in a CLIP community model." + "reason": "Tokenizer added-space behavior is unrelated to a MacOS bus error in CLIP." }, { "left": "issue:44554", "right": "issue:45356", "accept": false, - "reason": "MPS attention correctness and Kimi tokenizer codec handling are different issues in different components." + "reason": "MPS attention correctness and Kimi tokenizer codec-handling regression are unrelated." + }, + { + "left": "issue:45200", + "right": "issue:45325", + "accept": false, + "reason": "Gemma 4 mm_token_type_ids defaults and Qwen2.5-VL rope-index scaling are different multimodal bugs." }, { "left": "issue:43295", "right": "issue:44610", "accept": false, - "reason": "Processor.tokenizer access regression is unrelated to OmDet-Turbo producing 640px inputs instead of 224px." + "reason": "Processor.tokenizer regression with images is unrelated to OmDet-Turbo producing the wrong image size." }, { "left": "issue:44466", "right": "issue:45127", "accept": false, - "reason": "Device-dependent lm_head serialization is unrelated to LoRA merge collapse with extended vocabulary." - }, - { - "left": "issue:45200", - "right": "issue:45325", - "accept": false, - "reason": "mm_token_type_ids defaults are unrelated to the Qwen2.5-VL rope-index scaling bug." + "reason": "LM head serialization by device and LoRA merge collapse with extended vocabulary are different tied-weights problems." } ] }, @@ -7082,7 +7103,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 22, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -7154,31 +7175,31 @@ "issue:38175|issue:45412", "issue:42915|issue:43824", "issue:38175|issue:43493", - "issue:44514|issue:44521", "issue:44442|issue:45198", + "issue:44514|issue:44521", "issue:43278|issue:43856", "issue:43827|issue:43901", "issue:43653|issue:44112", "issue:43450|issue:43493", "issue:43450|issue:43575", "issue:44792|issue:45563", - "issue:44360|issue:44561", "issue:45127|issue:45245", + "issue:44360|issue:44561", "issue:43819|issue:45083", "issue:44206|issue:45584", - "issue:43819|issue:44112", "issue:43262|issue:43450", - "issue:44610|issue:44857", + "issue:43819|issue:44112", "issue:37428|issue:43425", + "issue:44610|issue:44857", "issue:44857|issue:45593", "issue:43278|issue:43825" ], - "prepared_review_unit_hash": "a48961fed2af815973f8dfb216c2e56e301d431718f9320a5a25e077a2ecec27", + "prepared_review_unit_hash": "06398aee776703e4995ecf27fc5854bbca24666a4b3a298477d2596bf4f2bf8d", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -7186,7 +7207,7 @@ "node_count": 47, "item_count": 47, "soft_pair_count": 33, - "serialized_chars": 36923, + "serialized_chars": 36924, "estimated_input_tokens": 9231, "estimated_eval_tokens": 18718 }, @@ -7195,220 +7216,217 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous; nearly all soft pairs are different bugs or docs/test regressions. The only plausible duplicate-like pair is the shared `pad_token_id` AttributeError regression across Qwen3-VL and Llama4 config loading.", - "confidence": 0.74, - "canonical_issue_reason": "issue:43334 is the clearest representative of the one plausible duplicate theme: config-loading failures caused by missing `pad_token_id` on newer text configs.", + "summary": "This cluster is mostly a set of superficially similar but actually distinct Transformers issues, many around processors, configs, and model-loading regressions. None of the soft-pair candidates look like true duplicates, so all should stay separate.", + "confidence": 0.61, + "canonical_issue_reason": "Issue 43295 is the broadest user-facing regression report in the processor/tokenizer area and is the closest thing here to a cluster representative.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43334 is the best cluster representative because it captures the common `pad_token_id` regression pattern and has enough discussion to anchor triage.", + "best_issue_reason": "Issue 43295 has the clearest regression framing and the widest apparent overlap with other processor-related reports in this set.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44898", "right": "issue:45412", "accept": false, - "reason": "Different problems: Perceiver image sizing vs RT-DETR memory reclamation." + "reason": "Different bugs: image-classification resolution handling vs RT-DETR model deletion memory release." }, { "left": "issue:43493", "right": "issue:43701", "accept": false, - "reason": "SigLIP2 output discrepancy and resume checkpoint key mismatch are unrelated." + "reason": "SigLIP2 numerical discrepancy and resume checkpoint key mismatch are unrelated failures." }, { "left": "issue:43572", "right": "issue:44987", "accept": false, - "reason": "Different models and failures: StableLm pad token attr vs loading `physical-intelligence/fast`." + "reason": "Both involve loading/config regressions, but they affect different models and symptoms." }, { "left": "issue:37428", "right": "issue:43957", "accept": false, - "reason": "ImportError for flash support is unrelated to meta-device model loading." + "reason": "Import error for a flash-attention helper is not the same as meta-device model-loading breakage." }, { "left": "issue:43572", "right": "issue:43957", "accept": false, - "reason": "No shared code path beyond general loading issues." + "reason": "Missing config attribute in StableLm is distinct from meta-device loading failures." }, { "left": "issue:43334", "right": "issue:43525", - "accept": true, - "reason": "Both are the same `pad_token_id` AttributeError regression during model loading; likely one fix." + "accept": false, + "reason": "Same symptom class, but different model families and likely separate config fixes." }, { "left": "issue:43873", "right": "issue:44464", "accept": false, - "reason": "Quantization/offloading behavior is unrelated to compiled chunked generation outputs." + "reason": "Quantized offloading behavior is unrelated to compiled-forward chunked generation output drift." }, { "left": "issue:43295", "right": "issue:43450", "accept": false, - "reason": "Different processor bugs: tokenizer/image regression vs batched video shape handling." + "reason": "Both concern processors, but one is a tokenizer/image regression and the other is batched video-shape handling." }, { "left": "issue:43824", "right": "issue:43975", "accept": false, - "reason": "ImportError for Qwen2.5-VL is unrelated to DeepSeek detokenization." + "reason": "Importing a VL model class and detokenization for DeepSeek Coder are different issues." }, { "left": "issue:43550", "right": "issue:43844", "accept": false, - "reason": "torch.compile SDPA failure and DeepSpeed gradient growth are different failures." + "reason": "Torch.compile + SDPA failure is not the same as ZeRO-3 gradient growth during training." }, { "left": "issue:43295", "right": "issue:43873", "accept": false, - "reason": "Processor regression vs quantization offloading are not the same bug." + "reason": "Processor/tokenizer regression and quantized offloading are different code paths." }, { "left": "issue:37428", "right": "issue:43824", "accept": false, - "reason": "Different import failures in different model families." + "reason": "Different import failures for different model APIs, not the same missing symbol." }, { "left": "issue:38175", "right": "issue:45412", "accept": false, - "reason": "SigLIP2 zero probabilities and RT-DETR memory leak are unrelated." + "reason": "SigLIP2 zero-probabilities bug and RT-DETR memory leak are unrelated." }, { "left": "issue:42915", "right": "issue:43824", "accept": false, - "reason": "Qwen3MoE FP8 failure is unrelated to Qwen2.5-VL import error." + "reason": "FineGrainedFP8 Qwen3MoE failure is not the same as Qwen2.5-VL import breakage." }, { "left": "issue:38175", "right": "issue:43493", "accept": false, - "reason": "Both are SigLIP2-related, but the reported symptoms are not the same concrete bug." + "reason": "Same model family, but one is zero probabilities and the other is HF-vs-JAX implementation mismatch." }, { - "left": "issue:44514", - "right": "issue:44521", + "left": "issue:44442", + "right": "issue:45198", "accept": false, - "reason": "Same API area, but one is a crash and the other is wrong assistant masks; not enough to treat as one bug." + "reason": "Different tokenizer/audio model failures with different APIs and failure modes." }, { - "left": "issue:44442", - "right": "issue:45198", + "left": "issue:44514", + "right": "issue:44521", "accept": false, - "reason": "Different tokenizer/save_pretrained failures in different speech models." + "reason": "Both are Qwen2.5-VL chat-template bugs, but one crashes on batched padding=False input while the other returns empty assistant masks." }, { "left": "issue:43278", "right": "issue:43856", "accept": false, - "reason": "Embedding dtype drift and MoE memory usage are different training issues." + "reason": "Embedding dtype drift during eval is not the same as Qwen3 MoE memory inefficiency." }, { "left": "issue:43827", "right": "issue:43901", "accept": false, - "reason": "Both are docs-related, but they cover different pipeline/API deprecations." + "reason": "Both are docs issues around pipelines, but they target different docs and different deprecated behaviors." }, { "left": "issue:43653", "right": "issue:44112", "accept": false, - "reason": "BigBirdTokenizer special-token registration and GraniteSpeech CI test staleness are unrelated." + "reason": "Tokenizer special-token registration and a stale CI test are not duplicates." }, { "left": "issue:43450", "right": "issue:43493", "accept": false, - "reason": "Video batch-shape bug is unrelated to SigLIP2 implementation discrepancy." + "reason": "Video batch-shape bug and SigLIP2 implementation discrepancy are unrelated." }, { "left": "issue:43450", "right": "issue:43575", "accept": false, - "reason": "Video processor shape handling and TP OOM on Qwen2-57B are unrelated." + "reason": "Processor shape mismatch is not the same as tensor-parallel OOM on model load." }, { "left": "issue:44792", "right": "issue:45563", "accept": false, - "reason": "Janus image-generation test failure and stale paged-generate warning are unrelated." + "reason": "A failing Janus generation test and a stale warning in paged generate are different issues." }, { - "left": "issue:44360", - "right": "issue:44561", + "left": "issue:45127", + "right": "issue:45245", "accept": false, - "reason": "DSA indexer activation issue and removed helper breaking trust_remote_code are unrelated." + "reason": "LoRA merge collapse and category-cardinality limit are unrelated errors." }, { - "left": "issue:45127", - "right": "issue:45245", + "left": "issue:44360", + "right": "issue:44561", "accept": false, - "reason": "LoRA merge collapse and category cardinality overflow are unrelated." + "reason": "DSA indexer ReLU discussion is unrelated to removal of is_torch_fx_available." }, { "left": "issue:43819", "right": "issue:45083", "accept": false, - "reason": "DAC latent mismatch and qwen3_omni_moe length helper behavior are different code paths." + "reason": "DAC latent/forward mismatch and qwen3_omni_moe length helper behavior are different bugs." }, { "left": "issue:44206", "right": "issue:45584", "accept": false, - "reason": "Feature-extractor arg regression and Whisper empty transcription bug are unrelated." - }, - { - "left": "issue:43819", - "right": "issue:44112", - "accept": false, - "reason": "DAC latent mismatch is unrelated to GraniteSpeech CI device override staleness." + "reason": "Unsupported center arg in a feature extractor is unrelated to Whisper empty-transcription generation failure." }, { "left": "issue:43262", "right": "issue:43450", "accept": false, - "reason": "Audio chat-template sampling-rate default bug is unrelated to video processor batching." + "reason": "Audio chat-template sampling-rate defaulting and video batch-shape bugs are different subsystems." }, { - "left": "issue:44610", - "right": "issue:44857", + "left": "issue:43819", + "right": "issue:44112", "accept": false, - "reason": "Processor output resolution mismatch and AMP loss crash are different problems." + "reason": "DAC latent mismatch and a GraniteSpeech CI test failure are not the same issue." }, { "left": "issue:37428", "right": "issue:43425", "accept": false, - "reason": "Flash-support import error is unrelated to Torch 2.10 compatibility." + "reason": "A missing import symbol and Torch 2.10 incompatibility are different root causes." + }, + { + "left": "issue:44610", + "right": "issue:44857", + "accept": false, + "reason": "OmDet image-size preprocessing and LwDetr AMP crash are separate model/training failures." }, { "left": "issue:44857", "right": "issue:45593", "accept": false, - "reason": "AMP/CUDA loss crash and missing auxiliary losses are different training bugs." + "reason": "AMP CUDA crash in LwDetrLoss is unrelated to D-FINE auxiliary-loss behavior." }, { "left": "issue:43278", "right": "issue:43825", "accept": false, - "reason": "Embedding dtype regression and pipeline translation-message docs mismatch are unrelated." + "reason": "Embedding dtype changes and pipeline translation error messaging are unrelated." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The writeup is grounded in the packet and stays conservative on the soft-edge pairs. The only clearly supported duplicate theme is the shared `pad_token_id` AttributeError during config/model loading (`issue:43334` / `issue:43525`), and the remaining pair rejections are phrased narrowly enough for the evidence available." - }, - "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 }, @@ -7417,7 +7435,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 23, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -7426,6 +7444,7 @@ "cluster_id": "cluster-15354-392", "nodes": [ "issue:28218", + "issue:29127", "issue:29942", "issue:32090", "issue:35141", @@ -7464,13 +7483,11 @@ "issue:45290", "issue:45310", "issue:45381", - "issue:45459", "issue:45478", "issue:45491", "issue:45520", "issue:45588", "issue:45593", - "issue:45712", "issue:45823", "issue:45859" ], @@ -7483,8 +7500,8 @@ "issue:45200|issue:45588", "issue:43611|issue:43931", "issue:39692|issue:43526", - "issue:44462|issue:44561", "issue:44206|issue:45823", + "issue:44462|issue:44561", "issue:44561|issue:44779", "issue:43388|issue:43526", "issue:43335|issue:43653", @@ -7509,252 +7526,252 @@ "issue:43606|issue:44857", "issue:44568|issue:45491", "issue:44857|issue:45072", - "issue:45459|issue:45712" + "issue:29127|issue:32090" ], - "prepared_review_unit_hash": "ab2b5d43213756b27829843f65cf00cbcf03e43d2aed5b0bcda4835a2d6020fb", + "prepared_review_unit_hash": "90b34757744392ca9dd30e6f65be3e18b362b4d0d36bce85b36d42bd9cb760dd", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, "budget": { - "node_count": 48, - "item_count": 48, + "node_count": 47, + "item_count": 47, "soft_pair_count": 35, - "serialized_chars": 38456, - "estimated_input_tokens": 9614, - "estimated_eval_tokens": 19484 + "serialized_chars": 37832, + "estimated_input_tokens": 9458, + "estimated_eval_tokens": 19172 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly false-positive similarity: the only clear duplicate is the repeated Qwen3.5 MoE from_pretrained error. The rest are related only at a broad subsystem level (tokenizers, flash-attn, loading, vision, CI) but describe different bugs.", - "confidence": 0.93, - "canonical_issue_reason": "issue:45310 is the best canonical issue because it is the earlier report of the exact same Qwen3.5 MoE from_pretrained failure later repeated as issue:45478.", + "summary": "One clear duplicate pair stands out: the two \"Qwen3.5 Moe from_pretrained error\" issues are the same underlying loading failure. The rest of the soft pairs are only loosely related by subsystem/version and should stay separate.", + "confidence": 0.95, + "canonical_issue_reason": "issue:45310 is the better canonical for the Qwen3.5 Moe from_pretrained failure: it is the earlier report with more context, and issue:45478 is the same bug with essentially the same title.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45310 is the strongest representative because it has an exact duplicate and a concrete, narrowly scoped failure mode with clear reproducibility.", + "best_issue_reason": "issue:45310 is the strongest issue candidate overall because it is the clearest duplicate target among the provided items and has the richest context for that specific bug.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45290", "right": "issue:45381", "accept": false, - "reason": "Different bugs: chat template/tool-call handling vs Qwen2.5-VL video position IDs." + "reason": "Different bugs: chat template/tool-call handling versus Qwen2.5-VL video position ids." }, { "left": "issue:43606", "right": "issue:45083", "accept": false, - "reason": "Unrelated failures in different models and code paths." + "reason": "Different failure modes in different code paths; one is CPU offload device mismatch, the other is a feat-length helper behavior issue." }, { "left": "issue:43335", "right": "issue:43550", "accept": false, - "reason": "Sparse-layer config bug is unrelated to Bamba torch.compile/SDPA failure." + "reason": "Unrelated model/config bug versus torch.compile+SDPA failure." }, { "left": "issue:44448", "right": "issue:44743", "accept": false, - "reason": "Different model families and different regressions (output drift vs recurrent state reset)." + "reason": "Both mention generation/state behavior changes, but they describe different model paths and different concrete defects." }, { "left": "issue:37428", "right": "issue:44351", "accept": false, - "reason": "Both are import errors, but for different missing symbols and different modules." + "reason": "Both are import errors, but for different missing symbols and likely different broken dependencies/paths." }, { "left": "issue:45200", "right": "issue:45588", "accept": false, - "reason": "Gemma4 token-type defaults and flash_attention s_aux handling are separate issues." + "reason": "Different issues: Gemma4 text-only token-type defaults versus flash_attention handling of sink-less models with s_aux=None." }, { "left": "issue:43611", "right": "issue:43931", "accept": false, - "reason": "Both loading errors, but one is a base_model_prefix regression and the other is a shape mismatch." + "reason": "Model-loading problems, but not the same one: base_model_prefix handling versus Qwen3-VL weight-shape mismatch." }, { "left": "issue:39692", "right": "issue:43526", "accept": false, - "reason": "Different image-processing problems in different models; not the same underlying bug." + "reason": "Docs/example errors versus a BeitImageProcessorFast label-reduction bug." }, { - "left": "issue:44462", - "right": "issue:44561", + "left": "issue:44206", + "right": "issue:45823", "accept": false, - "reason": "Tokenizer-file selection and removal of is_torch_fx_available are unrelated." + "reason": "Different models and different runtime failures: unsupported center arg versus Gemma4 PLE device mismatch." }, { - "left": "issue:44206", - "right": "issue:45823", + "left": "issue:44462", + "right": "issue:44561", "accept": false, - "reason": "Feature extractor arg validation vs Gemma4 device-map mismatch are not the same code-path." + "reason": "Tokenizer config loading issue versus removal of is_torch_fx_available breaking trust_remote_code models." }, { "left": "issue:44561", "right": "issue:44779", "accept": false, - "reason": "A missing utility symbol and a Deepseek tokenizer regression are different failures." + "reason": "Both are v5 regressions affecting models, but one is an API removal breakage and the other is tokenizer output correctness for Deepseek." }, { "left": "issue:43388", "right": "issue:43526", "accept": false, - "reason": "Both concern labels, but one is metric gathering and the other is Beit label reduction." + "reason": "Both involve labels, but one drops labels in metrics gathering while the other returns only one label in BeitImageProcessorFast." }, { "left": "issue:43335", "right": "issue:43653", "accept": false, - "reason": "SwitchTransformers sparse-layer config and BigBird tokenizer special-token registration are unrelated." + "reason": "Different tokenizer/config issues; sparse layer construction is unrelated to BigBirdTokenizer special-token registration." }, { "left": "issue:43819", "right": "issue:44493", "accept": false, - "reason": "DAC latent conversion mismatch and unexpected position-id keys are different bugs." + "reason": "Different bugs: DAC latent conversion mismatch versus unexpected key handling for position ids." }, { "left": "issue:45310", "right": "issue:45478", "accept": true, - "reason": "Exact same Qwen3.5 MoE from_pretrained error; clear duplicate." + "reason": "Same title and same reported from_pretrained error for Qwen3.5 Moe; these are clearly duplicate reports of the same loading bug." }, { "left": "issue:44855", "right": "issue:45083", "accept": false, - "reason": "Python 3.13 JIT parsing error is unrelated to qwen3_omni_moe feature-length behavior." + "reason": "Python 3.13 import/torch.jit parsing issue versus a qwen3_omni_moe helper-function behavior bug." }, { "left": "issue:45588", "right": "issue:45859", "accept": false, - "reason": "Both touch flash/offload paths, but the concrete failure modes differ." + "reason": "Both touch Qwen3_5Moe/attention/offload areas, but the concrete failures are different and not safely mergeable into one fix." }, { "left": "issue:43550", "right": "issue:44112", "accept": false, - "reason": "Bamba SDPA compile failure and GraniteSpeech CI device-override stale test are unrelated." + "reason": "Different CI/runtime problems in different models: SDPA compile failure versus stale device override test." }, { "left": "issue:29942", "right": "issue:32090", "accept": false, - "reason": "Flash Attention 2 test failures and Trainer _gpu_broadcast_one TypeError are different issues." + "reason": "Flash Attention 2 test failures and NoneType broadcast errors are unrelated bugs." }, { "left": "issue:43335", "right": "issue:43504", "accept": false, - "reason": "Sparse-layer creation bug is unrelated to Beit pretrained preset loading." + "reason": "Sparse-layer creation bug versus BEiT semantic-segmentation legacy-field loading failure." }, { "left": "issue:43335", - "right": "issue:45083", + "right": "issue:45072", "accept": false, - "reason": "Different model families and different helper/config bugs." + "reason": "Different model/runtime issues: SwitchTransformers sparse-layer bug versus dtype mismatch in inference." }, { "left": "issue:39692", "right": "issue:44493", "accept": false, - "reason": "SigLIP2 docs/model mismatch is unrelated to widespread position-id key warnings." + "reason": "Docs/example errors versus a broad position-id warning affecting many models." }, { "left": "issue:44292", "right": "issue:45520", "accept": false, - "reason": "Qwen-3-8B-NVFP4 runtime failure and flash_attn import KeyError are different problems." + "reason": "Different models and different errors: Qwen-3-8B-NVFP4 run failure versus Python 3.13 flash_attn import KeyError." }, { "left": "issue:38175", "right": "issue:44493", "accept": false, - "reason": "Unexpected zero probabilities in SigLIP2 is not the same as position-id key warnings." + "reason": "Unexpected zero probabilities in SigLIP2 is not the same as the position-id key warning." }, { "left": "issue:44448", "right": "issue:44779", "accept": false, - "reason": "Both are regressions across versions, but in different models and failure modes." + "reason": "Pegasus output regression and Deepseek tokenizer regression are distinct model-specific bugs." }, { "left": "issue:28218", "right": "issue:35141", "accept": false, - "reason": "Tokenizer spacing bug and embedding reinitialization on resize are unrelated." + "reason": "Tokenizer spacing after added token is unrelated to embedding reinitialization after resize." }, { "left": "issue:43335", "right": "issue:45072", "accept": false, - "reason": "Sparse-layer config bug and bfloat16 dtype mismatch are different code paths." + "reason": "Not the same concrete bug; both are inference/config issues but in different models and code paths." }, { "left": "issue:43335", "right": "issue:45593", "accept": false, - "reason": "SwitchTransformers config issue is unrelated to D-FINE auxiliary-loss behavior." + "reason": "Sparse-layer config bug versus D-FINE auxiliary-loss behavior are unrelated." }, { "left": "issue:43720", "right": "issue:44112", "accept": false, - "reason": "Packed-weight loading bug and GraniteSpeech CI stale test are unrelated." + "reason": "Packed-weight unpacking during accelerate loading is unrelated to GraniteSpeech device override test flakiness." }, { "left": "issue:44977", "right": "issue:45229", "accept": false, - "reason": "Qwen3.5 flash-attention generation bug and Gemma4 CUDA OOM are different failures." + "reason": "Different Qwen/Gemma runtime failures: flash-attention generation issue versus CUDA OOM in multi-GPU inference." }, { "left": "issue:44448", "right": "issue:44977", "accept": false, - "reason": "Different models and different output-generation regressions." + "reason": "Both affect generation outputs, but the model families and concrete defects differ." }, { "left": "issue:43606", "right": "issue:44857", "accept": false, - "reason": "CPU offload device mismatch and float16 AMP crash are separate issues." + "reason": "Different device/runtime crashes in unrelated models." }, { "left": "issue:44568", "right": "issue:45491", "accept": false, - "reason": "Tokenizer special-token behavior and Gemma3 NaN embeddings are unrelated." + "reason": "Tokenizer special-token behavior is unrelated to Gemma3 sliding-window NaN embeddings." }, { "left": "issue:44857", "right": "issue:45072", "accept": false, - "reason": "Float16 AMP crash and bfloat16 dtype mismatch are not the same bug." + "reason": "AMP crash in LwDetrImageLoss is unrelated to dtype mismatch in SwitchTransformers/TimmWrapperModel." }, { - "left": "issue:45459", - "right": "issue:45712", + "left": "issue:29127", + "right": "issue:32090", "accept": false, - "reason": "Tokenizer error masking and leftover dummy classes failing checks are unrelated." + "reason": "LayoutLMv3 error-message clarity issue is unrelated to the Trainer _gpu_broadcast_one NoneType failure." } ] }, "evaluator_result": { "accept": true, - "feedback": "The judgment is conservative and grounded in the packet. The only clearly supported duplicate is issue:45310/issue:45478, which share the same title and Qwen3.5 MoE from_pretrained failure. The remaining soft-edge rejections stay at the safe side of the evidence and do not overclaim duplication or mergeability." + "feedback": "The canonical pair 45310/45478 is well supported by the packet: identical titles and very similar issue context. The soft-edge rejections are appropriately conservative overall, with reasons grounded in differing titles and bug descriptions." }, "evaluator_used": true, "retried": false, @@ -7767,7 +7784,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 24, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -7776,7 +7793,6 @@ "cluster_id": "cluster-15354-392", "nodes": [ "issue:25251", - "issue:29127", "issue:29942", "issue:32090", "issue:34689", @@ -7821,11 +7837,12 @@ "issue:45563", "issue:45588", "issue:45698", + "issue:45712", "issue:45803", "issue:45823" ], "soft_pairs": [ - "issue:29127|issue:32090", + "issue:45459|issue:45712", "issue:43927|issue:45698", "issue:34689|issue:35141", "issue:45198|issue:45803", @@ -7843,9 +7860,9 @@ "issue:45372|issue:45459", "issue:44857|issue:45588", "issue:44448|issue:44466", + "issue:43278|issue:43381", "issue:43065|issue:45412", "issue:45588|issue:45823", - "issue:43278|issue:43381", "issue:25251|issue:32090", "issue:43653|issue:44743", "issue:44451|issue:45520", @@ -7856,12 +7873,12 @@ "issue:44361|issue:45198", "issue:44871|issue:44977" ], - "prepared_review_unit_hash": "0c711cf7c5b119f011fb4034dd9be5c0e0b579d01792d37d5929e3dc21fc3be9", + "prepared_review_unit_hash": "0fdb572cbfc0458894c57f9c4b8ac03faa16b1b3f606871dc013875a00ed6273", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -7869,201 +7886,201 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 36619, - "estimated_input_tokens": 9155, - "estimated_eval_tokens": 18566 + "serialized_chars": 36647, + "estimated_input_tokens": 9162, + "estimated_eval_tokens": 18580 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is not a duplicate cluster; the soft links are mostly superficial lexical matches across unrelated bugs. I found no PRs and no convincing canonical duplicate issue.", - "confidence": 0.86, - "canonical_issue_reason": "No single issue is a reliable canonical representative here: the linked items span unrelated code paths (tokenizers, generation, flash-attention, quantization, loading, eval/training behavior) and do not describe the same underlying bug.", + "summary": "This cluster is mostly heterogeneous: the paired issues share loose keywords like save/load, tokenizer, or import errors, but they do not look like the same underlying bug. No PRs are present.", + "confidence": 0.39, + "canonical_issue_reason": "issue:45698 is the best canonical issue here because it is open, broadly user-facing, and the most general save/load regression in the set. The other issues are either narrower manifestations or unrelated model/tokenizer failures.", "canonical_pr_reason": null, - "best_issue_reason": "If one issue must be selected as the closest thing to a representative, issue 45588 is the most concrete, reproducible core crash report in a central integration path; however, it is not a duplicate of the others.", + "best_issue_reason": "issue:45698 is the best overall issue to keep as the cluster representative for the same reasons: open, active, and broadly phrased enough to serve as the nearest umbrella report. That said, the cluster does not appear to contain true duplicates.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:29127", - "right": "issue:32090", + "left": "issue:45459", + "right": "issue:45712", "accept": false, - "reason": "Different subsystems and failures: LayoutLMv3 box validation/error messaging vs Trainer GPU broadcast rejecting NoneType." + "reason": "Tokenizer error handling vs leftover dummy classes; same theme of bad exception handling, but not the same bug." }, { "left": "issue:43927", "right": "issue:45698", "accept": false, - "reason": "Both involve save/load behavior, but one is about custom token IDs being lost and the other about loading the wrong custom module; different root causes." + "reason": "Both involve save/load behavior, but one is custom token IDs and generation, the other is wrong custom module resolution; different failure modes." }, { "left": "issue:34689", "right": "issue:35141", "accept": false, - "reason": "Model-loading breakage for a specific vision model is unrelated to embedding reinitialization after resizing token embeddings." + "reason": "Model loading breakage for Llama Vision vs embedding reinit after resizing; unrelated code paths." }, { "left": "issue:45198", "right": "issue:45803", "accept": false, - "reason": "Both touch tokenization/saving, but the reported failures are on different models and different code paths." + "reason": "save_pretrained/tokenization failure vs bare except in FuyuBatchFeature; different symptoms and fixes." }, { "left": "issue:44977", "right": "issue:45563", "accept": false, - "reason": "Flash-attention generation failure and a stale warning about num_return_sequences are unrelated bugs." + "reason": "Flash-attention generation issue vs stale warning in paged generate; not the same defect." }, { "left": "issue:40444", "right": "issue:43526", "accept": false, - "reason": "IterableDataset multi-image prompt failure for Qwen2.5-VL is unrelated to BeitImageProcessorFast reduce_labels behavior." + "reason": "IterableDataset multi-image finetuning vs BEiT fast processor label reduction; unrelated subsystems." }, { "left": "issue:43701", "right": "issue:45083", "accept": false, - "reason": "Checkpoint resume key mismatch is not the same bug as qwen3_omni_moe feature-length helper behavior." + "reason": "Checkpoint resume key mismatch vs feature-length helper behavior; no concrete overlap." }, { "left": "issue:43550", "right": "issue:45083", "accept": false, - "reason": "torch.compile with SDPA on Bamba-9B-v2 is a different concrete failure than qwen3_omni_moe feature-length calculation." + "reason": "torch.compile/SDPA bug vs feature extraction length helper; different code paths." }, { "left": "issue:45372", "right": "issue:45588", "accept": false, - "reason": "Gemma 4 processor import failure due to missing ReasoningEffort is unrelated to flash_attention.py crashing on s_aux=None." + "reason": "Gemma processor import failure vs flash-attention crash on s_aux=None; unrelated issues." }, { "left": "issue:43412", "right": "issue:45588", "accept": false, - "reason": "Executorch export issues in gemma3n are a different path than sink-less flash-attention integration crashing on s_aux=None." + "reason": "ExecuTorch export guard/support problem vs flash-attention sink-less model crash; different layers." }, { "left": "issue:45245", "right": "issue:45563", "accept": false, - "reason": "Category cardinality overflow and a stale generation warning are unrelated." + "reason": "Category-count runtime limit vs paged generate warning; not duplicates." }, { "left": "issue:29942", "right": "issue:35141", "accept": false, - "reason": "Flash Attention 2 test failures do not match an embedding reinitialization bug in post_init." + "reason": "Flash Attention 2 test failures vs embedding reinitialization after resize; unrelated." }, { "left": "issue:43873", "right": "issue:44493", "accept": false, - "reason": "Quantization offloading problems are unrelated to unexpected position-id key warnings." + "reason": "Quantization/offloading behavior vs unexpected position-id keys; no shared concrete bug." }, { "left": "issue:36010", "right": "issue:37428", "accept": false, - "reason": "Two distinct ImportError regressions involving different symbols and modules." + "reason": "GenerationMixin import removal vs flash_attention_utils import removal; both imports fail, but they are different symbols and fixes." }, { "left": "issue:43066", "right": "issue:44462", "accept": false, - "reason": "Wrong tokenizer decoder type in v5 is not the same as AutoTokenizer ignoring tokenizer.json from the repo." + "reason": "Tokenizer decoder type mismatch in v5 vs AutoTokenizer ignoring tokenizer.json; both loading-related, but different defects." }, { "left": "issue:45372", "right": "issue:45459", "accept": false, - "reason": "One is a missing import dependency for Gemma 4 processing; the other is exception masking when protobuf is absent." + "reason": "Gemma 4 processor import dependency vs tokenizer exception masking; different failures." }, { "left": "issue:44857", "right": "issue:45588", "accept": false, - "reason": "CUDA float16 loss crash in LwDetrImageLoss is unrelated to flash_attention.py's s_aux=None AttributeError." + "reason": "LwDetr loss under AMP/CUDA vs flash-attention integration crash; unrelated model paths." }, { "left": "issue:44448", "right": "issue:44466", "accept": false, - "reason": "Different issues around model output/serialization across versions; they do not share the same underlying bug." + "reason": "Pegasus output differences across versions vs lm_head serialization inconsistency; both model behavior regressions, but not the same bug." + }, + { + "left": "issue:43278", + "right": "issue:43381", + "accept": false, + "reason": "Embedding dtype drift in eval vs gradient checkpointing in eval mode; different evaluation-time issues." }, { "left": "issue:43065", "right": "issue:45412", "accept": false, - "reason": "Dummy Conv2d in Sam3PixelDecoder and RT-DETR memory release are separate model lifecycle issues." + "reason": "Dummy Conv2d in Sam3PixelDecoder vs RT-DETR memory release; unrelated." }, { "left": "issue:45588", "right": "issue:45823", "accept": false, - "reason": "Both involve Gemma 4/flash-attention adjacent code, but one is a sink-less flash-attention crash and the other is a device mismatch in PLE forward; not the same bug." - }, - { - "left": "issue:43278", - "right": "issue:43381", - "accept": false, - "reason": "Training/eval dtype drift is not the same as gradient checkpointing being disallowed in eval mode." + "reason": "Flash-attention aux handling vs Gemma4 PLE device mismatch; both runtime issues, but distinct code paths." }, { "left": "issue:25251", "right": "issue:32090", "accept": false, - "reason": "Pipeline top_k nesting behavior and Trainer NoneType GPU broadcast are unrelated." + "reason": "top_k pipeline output nesting vs Trainer _gpu_broadcast_one NoneType error; unrelated behavior." }, { "left": "issue:43653", "right": "issue:44743", "accept": false, - "reason": "Tokenizer special-token registration causing empty decode is unrelated to recurrent states resetting with cache in qwen3_omni_moe." + "reason": "BigBirdTokenizer special-token decode bug vs Qwen recurrent-state reset; different models and bugs." }, { "left": "issue:44451", "right": "issue:45520", "accept": false, - "reason": "ScandiBERT loading failure and Python 3.13 flash_attn import key error are separate environment/model-loading problems." + "reason": "Model loading failure for a specific repo vs KeyError for flash_attn on Python 3.13; different root causes." }, { "left": "issue:43976", "right": "issue:45440", "accept": false, - "reason": "Python version compatibility and DeepseekV3MoE divergence are different issues." + "reason": "Python version compatibility issue vs DeepseekV3MoE divergence; unrelated." }, { "left": "issue:44186", "right": "issue:45198", "accept": false, - "reason": "LayoutLMv2 NER/batched padding crashes are not the same as Wav2Vec2 save_pretrained/tokenization failures." + "reason": "LayoutLMv2Tokenizer NER/padding crash vs Wav2Vec2 save_pretrained/tokenization failure; different tokenizers and failures." }, { - "left": "issue:44361", - "right": "issue:45198", + "left": "issue:42915", + "right": "issue:42994", "accept": false, - "reason": "MLukeTokenizer AttributeError on tasks is unrelated to Wav2Vec2 save/tokenization failure." + "reason": "Qwen3Moe FP8 config failure vs quantized model saving failure; both quantization-related, but not the same bug." }, { - "left": "issue:44871", - "right": "issue:44977", + "left": "issue:43994", + "right": "issue:45412", "accept": false, - "reason": "EOS token configuration inconsistency is unrelated to flash-attention generation behavior in Qwen3.5." + "reason": "SigLIP2 AutoModel/pipeline nonsense output vs RT-DETR memory leak; unrelated." }, { - "left": "issue:45083", - "right": "issue:45588", + "left": "issue:44361", + "right": "issue:45198", "accept": false, - "reason": "Feature-extraction length helper behavior in qwen3_omni_moe is unrelated to a flash_attention integration crash." + "reason": "MLukeTokenizer task AttributeError vs Wav2Vec2 save/tokenization failure; different tokenizer problems." }, { - "left": "issue:45588", - "right": "issue:45823", + "left": "issue:44871", + "right": "issue:44977", "accept": false, - "reason": "Different Gemma 4 failures: one is an AttributeError in flash-attention integration, the other is a device placement mismatch during forward." + "reason": "Gemma eos_token_id config mismatch vs Qwen3.5 flash-attention generation issue; different model configs and symptoms." } ] }, @@ -8079,7 +8096,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 25, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -8158,20 +8175,20 @@ "issue:43653|issue:44442", "issue:45440|issue:45593", "issue:43278|issue:43329", - "issue:41720|issue:45229", "issue:29942|issue:36010", + "issue:41720|issue:45229", "issue:32090|issue:33357", "issue:43334|issue:43531", "issue:43526|issue:44186", "issue:44977|issue:45245", "issue:43824|issue:44279" ], - "prepared_review_unit_hash": "7aa0c03a362c4c4c2027fc81afdbb50f3d44f6a435f8f890e4ce1dc92e4a2f01", + "prepared_review_unit_hash": "952b7ea01fa2df0387d72013d797cd40fa84356061ad2dfd4c96ce14daf32b45", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -8179,189 +8196,189 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 28, - "serialized_chars": 36197, - "estimated_input_tokens": 9050, - "estimated_eval_tokens": 18356 + "serialized_chars": 36201, + "estimated_input_tokens": 9051, + "estimated_eval_tokens": 18358 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is heterogeneous rather than a duplicate cluster. The soft pairs span distinct bugs across tokenizers, vision models, training, serving, and multimodal processors, so none should be merged as the same underlying issue.", - "confidence": 0.84, - "canonical_issue_reason": "Issue 43873 is the closest thing to a cluster anchor: it is open, broadly framed, and has the strongest discussion/inbound-reference footprint. It is still not a duplicate of the others, just the least-specific representative.", + "summary": "This cluster is a loose grab bag of unrelated Transformers issues rather than a duplicate set. None of the soft pairs look like the same underlying bug/change, and there are no PRs to consider.", + "confidence": 0.98, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Issue 43873 is the best representative of the set because it is broad and active, with multiple inbound references, but the cluster does not contain a true duplicate family.", + "best_issue_reason": "issue:43873 is the broadest and most active report in the set (quantization/offloading runtime bug with inbound references), so it is the best representative issue if one must be chosen.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43421", "right": "issue:45491", "accept": false, - "reason": "Runtime special-token post-processing bug vs Gemma3 NaN embeddings/sliding-window attention; different code paths and symptoms." + "reason": "TokenizersBackend special-token updates vs Gemma3 NaN embeddings; different components and failure modes." }, { "left": "issue:44206", "right": "issue:44479", "accept": false, - "reason": "Unsupported `center` arg in a feature extractor vs Qwen VL video-input regression; unrelated subsystems." + "reason": "Feature extractor arg validation crash vs Qwen video-input regression; not the same code path." }, { "left": "issue:44265", "right": "issue:45198", "accept": false, - "reason": "`torch.export` / `torch_compilable_check` failure vs Wav2Vec2 save/tokenization failure; not the same bug." + "reason": "torch.export/torch_compilable_check failure vs Wav2Vec2 save/tokenization failure; unrelated APIs." }, { "left": "issue:29942", "right": "issue:30064", "accept": false, - "reason": "Flash Attention 2 test failures vs void segmentation-map processing; different failure modes." + "reason": "Flash Attention 2 test failures vs void segmentation map processing; different subsystems." }, { "left": "issue:44734", "right": "issue:45406", "accept": false, - "reason": "KV-cache continuation tensor indexing bug in serve vs Gemma4 processor missing `_tokenizer`; unrelated." + "reason": "Both are serve-related, but one is KV-cache indexing and the other is a Gemma4Processor init bug." }, { "left": "issue:43065", "right": "issue:43994", "accept": false, - "reason": "Dummy Conv2d in Sam3PixelDecoder vs SigLIP2 AutoModel/pipeline nonsense outputs; different models and defects." + "reason": "Sam3PixelDecoder dummy layer vs SigLIP2 AutoModel/pipeline outputs; unrelated model bugs." }, { "left": "issue:33357", "right": "issue:39692", "accept": false, - "reason": "MacOS bus error on community CLIP model vs SigLIP2 docs/model-processor mismatch and quantization example failure; not one change." + "reason": "MacOS bus error in community CLIP model vs SigLIP2 docs/model mismatch; different underlying issues." }, { "left": "issue:29127", "right": "issue:34567", "accept": false, - "reason": "LayoutLMv3 error-message clarity issue vs TrainerState token counter not updating; unrelated features." + "reason": "LayoutLMv3 box/error messaging vs TrainerState token counter update; unrelated behavior." }, { "left": "issue:44610", "right": "issue:45412", "accept": false, - "reason": "OmDet-Turbo image-size mismatch vs RT-DETR memory release issue; distinct bugs." + "reason": "Processor/model input-size mismatch vs RT-DETR memory release; different bug classes." }, { "left": "issue:45103", "right": "issue:45372", "accept": false, - "reason": "auto_docstring annotation handling vs Gemma4 processor import dependency failure; different layers entirely." + "reason": "auto_docstring future-annotations crash vs Gemma4 dependency import failure; unrelated." }, { "left": "issue:43756", "right": "issue:45440", "accept": false, - "reason": "Smollm3 RoPE-layer mismatch vs DeepSeekV3MoE divergence from remote impl; not the same code-path." + "reason": "Different model implementation divergences (Smollm3 RoPE layers vs DeepseekV3MoE parity)." }, { "left": "issue:43873", "right": "issue:45229", "accept": false, - "reason": "General quantization/offloading behavior vs Gemma4 multi-GPU CUDA OOM; too broad and not the same defect." + "reason": "Offloading/quantization behavior vs multi-GPU OOM; same broad area, but not the same concrete bug." }, { "left": "issue:43723", "right": "issue:44554", "accept": false, - "reason": "AutoTokenizer loading regression vs MPS attention correctness issue; unrelated." + "reason": "Tokenizer loading regression vs MPS attention correctness issue; unrelated." }, { "left": "issue:45372", "right": "issue:45406", "accept": false, - "reason": "Processor-loading import error vs serve crash from missing `_tokenizer`; different surfaces and fixes." + "reason": "Gemma4 processor dependency import failure vs serve-side missing _tokenizer attribute; different root causes." }, { "left": "issue:43278", "right": "issue:43575", "accept": false, - "reason": "Training/eval dtype drift vs tensor-parallel OOM on Qwen2-57B; not the same problem." + "reason": "Embedding dtype drift vs tensor-parallel OOM; not the same defect." }, { "left": "issue:43761", "right": "issue:45859", "accept": false, - "reason": "CLIPVisionModel hidden_states regression vs CPU-offload incompatibility in Qwen3_5Moe rotary embedding; unrelated." + "reason": "CLIPVisionModel hidden_states regression vs Qwen3_5MoE CPU-offload incompatibility; different models and paths." }, { "left": "issue:43526", "right": "issue:45834", "accept": false, - "reason": "BeitImageProcessorFast `reduce_labels` bug vs Kosmos2.5 long-OCR index error; different processors and failure modes." + "reason": "BeitImageProcessorFast label reduction bug vs Kosmos2.5 long-OCR index error; unrelated." }, { "left": "issue:43381", "right": "issue:43701", "accept": false, - "reason": "Gradient checkpointing in eval mode vs resume-from-checkpoint key mismatch; not the same bug." + "reason": "Gradient checkpointing in eval vs resume_from_checkpoint key mismatch; different training-flow issues." }, { "left": "issue:43653", "right": "issue:44442", "accept": false, - "reason": "BigBirdTokenizer special-token registration/decoding bug vs AutoTokenizer loading FastSpeech2ConformerTokenizer; distinct tokenizer issues." + "reason": "BigBirdTokenizer special-token registration vs FastSpeech2Conformer tokenizer loading; both tokenizer-related but distinct bugs." }, { "left": "issue:45440", "right": "issue:45593", "accept": false, - "reason": "DeepSeekV3MoE implementation divergence vs D-FINE auxiliary-loss behavior; different model logic." + "reason": "DeepseekV3MoE parity gap vs D-FINE auxiliary-loss omission; different models and behaviors." }, { "left": "issue:43278", "right": "issue:43329", "accept": false, - "reason": "Embedding dtype mismatch vs undefined variables in multimodal-token counting video branch; unrelated." + "reason": "Embedding dtype mismatch vs multimodal token counting video-branch NameError; unrelated." }, { - "left": "issue:41720", - "right": "issue:45229", + "left": "issue:29942", + "right": "issue:36010", "accept": false, - "reason": "Qwen3 auto device-mapping assert vs Gemma4 multi-GPU OOM; different models and root causes." + "reason": "Flash Attention test failures vs GenerationMixin import error; no overlap in root cause." }, { - "left": "issue:29942", - "right": "issue:36010", + "left": "issue:41720", + "right": "issue:45229", "accept": false, - "reason": "Flash Attention 2 tests vs `GenerationMixin` import error; no shared code path." + "reason": "Qwen3 auto-device-map assert on A800 vs Gemma4 multi-GPU OOM; both CUDA, but not the same failure." }, { "left": "issue:32090", "right": "issue:33357", "accept": false, - "reason": "Trainer NoneType broadcast error vs MacOS bus error on CLIP model; unrelated runtime failures." + "reason": "Trainer _gpu_broadcast_one NoneType error vs MacOS CLIP bus error; unrelated." }, { "left": "issue:43334", "right": "issue:43531", "accept": false, - "reason": "Qwen3-VL missing `pad_token_id` vs Qwen3-MoE sliding-window issue; both Qwen-family but different defects." + "reason": "Qwen3-VL pad_token_id loading bug vs Qwen3-MoE sliding_window bug; same family but different concrete issues." }, { "left": "issue:43526", "right": "issue:44186", "accept": false, - "reason": "Beit fast label-reduction bug vs LayoutLMv2Tokenizer NER/padding crash; different token/image processing logic." + "reason": "BeitImageProcessorFast label reduction vs LayoutLMv2Tokenizer NER/padding crash; different components." }, { "left": "issue:44977", "right": "issue:45245", "accept": false, - "reason": "Qwen3.5 flash-attention generation bug vs category-count ceiling error; unrelated." + "reason": "Qwen3.5 flash-attention generation regression vs category-count limit error; unrelated." }, { "left": "issue:43824", "right": "issue:44279", "accept": false, - "reason": "Specific Qwen2_5_VL import failure vs generic dependency issue; too little evidence of the same underlying bug." + "reason": "Specific Qwen2_5_VL import failure vs vague dependency issue; not enough evidence of the same bug." } ] }, @@ -8377,7 +8394,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 26, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -8464,12 +8481,12 @@ "issue:43761|issue:44188", "issue:43381|issue:43873" ], - "prepared_review_unit_hash": "036b88c991f5f8ba7a120b8f0b42fd14aa328fdafcc33624dfaf2d5d4602f421", + "prepared_review_unit_hash": "2bb8a707f1d21f2c231a08edd017755f4f1e8c187d9f6a7757655df2e0c1e9fb", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -8477,189 +8494,189 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 28, - "serialized_chars": 36120, - "estimated_input_tokens": 9030, - "estimated_eval_tokens": 18316 + "serialized_chars": 36130, + "estimated_input_tokens": 9033, + "estimated_eval_tokens": 18322 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These items are a heterogeneous mix of unrelated Transformers issues. None of the soft pairs appear to be the same underlying bug/change, so all soft edges should be rejected.", - "confidence": 0.92, - "canonical_issue_reason": "No single issue is clearly canonical for this set: the candidates span unrelated tokenizer, audio, vision, training, quantization, and model-loading problems.", + "summary": "These items do not form a coherent duplicate set; they span unrelated bugs across tokenizers, audio, vision, training, quantization, loading/saving, and model-specific regressions. No soft edge pair looks like the same underlying bug/change.", + "confidence": 0.98, + "canonical_issue_reason": "No strong canonical duplicate exists in this heterogeneous set; if a representative issue is needed, issue 43873 is the broadest and most actively discussed report.", "canonical_pr_reason": null, - "best_issue_reason": "No global best issue stands out as a representative duplicate target because the cluster is not a single coherent problem area.", + "best_issue_reason": "Issue 43873 is the best single representative because it has the widest impact description and the most discussion/inbound references among these unrelated reports.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43526", "right": "issue:44857", "accept": false, - "reason": "Different bugs in different components: BeitImageProcessorFast label reduction vs AMP/CUDA crash in LwDetrImageLoss." + "reason": "Different subsystems and failures: Beit image processor label reduction vs LwDETR AMP/CUDA crash." }, { "left": "issue:43262", "right": "issue:44206", "accept": false, - "reason": "Both are audio-related, but one is a sampling-rate default in apply_chat_template and the other is an unsupported argument passed by LasrFeatureExtractor." + "reason": "Both are audio-related, but one is a chat-template sampling-rate bug and the other is a feature extractor argument crash." }, { "left": "issue:43441", "right": "issue:45588", "accept": false, - "reason": "Both mention flash attention, but they involve different models and different failures: Ministral-3 vs sink-less models with s_aux=None." + "reason": "Both mention flash attention, but they affect different models/code paths and failure modes." }, { "left": "issue:42915", "right": "issue:43931", "accept": false, - "reason": "Different model/config issues: FineGrainedFP8Config failure for Qwen3Moe vs weight-shape mismatch loading Qwen3-VL-30B." + "reason": "Different models and problems: FP8 config failure vs weight-shape mismatch on model load." }, { "left": "issue:44442", "right": "issue:45072", "accept": false, - "reason": "Unrelated problems: tokenizer loading failure vs dtype mismatches in bfloat16 inference." + "reason": "Unrelated areas: tokenizer loading failure vs dtype mismatch in inference." }, { "left": "issue:44464", "right": "issue:45491", "accept": false, - "reason": "Different generation/runtime bugs: compiled-forward chunked generation inconsistency vs NaNs from sliding-window attention on mixed-length batches." + "reason": "Different bugs: compiled-forward chunked generation inconsistency vs Gemma3 NaN embeddings with sliding-window attention." }, { "left": "issue:44743", "right": "issue:44811", "accept": false, - "reason": "Different code paths and symptoms: Qwen3.5 recurrent state reset vs Whisper batch_decode skip_special_tokens handling." + "reason": "Different features: recurrent-state reset in Qwen3.5 vs Whisper skip_special_tokens handling." }, { "left": "issue:43575", "right": "issue:43701", "accept": false, - "reason": "Different classes of failures: tensor-parallel OOM during model load vs resume_from_checkpoint key mismatch." + "reason": "Different failure types: tensor-parallel OOM vs resume-from-checkpoint key mismatch." }, { "left": "issue:43646", "right": "issue:44077", "accept": false, - "reason": "Related to initialization, but not the same bug: generic custom model init regression vs patchtsmixer-specific post_init allowance." + "reason": "Generic custom-model initialization regression vs a specific patchtsmixer post_init policy issue." }, { "left": "issue:29127", "right": "issue:35141", "accept": false, - "reason": "Different subsystems: LayoutLMv3 error-message clarity vs embedding reinitialization after resize when tie_word_embedding is False." + "reason": "LayoutLMv3 error-message clarity and embedding reinitialization are unrelated bugs." }, { "left": "issue:43575", "right": "issue:44387", "accept": false, - "reason": "Both are OOM reports, but one is TP loading OOM and the other is increased reserved memory under int4 quantization." + "reason": "Both are OOM-related, but one is tp load OOM and the other is increased reserved memory under int4 quantization." }, { "left": "issue:33357", "right": "issue:38175", "accept": false, - "reason": "Different models and failure modes: MacOS bus error on CLIP vs unexpected zero probabilities on SigLIP2." + "reason": "Different models and symptoms: MacOS bus error for CLIP vs zero probabilities for SigLIP2." }, { "left": "issue:44977", "right": "issue:45584", "accept": false, - "reason": "Both affect generation, but the causes are different: flash-attention behavior in Qwen3.5 vs empty-transcription handling after align_special_tokens in Whisper." + "reason": "Different regressions: Qwen3.5 flash-attention generation vs Whisper empty-transcription handling." }, { "left": "issue:44442", "right": "issue:45803", "accept": false, - "reason": "Tokenizer loading failure vs a bare-except swallowing errors in FuyuBatchFeature; not the same bug." + "reason": "Tokenizer loading failure is unrelated to FuyuBatchFeature's bare-except bug." }, { "left": "issue:43316", "right": "issue:43525", "accept": false, - "reason": "Both are config/API discrepancies, but they concern different models and different missing attributes." + "reason": "Both are config/API issues, but they concern different models and different missing/discrepant attributes." }, { "left": "issue:44964", "right": "issue:45440", "accept": false, - "reason": "Different problems: loading Phi-4-multimodal-instruct fails, while DeepseekV3MoE diverges from the remote implementation." + "reason": "Different model families and problems: Phi-4 multimodal loading vs DeepSeekV3MoE implementation divergence." }, { "left": "issue:44479", "right": "issue:45290", "accept": false, - "reason": "Different regressions: video-input handling for Qwen VL models vs chat-template crashes on assistant tool-call messages." + "reason": "Video-input regression across Qwen variants is unrelated to chat-template crashes with tool-call assistant messages." }, { "left": "issue:28218", - "right": "issue:32090", + "right": "issue:29127", "accept": false, - "reason": "Tokenizer spacing bug vs Trainer GPU broadcast TypeError; unrelated." + "reason": "Tokenizer spacing bug and LayoutLMv3 error-message clarity issue are unrelated." }, { "left": "issue:43761", "right": "issue:44079", "accept": false, - "reason": "CLIPVisionModel hidden_states regression vs ModelOutput key-assignment bug; distinct code paths and symptoms." + "reason": "Possible superficial relation through ModelOutput, but the reports describe different bugs and are not clearly the same code-path issue." }, { "left": "issue:42907", "right": "issue:45698", "accept": false, - "reason": "Quantization/offloading issue vs save/load custom-module mismatch; not the same underlying bug." + "reason": "Both involve save/load behavior, but one is saving dequantized models and the other is custom module resolution after save_pretrained." }, { "left": "issue:28218", "right": "issue:32090", "accept": false, - "reason": "Tokenizer spacing bug vs Trainer GPU broadcast TypeError; unrelated." + "reason": "Tokenizer spacing bug and Trainer broadcast TypeError are unrelated." }, { "left": "issue:43931", "right": "issue:45216", "accept": false, - "reason": "Loading weight-shape mismatch in Qwen3-VL vs incorrect checkpoint saving in Qwen3.5; different stages of the model lifecycle." + "reason": "Different checkpoint/model-loading failures: shape mismatch on a VL model vs incorrect saved checkpoint for Qwen3.5." }, { "left": "issue:33290", "right": "issue:34567", "accept": false, - "reason": "OOM with Adafactor in DeepSpeed vs TrainerState token counter not updating; unrelated." + "reason": "OOM with Adafactor/DeepSpeed is unrelated to TrainerState token counting." }, { "left": "issue:34689", "right": "issue:43611", "accept": false, - "reason": "Both are loading regressions, but they target different versions and different causes." + "reason": "Both concern loading, but they are different regression reports with different root causes and model contexts." }, { "left": "issue:44442", "right": "issue:44898", "accept": false, - "reason": "Tokenizer loading failure vs Perceiver non-default-resolution failure; unrelated." + "reason": "Tokenizer loading and Perceiver image resolution handling are unrelated." }, { "left": "issue:39692", "right": "issue:45491", "accept": false, - "reason": "Documentation/example errors vs a runtime NaN bug; not the same change or bug." + "reason": "Documentation/example errors and Gemma3 NaN embeddings are different issue types and code paths." }, { "left": "issue:43761", "right": "issue:44188", "accept": false, - "reason": "Different model/runtime issues: CLIPVisionModel hidden_states regression vs attention-kernel divergence under torch.compile." + "reason": "CLIP hidden_states regression and attention-kernel divergence under torch.compile are unrelated." }, { "left": "issue:43381", "right": "issue:43873", "accept": false, - "reason": "Gradient checkpointing in eval mode vs quantization offloading behavior; different defects." + "reason": "Gradient checkpointing eval-mode restriction is unrelated to quantization offloading behavior." } ] }, @@ -8675,7 +8692,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 27, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -8741,8 +8758,8 @@ "issue:43720|issue:44442", "issue:43643|issue:44913", "issue:32090|issue:33290", - "issue:44190|issue:44496", "issue:43873|issue:44871", + "issue:44190|issue:44496", "issue:34689|issue:36010", "issue:43381|issue:43856", "issue:44855|issue:45137", @@ -8755,18 +8772,18 @@ "issue:42175|issue:43316", "issue:33290|issue:34689", "issue:44162|issue:44792", - "issue:43404|issue:43441", "issue:25251|issue:28282", + "issue:43404|issue:43441", "issue:41950|issue:43475", "issue:43295|issue:43825", "issue:43232|issue:43388" ], - "prepared_review_unit_hash": "e536a6e270e6323be3306990329e8df0772ab1a277bb102732135f22307e76d9", + "prepared_review_unit_hash": "203f34b80f33e069b7d0d161ce989e16b2067416e8273b769391392a9a3c237e", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -8774,7 +8791,7 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 27, - "serialized_chars": 36089, + "serialized_chars": 36090, "estimated_input_tokens": 9023, "estimated_eval_tokens": 18302 }, @@ -8783,174 +8800,174 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is a broad mix of unrelated bug reports across pipelines, config loading, multimodal models, and distributed training. None of the soft pairs look like the same underlying bug/change, so I reject all proposed duplicate links.", + "summary": "This cluster is a broad mix of unrelated Transformers issues, mostly around model loading, configs, processors, and distributed/training edge cases. I don\u2019t see any true duplicate pair among the soft candidates.", "confidence": 0.91, - "canonical_issue_reason": "issue:41950 is the only open item and is phrased as a concrete, reproducible pipeline regression, making it the most useful anchor in this set.", + "canonical_issue_reason": "issue:44479 is the strongest representative because it describes a concrete, high-impact runtime regression spanning multiple Qwen video variants, which is more central than the other narrowly scoped reports.", "canonical_pr_reason": null, - "best_issue_reason": "issue:41950 is the clearest and most actionable issue here: specific failure mode, current open status, and a well-scoped title.", + "best_issue_reason": "issue:44479 is the most broadly impactful user-facing bug in the set and best captures the recent multimodal regression theme.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43493", "right": "issue:43827", "accept": false, - "reason": "Different problems: SigLIP2 implementation mismatch vs stale docs referencing removed pipelines." + "reason": "SigLIP2 implementation discrepancy vs documentation still referencing pipeline(); different problems." }, { "left": "issue:43550", "right": "issue:44743", "accept": false, - "reason": "Different model/code paths and failures: torch.compile+SDPA issue vs cache/recurrent-state reset bug." + "reason": "Bamba torch.compile/SDPA failure vs Qwen3.5 recurrent-state cache reset; unrelated code paths." }, { "left": "issue:44568", "right": "issue:45479", "accept": false, - "reason": "Tokenizer special-token behavior and sequence-classification loss behavior are unrelated." + "reason": "Tokenizer special-token regression vs sequence-classification zero-loss bug; not the same issue." }, { "left": "issue:43316", "right": "issue:45759", "accept": false, - "reason": "Both are config/AutoModel-adjacent, but they concern different models and different failure mechanisms." + "reason": "Gemma3TextConfig API mismatch vs Qwen multimodal from_config text_config unwrapping; different configs/models." }, { "left": "issue:41628", "right": "issue:45372", "accept": false, - "reason": "Different import errors in different components; no shared code-path or symptom beyond import-time failure." + "reason": "AutoImageProcessor import failure vs missing ReasoningEffort import for Gemma 4 processor loading; unrelated import issues." }, { "left": "issue:43720", "right": "issue:44442", "accept": false, - "reason": "BitNet weight-loading bug and tokenizer loading bug are unrelated subsystems." + "reason": "BitNet packed-weight loading bug vs FastSpeech2ConformerTokenizer loading failure; separate load paths." }, { "left": "issue:43643", "right": "issue:44913", "accept": false, - "reason": "One is trust_remote_code returning incomplete config fields; the other is a GPTNeoX config persistence bug." + "reason": "trust_remote_code config field loss vs GPTNeoX rotary_pct not persisting on reload; different config bugs." }, { "left": "issue:32090", "right": "issue:33290", "accept": false, - "reason": "Both involve Trainer/DeepSpeed, but one is a NoneType broadcast error and the other is an optimizer OOM." + "reason": "NoneType broadcast error in Trainer vs Adafactor OOM under deepspeed; not the same underlying failure." }, { - "left": "issue:44190", - "right": "issue:44496", + "left": "issue:43873", + "right": "issue:44871", "accept": false, - "reason": "Dataset loading in a script and unrecognized model config loading are different issues." + "reason": "Quantization/offloading behavior vs Gemma-3 eos_token_id inconsistency; unrelated configuration problems." }, { - "left": "issue:43873", - "right": "issue:44871", + "left": "issue:44190", + "right": "issue:44496", "accept": false, - "reason": "Quantization/offloading behavior and Gemma eos_token_id mismatch are unrelated." + "reason": "Local dataset loading in a training script vs unrecognized model/config loading error; different surfaces." }, { "left": "issue:34689", "right": "issue:36010", "accept": false, - "reason": "Model-loading regression for a specific model family vs a missing GenerationMixin import are different failures." + "reason": "Llama vision model loading regression vs GenerationMixin import error; unrelated bugs." }, { "left": "issue:43381", "right": "issue:43856", "accept": false, - "reason": "Gradient checkpointing in eval mode and MoE training memory inefficiency are distinct problems." + "reason": "Gradient checkpointing in eval mode vs Qwen3 MoE memory inefficiency; different issues." }, { "left": "issue:44855", "right": "issue:45137", "accept": false, - "reason": "Python 3.13 import parsing failure vs DeepSpeed ZeRO3 deque underflow are unrelated." + "reason": "PyTorch JIT parse/IndentationError on import vs DeepSpeed ZeRO3 deque underflow; unrelated." }, { "left": "issue:44077", "right": "issue:44479", "accept": false, - "reason": "PatchTSMixer post_init policy and Qwen video-input regression do not share the same bug." + "reason": "patchtsmixer post_init policy change vs Qwen video input regression; different models and code paths." }, { "left": "issue:33290", "right": "issue:45656", "accept": false, - "reason": "Both mention DeepSpeed/optimizers, but OOM and double optimizer-step are different code-path failures." + "reason": "Both involve deepspeed/optimizer behavior, but one is OOM and the other is double optimizer stepping; not a duplicate." }, { "left": "issue:29127", "right": "issue:33357", "accept": false, - "reason": "LayoutLMv3 error messaging issue and CLIP bus error on macOS are unrelated." + "reason": "LayoutLMv3 error-message clarity vs MacOS CLIP bus error; unrelated model-specific bugs." }, { "left": "issue:43381", "right": "issue:43742", "accept": false, - "reason": "Gradient checkpointing/eval issue is not the same as a MobileLLM key error on load." + "reason": "Gradient-checkpointing eval-mode issue vs MobileLLM config key error; not the same bug." }, { "left": "issue:43540", "right": "issue:44514", "accept": false, - "reason": "Both are video/multimodal, but the failing inputs and processor code paths are different." + "reason": "Both are Qwen video/multimodal processor issues, but the concrete failures differ enough that they should not be merged." }, { "left": "issue:43316", "right": "issue:44877", "accept": false, - "reason": "Different config-loading bugs for different model families; not the same underlying defect." + "reason": "Gemma3TextConfig discrepancy vs strict config blocking granite_speech loading; different config incompatibilities." }, { "left": "issue:42175", "right": "issue:43316", "accept": false, - "reason": "Dependency/backend packaging issue vs Gemma config API discrepancy are unrelated." + "reason": "Packaging extras missing TensorFlow vs Gemma3TextConfig API discrepancy; unrelated." }, { "left": "issue:33290", "right": "issue:34689", "accept": false, - "reason": "DeepSpeed optimizer OOM and a model-loading regression are different failure modes." + "reason": "Adafactor/deepspeed OOM vs Llama 3.2 vision loading regression; unrelated." }, { "left": "issue:44162", "right": "issue:44792", "accept": false, - "reason": "ESM2 model breakage and a janus test failure are not the same bug." + "reason": "ESM2 broken vs janus test failure; different models and failure modes." }, { - "left": "issue:43404", - "right": "issue:43441", + "left": "issue:25251", + "right": "issue:28282", "accept": false, - "reason": "Weight tying bug in one model class and FlashAttention failure in another are separate issues." + "reason": "Pipeline top_k nesting behavior vs missing PyTorch import error; unrelated." }, { - "left": "issue:25251", - "right": "issue:28282", + "left": "issue:43404", + "right": "issue:43441", "accept": false, - "reason": "Pipeline top_k nesting bug is unrelated to missing PyTorch import error." + "reason": "Mistral3 lm_head tying bug vs Ministral FlashAttention failure; same family but different concrete defects." }, { "left": "issue:41950", "right": "issue:43475", "accept": false, - "reason": "Pipeline selecting image processors and SAM 3 video output attribute error are different model/pipeline bugs." + "reason": "Video-classification pipeline processor lookup bug vs SAM 3 Video missing attribute; unrelated video-model issues." }, { "left": "issue:43295", "right": "issue:43825", "accept": false, - "reason": "Processor/tokenizer regression and pipeline error-message regression are different issues." + "reason": "Processor/tokenizer regression vs pipeline() translation-message regression; different user-visible behaviors." }, { "left": "issue:43232", "right": "issue:43388", "accept": false, - "reason": "Generation kwargs update after sync_gpus and metric gathering last-batch label dropping are unrelated distributed-training bugs." + "reason": "Generation kwargs sync_gpus bug vs metric-gathering label truncation; unrelated training/eval paths." } ] }, @@ -8966,7 +8983,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 28, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -9030,14 +9047,14 @@ "issue:43606|issue:43701", "issue:43295|issue:44871", "issue:43065|issue:44617", - "issue:43761|issue:44479", "issue:33290|issue:35141", "issue:33290|issue:36331", + "issue:43761|issue:44479", "issue:43452|issue:44496", "issue:43575|issue:43742", - "issue:43673|issue:44743", "issue:43646|issue:44913", "issue:42617|issue:43575", + "issue:43673|issue:44743", "issue:44936|issue:45698", "issue:43761|issue:44242", "issue:43575|issue:43873", @@ -9046,8 +9063,8 @@ "issue:44464|issue:44871", "issue:44479|issue:44734", "issue:44617|issue:45584", - "issue:43906|issue:45290", "issue:44792|issue:44977", + "issue:43906|issue:45290", "issue:43065|issue:44610", "issue:43827|issue:43994", "issue:44534|issue:44913", @@ -9056,12 +9073,12 @@ "issue:44792|issue:45600", "issue:44855|issue:45588" ], - "prepared_review_unit_hash": "8add0b8968d643f55cc1a8945bde92962636969ddc51e8c974b4742a4183b4bb", + "prepared_review_unit_hash": "835a8191cf4d1aa7ba31f46569306698c83894d29423863629af39995eb54e10", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -9069,207 +9086,207 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 31, - "serialized_chars": 36968, - "estimated_input_tokens": 9242, - "estimated_eval_tokens": 18740 + "serialized_chars": 36970, + "estimated_input_tokens": 9243, + "estimated_eval_tokens": 18742 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is a grab bag of unrelated model-loading, training, generation, and regression reports. None of the soft pairs look like the same underlying bug/change closely enough to merge.", - "confidence": 0.92, - "canonical_issue_reason": "issue:43646 is the broadest, most central umbrella here: it describes a generic custom-model initialization breakage in Transformers 5.0.0, which is more representative than the many narrower, model-specific reports.", + "summary": "This set is very heterogeneous: most pairs are only superficially similar and do not look like the same underlying bug/change. No soft edge is strong enough to merge, so the cluster should not be collapsed into duplicates.", + "confidence": 0.56, + "canonical_issue_reason": "Issue 43646 is the broadest umbrella here ('Transformers 5.0.0 breaks custom model initialization') and best matches the recurring v5/custom-loading regression theme, while most other items are narrower model-specific failures.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43646 is the best representative issue to keep because it is generic, user-facing, and broad enough to subsume closely related custom-model init/load regressions.", + "best_issue_reason": "43646 is the most reusable anchor for the cluster because it is general, regression-oriented, and closest to several loading/initialization reports; still, the overall cluster is not a clean duplicate set.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44871", "right": "issue:45584", "accept": false, - "reason": "Different bugs: Gemma eos token config mismatch vs Whisper empty-transcription generation failure." + "reason": "Different bugs: config eos_token mismatch vs Whisper empty-transcription failure after align_special_tokens." }, { "left": "issue:45127", "right": "issue:45200", "accept": false, - "reason": "Both involve model behavior around tokens/embeddings, but one is LoRA merging collapse and the other is Gemma 4 multimodal token-type defaults." + "reason": "Different code paths: LoRA/vocab merge collapse on tied embeddings vs mm_token_type_ids defaulting for text-only fine-tuning." }, { "left": "issue:43550", "right": "issue:43701", "accept": false, - "reason": "Unrelated failures: torch.compile+SDPA on Bamba versus resume_from_checkpoint key mismatch." + "reason": "Unrelated failures: torch.compile/SDPA in Bamba vs resume_from_checkpoint key mismatch." }, { "left": "issue:43606", "right": "issue:43701", "accept": false, - "reason": "CPU offload device mismatch is a different problem from checkpoint key mapping." + "reason": "Device offload mismatch in bark-small is not the same as checkpoint key mismatch." }, { "left": "issue:43295", "right": "issue:44871", "accept": false, - "reason": "One is custom model/processor API regression; the other is eos_token_id config inconsistency." + "reason": "Regression around processor.tokenizer/images is unrelated to eos_token_id config inconsistency." }, { "left": "issue:43065", "right": "issue:44617", "accept": false, - "reason": "Same family only at a high level (Sam3), but one is a dummy Conv2d concern and the other is a CUDA OOM in video inference." - }, - { - "left": "issue:43761", - "right": "issue:44479", - "accept": false, - "reason": "Different model paths and symptoms: CLIP hidden_states omission versus video-input regression in Qwen VL models." + "reason": "Both involve Sam3, but one is a dummy Conv2d implementation issue and the other is a CUDA OOM; not the same bug." }, { "left": "issue:33290", "right": "issue:35141", "accept": false, - "reason": "OOM in DeepSpeed Adafactor is unrelated to token-embedding reinitialization after resize." + "reason": "OOM in DeepSpeed Adafactor and embedding reinitialization in post_init are distinct issues." }, { "left": "issue:33290", "right": "issue:36331", "accept": false, - "reason": "Optimizer memory blow-up is not the same as a Trainer compute_loss signature TypeError." + "reason": "Different training failures: optimizer memory blow-up vs CustomTrainer API signature break." + }, + { + "left": "issue:43761", + "right": "issue:44479", + "accept": false, + "reason": "CLIPVision hidden_states regression and Qwen video-input regression are separate model-path bugs." }, { "left": "issue:43452", "right": "issue:44496", "accept": false, - "reason": "Tokenizer/model GGUF loading breakage is unrelated to an unrecognized custom model config error." + "reason": "GGUF/from_pretrained breakage is not the same as an unrecognized model config error." }, { "left": "issue:43575", "right": "issue:43742", "accept": false, - "reason": "Both are loading failures, but one is TP memory pressure on a large model and the other is a key error on a small model." - }, - { - "left": "issue:43673", - "right": "issue:44743", - "accept": false, - "reason": "Both mention cache/state handling, but one is missing GenerationMixin cache in chunked prefill and the other is Qwen3.5 recurrent state reset." + "reason": "Qwen2 TP OOM and MobileLLM key error are different loading problems." }, { "left": "issue:43646", "right": "issue:44913", "accept": false, - "reason": "Generic custom-model initialization breakage is not the same as GPTNeoX rotary_pct not persisting on reload." + "reason": "Custom model initialization regression is not the same as GPTNeoX rotary_pct not persisting on reload." }, { "left": "issue:42617", "right": "issue:43575", "accept": false, - "reason": "3d_parallel.py execution failure is not the same underlying issue as TP loading OOM." + "reason": "3d_parallel.py failure and Qwen2 TP OOM are unrelated issues." + }, + { + "left": "issue:43673", + "right": "issue:44743", + "accept": false, + "reason": "Both are cache-related, but chunked_prefill cache missing and recurrent states resetting are different concrete bugs." }, { "left": "issue:44936", "right": "issue:45698", "accept": false, - "reason": "Trainer evaluate-after-train failure differs from wrong custom module being loaded after save_pretrained." + "reason": "trainer.evaluate after train and wrong custom module loading after save_pretrained are separate problems." }, { "left": "issue:43761", "right": "issue:44242", "accept": false, - "reason": "CLIPVisionModel hidden_states regression and load-balancing loss omission are separate code paths." + "reason": "CLIPVision hidden_states regression does not match router-loss omission when output_router_logits=False." }, { "left": "issue:43575", "right": "issue:43873", "accept": false, - "reason": "OOM under tensor parallelism is different from offloading/quantization not behaving as expected." + "reason": "Both mention memory/offload themes, but tp OOM and quantization offloading misbehavior are not the same issue." }, { "left": "issue:44077", "right": "issue:44534", "accept": false, - "reason": "PatchTSMixer post_init allowance and non-persistent buffer junk are distinct initialization regressions." + "reason": "patchtsmixer post_init policy and non-persistent buffer junk are unrelated v5 behavior changes." }, { "left": "issue:43931", "right": "issue:44060", "accept": false, - "reason": "Weight-shape mismatch while loading Qwen3-VL is unrelated to a bad tied-weights warning in Qwen3-Next." + "reason": "Shape mismatch while loading Qwen3-VL is unrelated to the tied-weights warning on Qwen3-Next." }, { "left": "issue:44464", "right": "issue:44871", "accept": false, - "reason": "Chunked generation inconsistency with compiled forward is unrelated to Gemma eos token config." + "reason": "Compiled chunked generation inconsistency is a different failure from eos_token_id configuration mismatch." }, { "left": "issue:44479", "right": "issue:44734", "accept": false, - "reason": "Video input regression in Qwen VL models is different from KV-cache continuation indexing in serve /v1/responses." + "reason": "Video-input regression in Qwen VL models and KV-cache continuation crash in serve are different code paths." }, { "left": "issue:44617", "right": "issue:45584", "accept": false, - "reason": "CUDA OOM in Sam3Video and Whisper empty-transcription failure are unrelated runtime issues." + "reason": "Sam3Video CUDA OOM and Whisper empty transcription are entirely separate model bugs." }, { - "left": "issue:43906", - "right": "issue:45290", + "left": "issue:44792", + "right": "issue:44977", "accept": false, - "reason": "Isolated reproduction of issue 38071 is too vague and not clearly the same as tool-call chat template crashes." + "reason": "Janus image-generation test failure and Qwen3.5 flash-attention generation bug are not the same underlying issue." }, { - "left": "issue:44792", - "right": "issue:44977", + "left": "issue:43906", + "right": "issue:45290", "accept": false, - "reason": "Janus image-generation test failure and Qwen3.5 flash-attention generation bug are different models and failure modes." + "reason": "Isolated reproduction of an unrelated issue and apply_chat_template tool-call crash do not share a concrete bug." }, { "left": "issue:43065", "right": "issue:44610", "accept": false, - "reason": "Dummy Conv2d in Sam3PixelDecoder does not match OmDet-Turbo processor output-size mismatch." + "reason": "Dummy Conv2d in Sam3PixelDecoder and OmDet processor/model size mismatch are different problems." }, { "left": "issue:43827", "right": "issue:43994", "accept": false, - "reason": "Docs still mentioning pipeline() is not the same as nonsensical outputs from AutoModel/pipeline on SigLIP2." + "reason": "Docs still referencing pipeline() and SigLIP2 nonsensical outputs are unrelated." }, { "left": "issue:44534", "right": "issue:44913", "accept": false, - "reason": "Non-persistent buffer initialization junk and GPTNeoX rotary_pct reload mismatch are unrelated." + "reason": "Non-persistent buffer initialization garbage and rotary_pct reload default are different regressions." }, { "left": "issue:44190", "right": "issue:44964", "accept": false, - "reason": "Local dataset loading in a no-trainer script is a different bug from loading Phi-4 multimodal-instruct." + "reason": "Local dataset loading failure and Phi-4-multimodal model loading error are unrelated." }, { "left": "issue:41720", "right": "issue:45245", "accept": false, - "reason": "Qwen3 auto-device-map cudaErrorAssert is unrelated to the 2^24 category limit." + "reason": "CUDA assert with auto device mapping and category-count limit error are different runtime failures." }, { "left": "issue:44792", "right": "issue:45600", "accept": false, - "reason": "Janus generate-images test failure is unrelated to stale auto_mappings entries for removed Sam3LiteText configs." + "reason": "Janus image-generation test failure is unrelated to stale auto_mappings references breaking CI." }, { "left": "issue:44855", "right": "issue:45588", "accept": false, - "reason": "Python 3.13 TorchScript parsing failure in DebertaV2Model is unrelated to flash_attention s_aux=None crashes." + "reason": "Python 3.13 IndentationError in DebertaV2 import is not the same as flash_attention crashing on s_aux=None." } ] }, @@ -9285,7 +9302,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 29, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -9348,8 +9365,8 @@ "issue:43335|issue:44855", "issue:44938|issue:45542", "issue:43976|issue:44855", - "issue:43550|issue:44190", "issue:43644|issue:44913", + "issue:43550|issue:44190", "issue:44077|issue:44877", "issue:44496|issue:45803", "issue:43540|issue:44734", @@ -9364,20 +9381,20 @@ "issue:36246|issue:41628", "issue:44933|issue:45362", "issue:44186|issue:44734", - "issue:43404|issue:45216", "issue:44464|issue:45563", + "issue:43404|issue:45216", "issue:44683|issue:45446", "issue:38175|issue:43065", "issue:44734|issue:45632", "issue:44561|issue:45632", "issue:44466|issue:44913" ], - "prepared_review_unit_hash": "5222244dc94fbace13dcf65f79e2713a592886ca484687a11a521c21985ce478", + "prepared_review_unit_hash": "2dfb3a09ae952b1244d4016266bb62ea7a61e7c9d9400334f4ef74ba5030a0e0", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -9385,7 +9402,7 @@ "node_count": 47, "item_count": 47, "soft_pair_count": 29, - "serialized_chars": 35963, + "serialized_chars": 35964, "estimated_input_tokens": 8991, "estimated_eval_tokens": 18238 }, @@ -9394,186 +9411,186 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly noisy and heterogeneous: the soft-pair candidates do not appear to share the same underlying bug or change, so I reject all of them. The strongest issue in the set is the multimodal `apply_chat_template` bug because it is the most active, well-scoped, and well-referenced report.", - "confidence": 0.87, - "canonical_issue_reason": "issue:44521 is the most actionable and best-supported report in the set, with the highest discussion/inbound activity and a clear reproducible multimodal bug.", + "summary": "These issues are largely unrelated one-off bugs across different models, configs, and code paths. I found no soft pair that looks like the same underlying defect or change, so all candidate merges should be rejected.", + "confidence": 0.93, + "canonical_issue_reason": "issue:44521 is the strongest general representative here: it is open, has the most inbound references and discussion, and concerns a core library API (`apply_chat_template`) rather than a narrow model-specific edge case.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44521 is the best representative issue here because it is concrete, broadly useful, and has the strongest evidence trail among otherwise unrelated reports.", + "best_issue_reason": "issue:44521 has the broadest impact and most activity, so it is the best single issue to anchor the cluster even though the cluster does not contain clear duplicates.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44737", "right": "issue:45803", "accept": false, - "reason": "Different subsystems and failure modes: XLNet CPU placement bug vs Fuyu tensor conversion exception handling." + "reason": "Different bugs in different components: XLNet device placement vs. Fuyu tensor conversion error handling." }, { "left": "issue:44521", "right": "issue:45381", "accept": false, - "reason": "Both involve multimodal inputs, but one is assistant mask generation and the other is video position IDs in Qwen2.5-VL; root causes do not match." + "reason": "Both are multimodal-related, but one is assistant mask generation in `apply_chat_template` and the other is video `vision_position_ids`; distinct code paths and symptoms." }, { "left": "issue:45127", "right": "issue:45357", "accept": false, - "reason": "Distinct regression areas: LoRA merge/tied embeddings vs incorrect visual-encoder keys in `save_pretrained`." + "reason": "One is LoRA merge/tied-weights collapse, the other is incorrect visual encoder keys in `save_pretrained`; not the same defect." }, { "left": "issue:43335", "right": "issue:44855", "accept": false, - "reason": "Unrelated models and bugs: SwitchTransformers config layer creation vs DebertaV2 import parsing on Python 3.13." + "reason": "Unrelated: SwitchTransformers sparse-layer construction vs. Python 3.13 import/`torch.jit.script` parsing failure." }, { "left": "issue:44938", "right": "issue:45542", "accept": false, - "reason": "Both are environment/load issues, but one is Python 3.14 import failure and the other is a missing TensorFlow backend fallback; not the same bug." + "reason": "Different failures: Python 3.14 import/load breakage vs. tensorboard-without-TF backend handling." }, { "left": "issue:43976", "right": "issue:44855", "accept": false, - "reason": "Different Python-version regressions with unrelated mechanisms and code paths." + "reason": "Both mention Python version compatibility, but one is a broad 5.1.0 support issue and the other is a specific DebertaV2 import parsing error." }, { - "left": "issue:43550", - "right": "issue:44190", + "left": "issue:43644", + "right": "issue:44913", "accept": false, - "reason": "Completely different domains: torch.compile SDPA model failure vs dataset loading in an example script." + "reason": "Non-persistent buffer initialization bug is unrelated to GPTNeoX config reload losing `rotary_pct`." }, { - "left": "issue:43644", - "right": "issue:44913", + "left": "issue:43550", + "right": "issue:44190", "accept": false, - "reason": "Both touch model state/config, but one is non-persistent buffer junk in v5 and the other is a GPTNeoX config reload issue." + "reason": "Different areas entirely: Bamba SDPA/torch.compile vs. image-classification script local dataset loading." }, { "left": "issue:44077", "right": "issue:44877", "accept": false, - "reason": "Both mention config handling, but one is about forbidding optional `post_init` and the other is strict config loading for a specific model." + "reason": "PatchTSMixer `post_init` restriction and GraniteSpeech strict-config loading are separate config-validation problems." }, { "left": "issue:44496", "right": "issue:45803", "accept": false, - "reason": "Unrelated: model-type/config loading error vs a bare `except` swallowing errors in Fuyu tensor conversion." + "reason": "Unrecognized model config loading and Fuyu bare-except error handling are unrelated." }, { "left": "issue:43540", "right": "issue:44734", "accept": false, - "reason": "Different code paths: Qwen3OmniMoe video preprocessing vs serve KV-cache continuation indexing." + "reason": "Qwen3OmniMoe video input validation and serve KV-cache continuation indexing are different code paths." }, { "left": "issue:45276", "right": "issue:45584", "accept": false, - "reason": "Different bugs in different models: Gemma4 embedding resize propagation vs Whisper empty transcription handling." + "reason": "Gemma4 embedding resize bug and Whisper empty-transcription generation failure are unrelated model-specific issues." }, { "left": "issue:44112", "right": "issue:45600", "accept": false, - "reason": "Both are CI-related, but one is a stale test override and the other is stale autogenerated mappings; not the same root cause." + "reason": "CI stale device override test and auto_mappings cleanup for removed Sam3LiteText configs are not the same bug." }, { "left": "issue:43650", "right": "issue:44220", "accept": false, - "reason": "No shared underlying bug; the titles are unrelated and provide no common code path." + "reason": "Placeholder issue title and `_torch_extract_fbank_features()` failure have no concrete overlap." }, { "left": "issue:43335", "right": "issue:44190", "accept": false, - "reason": "SwitchTransformers config initialization and example dataset loading are unrelated." + "reason": "SwitchTransformers config construction is unrelated to the image-classification example script's local dataset loading." }, { "left": "issue:43116", "right": "issue:44190", "accept": false, - "reason": "Different example-script failures: multi-label classification output bug vs local dataset loading." + "reason": "Multi-label classification empty results and local dataset loading failure are different example-script bugs." }, { "left": "issue:43295", "right": "issue:45276", "accept": false, - "reason": "Different multimodal/model-management regressions; no shared code path or fixable overlap." + "reason": "Processor/tokenizer regression and Gemma4 embedding resize behavior affect different APIs and model paths." }, { "left": "issue:45245", "right": "issue:45584", "accept": false, - "reason": "Completely unrelated error conditions: category cardinality limit vs Whisper transcription edge case." + "reason": "Category-count runtime limit is unrelated to Whisper empty-transcription handling." }, { "left": "issue:43479", "right": "issue:45375", "accept": false, - "reason": "Both are config-schema issues, but they affect different model families and different missing-field behavior." + "reason": "Phi4Multimodal default config initialization and Qwen3_5MoeVisionConfig strict-field dropping are separate config issues." }, { "left": "issue:36246", "right": "issue:41628", "accept": false, - "reason": "Both are import errors, but they refer to different symbols and likely different export/registry problems." + "reason": "Both are import errors, but for different symbols and modules (`Qwen2_5_VLImageProcessor` vs. `AutoImageProcessor`)." }, { "left": "issue:44933", "right": "issue:45362", "accept": false, - "reason": "A missing import in `image_utils` is not the same as a chat crash in Qwen3.5." + "reason": "Removed image_utils import and Qwen3.5 chat crash are unrelated." }, { "left": "issue:44186", "right": "issue:44734", "accept": false, - "reason": "Tokenizer padding/truncation crash vs server KV-cache continuation indexing; distinct bugs." + "reason": "Tokenizer crashes on NER/padding versus server KV-cache continuation indexing are distinct bugs." }, { - "left": "issue:43404", - "right": "issue:45216", + "left": "issue:44464", + "right": "issue:45563", "accept": false, - "reason": "Both involve model weights, but one is tied `lm_head` in Mistral3 and the other is Qwen3.5 checkpoint saving." + "reason": "Compiled forward chunked generation inconsistency is not the same as a stale warning in paged generate()." }, { - "left": "issue:44464", - "right": "issue:45563", + "left": "issue:43404", + "right": "issue:45216", "accept": false, - "reason": "Generation inconsistency under compilation vs a stale warning about `num_return_sequences`; not the same issue." + "reason": "Tied `lm_head` weights in Mistral3 vs. incorrect Qwen3.5 checkpoint saving are different serialization/model-weight issues." }, { "left": "issue:44683", "right": "issue:45446", "accept": false, - "reason": "Both are in flex_attention, but one is a compiled-kernel failure on newer torch and the other is a version-check/import bug for AuxRequest." + "reason": "Compiled flex_attention failing on torch>=2.9 and a PyTorch version check for AuxRequest import are separate flex_attention problems." }, { "left": "issue:38175", "right": "issue:43065", "accept": false, - "reason": "Different models and failure modes: zero probabilities in SigLIP2 vs a dummy Conv2d in Sam3 pixel decoder." + "reason": "Siglip2 zero probabilities and Sam3PixelDecoder dummy Conv2d are unrelated model bugs." }, { "left": "issue:44734", "right": "issue:45632", "accept": false, - "reason": "Serve KV-cache indexing and trust_remote_code cache path collisions are unrelated." + "reason": "Serve KV-cache indexing bug and `trust_remote_code` cache-path collision are different subsystems and failure modes." }, { "left": "issue:44561", "right": "issue:45632", "accept": false, - "reason": "Different regression classes: removed helper breaking trust_remote_code vs cache-path collision for local models." + "reason": "Removal of `is_torch_fx_available` breaking trust_remote_code models is unrelated to cache-path collisions for local models." }, { "left": "issue:44466", "right": "issue:44913", "accept": false, - "reason": "Serialization of tied weights depending on device vs GPTNeoX config reload behavior; not the same bug." + "reason": "Chunked generation under compilation and GPTNeoX config reload losing `rotary_pct` are separate issues." } ] }, @@ -9589,7 +9606,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 30, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -9652,11 +9669,11 @@ "issue:43643|issue:44496", "issue:45406|issue:45632", "issue:45563|issue:45584", - "issue:41950|issue:44016", "issue:44964|issue:45600", + "issue:41950|issue:44016", "issue:43388|issue:43688", - "issue:42907|issue:43441", "issue:44112|issue:44964", + "issue:42907|issue:43441", "issue:43295|issue:45335", "issue:43854|issue:44964", "issue:44016|issue:44220", @@ -9679,12 +9696,12 @@ "issue:41950|issue:45020", "issue:43976|issue:45405" ], - "prepared_review_unit_hash": "26caec4c4b1c2a0d3ce2f4f1f8c327e109c9fd30d7f9e5f97cee67eb504c3d71", + "prepared_review_unit_hash": "03fbcace3003f78cc66f2c5617e55847c5004d35a862303f1e89bf7498ed78d8", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -9692,211 +9709,214 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 31, - "serialized_chars": 37045, - "estimated_input_tokens": 9262, - "estimated_eval_tokens": 18780 + "serialized_chars": 37050, + "estimated_input_tokens": 9263, + "estimated_eval_tokens": 18782 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous, but it has one plausible duplicate axis around post-upgrade import/export regressions in Transformers v5. Most other pairs are different bugs in different code paths and should stay separate.", - "confidence": 0.58, - "canonical_issue_reason": "issue:45278 is the broadest representative report in the set: it describes widespread import errors after upgrading to 5.5.0 and can plausibly subsume concrete missing-symbol cases like issue:44351.", + "summary": "This cluster is heterogeneous: most items are separate regression reports, import errors, model-loading issues, or docs/test bugs rather than true duplicates. No soft edge looks safe to merge under a strict duplicate policy.", + "confidence": 0.86, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the best umbrella issue because it captures the shared upgrade/regression theme with the widest scope and open discussion, making it the most useful canonical target for related import failures.", + "best_issue_reason": "issue:45020 is the broadest open report and the closest thing to an umbrella for recent remote_code/model-loading regressions, but it is not a true duplicate of the rest.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44246", "right": "issue:45003", "accept": false, - "reason": "Both are import-related, but one is a performance complaint about importing Transformers and the other is a specific sys.modules access bug; different symptoms and likely different fixes." + "reason": "Both mention import/runtime behavior, but one is about slow import and the other about unsafe sys.modules access; different bugs." }, { "left": "issue:36246", "right": "issue:38617", "accept": false, - "reason": "Both are ImportError reports, but they concern different missing symbols from different modules, so they are not the same underlying bug." + "reason": "Both are ImportErrors, but for unrelated symbols in different modules; not the same failure path." }, { "left": "issue:43643", "right": "issue:44496", "accept": false, - "reason": "Both involve config/model-loading failures, but one is about trust_remote_code returning incomplete configs and the other is an unrecognized model/config issue; different root causes." + "reason": "Both concern config/model loading, but one is about trust_remote_code dropping fields and the other is an unrecognized model/config issue." }, { "left": "issue:45406", "right": "issue:45632", "accept": false, - "reason": "Both mention trust_remote_code behavior, but one is a missing _tokenizer attribute on Gemma4Processor and the other is a cache-path collision for local models; unrelated bugs." + "reason": "Gemma4Processor _tokenizer access and trust_remote_code cache collisions are different code paths." }, { "left": "issue:45563", "right": "issue:45584", "accept": false, - "reason": "Both are generation-related, but a stale warning on paged generate and a Whisper empty-transcription failure after token alignment are different code paths." + "reason": "A stale generation warning and Whisper empty-transcription failure are unrelated generation bugs." }, { - "left": "issue:41950", - "right": "issue:44016", + "left": "issue:44964", + "right": "issue:45600", "accept": false, - "reason": "A video-classification pipeline bug and a notebook syntax error are clearly unrelated." + "reason": "Both touch model-loading/auto-mapping paths, but they concern different models and different failures." }, { - "left": "issue:44964", - "right": "issue:45600", + "left": "issue:41950", + "right": "issue:44016", "accept": false, - "reason": "Both are model-loading/CI issues, but they affect different models and different failure modes; no shared concrete bug." + "reason": "Pipeline image-processor lookup and a notebook syntax error are unrelated." }, { "left": "issue:43388", "right": "issue:43688", "accept": false, - "reason": "These concern different training utilities: one drops labels in gather_for_metrics, the other misnormalizes auxiliary loss." + "reason": "Both affect training/metrics behavior, but the label-batching bug and auxiliary-loss normalization bug are distinct." }, { - "left": "issue:42907", - "right": "issue:43441", + "left": "issue:44112", + "right": "issue:44964", "accept": false, - "reason": "Both are about Ministral/Devstral families, but saving dequantized weights and FlashAttention model loading are distinct problems." + "reason": "A GraniteSpeech CI test failure and a GLM-4.7 model-loading issue are unrelated." }, { - "left": "issue:44112", - "right": "issue:44964", + "left": "issue:42907", + "right": "issue:43441", "accept": false, - "reason": "A stale GraniteSpeech CI test and a Phi-4 multimodal loading failure are unrelated." + "reason": "Both mention Ministral models, but saving dequantized checkpoints and FlashAttention loading are different problems." }, { "left": "issue:43295", "right": "issue:45335", "accept": false, - "reason": "Both are regressions, but one is about processor.tokenizer/image handling in custom multimodal code and the other is resize_token_embeddings not updating decoder embeddings." + "reason": "Processor/tokenizer regressions and t5gemma embedding resizing are different code paths." }, { "left": "issue:43854", "right": "issue:44964", "accept": false, - "reason": "Both are model-load failures, but they involve different models and different root causes." + "reason": "Different models and different unit-test loading failures; not duplicates." }, { "left": "issue:44016", "right": "issue:44220", "accept": false, - "reason": "A notebook syntax error and an audio feature-extraction bug are unrelated." + "reason": "Notebook syntax error versus audio feature extraction bug; unrelated." }, { "left": "issue:43673", "right": "issue:44336", "accept": false, - "reason": "Chunked-prefill cache handling and ANSI coloring in loading_report are unrelated." + "reason": "Chunked-prefill cache regression and ANSI color output in loading_report are unrelated." }, { "left": "issue:44496", "right": "issue:45042", "accept": false, - "reason": "An unrecognized OLMo model config and a PIL/torchvision dependency regression are different issues." + "reason": "Model config loading failure and PIL backend torchvision requirement are unrelated." }, { "left": "issue:43299", "right": "issue:45216", "accept": false, - "reason": "Both involve Qwen3.5/Qwen3VL regressions, but one is a loading failure for MoE models and the other is an incorrect save_pretrained checkpoint layout; different code paths." + "reason": "Both involve Qwen models, but one is a loading regression and the other is an incorrect saved checkpoint." }, { "left": "issue:43531", "right": "issue:45600", "accept": false, - "reason": "Sliding_window behavior for Qwen3-MoE and removed auto_mappings references for Sam3LiteText are unrelated." + "reason": "Qwen3-MoE sliding-window behavior and stale auto_mappings references are unrelated." }, { "left": "issue:43526", "right": "issue:43901", "accept": false, - "reason": "One is an image-processor label reduction bug, the other is a docs/behavior mismatch in text classification; not the same bug." + "reason": "BEiT label reduction bug and text-classification docs mismatch are different issues." }, { "left": "issue:42175", "right": "issue:44279", "accept": false, - "reason": "A missing TensorFlow backend in the torch extra and a generic dependency issue are too vague and not the same concrete failure." + "reason": "A missing tensorflow backend extra and a generic dependency issue are not the same bug." }, { "left": "issue:45335", "right": "issue:45584", "accept": false, - "reason": "These are different functional areas: embedding resize behavior vs Whisper generation after token alignment." + "reason": "Embedding resize behavior and Whisper empty-transcription generation failure are unrelated." }, { "left": "issue:44075", "right": "issue:44368", "accept": false, - "reason": "Optimizer argument handling and a warning about tie_word_embeddings in Qwen fine-tuning are unrelated." + "reason": "Optimizer arguments being ignored and a tie_word_embeddings warning are unrelated." }, { "left": "issue:43381", "right": "issue:45593", "accept": false, - "reason": "Gradient checkpointing in eval mode and missing auxiliary losses in D-FINE are different training bugs." + "reason": "Gradient checkpointing in eval mode and D-FINE auxiliary-loss handling are different training bugs." }, { "left": "issue:43299", "right": "issue:45357", "accept": false, - "reason": "Both are Qwen3.5/Qwen3VL regressions, but the reported failures are different: loading vs incorrect save_pretrained output." + "reason": "Both are Qwen3.5-related regressions, but one is model loading and the other is save_pretrained key serialization." }, { "left": "issue:43901", "right": "issue:44496", "accept": false, - "reason": "TextClassificationPipeline docs/behavior and OLMo model loading have no shared underlying bug." + "reason": "Docs mentioning return_all_scores and an unrecognized model/config error are unrelated." + }, + { + "left": "issue:44496", + "right": "issue:45759", + "accept": false, + "reason": "Both involve config/model instantiation, but one is an unrecognized-model error and the other is missing text_config unwrapping." }, { "left": "issue:44351", "right": "issue:45278", - "accept": true, - "reason": "These look like the same upgrade-induced import/export regression: 45278 is a broad report of many import errors after moving to 5.5.0, and 44351 is a concrete missing-symbol instance (HybridCache)." + "accept": false, + "reason": "A specific HybridCache import error and a broad many-import-errors report are not the same concrete bug." }, { "left": "issue:44016", "right": "issue:44062", "accept": false, - "reason": "Notebook syntax and AddedToken keyword-argument errors are unrelated." + "reason": "Notebook syntax error and AddedToken keyword collision are unrelated." }, { "left": "issue:44242", "right": "issue:45200", "accept": false, - "reason": "Load-balancing loss gating and Gemma 4 mm_token_type_ids defaults are different model/training issues." + "reason": "Load-balancing loss omission and Gemma 4 mm_token_type_ids defaults are different model-training issues." }, { "left": "issue:43388", "right": "issue:43827", "accept": false, - "reason": "Metric label truncation and outdated docs references are unrelated." + "reason": "Metrics tuple-label truncation and pipeline() docs still mentioned after removals are unrelated." }, { "left": "issue:41950", "right": "issue:45020", "accept": false, - "reason": "A pipeline image-processor bug and broad remote_code breakage are both version regressions, but not the same concrete code-path problem." + "reason": "A video-classification pipeline bug and broad remote_code regressions are not the same underlying issue." }, { "left": "issue:43976", "right": "issue:45405", "accept": false, - "reason": "Python version compatibility and an unreleased peft version bump are unrelated." + "reason": "Python version compatibility and an unreleased MIN_PEFT_VERSION bump are unrelated dependency problems." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The cluster summary is grounded in the packet: it correctly treats the set as mostly heterogeneous while identifying a narrow import-regression axis centered on issue:45278. The one accepted soft pair, issue:44351 and issue:45278, is a conservative match on an upgrade-induced import failure theme. The other pairwise rejections are also suitably cautious and do not overclaim shared root causes." - }, - "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 }, @@ -9905,7 +9925,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 31, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -9967,8 +9987,8 @@ "issue:43577|issue:45216", "issue:43479|issue:43525", "issue:41950|issue:45823", - "issue:43299|issue:43854", "issue:44683|issue:45542", + "issue:43299|issue:43854", "issue:44279|issue:45405", "issue:38175|issue:44617", "issue:39692|issue:43901", @@ -9986,19 +10006,19 @@ "issue:43450|issue:44279", "issue:42994|issue:43317", "issue:44261|issue:44263", - "issue:43065|issue:44898", "issue:44466|issue:45276", + "issue:43065|issue:44898", "issue:43650|issue:45290", "issue:43441|issue:44683", "issue:43723|issue:44162", "issue:44623|issue:45397" ], - "prepared_review_unit_hash": "e91c99e1aadaa4b401e935290d8eb83732e108927e85e6ff954de4d07f8b55e7", + "prepared_review_unit_hash": "4dda6bcc98b47429169ef4b5b16f3ba95b424b9dc8bd92267aef8e0104fb3fb1", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -10006,195 +10026,201 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 29, - "serialized_chars": 36323, - "estimated_input_tokens": 9081, - "estimated_eval_tokens": 18418 + "serialized_chars": 36332, + "estimated_input_tokens": 9083, + "estimated_eval_tokens": 18422 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a loose collection of Transformers regression reports around tokenizers/processors, multimodal loading, and save/load behavior, but the soft pairs generally describe different bugs rather than true duplicates.", - "confidence": 0.66, - "canonical_issue_reason": "issue:44462 is the most representative tokenizer-loading regression here: it is concrete, user-facing, and sits near several other tokenizer-related reports without being overly narrow.", + "summary": "This cluster is highly heterogeneous: the soft pairs share broad keywords (tokenizers, multimodal, serialization, attention, loading) but do not appear to be the same underlying bug or change. No soft edge should be merged.", + "confidence": 0.93, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:44462 best captures the cluster\u2019s strongest recurring theme\u2014v5 tokenizer loading/selection regressions\u2014and has the clearest chance of serving as the umbrella issue for related tokenizer bugs.", + "best_issue_reason": "issue:44462 is the most concrete and self-contained user-facing bug in the set (AutoTokenizer ignoring repository tokenizer.json), but it does not represent the rest of the cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43824", "right": "issue:44933", "accept": false, - "reason": "Both are import/load problems in the multimodal/image stack, but one is a missing Qwen2.5-VL symbol and the other is a nonexistent image_utils import; different concrete failures." + "reason": "Both are import errors, but one is a missing Qwen2.5-VL export and the other is a nonexistent image_utils import; different code paths." }, { "left": "issue:43577", "right": "issue:45216", "accept": false, - "reason": "Both involve save/load serialization, but BLIP2 dtype handling and Qwen3.5 checkpoint corruption are different bugs in different code paths." + "reason": "Both involve saving/loading dtype or checkpoints, but Blip2 dtype casting and Qwen3.5 save_pretrained corruption are distinct failures." }, { "left": "issue:43479", "right": "issue:43525", "accept": false, - "reason": "One is default multimodal config initialization from None, the other is a missing pad_token_id attribute; related configuration surface, not the same defect." + "reason": "Both are config initialization issues, but one concerns multimodal vision/audio defaults and the other a missing Llama4 pad_token_id." }, { "left": "issue:41950", "right": "issue:45823", "accept": false, - "reason": "Video-classification processor lookup and Gemma4 PLE device mismatch are unrelated failures despite both being pipeline/model issues." + "reason": "Video-classification processor selection and Gemma4 device placement are unrelated bugs." }, { - "left": "issue:43299", - "right": "issue:43854", + "left": "issue:44683", + "right": "issue:45542", "accept": false, - "reason": "Both are model-loading failures, but they concern different models and different breakpoints." + "reason": "One is a torch flex_attention compile regression; the other is a TensorBoard/TensorFlow dependency issue." }, { - "left": "issue:44683", - "right": "issue:45542", + "left": "issue:43299", + "right": "issue:43854", "accept": false, - "reason": "Compiled flex_attention on torch>=2.9 and tensorboard/TensorFlow backend detection are unrelated." + "reason": "Both are model-loading problems, but Qwen3VL MOE loading and GLM-4.7-Flash loading fail for different reasons." }, { "left": "issue:44279", "right": "issue:45405", "accept": false, - "reason": "A vague dependency issue and a specific PEFT version bump problem are not the same bug." + "reason": "A vague dependency complaint vs. a specific PEFT minimum-version bump; not the same change." }, { "left": "issue:38175", "right": "issue:44617", "accept": false, - "reason": "Unexpected zero probabilities in SigLIP2 and CUDA OOM in Sam3Video are clearly different problems." + "reason": "SigLIP2 zero probabilities and Sam3Video OOM are unrelated runtime issues." }, { "left": "issue:39692", "right": "issue:43901", "accept": false, - "reason": "SigLIP2 doc example errors and TextClassificationPipeline docs mismatch are documentation issues in different areas, not duplicates." + "reason": "Both mention docs, but one is a SigLIP2 example failure and the other is a pipeline docs/behavior mismatch." }, { "left": "issue:32090", "right": "issue:35141", "accept": false, - "reason": "Trainer GPU broadcast of NoneType and embedding reinitialization after resize_token_embeddings are distinct model/training bugs." + "reason": "Trainer GPU broadcast TypeError and embedding reinitialization after resize are different model-training bugs." }, { "left": "issue:43295", "right": "issue:44779", "accept": false, - "reason": "A regression in custom model code using processor.tokenizer/images and Deepseek tokenizer output corruption are different tokenizer-facing failures." + "reason": "Both are tokenizer regressions, but one is processor/tokenizer API breakage in v4.57.5 and the other is DeepSeek tokenization output corruption." }, { "left": "issue:44462", "right": "issue:45081", "accept": false, - "reason": "Ignoring tokenizer.json during AutoTokenizer loading is not the same as Mistral regex patch crashing on backend_tokenizer access." + "reason": "Both concern tokenizer loading, but one ignores tokenizer.json and the other crashes while patching Mistral regex." }, { "left": "issue:44297", "right": "issue:44462", "accept": false, - "reason": "Tokenizer class metadata written by save_pretrained and repository tokenizer.json selection are related serialization/loading topics but separate bugs." + "reason": "Both touch tokenizer serialization/loading, but tokenizer_class metadata mismatch is not the same as AutoTokenizer ignoring repository tokenizer.json." }, { "left": "issue:41950", "right": "issue:43650", "accept": false, - "reason": "Video-classification processor lookup and a nonspecific 'ADD THE DATA' issue are unrelated." + "reason": "Video pipeline processor lookup and an unrelated placeholder issue are not the same bug." }, { "left": "issue:43976", "right": "issue:44279", "accept": false, - "reason": "Python version support for Transformers 5.1.0 and a dependency issue are not the same underlying defect." + "reason": "Python version compatibility and a dependency issue are different problems." }, { "left": "issue:43976", "right": "issue:44987", "accept": false, - "reason": "Python compatibility and loading physical-intelligence/fast are different issues." + "reason": "Python version support and a model-loading failure on transformers>=5.1.0 are unrelated." }, { "left": "issue:45600", "right": "issue:45712", "accept": false, - "reason": "Broken auto_mappings references to Sam3LiteText configs and leftover dummy classes are different cleanup/CI problems." + "reason": "Both are repo hygiene/CI problems, but removed Sam3LiteText references and leftover dummy classes are separate cleanup tasks." }, { "left": "issue:44462", "right": "issue:44779", "accept": false, - "reason": "AutoTokenizer ignoring tokenizer.json and Deepseek tokenizer producing wrong results are both tokenizer regressions, but they affect different models and mechanisms." + "reason": "Both involve tokenizers, but one is repository file precedence and the other is DeepSeek tokenization correctness." }, { "left": "issue:44521", "right": "issue:45325", "accept": false, - "reason": "Assistant masks being all-zero in multimodal chat templates is unrelated to Qwen2.5-VL rope index scaling." + "reason": "Both are multimodal/vision-adjacent, but assistant mask generation and rope index temporal scaling are different code paths." }, { "left": "issue:43441", - "right": "issue:45834", + "right": "issue:44683", "accept": false, - "reason": "FlashAttention failure in Ministral-3 and Kosmos2.5 OCR long-input index error are different model-specific runtime bugs." + "reason": "Both are attention-kernel related, but Ministral-3 flash-attention failure and compiled flex_attention torch>=2.9 regression are distinct." }, { "left": "issue:43450", "right": "issue:44279", "accept": false, - "reason": "Incorrect batched video processor output shape and a generic dependency issue are unrelated." + "reason": "Video processor batching shape bug and a dependency complaint are unrelated." }, { "left": "issue:42994", "right": "issue:43317", "accept": false, - "reason": "Quantized model saving failure and dequantized model loading with device_map=auto are different quantization lifecycle bugs." + "reason": "Both involve quantization/offload, but save failure and dequantized model loading failure are different phases and bugs." }, { "left": "issue:44261", "right": "issue:44263", "accept": false, - "reason": "Missing rms_norm_eps in MLA q_a_layernorm and torch.split return values in GlmMoeDsaIndexer are distinct math/indexing problems." + "reason": "One is a missing config field causing precision drift; the other is torch.split return handling in a different model." }, { - "left": "issue:43065", - "right": "issue:44898", + "left": "issue:44466", + "right": "issue:45276", "accept": false, - "reason": "Dummy Conv2d in Sam3PixelDecoder and Perceiver non-default-resolution classification failure are unrelated vision-model bugs." + "reason": "Both concern weight/embedding serialization, but device-dependent lm_head saving and resize_token_embeddings not updating Gemma4 outputs are separate issues." }, { - "left": "issue:44466", - "right": "issue:45276", + "left": "issue:43065", + "right": "issue:44898", "accept": false, - "reason": "Inconsistent lm_head.weight serialization and Gemma4 resize_token_embeddings not updating embeddings are both weight/resize issues, but they are different model families and code paths." + "reason": "Dummy Conv2d cleanup and Perceiver non-default resolution failure are unrelated." }, { "left": "issue:43650", "right": "issue:45290", "accept": false, - "reason": "A placeholder issue and chat template crashes with tool-call assistant messages are not duplicates." + "reason": "An unclear placeholder issue and apply_chat_template crashing on tool-call messages are unrelated." }, { - "left": "issue:43441", - "right": "issue:44683", + "left": "issue:43723", + "right": "issue:44162", "accept": false, - "reason": "Ministral FlashAttention failure and compiled flex_attention failing on torch>=2.9 are both attention-related but clearly separate failure modes." + "reason": "AutoTokenizer v5 loading regression and ESM2 breakage are different failures." }, { - "left": "issue:43723", - "right": "issue:44162", + "left": "issue:45600", + "right": "issue:45712", "accept": false, - "reason": "Tokenizer loading regression in v5 and ESM2 broken workflow are unrelated." + "reason": "Both are CI/repo-check issues, but stale auto_mappings refs and dummy pt objects are separate files/bugs." }, { "left": "issue:44623", "right": "issue:45397", "accept": false, - "reason": "Missing processor.save_pretrained files and Gemma4 zero3 from_pretrained are different save/load issues." + "reason": "processor.save_pretrained missing files and gemma-4 zero3 from_pretrained are different save/load paths." + }, + { + "left": "issue:45834", + "right": "issue:43441", + "accept": false, + "reason": "Kosmos2.5 OCR indexing and Ministral-3 FlashAttention failure are unrelated." } ] }, @@ -10210,7 +10236,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 32, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -10278,9 +10304,9 @@ "issue:43122|issue:43650", "issue:44016|issue:44291", "issue:43262|issue:44521", - "issue:43673|issue:43761", "issue:44188|issue:44336", "issue:43525|issue:43881", + "issue:43673|issue:43761", "issue:44297|issue:45397", "issue:43450|issue:44617", "issue:43525|issue:43643", @@ -10296,12 +10322,12 @@ "issue:44246|issue:44496", "issue:41950|issue:44220" ], - "prepared_review_unit_hash": "d0520b907a9db231559c86ca2e314ba0215eb2d8ea5319e55ab533e30ddd6a50", + "prepared_review_unit_hash": "6ba5b88c9f7d719af61ee86d73d52f58108797bea66aba4c97ae39f9e3924f51", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -10309,7 +10335,7 @@ "node_count": 47, "item_count": 47, "soft_pair_count": 28, - "serialized_chars": 35153, + "serialized_chars": 35155, "estimated_input_tokens": 8789, "estimated_eval_tokens": 17834 }, @@ -10318,180 +10344,180 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a grab bag of unrelated Transformers issues across tokenization, model loading, processors, docs, and performance. None of the proposed soft pairs look like the same underlying bug/change; they are at best loosely similar by subsystem or version.", - "confidence": 0.92, - "canonical_issue_reason": null, + "summary": "These items are mostly unrelated bug reports spanning different models, pipelines, tokenizers, and docs; none of the soft links is strong enough to treat as a true duplicate pair.", + "confidence": 0.87, + "canonical_issue_reason": "issue:44521 is the strongest canonical issue: it is a clear, currently open, user-facing regression in a broadly used multimodal API with concrete repro details.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44521 is the strongest standalone report: it describes a concrete, reproducible multimodal chat-template regression with broader user impact than the more niche or vague reports here.", + "best_issue_reason": "issue:44521 is the best single issue to anchor the cluster because it is specific, well-described, and has the clearest practical impact among the listed issues.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44623", "right": "issue:44749", "accept": false, - "reason": "Processor save/load files regression vs a tokenization slowdown report; different symptoms and code paths." + "reason": "Different bugs: processor save_pretrained file generation vs a token-filtering slowdown regression." }, { "left": "issue:43653", "right": "issue:45593", "accept": false, - "reason": "BigBirdTokenizer special-token registration bug vs D-FINE auxiliary-loss behavior; unrelated models and failures." + "reason": "Tokenizer special-token registration/empty decode is unrelated to D-FINE auxiliary loss behavior." }, { "left": "issue:44671", "right": "issue:44779", "accept": false, - "reason": "Different tokenizer/model correctness bugs affecting different model families; not the same underlying defect." + "reason": "Both are v5 regressions, but one is CamemBERT MLM quality and the other is DeepSeek tokenization; different code paths and symptoms." }, { "left": "issue:43784", "right": "issue:45542", "accept": false, - "reason": "Import-time NameError in sentence-transformers integration vs TensorFlow backend detection issue; unrelated." + "reason": "Import-time NameError in sentence-transformers is unrelated to TensorFlow backend detection when only tensorboard is installed." }, { "left": "issue:44016", "right": "issue:45823", "accept": false, - "reason": "Notebook syntax error vs Gemma4 device-mismatch runtime bug; completely different problem types." + "reason": "Notebook syntax error and Gemma4 device-map mismatch are unrelated." }, { "left": "issue:44361", "right": "issue:45593", "accept": false, - "reason": "MLukeTokenizer task AttributeError vs D-FINE auxiliary-loss omission; unrelated subsystems." + "reason": "MLukeTokenizer task AttributeError does not match D-FINE's missing auxiliary losses." }, { "left": "issue:44987", "right": "issue:45542", "accept": false, - "reason": "Model loading failure for a specific checkpoint vs backend-import error; no shared code-path evidence." + "reason": "Model-loading failure for a specific repo is unrelated to the TensorFlow/tensorboard backend error." }, { "left": "issue:43901", "right": "issue:43994", "accept": false, - "reason": "Docs mismatch about return_all_scores vs a model inference quality bug; not the same issue." + "reason": "Docs mismatch for return_all_scores is not the same as incorrect SigLIP2 model outputs." }, { "left": "issue:43122", "right": "issue:43650", "accept": false, - "reason": "Tokenizer output changed across versions vs a nonsensical placeholder issue title; no technical overlap." + "reason": "Tokenization regression and a placeholder/bodyless issue are not the same underlying bug." }, { "left": "issue:44016", "right": "issue:44291", "accept": false, - "reason": "Notebook syntax error vs init_empty_weights argument mismatch; unrelated." + "reason": "Notebook syntax error is unrelated to the init_empty_weights unexpected argument regression." }, { "left": "issue:43262", "right": "issue:44521", "accept": false, - "reason": "Both touch chat/processor behavior, but one is audio sampling-rate defaulting and the other is multimodal assistant-mask generation; different bugs." - }, - { - "left": "issue:43673", - "right": "issue:43761", - "accept": false, - "reason": "Generation cache/chunked_prefill regression vs CLIPVision hidden_states handling; unrelated models and code paths." + "reason": "Both involve apply_chat_template, but one is an audio sampling-rate default and the other is multimodal assistant mask generation." }, { "left": "issue:44188", "right": "issue:44336", "accept": false, - "reason": "torch.compile attention-kernel divergence vs ANSI escaping in loading_report; unrelated." + "reason": "Torch.compile attention-kernel divergence and ANSI color emission in loading_report are unrelated." }, { "left": "issue:43525", "right": "issue:43881", "accept": false, - "reason": "Missing config attribute on Llama4Config vs GLM-4V loading failure; different model-specific loading issues." + "reason": "Missing pad_token_id on Llama4Config is not the same as glm-4v loading failure." + }, + { + "left": "issue:43673", + "right": "issue:43761", + "accept": false, + "reason": "Generation cache regression and CLIPVision hidden_states regression affect different subsystems and outputs." }, { "left": "issue:44297", "right": "issue:45397", "accept": false, - "reason": "Tokenizer save_pretrained metadata mismatch vs Gemma-4 zero3 from_pretrained failure; unrelated." + "reason": "Tokenizer save metadata mismatch is unrelated to Gemma-4 zero3 loading." }, { "left": "issue:43450", "right": "issue:44617", "accept": false, - "reason": "Incorrect batched video-processor shape vs CUDA OOM; one is a shape bug, the other is resource exhaustion." + "reason": "Batched video processor shape error is not the same as Sam3Video CUDA OOM." }, { "left": "issue:43525", "right": "issue:43643", "accept": false, - "reason": "Missing pad_token_id on one config vs missing fields when trust_remote_code=True; both are config-related but not the same bug." + "reason": "Both mention missing fields/config objects, but one is a specific Llama4Config attribute error and the other is a trust_remote_code AutoConfig field-loss issue." }, { "left": "issue:42491", "right": "issue:43299", "accept": false, - "reason": "Both involve Qwen3 MoE loading, but one is a LoRA compatibility break and the other is base-model loading in v5; too different to merge." + "reason": "Both concern Qwen3 MoE on newer transformers, but one is LoRA compatibility and the other is base model loading; not clearly one concrete bug." }, { "left": "issue:44589", "right": "issue:45362", "accept": false, - "reason": "Float8 storage deserialization error vs Qwen3.5 chat crash; no shared failure mode." + "reason": "Float8 storage deserialization failure is unrelated to Qwen3.5 chat crashes." }, { "left": "issue:41628", "right": "issue:43976", "accept": false, - "reason": "Missing AutoImageProcessor export vs Python-version compatibility regression; unrelated." + "reason": "Importing AutoImageProcessor and Python version compatibility are different issues." }, { "left": "issue:43901", "right": "issue:44246", "accept": false, - "reason": "Documentation mismatch vs slow import performance; different issue classes." + "reason": "Pipeline docs mismatch is unrelated to intermittent import latency." }, { "left": "issue:44336", "right": "issue:44373", "accept": false, - "reason": "ANSI codes in loading_report vs wrong position_ids docstring; unrelated docs/utility issues." + "reason": "ANSI codes in loading_report and a wrong docstring for position_ids are unrelated documentation/formatting issues." }, { "left": "issue:44242", "right": "issue:45593", "accept": false, - "reason": "Load-balancing loss gating bug vs D-FINE auxiliary-loss omission; both are loss-related but not the same architecture or code path." + "reason": "Both are loss-related, but one is router/load-balancing loss and the other is D-FINE auxiliary losses under a different flag." }, { "left": "issue:16998", "right": "issue:22355", "accept": false, - "reason": "Model_max_length question for DeBERTa vs missing transformers.onnx module import; unrelated." + "reason": "Model_max_length behavior and missing transformers.onnx are unrelated." }, { "left": "issue:43352", "right": "issue:45250", "accept": false, - "reason": "Specific model not supporting Flash Attention 2.0 yet vs a generic Flash Attention 2.0 issue; not the same concrete bug." + "reason": "A specific model lacking Flash Attention 2 support is not the same as a generic Flash Attention 2 topic issue." }, { "left": "issue:44295", "right": "issue:45397", "accept": false, - "reason": "position_ids buffer access error vs Gemma-4 zero3 loading failure; unrelated." + "reason": "Position_ids buffer-reading error is unrelated to Gemma-4 zero3 loading." }, { "left": "issue:44246", "right": "issue:44496", "accept": false, - "reason": "Import performance complaint vs unrecognized model/config missing model_type; different failure modes." + "reason": "Slow import timing and unrecognized model/config missing model_type are unrelated." }, { "left": "issue:41950", "right": "issue:44220", "accept": false, - "reason": "Video-classification pipeline using image processors vs _torch_extract_fbank_features() bug; both are pipeline/helper issues but not the same defect." + "reason": "Video-classification processor choosing image processors and _torch_extract_fbank_features are different pipeline bugs." } ] }, @@ -10507,7 +10533,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 33, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -10526,6 +10552,7 @@ "issue:43526", "issue:43540", "issue:43596", + "issue:43653", "issue:43673", "issue:43824", "issue:43901", @@ -10593,216 +10620,223 @@ "issue:43262|issue:44246", "issue:43475|issue:43540", "issue:44466|issue:45335", - "issue:44995|issue:45588" + "issue:44995|issue:45588", + "issue:43653|issue:44162" ], - "prepared_review_unit_hash": "c6642a9653d9ee3307a10ba8b671e78efa09ee5e5fe99163974bc31e10133f7d", + "prepared_review_unit_hash": "b95e49dd3041b7833f5c574a5eb241c46dcf4f4c19de48c3c8b7c421aad9a54a", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 30, - "serialized_chars": 36195, - "estimated_input_tokens": 9049, - "estimated_eval_tokens": 18354 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37092, + "estimated_input_tokens": 9273, + "estimated_eval_tokens": 18802 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is heterogeneous: the paired issues share at most superficial wording (imports, generation, config, embeddings, or model-family names) but describe different failures and code paths. I would not merge any of the soft pairs as duplicates.", - "confidence": 0.95, - "canonical_issue_reason": "No single issue is a true duplicate hub for this cluster; if one must be selected, issue 45292 is the closest generic core-library bug because it concerns a reusable modeling utility regression and has the broadest overlap with nearby embedding-related reports.", + "summary": "The cluster is heterogeneous: the soft pairs span unrelated import errors, model/config regressions, generation issues, tokenizer bugs, and performance reports. I would reject every proposed duplicate edge. If forced to choose a representative issue, the Qwen2.5-VL import regression (#43824) is the strongest anchor because it is a clear core-package import failure with the most discussion/references among the set.", + "confidence": 0.68, + "canonical_issue_reason": "Issue #43824 is the most central, user-facing core-package import regression in this set and has the strongest discussion/reference signal, so it is the best representative anchor.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45292 is the best representative issue only in a loose sense: it is a concrete framework-level bug with a reusable API impact, whereas most other items are model-specific or unrelated. Still, the cluster overall is too mixed for a strong canonical choice.", + "best_issue_reason": "Among these mostly unrelated reports, #43824 is the best duplicate-triage target because it is concrete, broadly impactful, and well-supported by discussion and inbound references.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:36246", "right": "issue:42757", "accept": false, - "reason": "Both are ImportError reports, but for different missing symbols in different packages; unrelated failures." + "reason": "Different missing symbols in different libraries/modules; not the same bug." }, { "left": "issue:36246", "right": "issue:44351", "accept": false, - "reason": "Qwen2.5-VL image processor import failure is unrelated to missing HybridCache export." + "reason": "Qwen import error vs HybridCache import error; unrelated symbols and fixes." }, { "left": "issue:44336", "right": "issue:44485", "accept": false, - "reason": "ANSI color output in loading_report and GLM-5 RoPE implementation are unrelated subsystems and bugs." + "reason": "ANSI/terminal rendering bug vs GLM-5 RoPE discussion; unrelated." }, { "left": "issue:43673", "right": "issue:44561", "accept": false, - "reason": "Chunked-prefill cache handling and removal of is_torch_fx_available are different generation/runtime issues." + "reason": "Generation cache issue vs trust_remote_code import breakage; different code paths." }, { "left": "issue:43824", "right": "issue:43976", "accept": false, - "reason": "Missing Qwen2_5_VLForConditionalGeneration export is unrelated to Python version compatibility." + "reason": "Missing model export vs Python-version support issue; not the same bug." }, { "left": "issue:43976", "right": "issue:44964", "accept": false, - "reason": "Python 3.9/3.10 support mismatch is unrelated to loading Phi-4 multimodal." + "reason": "Python compatibility issue vs Phi-4 multimodal loading failure; unrelated." }, { "left": "issue:44246", "right": "issue:44871", "accept": false, - "reason": "Slow imports and inconsistent eos_token_id configuration are different problems." + "reason": "Import-time slowdown vs Gemma-3 EOS config mismatch; unrelated." }, { "left": "issue:44242", "right": "issue:44857", "accept": false, - "reason": "MoE load-balancing loss logic and LwDetrImageLoss AMP crash do not share the same code path." + "reason": "Router-loss omission vs CUDA AMP crash; different failures." }, { "left": "issue:45362", "right": "issue:45375", "accept": false, - "reason": "Both mention Qwen3.5, but one is a chat crash and the other is a config field being dropped; not the same bug." + "reason": "Qwen chat crash vs missing vision-config field; not the same concrete bug." }, { "left": "issue:44162", "right": "issue:45200", "accept": false, - "reason": "ESM2 breakage and Gemma-4 mm_token_type_ids defaulting are unrelated model-specific issues." + "reason": "ESM2 model breakage vs Gemma 4 token-type default; unrelated." }, { "left": "issue:44295", "right": "issue:44749", "accept": false, - "reason": "Position_ids buffer access error and preprocessing slowdown after upgrade are different failures." + "reason": "Position buffer read error vs performance regression report; unrelated." }, { "left": "issue:44779", "right": "issue:45292", "accept": false, - "reason": "Tokenizer output changes and resize_token_embeddings not updating output embeddings are distinct regressions." + "reason": "Tokenizer correctness bug vs embedding-resize bug; different code paths." }, { "left": "issue:44877", "right": "issue:45375", "accept": false, - "reason": "Strict config rejection for granite_speech is unrelated to the Qwen3_5MoeVisionConfig field-drop bug." + "reason": "Granite config loading vs Qwen vision-config field handling; unrelated." }, { "left": "issue:45292", "right": "issue:45584", "accept": false, - "reason": "Embedding resize propagation and Whisper empty-transcription generation failure are not the same underlying bug." + "reason": "Embedding resize bug vs Whisper empty-transcription failure; unrelated." }, { "left": "issue:45292", "right": "issue:45701", "accept": false, - "reason": "resize_token_embeddings behavior and general tokenization changes across versions are not the same code-path problem." + "reason": "Embedding resize bug vs tokenization-version behavior change; unrelated." }, { "left": "issue:43901", "right": "issue:45003", "accept": false, - "reason": "Pipeline docs mismatch and unsafe sys.modules access are unrelated." + "reason": "Docs mismatch vs sys.modules access bug; unrelated." }, { "left": "issue:45561", "right": "issue:45563", "accept": false, - "reason": "xdist race on captured_info.txt and stale warning in paged generate are separate testing vs generation issues." + "reason": "xdist file race vs stale generation warning; unrelated." }, { "left": "issue:44987", "right": "issue:45459", "accept": false, - "reason": "Model loading failure with transformers>=5.1.0 and tokenizer error masking without protobuf are different bugs." + "reason": "Model loading failure vs protobuf-error masking; unrelated." }, { "left": "issue:36246", "right": "issue:43596", "accept": false, - "reason": "Qwen2.5-VL import error is unrelated to the DeepSpeed ZeRO3 BertModel index error." + "reason": "Qwen import regression vs Bert/ZeRO3 indexing error; unrelated." }, { "left": "issue:43232", "right": "issue:44336", "accept": false, - "reason": "Generation kwargs update after sync_gpus and ANSI codes in loading_report are unrelated." + "reason": "Generation-kwargs bug vs ANSI output bug; unrelated." }, { "left": "issue:43526", "right": "issue:45003", "accept": false, - "reason": "BeitImageProcessorFast label reduction bug is unrelated to sys.modules access in modeling_utils." + "reason": "BEiT label reduction bug vs sys.modules access bug; unrelated." }, { "left": "issue:45375", "right": "issue:45759", "accept": false, - "reason": "Both are about Qwen multimodal configs, but one drops a new field under strict config and the other fails to unwrap text_config from composite configs." + "reason": "Qwen config field issue vs from_config text_config unwrap bug; different fixes." }, { "left": "issue:44496", "right": "issue:45003", "accept": false, - "reason": "Unrecognized model/config loading and unsafe sys.modules access are different load-time issues." + "reason": "Missing model_type for a repo vs sys.modules access bug; unrelated." }, { "left": "issue:43065", "right": "issue:43408", "accept": false, - "reason": "Dummy conv in Sam3PixelDecoder and a sam3_video/sam3_tracker warning are not the same defect." + "reason": "Same SAM3 family, but dummy Conv2d vs wrong model-type warning are different bugs." }, { "left": "issue:43257", "right": "issue:45137", "accept": false, - "reason": "Qwen3 MOE weight conversion under accelerate+deepspeed and ZeRO3 deque underflow are different DeepSpeed problems." + "reason": "Qwen/DeepSpeed loading bug vs ZeRO3 deque error; different code paths." }, { "left": "issue:44995", "right": "issue:45200", "accept": false, - "reason": "GlmMoeDsa stale indexer cache crash and Gemma-4 token-id defaults are unrelated." + "reason": "Stale indexer cache vs Gemma token-type default; unrelated." }, { "left": "issue:43262", "right": "issue:44246", "accept": false, - "reason": "Audio chat-template sampling rate behavior and import slowness are unrelated." + "reason": "Audio chat-template sampling-rate bug vs import slowdown; unrelated." }, { "left": "issue:43475", "right": "issue:43540", "accept": false, - "reason": "Missing fpn_position_embeddings in SAM3 video output and Qwen3OmniMoe video-input ValueError are different bugs." + "reason": "SAM3 output-field bug vs Qwen3OmniMoe video-input error; unrelated." }, { "left": "issue:44466", "right": "issue:45335", "accept": false, - "reason": "Inconsistent serialization of tied weights and resize_token_embeddings not reaching decoder.embed_tokens are different weight-handling issues." + "reason": "Device-dependent serialization vs T5Gemma embedding resize; different issues." }, { "left": "issue:44995", "right": "issue:45588", "accept": false, - "reason": "Stale indexer cache in GlmMoeDsa and flash_attention AttributeError on s_aux=None are different runtime paths." + "reason": "Stale cache bug vs flash-attention s_aux handling; unrelated." + }, + { + "left": "issue:43653", + "right": "issue:44162", + "accept": false, + "reason": "Tokenizer special-token registration bug vs ESM2 model breakage; unrelated." } ] }, @@ -10818,7 +10852,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 34, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -10839,7 +10873,6 @@ "issue:43525", "issue:43643", "issue:43646", - "issue:43653", "issue:43673", "issue:43827", "issue:43931", @@ -10877,7 +10910,6 @@ ], "soft_pairs": [ "issue:42886|issue:45229", - "issue:43653|issue:44162", "issue:44368|issue:45563", "issue:44368|issue:44977", "issue:45397|issue:45656", @@ -10892,15 +10924,15 @@ "issue:43646|issue:44162", "issue:44361|issue:44749", "issue:43232|issue:43673", - "issue:43673|issue:43827", "issue:43452|issue:45003", + "issue:43673|issue:43827", "issue:44623|issue:45656", "issue:28282|issue:30990", "issue:42994|issue:43482", "issue:44749|issue:45310", "issue:44749|issue:45656", - "issue:42371|issue:45092", "issue:43475|issue:43643", + "issue:42371|issue:45092", "issue:43475|issue:45381", "issue:45230|issue:45397", "issue:44038|issue:44623", @@ -10909,226 +10941,220 @@ "issue:45375|issue:45478", "issue:42994|issue:43525" ], - "prepared_review_unit_hash": "852c1418e25fa469c9f2c60fe559407a6afeb135920adbe61dd15aa30fe64976", + "prepared_review_unit_hash": "4046ae5a2a2afd5ac3ab4846fa8b1db659cdd0b86baec027aee28a129e8643dd", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 32, - "serialized_chars": 37218, - "estimated_input_tokens": 9305, - "estimated_eval_tokens": 18866 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "serialized_chars": 36322, + "estimated_input_tokens": 9081, + "estimated_eval_tokens": 18418 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is heterogeneous: most items are distinct Transformers regressions, model-specific loading bugs, or docs/tests issues rather than duplicates. No soft edge looks like the same underlying bug/change.", - "confidence": 0.71, - "canonical_issue_reason": "issue:43646 is the broadest cross-cutting regression here: Transformers 5.0 breaking custom model initialization. It is the best anchor among otherwise unrelated, model-specific reports.", + "summary": "This cluster is heterogeneous: most items are separate Transformers regressions, model-specific loading bugs, or unrelated docs/testing issues rather than true duplicates. No soft pair looks safe to merge as one underlying bug/change.", + "confidence": 0.21, + "canonical_issue_reason": "No single issue cleanly represents a duplicate set here; the cluster spans many distinct code paths and model families.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43646 is the most representative and general issue in the set, with the widest apparent impact on downstream custom models.", + "best_issue_reason": "issue:43646 is the broadest representative of the dominant theme (Transformers v5 breaking custom model initialization), but it is still not a reliable duplicate anchor for the rest of the cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:42886", "right": "issue:45229", "accept": false, - "reason": "Offline tokenizer cache failure and Gemma4 multi-GPU OOM are unrelated bugs." - }, - { - "left": "issue:43653", - "right": "issue:44162", - "accept": false, - "reason": "BigBirdTokenizer special-token decode bug vs. an ESM2 breakage; different code paths and failures." + "reason": "Tokenizer cache/offline loading failure vs multi-GPU inference CUDA OOM; different failure modes and code paths." }, { "left": "issue:44368", "right": "issue:45563", "accept": false, - "reason": "Both mention warnings, but one is a Qwen3.5 LoRA tie-weights warning and the other is a stale generate warning for num_return_sequences." + "reason": "A warning about tie_word_embeddings during Qwen3.5 LoRA fine-tuning is unrelated to a stale paging warning in generate()." }, { "left": "issue:44368", "right": "issue:44977", "accept": false, - "reason": "Qwen3.5 tie-weights warning and flash-attention generation failure are distinct issues." + "reason": "Both mention Qwen3.5, but one is a config warning and the other is a flash-attention generation failure; not the same bug." }, { "left": "issue:45397", "right": "issue:45656", "accept": false, - "reason": "Gemma-4 ZeRO3 from_pretrained failure and a deepspeed double-step bug are not the same bug." + "reason": "Gemma-4 ZeRO3 from_pretrained breakage is unrelated to deepspeed causing optimizer.step to run twice." }, { "left": "issue:44060", "right": "issue:44077", "accept": false, - "reason": "Qwen3-Next tied-weights warning and patchtsmixer post_init compatibility are unrelated." + "reason": "Qwen3-Next tied-weights warning and PatchTSMixer post_init policy are different API/validation issues." }, { "left": "issue:45003", "right": "issue:45561", "accept": false, - "reason": "Unsafe sys.modules access and pytest-xdist race on captured_info.txt are different failures." + "reason": "Unsafe sys.modules access in modeling_utils is unrelated to a pytest-xdist race on captured_info.txt." }, { "left": "issue:43673", "right": "issue:44734", "accept": false, - "reason": "Both are generation/cache-related, but one is a chunked_prefill cache regression and the other is a serve KV-cache indexing crash." + "reason": "GenerationMixin cache handling during chunked_prefill is a different path from serve KV-cache continuation tensor indexing." }, { "left": "issue:45137", "right": "issue:45600", "accept": false, - "reason": "DeepSpeed ZeRO3 deque pop error and a stale auto_mappings reference are unrelated." + "reason": "DeepSpeed ZeRO3 deque underflow is unrelated to stale auto_mappings references to removed configs." }, { "left": "issue:43931", "right": "issue:44368", "accept": false, - "reason": "Qwen3-VL weight-shape mismatch and Qwen3.5 tie-word-embeddings warning are different bugs." + "reason": "Qwen3-VL weight-shape mismatch is a model-loading error, not the LoRA tie_word_embeddings warning." }, { "left": "issue:44933", "right": "issue:45459", "accept": false, - "reason": "Missing image_utils import and tokenizer error masking when protobuf is absent are separate issues." + "reason": "Missing import from image_utils is unrelated to tokenizer error masking when protobuf is absent." }, { "left": "issue:44869", "right": "issue:45356", "accept": false, - "reason": "Whisper word-timestamp decode crash and Kimi-K2.5 tokenizer codec regression are not the same underlying bug." + "reason": "Whisper timestamp decoding crash and Kimi-K2.5 codec handling regression are different tokenizer/decoding bugs." }, { "left": "issue:44297", "right": "issue:44623", "accept": false, - "reason": "Tokenizer save metadata mismatch and processor save missing files affect different save_pretrained paths." + "reason": "tokenizer.save_pretrained writing the wrong class is not the same as processor.save_pretrained missing files." }, { "left": "issue:43646", "right": "issue:44162", "accept": false, - "reason": "Generic custom model initialization breakage is broader, but ESM2 is a separate model-specific regression." + "reason": "Generic custom model initialization breakage vs ESM2-specific failure impacting scientists; too broad and different root causes." }, { "left": "issue:44361", "right": "issue:44749", "accept": false, - "reason": "MLukeTokenizer AttributeError and a multilingual text slowdown regression are unrelated." + "reason": "MLukeTokenizer task AttributeError and a slowdown after upgrade are unrelated issues." }, { "left": "issue:43232", "right": "issue:43673", "accept": false, - "reason": "Different generation internals: sync_gpus update bug vs. chunked_prefill cache regression." + "reason": "Both are generation internals, but one is sync_gpus keyword update and the other is chunked_prefill cache missing; not the same bug." }, { - "left": "issue:43673", - "right": "issue:43827", + "left": "issue:43452", + "right": "issue:45003", "accept": false, - "reason": "Generation cache regression and docs still referencing removed pipeline() API are unrelated." + "reason": "gguf_file breaking AutoTokenizer/AutoModel loading is unrelated to unsafe sys.modules access." }, { - "left": "issue:43452", - "right": "issue:45003", + "left": "issue:43673", + "right": "issue:43827", "accept": false, - "reason": "GGUF loading failures and unsafe sys.modules access are different code paths." + "reason": "Generation cache bug and docs still referencing removed pipeline() are different kinds of changes." }, { "left": "issue:44623", "right": "issue:45656", "accept": false, - "reason": "Processor save regression and deepspeed double optimizer step are unrelated." + "reason": "Missing files from processor.save_pretrained is unrelated to optimizer.step being called twice with deepspeed." }, { "left": "issue:28282", "right": "issue:30990", "accept": false, - "reason": "Missing PyTorch import error and Sentence Transformers loading hang are not the same bug." + "reason": "PyTorch missing ImportError and Sentence Transformers hanging on load are not the same underlying issue." }, { "left": "issue:42994", "right": "issue:43482", "accept": false, - "reason": "Quantized model saving failure and GGUF loading failure are separate quantization-related issues." + "reason": "Quantized model saving failure and Qwen2.5-GGUF loading failure are opposite directions and distinct code paths." }, { "left": "issue:44749", "right": "issue:45310", "accept": false, - "reason": "A slowdown regression after upgrade and a Qwen3.5 Moe from_pretrained error are different failures." + "reason": "Data filtering slowdown after upgrade is unrelated to a Qwen3.5 Moe from_pretrained error." }, { "left": "issue:44749", "right": "issue:45656", "accept": false, - "reason": "Performance regression in data filtering and deepspeed optimizer stepping are unrelated." + "reason": "Performance regression in filtering and deepspeed optimizer duplication are unrelated." }, { - "left": "issue:42371", - "right": "issue:45092", + "left": "issue:43475", + "right": "issue:43643", "accept": false, - "reason": "TF32 settings guidance and remote-code meta-initialization incompatibility are unrelated." + "reason": "SAM3 missing fpn_position_embeddings and trust_remote_code AutoConfig missing fields are different model/config problems." }, { - "left": "issue:43475", - "right": "issue:43643", + "left": "issue:42371", + "right": "issue:45092", "accept": false, - "reason": "SAM3 output attribute error and missing fields in trust_remote_code AutoConfig are different bugs." + "reason": "TF32 settings API guidance is unrelated to InternVL2 remote-code meta-init incompatibility." }, { "left": "issue:43475", "right": "issue:45381", "accept": false, - "reason": "SAM3 vision encoder missing attribute and qwen2.5-vl video position IDs are different model-specific issues." + "reason": "SAM3 video encoder attribute error and Qwen2.5-VL vision_position_ids bug are different model-specific failures." }, { "left": "issue:45230", "right": "issue:45397", "accept": false, - "reason": "Generic bug report placeholder and Gemma-4 ZeRO3 from_pretrained failure are not duplicates." + "reason": "Generic bug report provides no concrete overlap with Gemma-4 ZeRO3 from_pretrained failure." }, { "left": "issue:44038", "right": "issue:44623", "accept": false, - "reason": "Qwen3-VL-Moe v5 breakage and processor.save_pretrained missing files are unrelated." + "reason": "Qwen3-VL-Moe v5 breakage and processor.save_pretrained missing files do not share a concrete code path." }, { "left": "issue:41628", "right": "issue:44933", "accept": false, - "reason": "AutoImageProcessor import failure and a missing image_utils import are similar only superficially; they are different symbols and failure points." + "reason": "Cannot import AutoImageProcessor and nonexistent import from image_utils are similar in surface form only; different symbols/modules." }, { "left": "issue:45081", "right": "issue:45103", "accept": false, - "reason": "Mistral regex/tokenizer backend crash and auto-docstring future-annotations crash are unrelated." + "reason": "Mistral regex patch crashing on tokenizer internals is unrelated to docstring processing with future annotations." }, { "left": "issue:45375", "right": "issue:45478", "accept": false, - "reason": "Missing config field in Qwen3_5MoeVisionConfig and Qwen3.5 Moe from_pretrained error are not the same concrete bug." + "reason": "Qwen3_5MoeVisionConfig missing a field due to @strict and a generic Qwen3.5 Moe from_pretrained error are too weakly connected to treat as the same bug." }, { "left": "issue:42994", "right": "issue:43525", "accept": false, - "reason": "Quantized save failure and Llama4Config missing pad_token_id are different issues." + "reason": "Quantized model saving failure and Llama4Config missing pad_token_id are unrelated model/save vs config issues." } ] }, @@ -11144,7 +11170,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 35, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -11217,9 +11243,9 @@ "issue:44496|issue:45561", "issue:44964|issue:45137", "issue:45561|issue:45600", + "issue:42898|issue:44568", "issue:43901|issue:45561", "issue:43232|issue:44792", - "issue:42898|issue:44568", "issue:30990|issue:35141", "issue:43232|issue:44188", "issue:42898|issue:45812", @@ -11234,12 +11260,12 @@ "issue:44060|issue:45125", "issue:43874|issue:45092" ], - "prepared_review_unit_hash": "cd2428df64605287eabe893b99733196faf47804324479cd473e957e01530f0c", + "prepared_review_unit_hash": "57ed0a7806103e4d8b88608682f21780839d6b2d4cbf5f519420334548ff8b65", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -11247,7 +11273,7 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 31, - "serialized_chars": 37036, + "serialized_chars": 37034, "estimated_input_tokens": 9259, "estimated_eval_tokens": 18774 }, @@ -11256,204 +11282,204 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is mostly a loose collection of unrelated Transformers issues; the only clear duplicate pair is the two identical Qwen3ForCausalLM VRAM-leak reports. Everything else looks like adjacent but distinct bugs, regressions, or docs/test issues.", - "confidence": 0.88, - "canonical_issue_reason": "issue:42673 is the best canonical issue because it is the older of the only exact duplicate pair and the titles/body indicate the same concrete bug as issue:43704.", + "summary": "This cluster is mostly heterogeneous and not a true duplicate group. I only accept one soft edge: the two identically titled Qwen3ForCausalLM VRAM-leak reports. All other pairs describe different code paths, models, or symptoms.", + "confidence": 0.89, + "canonical_issue_reason": "issue:42673 is the original report for the only clear duplicate pair (with issue:43704): same title, same Qwen3ForCausalLM multi-dataloader-thread VRAM leak symptom.", "canonical_pr_reason": null, - "best_issue_reason": "issue:42673 is the best overall representative because it is the clearest duplicate target in the cluster and anchors the only strong same-bug pairing.", + "best_issue_reason": "issue:45310 is the broadest representative of the remaining loose Qwen3.5-MoE subtheme, but it is not a duplicate-safe representative for the whole cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:42673", "right": "issue:43704", "accept": true, - "reason": "Exact same title and same reported VRAM leak in Qwen3ForCausalLM with multiple dataloader threads; these are the same underlying bug." + "reason": "Exact same title and same underlying Qwen3ForCausalLM VRAM leak in multi-dataloader-thread use." }, { "left": "issue:43475", "right": "issue:44661", "accept": false, - "reason": "Different failures: one is a Sam3VisionEncoderOutput attribute error, the other is an auto-mapping/config handling failure for tokenizer mapping names." + "reason": "Different bug classes: SAM 3 vision encoder attribute error vs tokenizer-mapping/config helper failure." }, { "left": "issue:45310", "right": "issue:45375", "accept": false, - "reason": "Both involve Qwen3.5 MoE, but one is a from_pretrained error while the other is a missing config field dropped by strict loading; not the same code-path." + "reason": "Same model family, but different concrete failures: from_pretrained/config loading error vs missing config field being dropped." }, { "left": "issue:41628", "right": "issue:44351", "accept": false, - "reason": "Both are import errors, but for different symbols and likely different export paths; not the same missing-import bug." + "reason": "Both are import errors, but for unrelated symbols and code paths (AutoImageProcessor vs HybridCache)." }, { "left": "issue:42831", "right": "issue:44222", "accept": false, - "reason": "Accuracy with FineGrainedFP8 and FP8 save_pretrained for moe are different problems affecting different code paths." + "reason": "Different FP8 issues: training accuracy regression vs save_pretrained/mode-saving failure." }, { "left": "issue:42222", "right": "issue:45200", "accept": false, - "reason": "VitPose breakage and Gemma 4 mm_token_type_ids defaults are unrelated model-specific bugs." + "reason": "Unrelated models and symptoms: broken vitpose models vs Gemma 4 mm_token_type_ids defaulting." }, { "left": "issue:44222", "right": "issue:45310", "accept": false, - "reason": "Shared MoE/FP8 context is too broad; one is save_pretrained behavior, the other is a from_pretrained error in a different path." + "reason": "One is FP8 save_pretrained for MoE, the other is a Qwen3.5-MoE from_pretrained/config error." }, { "left": "issue:42994", "right": "issue:43824", "accept": false, - "reason": "Quantized model saving failure and missing Qwen2_5_VLForConditionalGeneration import are unrelated issues." + "reason": "Quantized model saving failure and a separate import error for a multimodal class." }, { "left": "issue:42175", "right": "issue:45712", "accept": false, - "reason": "TensorFlow backend packaging and leftover dummy classes are different maintenance/packaging problems." + "reason": "Packaging/backend extra mismatch is unrelated to leftover dummy-class cleanup." }, { "left": "issue:36010", "right": "issue:41628", "accept": false, - "reason": "Both are import-name errors, but for different classes from different modules; not the same missing export." + "reason": "Different missing imports: GenerationMixin vs AutoImageProcessor." }, { "left": "issue:43377", "right": "issue:44242", "accept": false, - "reason": "MIMI padding-mask batching bug and MoE load-balancing loss omission are unrelated model behaviors." + "reason": "Different subsystems: MIMI padding-mask batching bug vs MoE load-balancing-loss gating." }, { "left": "issue:44038", "right": "issue:45310", "accept": false, - "reason": "Different Qwen model families and different failure modes; too broad to be the same underlying bug." + "reason": "Same broad Qwen area, but the reported failures are different and not mergeable into one fix." }, { "left": "issue:44496", "right": "issue:45561", "accept": false, - "reason": "Unrecognized model loading and xdist captured-info race are unrelated." + "reason": "Model config loading error vs pytest-xdist file race; unrelated root causes." }, { "left": "issue:44964", "right": "issue:45137", "accept": false, - "reason": "Phi-4 multimodal load failure and DeepSpeed ZeRO3 deque error are unrelated." + "reason": "Model loading incompatibility and DeepSpeed ZeRO3 deque underflow are unrelated failures." }, { "left": "issue:45561", "right": "issue:45600", "accept": false, - "reason": "A pytest-xdist race on captured_info.txt is not the same as stale auto_mappings references to removed configs." + "reason": "Testing race on captured_info.txt vs stale auto_mappings references; different files and bugs." + }, + { + "left": "issue:42898", + "right": "issue:44568", + "accept": false, + "reason": "Both concern tokenizer behavior, but one is cleanup-space semantics and the other is add_special_tokens not emitting BOS/EOS." }, { "left": "issue:43901", "right": "issue:45561", "accept": false, - "reason": "Documentation mismatch for return_all_scores and xdist worker file race are unrelated." + "reason": "Docs mismatch for text classification pipeline vs a pytest-xdist race bug." }, { "left": "issue:43232", "right": "issue:44792", "accept": false, - "reason": "Generation KV/sync_gpus handling and Janus image-generation test failure are different issues." - }, - { - "left": "issue:42898", - "right": "issue:44568", - "accept": false, - "reason": "Both concern tokenizer behavior in v5, but one is cleanup spacing semantics while the other is BOS/EOS insertion for a specific tokenizer." + "reason": "Generation kwargs/sync-gpus bug and a janus image-generation test failure are not the same code path." }, { "left": "issue:30990", "right": "issue:35141", "accept": false, - "reason": "Sentence Transformers loading stall and token embedding resize reinitialization are unrelated." + "reason": "Sentence-transformers loading stall vs token-embedding reinitialization after resize; unrelated." }, { "left": "issue:43232", "right": "issue:44188", "accept": false, - "reason": "Generation kwargs update after sync_gpus and attention-kernel divergence under torch.compile are different code paths." + "reason": "Generation-kwargs update bug vs attention-kernel divergence under torch.compile are different issues." }, { "left": "issue:42898", "right": "issue:45812", "accept": false, - "reason": "Different tokenizer regressions affecting different behaviors and models." + "reason": "Tokenizer cleanup behavior change is separate from Granite token-ID regression." }, { "left": "issue:44188", "right": "issue:44373", "accept": false, - "reason": "Attention kernel branching bug and docstring typo/mismatch for position_ids are unrelated." + "reason": "Kernel branching bug vs a wrong docstring; no shared bug or fix." }, { "left": "issue:43784", "right": "issue:43824", "accept": false, - "reason": "Sentence-transformers import NameError and missing Qwen2.5-VL class import are different import failures." + "reason": "Both are import-related, but they affect different packages/symbols and stem from different causes." }, { "left": "issue:44623", "right": "issue:45310", "accept": false, - "reason": "Processor save_pretrained file emission and Qwen3.5 MoE from_pretrained error are separate failures." + "reason": "Processor save_pretrained missing files is unrelated to Qwen3.5-MoE loading errors." }, { "left": "issue:43278", "right": "issue:45137", "accept": false, - "reason": "Embedding dtype drift in evaluate and DeepSpeed ZeRO3 deque underflow are unrelated." + "reason": "Embedding dtype drift during eval and a ZeRO3 deque IndexError are unrelated." }, { "left": "issue:44734", "right": "issue:45103", "accept": false, - "reason": "KV cache continuation crash in serve and auto_docstring crash with future annotations are different subsystems." + "reason": "Serve KV-cache indexing crash vs auto_docstring AttributeError under future annotations; different subsystems." }, { "left": "issue:30333", "right": "issue:33290", "accept": false, - "reason": "MLflow reporting on failed training jobs and OOM with adafactor in deepspeed are unrelated." + "reason": "MLflow reporting after failed training job vs DeepSpeed OOM during Adafactor are unrelated." }, { "left": "issue:43723", "right": "issue:44568", "accept": false, - "reason": "General tokenizer loading issue and a specific add_special_tokens/BOS-EOS regression are not the same bug." + "reason": "Tokenizer loading regression in v5 and missing BOS/EOS with add_special_tokens are different failures." }, { "left": "issue:42898", "right": "issue:45356", "accept": false, - "reason": "Different tokenizer regressions: cleanup spacing behavior versus codec handling and warning text for Kimi-K2.5." + "reason": "Different tokenizer regressions: clean_up_tokenization_spaces behavior vs Kimi codec/regex handling." }, { "left": "issue:44060", "right": "issue:45125", "accept": false, - "reason": "Incorrect tied-weights warning and missing tensor-parallel plan are unrelated Qwen3.5/Moe issues." + "reason": "Different Qwen3.5-MoE config bugs: incorrect tied-weights warning vs missing _tp_plan for tensor parallelism." }, { "left": "issue:43874", "right": "issue:45092", "accept": false, - "reason": "Missing image-patch counting method and meta-init incompatibility for InternVL2 are different multimodal loading problems." + "reason": "Multimodal image-patch counting bug and remote-code meta-init incompatibility are not the same issue." } ] }, "evaluator_result": { "accept": true, - "feedback": "The writeup is grounded in the packet: the only clearly supported duplicate pair is issue:42673 \u2194 issue:43704, which do have identical titles and matching VRAM-leak descriptions. The remaining pair judgments stay conservative and do not overclaim equivalence based on broad thematic similarity alone. " + "feedback": "Grounded overall. The canonical duplicate pair (issue:42673 / issue:43704) is well supported by the packet: identical title and matching VRAM-leak symptom. The remaining soft-edge rejections are conservative and stay within the evidence shown in the issue titles/descriptions. The summary correctly characterizes the cluster as mostly heterogeneous and avoids overstating duplicate evidence." }, "evaluator_used": true, "retried": false, @@ -11466,7 +11492,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 36, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -11528,9 +11554,9 @@ "issue:45405|issue:45712", "issue:42898|issue:44448", "issue:44188|issue:44964", - "issue:44295|issue:45656", - "issue:43479|issue:44079", "issue:44933|issue:45712", + "issue:43479|issue:44079", + "issue:44295|issue:45656", "issue:42175|issue:44933", "issue:44222|issue:44297", "issue:43976|issue:44933", @@ -11546,8 +11572,8 @@ "issue:43723|issue:44977", "issue:44222|issue:44484", "issue:44297|issue:45310", - "issue:43873|issue:44945", "issue:28282|issue:30333", + "issue:43873|issue:44945", "issue:30333|issue:35141", "issue:44263|issue:45092", "issue:44263|issue:44360", @@ -11556,16 +11582,16 @@ "issue:44514|issue:45103", "issue:44295|issue:44623", "issue:43479|issue:43644", - "issue:44261|issue:45092", "issue:43723|issue:44871", - "issue:45092|issue:45357" + "issue:45092|issue:45357", + "issue:44261|issue:45092" ], - "prepared_review_unit_hash": "34e8d5637beb7c0e9b9c38ec411cf49564020d061a571554407fa99967276cbb", + "prepared_review_unit_hash": "4f6a9ddb6b63efaaab7190afc3b8417dbd9ab1fd4216c19bee7bfe44c122c11c", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -11573,231 +11599,231 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 35, - "serialized_chars": 38020, - "estimated_input_tokens": 9505, - "estimated_eval_tokens": 19266 + "serialized_chars": 38022, + "estimated_input_tokens": 9506, + "estimated_eval_tokens": 19268 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a loose topical grouping of unrelated Transformers issues (tokenizers, save/load, model loading, training, backend imports, docs, and assorted regressions). None of the soft pairs look like the same underlying defect, so I reject all merges.", - "confidence": 0.82, - "canonical_issue_reason": "issue:44297 is the most concrete, self-contained bug report in the set (tokenizer.save_pretrained writes a mismatched tokenizer_class), so it is a reasonable anchor if one issue must represent the cluster.", + "summary": "The items are a mixed set of unrelated issues rather than one duplicate cluster. None of the soft pairs look like the same underlying bug/change, so all are rejected. #43873 is the best issue anchor because it is an active, concrete bug report with multiple references, but the set overall is heterogeneous.", + "confidence": 0.79, + "canonical_issue_reason": "#43873 is the most active open bug report in the set, with the strongest inbound discussion signal and a concrete runtime-failure focus, so it is the best anchor among these mixed issues.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44297 is the clearest actionable report here: specific failure mode, specific API, and easier to triage than the broader version-wide or import-related regressions.", + "best_issue_reason": "#43873 has the broadest relevance and highest activity among the issues here; the rest are narrower, model- or component-specific regressions.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:42898", "right": "issue:44779", "accept": false, - "reason": "Both are tokenizer-related, but one is a v5 cleanup-space behavior change and the other is a Deepseek tokenization regression; different code paths and symptoms." + "reason": "Both involve tokenizer behavior in v5, but one is about `clean_up_tokenization_spaces` semantics and the other is a DeepSeek tokenizer correctness regression." }, { "left": "issue:45405", "right": "issue:45712", "accept": false, - "reason": "Unrelated: a dependency version bump vs leftover dummy classes leaking into dir() and repo checks." + "reason": "One is a dependency version bump (`MIN_PEFT_VERSION`), the other is cleanup of dummy torch objects; different problems and fixes." }, { "left": "issue:42898", "right": "issue:44448", "accept": false, - "reason": "One is a tokenizer cleanup-space behavior change; the other is a model output drift report for Pegasus. Same broad area, not the same bug." + "reason": "Both are version-regression reports, but they target different behaviors: token cleanup vs Pegasus output drift." }, { "left": "issue:44188", "right": "issue:44964", "accept": false, - "reason": "Attention-kernel branching under torch.compile vs a Phi-4 multimodal model-loading failure are different defects." + "reason": "One is a torch.compile attention-kernel branching bug; the other is a Phi-4 multimodal loading failure. Unrelated code paths." }, { - "left": "issue:44295", - "right": "issue:45656", + "left": "issue:44933", + "right": "issue:45712", "accept": false, - "reason": "A position_ids buffer-read issue is unrelated to deepspeed calling optimizer.step() twice." + "reason": "Both mention imports, but one is a missing symbol from `image_utils` and the other is stray dummy classes leaking into `dir(transformers)`." }, { "left": "issue:43479", "right": "issue:44079", "accept": false, - "reason": "Config initialization bug for Phi4MultimodalConfig vs ModelOutput key assignment bug; distinct objects and failure modes." + "reason": "Both mention `None`, but one is multimodal config initialization and the other is `ModelOutput` key assignment. Different classes and failures." }, { - "left": "issue:44933", - "right": "issue:45712", + "left": "issue:44295", + "right": "issue:45656", "accept": false, - "reason": "Import from image_utils vs leftover dummy class leakage; different modules and errors." + "reason": "One concerns reading a registered buffer; the other is double optimizer stepping under deepspeed. Not the same bug." }, { "left": "issue:42175", "right": "issue:44933", "accept": false, - "reason": "Packaging/backend omission with pip install .[torch] vs a missing/nonexistent image_utils import." + "reason": "Different import/package issues: backend extras missing TensorFlow vs a nonexistent image_utils import." }, { "left": "issue:44222", "right": "issue:44297", "accept": false, - "reason": "Both mention save_pretrained, but one is FP8 MoE persistence and the other is tokenizer config metadata; not the same bug." + "reason": "One is FP8 save_pretrained for MoE models; the other is tokenizer config serialization. Same broad area only superficially." }, { "left": "issue:43976", "right": "issue:44933", "accept": false, - "reason": "Python 3.9/3.10 compatibility regression vs an image_utils import failure; unrelated." + "reason": "A Python-version compatibility issue and a missing import are unrelated failures." }, { - "left": "issue:43479", - "right": "issue:44869", + "left": "issue:43232", + "right": "issue:45834", "accept": false, - "reason": "Config default initialization vs Whisper word-timestamp decode crash; different subsystems." + "reason": "One is generation-state handling after `sync_gpus`; the other is an OCR index error in Kosmos2.5. Different code paths." }, { - "left": "issue:44297", - "right": "issue:45656", + "left": "issue:43723", + "right": "issue:44977", "accept": false, - "reason": "Tokenizer save metadata mismatch vs deepspeed optimizer double-step; no shared code path." + "reason": "Both are model/tokenizer generation problems, but one is AutoTokenizer loading in v5 and the other is flash-attention generation behavior for Qwen3.5." }, { "left": "issue:44206", "right": "issue:45103", "accept": false, - "reason": "Feature extractor center-arg regression vs auto_docstring annotation crash; unrelated areas." + "reason": "One is a feature extractor argument regression; the other is an auto_docstring crash from future annotations. Not the same underlying bug." }, { "left": "issue:44222", "right": "issue:44623", "accept": false, - "reason": "FP8 save_pretrained on MoE models vs processor.save_pretrained missing files; same broad save API, different concrete defects." + "reason": "Both touch save_pretrained, but one is MoE FP8 serialization and the other is missing processor files." }, { "left": "issue:42831", "right": "issue:44623", "accept": false, - "reason": "FP8 accuracy problem vs missing processor files on save; not the same failure." + "reason": "Accuracy drift from FineGrainedFP8 is unrelated to missing processor artifacts during save_pretrained." }, { "left": "issue:41628", "right": "issue:42757", "accept": false, - "reason": "Different missing imports: AutoImageProcessor vs is_offline_mode." + "reason": "Both are import errors, but they concern different missing symbols from different modules and likely different fixes." }, { "left": "issue:30333", "right": "issue:36331", "accept": false, - "reason": "MLflow reporting after failed training jobs vs a Trainer compute_loss signature mismatch." + "reason": "Training-job reporting/MLflow tracking is unrelated to a Trainer API signature change." }, { "left": "issue:30333", "right": "issue:34689", "accept": false, - "reason": "Training-job reporting/MLflow issue vs Llama 3.2 vision model-loading regression." + "reason": "MLflow reporting on failed jobs and model loading breakage in Transformers 4.46.2 are different issues." }, { "left": "issue:43232", "right": "issue:45834", "accept": false, - "reason": "Generation kwarg handling after sync_gpus vs long OCR input index error; different models and code paths." + "reason": "Same as above: generation kwargs syncing vs long-input OCR indexing are unrelated." }, { "left": "issue:43723", - "right": "issue:44977", + "right": "issue:44871", "accept": false, - "reason": "Tokenizer loading regression in v5 vs Qwen3.5 generation issues with flash-attention." + "reason": "Tokenizer loading in v5 versus an eos_token_id mismatch for Gemma-3 are different bugs." }, { "left": "issue:44222", "right": "issue:44484", "accept": false, - "reason": "FP8 save_pretrained bug vs a question about max_shard_size in save_pretrained; not the same defect." + "reason": "FP8 MoE save_pretrained and the default 50GB shard size are unrelated save_pretrained concerns." }, { "left": "issue:44297", "right": "issue:45310", "accept": false, - "reason": "Tokenizer save_pretrained metadata mismatch vs Qwen3.5 MoE from_pretrained regression; different layers of the stack." + "reason": "Tokenizer-class serialization and a Qwen3.5 MoE from_pretrained regression are different failure modes." }, { - "left": "issue:43873", - "right": "issue:44945", + "left": "issue:28282", + "right": "issue:30333", "accept": false, - "reason": "Quantized offloading behavior vs incorrect pipeline-parallel output; related broad area, but distinct bugs." + "reason": "A missing PyTorch dependency import error is unrelated to MLflow not reflecting failed training jobs." }, { - "left": "issue:28282", - "right": "issue:30333", + "left": "issue:43873", + "right": "issue:44945", "accept": false, - "reason": "PyTorch-missing import error vs MLflow job-reporting problem." + "reason": "Quantization/offloading behavior is unrelated to incorrect LLM output under pipeline parallelism." }, { "left": "issue:30333", "right": "issue:35141", "accept": false, - "reason": "MLflow/reporting issue vs embedding reinitialization after resizing token embeddings." + "reason": "Failed-job MLflow reporting and embedding reinitialization after resizing token embeddings are unrelated." }, { "left": "issue:44263", "right": "issue:45092", "accept": false, - "reason": "torch.split return-value bug in a DSA indexer vs InternVL2 meta-init incompatibility; unrelated." + "reason": "A torch.split return-value issue in an indexer is unrelated to meta-initialization incompatibility for old InternVL2 checkpoints." }, { "left": "issue:44263", "right": "issue:44360", "accept": false, - "reason": "Both touch the DSA indexer, but one is a torch.split shape/return issue and the other is a missing ReLU; same subsystem, different bugs." + "reason": "Both are DSA/indexer-related, but one is about split outputs and the other about a missing ReLU. Different concrete bugs." }, { "left": "issue:44483", "right": "issue:45406", "accept": false, - "reason": "Chat/completions API rejection vs Gemma4Processor missing _tokenizer; distinct failures." + "reason": "A chat/completions request handling issue and a Gemma4Processor missing `_tokenizer` attribute are unrelated." }, { "left": "issue:44373", "right": "issue:44485", "accept": false, - "reason": "Wrong docstring for position_ids vs GLM-5 RoPE implementation; one is documentation, the other is model math." + "reason": "This is a docstring issue, while the other is a RoPE implementation bug. No shared fix." }, { "left": "issue:44514", "right": "issue:45103", "accept": false, - "reason": "Batched chat-template crash vs auto_docstring annotation crash; unrelated functionality." + "reason": "A batched chat-template crash and an auto_docstring AttributeError are unrelated." }, { "left": "issue:44295", "right": "issue:44623", "accept": false, - "reason": "Reading a registered buffer issue vs processor.save_pretrained missing files; different APIs and symptoms." + "reason": "Buffer registration/readback and missing processor files are different save/load problems." }, { "left": "issue:43479", "right": "issue:43644", "accept": false, - "reason": "Phi4Multimodal config defaulting bug vs non-persistent buffers being filled with junk in Transformers 5.0.0." - }, - { - "left": "issue:44261", - "right": "issue:45092", - "accept": false, - "reason": "MLA q_a_layernorm precision/config bug vs old InternVL2 remote-code meta-init incompatibility; not the same underlying defect." + "reason": "Default config initialization for Phi-4 multimodal is unrelated to junk non-persistent buffers in v5.0.0." }, { "left": "issue:43723", "right": "issue:44871", "accept": false, - "reason": "Tokenizer loading failure in v5 vs Gemma-3 eos_token_id configuration mismatch." + "reason": "Tokenizer loading regressions and an eos_token_id config mismatch are not the same bug." }, { "left": "issue:45092", "right": "issue:45357", "accept": false, - "reason": "InternVL2 meta-init compatibility bug vs Qwen3.5 save_pretrained writing incorrect visual encoder keys." + "reason": "Meta-init incompatibility for old checkpoints and incorrect visual encoder keys in `save_pretrained` are distinct regressions." + }, + { + "left": "issue:44261", + "right": "issue:45092", + "accept": false, + "reason": "A missing `rms_norm_eps` in MLA q_a_layernorm causing precision error is unrelated to old InternVL2 meta-init incompatibility." } ] }, @@ -11813,7 +11839,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 37, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -11872,12 +11898,12 @@ "soft_pairs": [ "issue:30990|issue:38175", "issue:41628|issue:43824", - "issue:39401|issue:44568", "issue:43479|issue:44913", + "issue:39401|issue:44568", "issue:22355|issue:28282", "issue:42831|issue:45310", - "issue:42886|issue:42994", "issue:44263|issue:44373", + "issue:42886|issue:42994", "issue:44945|issue:45753", "issue:42757|issue:45278", "issue:42831|issue:44038", @@ -11901,12 +11927,12 @@ "issue:44261|issue:44373", "issue:43408|issue:43475" ], - "prepared_review_unit_hash": "ff07c3af84ba9bd3a9fd71850e6018ee92f5b36966b4109f03d7dfbc1e3cf667", + "prepared_review_unit_hash": "c3ddf83cac4f5aa02788a580a1b214376fc0224cba0acff98899b032c2d11185", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -11914,201 +11940,201 @@ "node_count": 47, "item_count": 47, "soft_pair_count": 30, - "serialized_chars": 35655, - "estimated_input_tokens": 8914, - "estimated_eval_tokens": 18084 + "serialized_chars": 35651, + "estimated_input_tokens": 8913, + "estimated_eval_tokens": 18082 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is a loose collection of mostly unrelated bug reports, with some superficial similarity around imports/tokenizers/model-specific regressions but no single duplicate family.", - "confidence": 0.95, - "canonical_issue_reason": "No clear canonical issue: the items span many distinct subsystems and failure modes, so they do not form one duplicate cluster.", + "summary": "These are mostly unrelated closed issues that only share broad Transformers API/regression wording. The soft pairs are not close enough to be duplicates, so I would reject them all.", + "confidence": 0.71, + "canonical_issue_reason": "issue:45278 is the best umbrella candidate because it broadly covers multiple import regressions after upgrading to v5.5.0 and is still open, making it the most natural central triage point among the listed issues.", "canonical_pr_reason": null, - "best_issue_reason": "If one issue must be highlighted, issue 45278 is the broadest umbrella for upgrade-related import errors, but it still does not represent the whole mixed cluster.", + "best_issue_reason": "issue:45278 is the strongest representative issue for this cluster: it is broad, current, and framed as a generalized import-breakage report rather than a narrow model-specific symptom.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:30990", "right": "issue:38175", "accept": false, - "reason": "Both are model-loading / inference complaints, but they affect different models and different symptoms." + "reason": "Different failure modes: Sentence-Transformers loading hang vs zero-probabilities in SIGLIP2; no shared code-path implied." }, { "left": "issue:41628", "right": "issue:43824", "accept": false, - "reason": "Both are import errors, but for different missing symbols and likely different code paths." + "reason": "Both are import errors, but for different missing symbols/models (`AutoImageProcessor` vs `Qwen2_5_VLForConditionalGeneration`), so they are not the same bug." }, { - "left": "issue:39401", - "right": "issue:44568", + "left": "issue:43479", + "right": "issue:44913", "accept": false, - "reason": "Both are tokenizer issues, but one is offset mapping and the other is special-token insertion behavior." + "reason": "One is config initialization with None for multimodal defaults; the other is a rotary_pct persistence/reload issue in GPTNeoXConfig." }, { - "left": "issue:43479", - "right": "issue:44913", + "left": "issue:39401", + "right": "issue:44568", "accept": false, - "reason": "Different config persistence bugs in different model classes; not the same defect." + "reason": "Tokenizer offset_mapping corruption and missing BOS/EOS insertion are distinct tokenizer behaviors and likely separate fixes." }, { "left": "issue:22355", "right": "issue:28282", "accept": false, - "reason": "One is a missing transformers.onnx module, the other is an AutoModel PyTorch dependency error." + "reason": "`transformers.onnx` missing module and PyTorch-not-found AutoModel import error are different dependency/import issues." }, { "left": "issue:42831", "right": "issue:45310", "accept": false, - "reason": "One is an FP8 accuracy issue, the other is a Qwen3.5 MoE from_pretrained failure." + "reason": "FineGrainedFP8 accuracy concerns and a Qwen3.5-Moe from_pretrained error are unrelated at the code-path level." }, { - "left": "issue:42886", - "right": "issue:42994", + "left": "issue:44263", + "right": "issue:44373", "accept": false, - "reason": "Offline tokenizer cache loading and quantized model saving are unrelated code paths." + "reason": "A torch.split return-value bug in GLM MoE indexing is not the same as a docstring correction for position_ids." }, { - "left": "issue:44263", - "right": "issue:44373", + "left": "issue:42886", + "right": "issue:42994", "accept": false, - "reason": "A tensor-splitting bug and a docstring issue are not the same underlying problem." + "reason": "Offline tokenizer cache loading failure and quantized model saving failure are separate subsystems." }, { "left": "issue:44945", "right": "issue:45753", "accept": false, - "reason": "Pipeline-parallel output corruption and a Qwen3.5 image loop are different model/runtime failures." + "reason": "Pipeline-parallelism output corruption and Qwen3_5 infinite-loop behavior are different runtime bugs with no clear common fix." }, { "left": "issue:42757", "right": "issue:45278", "accept": false, - "reason": "The first is one missing import from huggingface_hub; the second is a broad report of many import errors, but not the same concrete bug." + "reason": "`is_offline_mode` import failure is a specific symbol-level breakage; 45278 is a broader umbrella of many import errors, not the same underlying bug." }, { "left": "issue:42831", "right": "issue:44038", "accept": false, - "reason": "Different model- and version-specific issues with no shared failing code path." + "reason": "Both mention model behavior regressions, but one is FP8 accuracy and the other is Qwen3-VL-Moe compatibility; not the same defect." }, { "left": "issue:43576", "right": "issue:43784", "accept": false, - "reason": "Broken CLI env command and a NameError during sentence-transformers import are different failures." + "reason": "Broken `transformers env` CLI and a sentence-transformers import NameError are unrelated issues." }, { "left": "issue:42886", "right": "issue:43066", "accept": false, - "reason": "Offline cache loading and tokenizer decoder type mismatch are unrelated tokenizer/config bugs." + "reason": "Offline cache loading and wrong tokenizer decoder type in v5 are different parts of the tokenizer stack." }, { "left": "issue:43232", "right": "issue:45593", "accept": false, - "reason": "Generation kwargs handling and D-FINE auxiliary loss behavior are different subsystems." + "reason": "Generation kwargs update after sync_gpus and D-FINE auxiliary loss handling are unrelated code paths." }, { "left": "issue:42371", "right": "issue:44263", "accept": false, - "reason": "TF32 configuration guidance and torch.split return values are unrelated." + "reason": "TF32 settings warning and GLM MoE indexing bug do not describe the same problem." }, { "left": "issue:43756", "right": "issue:44060", "accept": false, - "reason": "Different model architecture/config bugs; same broad family only." + "reason": "Smollm3 RoPE-layer mismatch and Qwen3-Next tied-weights warning are model-specific configuration issues, not duplicates." }, { "left": "issue:44117", "right": "issue:44704", "accept": false, - "reason": "Tokenizer mapping fallback and AutoProcessor cached_file kwargs are different loader issues." + "reason": "TOKENIZER_MAPPING_NAMES returning None and AutoProcessor not passing kwargs to cached_file are different loader bugs." }, { "left": "issue:30990", "right": "issue:33357", "accept": false, - "reason": "Both mention loading/inference, but one is a Sentence Transformers hang and the other is a macOS bus error with a CLIP model." + "reason": "A loading hang in Sentence Transformers and a MacOS bus error with a CLIP model are different symptoms and likely different root causes." }, { "left": "issue:42907", "right": "issue:44945", "accept": false, - "reason": "Quantized model saving and pipeline-parallel output errors are unrelated." + "reason": "Saving dequantized models and incorrect pipeline-parallel outputs are separate functionality failures." }, { "left": "issue:44704", "right": "issue:45290", "accept": false, - "reason": "AutoProcessor kwargs forwarding and chat template tool-call crashing are distinct behaviors." + "reason": "AutoProcessor kwargs propagation and chat template crashes on tool-call assistant messages are unrelated." }, { "left": "issue:43122", "right": "issue:44514", "accept": false, - "reason": "Tokenizer output changes and processor chat-template batching failures do not indicate the same bug." + "reason": "Tokenization drift across versions and batched chat-template crash with padding=False are different tokenizer/processor bugs." }, { "left": "issue:44295", "right": "issue:44297", "accept": false, - "reason": "Reading a registered buffer and saving tokenizer metadata are different serialization issues." + "reason": "Reading a buffer-registered position_ids tensor and saving tokenizer_class mismatch are separate save/load issues." }, { "left": "issue:41628", "right": "issue:45278", "accept": false, - "reason": "One specific missing import is not enough to treat it as the same defect as a broad multi-import regression report." + "reason": "`AutoImageProcessor` import failure is a specific missing export, while 45278 is a broad report of multiple import errors; not the same concrete bug." }, { "left": "issue:43723", "right": "issue:44779", "accept": false, - "reason": "Both involve tokenizer loading/behavior, but they target different failure modes and likely different tokenizer implementations." + "reason": "AutoTokenizer loading failure in v5 and Deepseek tokenizer output regressions are both tokenizer-related but not the same failure mode." }, { "left": "issue:43723", "right": "issue:44442", "accept": false, - "reason": "AutoTokenizer loading failure and a specific FastSpeech2ConformerTokenizer failure are not the same issue." + "reason": "AutoTokenizer load failure for FastSpeech2ConformerTokenizer and a specific tokenizer class loading issue are distinct incompatibilities." }, { "left": "issue:43784", "right": "issue:45600", "accept": false, - "reason": "Sentence-transformers import NameError and stale auto_mappings references break for different reasons." + "reason": "Importing sentence-transformers with NameError and broken auto_mappings references to removed Sam3LiteText configs are unrelated import-time problems." }, { "left": "issue:42907", "right": "issue:43937", "accept": false, - "reason": "Model saving and invalid GenerationConfig validation are unrelated." + "reason": "Quantized model save failure and GLM-5 GenerationConfig validation are different bug classes." }, { "left": "issue:43232", "right": "issue:45245", "accept": false, - "reason": "Generation sync behavior and category-count limits are different code paths." + "reason": "Generation-state update bug and category-count limit runtime error are not the same underlying defect." }, { "left": "issue:44261", "right": "issue:44373", "accept": false, - "reason": "A precision/config bug and a wrong docstring are not duplicates." + "reason": "A missing rms_norm_eps precision issue and a docstring error for position_ids are not duplicates." }, { "left": "issue:43408", "right": "issue:43475", "accept": false, - "reason": "Both touch SAM 3 video, but one is a model-type warning and the other is a missing attribute crash; not clearly the same bug." + "reason": "Wrong model type warning on sam3_tracker instantiation and missing fpn_position_embeddings attribute are separate SAM 3 video issues." } ] }, @@ -12124,7 +12150,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 38, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -12191,8 +12217,8 @@ "issue:44038|issue:44297", "issue:42907|issue:43452", "issue:39401|issue:44488", - "issue:44038|issue:44295", "issue:43824|issue:44351", + "issue:44038|issue:44295", "issue:36296|issue:43116", "issue:44038|issue:44222", "issue:39401|issue:44521", @@ -12202,8 +12228,8 @@ "issue:22355|issue:28218", "issue:42907|issue:44222", "issue:43122|issue:44977", - "issue:43992|issue:44704", "issue:43784|issue:45446", + "issue:43992|issue:44704", "issue:43937|issue:44485", "issue:42222|issue:43441", "issue:42371|issue:43874", @@ -12217,12 +12243,12 @@ "issue:43116|issue:43493", "issue:45083|issue:45446" ], - "prepared_review_unit_hash": "deee57f29e32d9952ddadc204d11b6ac04eca99e944ccf1262d4287023215377", + "prepared_review_unit_hash": "f879cba6393c0337c1dcfc504b973f9cbae1e5ed555e3051064f93d518abccdb", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -12239,229 +12265,208 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly false-positive similarity matches: the items span unrelated tokenizer, model-loading, training, export, and config bugs, so there is no cohesive duplicate cluster.", - "confidence": 0.96, - "canonical_issue_reason": "No single canonical issue fits well; the cluster is heterogeneous and the soft links appear to connect unrelated bugs rather than one underlying defect.", + "summary": "Mostly heterogeneous issue cluster. I only see two plausible duplicate families: tokenizer regressions around v5, and Qwen3.5 save/load regressions around 5.4.0. The rest of the soft pairs point to different subsystems or different failure modes and should stay separate.", + "confidence": 0.66, + "canonical_issue_reason": "issue:43122 is the best anchor for the clearest duplicate family: a broad tokenizer regression between v4.57.3 and v5.0, and it can plausibly subsume the Deepseek tokenizer regression in the accepted pair.", "canonical_pr_reason": null, - "best_issue_reason": "If forced to pick a representative, issue:43122 is the broadest tokenizer-regression report, but it still does not subsume the rest of the cluster.", + "best_issue_reason": "issue:43122 is the strongest overall issue to keep as the representative anchor because it is open, user-facing, and describes a broad v5 tokenizer regression with a clear version comparison.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44360", "right": "issue:44485", "accept": false, - "reason": "Unrelated DSA/indexer discussion versus GLM-5 RoPE implementation." + "reason": "Different topics: DSA indexer/ReLU discussion vs GLM-5 RoPE implementation." }, { "left": "issue:43122", "right": "issue:44521", "accept": false, - "reason": "Tokenizer regression and multimodal assistant-mask bug are different code paths." + "reason": "Tokenizer regression vs multimodal assistant-mask bug; different code paths." }, { "left": "issue:44625", "right": "issue:44829", "accept": false, - "reason": "num_labels propagation issue is unrelated to flash_attention_3 training degeneration." + "reason": "Qwen3.5 num_labels propagation is unrelated to flash_attention_3 training degeneration." }, { "left": "issue:43116", "right": "issue:45200", "accept": false, - "reason": "Example-script classification output bug is unrelated to mm_token_type_ids defaults." + "reason": "Example-script multi-label output issue vs Gemma 4 mm_token_type_ids defaulting." }, { "left": "issue:29127", "right": "issue:30990", "accept": false, - "reason": "LayoutLMv3 error messaging and Sentence Transformers loading hang are unrelated." + "reason": "LayoutLMv3 error-message clarity and sentence-transformers loading are unrelated." }, { "left": "issue:42907", "right": "issue:44964", "accept": false, - "reason": "Save-dequantized failure and Phi-4 multimodal load failure are different problems." + "reason": "Different bugs: dequantized save_pretrained failure vs model loading failure for Phi-4 multimodal." }, { "left": "issue:43122", "right": "issue:44779", - "accept": false, - "reason": "Both are tokenization regressions, but on different models with different symptoms and code paths." + "accept": true, + "reason": "Both describe a v5 tokenizer regression relative to v4 behavior; Deepseek looks like a specific instance of the same changed tokenization path." }, { "left": "issue:44038", "right": "issue:44297", "accept": false, - "reason": "Qwen3-VL-Moe loading failure is unrelated to tokenizer_class metadata saved by save_pretrained." + "reason": "Qwen3-VL-Moe failure vs tokenizer_config save_pretrained class mismatch; not the same bug." }, { "left": "issue:42907", "right": "issue:43452", "accept": false, - "reason": "Dequantized-save bug and gguf_file/pretrained loading bug are not the same defect." + "reason": "Quantized save_pretrained failure and gguf_file from_pretrained breakage are different serialization/loading paths." }, { "left": "issue:39401", "right": "issue:44488", "accept": false, - "reason": "offset_mapping bug and model loading failure are unrelated." + "reason": "Wrong offset_mapping for Qwen3 tokenizer is unrelated to loading cjvt/sleng-bert." }, { - "left": "issue:44038", - "right": "issue:44295", + "left": "issue:43824", + "right": "issue:44351", "accept": false, - "reason": "Qwen3-VL-Moe loading issue and position_ids buffer access error are unrelated." + "reason": "Different missing imports for different symbols; not the same underlying issue." }, { - "left": "issue:43824", - "right": "issue:44351", + "left": "issue:44038", + "right": "issue:44295", "accept": false, - "reason": "Both are import errors, but for different symbols and different causes." + "reason": "Qwen3-VL-Moe issue vs position_ids buffer read error; separate problems." }, { "left": "issue:36296", "right": "issue:43116", "accept": false, - "reason": "Tensor-parallel training bug is unrelated to the example script's empty multi-label results." + "reason": "Tensor-parallel training bug vs example-script multi-label classification bug." }, { "left": "issue:44038", "right": "issue:44222", "accept": false, - "reason": "Model loading failure and FP8 save_pretrained bug affect different code paths." + "reason": "Both mention MoE/FP8 contexts, but the concrete failures are different and not mergeable into one fix." }, { "left": "issue:39401", "right": "issue:44521", "accept": false, - "reason": "Tokenizer offset_mapping and multimodal assistant_masks are unrelated tokenizer features." + "reason": "Tokenizer offset_mapping regression is different from multimodal assistant_mask generation." }, { "left": "issue:42757", "right": "issue:44351", "accept": false, - "reason": "Different import failures from different packages/symbols; not the same bug." + "reason": "Import errors from different packages/symbols; unrelated." }, { "left": "issue:45216", "right": "issue:45478", - "accept": false, - "reason": "Same model family, but save_pretrained checkpoint corruption and from_pretrained failure are distinct bugs." + "accept": true, + "reason": "Both are Qwen3.5 save/load regressions around 5.4.0, and the save_pretrained corruption plausibly explains the from_pretrained failure." }, { "left": "issue:43066", "right": "issue:44779", "accept": false, - "reason": "Wrong decoder type and Deepseek tokenization regression are different issues." + "reason": "Wrong tokenizer decoder type is a different tokenizer bug than general incorrect tokenization output." }, { "left": "issue:22355", "right": "issue:28218", "accept": false, - "reason": "Missing transformers.onnx module and extra tokenizer space are unrelated." + "reason": "Missing transformers.onnx module and extra-space-after-added-token are unrelated." }, { "left": "issue:42907", "right": "issue:44222", "accept": false, - "reason": "Both touch saving, but they are model-specific quantization/save bugs with different failure modes." + "reason": "Both involve save_pretrained, but one is dequantized Ministral/Devstral and the other is FP8 MoE; different bugs." }, { "left": "issue:43122", "right": "issue:44977", "accept": false, - "reason": "Tokenizer regression and Qwen3.5 flash-attention generation bug are unrelated." + "reason": "Tokenizer regression vs Qwen3.5 flash-attention generation failure; different failure modes." }, { - "left": "issue:43992", - "right": "issue:44704", + "left": "issue:43784", + "right": "issue:45446", "accept": false, - "reason": "Missing embed_tokens.weight and cached_file kwargs forwarding are unrelated." + "reason": "Sentence-transformers import NameError and flex_attention PyTorch version check are unrelated." }, { - "left": "issue:43784", - "right": "issue:45446", + "left": "issue:43992", + "right": "issue:44704", "accept": false, - "reason": "sentence-transformers import NameError and flex_attention version check are unrelated." + "reason": "Missing embed_tokens.weight in UMT5Encoder is unrelated to AutoProcessor kwargs forwarding." }, { "left": "issue:43937", "right": "issue:44485", "accept": false, - "reason": "Invalid GenerationConfig and RoPE implementation are unrelated." + "reason": "GenerationConfig invalid for GLM-5 is unrelated to GLM-5 RoPE implementation." }, { "left": "issue:42222", "right": "issue:43441", "accept": false, - "reason": "Vitpose model breakage and Ministral FlashAttention failure are unrelated." + "reason": "Broken vitpose models and Ministral-3 flash-attention failure are unrelated." }, { "left": "issue:42371", "right": "issue:43874", "accept": false, - "reason": "TF32 settings warning and missing image-patch helper are unrelated." + "reason": "TF32 API guidance and missing get_number_of_image_patches are different issues." }, { "left": "issue:43976", "right": "issue:45446", "accept": false, - "reason": "Python version compatibility issue and flex_attention version check are unrelated." + "reason": "Python version compatibility complaint vs incorrect PyTorch version check; not the same bug." }, { "left": "issue:43493", "right": "issue:45753", "accept": false, - "reason": "SigLIP2 implementation discrepancy and Qwen3_5 infinite-loop bug are unrelated." + "reason": "SigLIP2 implementation discrepancy and Qwen3_5 image-specific infinite loop are unrelated." }, { "left": "issue:44075", "right": "issue:44936", "accept": false, - "reason": "Optimizer argument handling and trainer.evaluate-after-train are different trainer bugs." + "reason": "Optimizer SGD args not used vs trainer.evaluate() after train() are different trainer/optimizer bugs." }, { "left": "issue:42831", "right": "issue:45753", "accept": false, - "reason": "FineGrainedFP8 accuracy issue and image-specific infinite loop are unrelated." + "reason": "FineGrainedFP8 accuracy issue is unrelated to the Qwen3_5 image infinite-loop bug." }, { "left": "issue:43116", "right": "issue:43825", "accept": false, - "reason": "Example-script classification bug and pipeline translation error message are unrelated." - }, - { - "left": "issue:44038", - "right": "issue:45478", - "accept": false, - "reason": "Related model area, but Qwen3-VL-Moe load failure and Qwen3.5 MoE from_pretrained error are not the same concrete bug." - }, - { - "left": "issue:44222", - "right": "issue:45478", - "accept": false, - "reason": "FP8 save_pretrained bug and Qwen3.5 MoE from_pretrained failure are distinct save/load problems." - }, - { - "left": "issue:43116", - "right": "issue:43493", - "accept": false, - "reason": "Classification example bug and SigLIP2 discrepancy are unrelated." - }, - { - "left": "issue:45083", - "right": "issue:45446", - "accept": false, - "reason": "qwen3_omni_moe feature-length helper bug and flex_attention import/version check are unrelated." + "reason": "Example-script multi-label output bug vs pipeline translation-task error-message issue are unrelated." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "The assessment is grounded in the packet and stays conservative. The two accepted soft pairs are the only ones that look plausibly mergeable into a single bugfix family, while the rejected pairs are described at a sufficiently high level and do not overclaim shared root cause. The summary also avoids overstating the cluster cohesion beyond the two noted families." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -12470,7 +12475,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 39, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -12558,12 +12563,12 @@ "issue:43012|issue:43577", "issue:43066|issue:43122" ], - "prepared_review_unit_hash": "d4d76187492f6c77e4f04646167697b1e8c80d3ff4c2300fd4339d5566f22b38", + "prepared_review_unit_hash": "50d2aa60e5186173bb384f0093ea0b3f19bd4cc63a9888402710b72884edf344", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -12571,7 +12576,7 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 29, - "serialized_chars": 36332, + "serialized_chars": 36331, "estimated_input_tokens": 9083, "estimated_eval_tokens": 18422 }, @@ -12580,174 +12585,174 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These issues are mostly unrelated individual regressions; none of the soft edges look like true duplicates or mergeable PR-equivalent changes.", - "confidence": 0.94, - "canonical_issue_reason": null, + "summary": "The cluster is mostly a set of unrelated Transformers bug reports; the only plausible umbrella issue is the broad import-regression report after upgrading to v5.5.0.", + "confidence": 0.79, + "canonical_issue_reason": "issue:45278 is the broadest and most recent umbrella report, describing multiple import errors after upgrading to 5.5.0.", "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "issue:45278 is the best global dedupe target because it is open, broadly scoped, and likely to attract related import-regression reports.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43064", "right": "issue:43673", "accept": false, - "reason": "Different failures: distributed optimizer state corruption vs missing GenerationMixin cache during chunked prefill." + "reason": "Different subsystems and failure modes: optimizer state placement vs generation cache handling." }, { "left": "issue:43937", "right": "issue:45563", "accept": false, - "reason": "Both mention generation, but one is invalid GenerationConfig and the other is a stale warning for num_return_sequences." + "reason": "Unrelated bugs: invalid GenerationConfig vs a stale warning about num_return_sequences." }, { "left": "issue:38617", "right": "issue:45278", "accept": false, - "reason": "Same broad import-error theme, but different missing symbols and likely different regressions." + "reason": "Both are import-related, but one is a specific missing symbol while the other is a broad upgrade report; not clearly the same concrete bug." }, { "left": "issue:39401", "right": "issue:44779", "accept": false, - "reason": "Tokenizer-related, but Qwen3 wrong offset mapping and Deepseek incorrect tokenization are different bugs." + "reason": "Different model/tokenizer regressions with distinct symptoms and code paths." }, { "left": "issue:33453", "right": "issue:39401", "accept": false, - "reason": "Both are tokenizer regressions, but one is generic loading regression and the other is a model-specific offset_mapping bug." + "reason": "Both mention tokenizer issues, but loading regressions and offset_mapping bugs are not the same defect." }, { "left": "issue:22355", "right": "issue:29127", "accept": false, - "reason": "Completely different problems: missing transformers.onnx module vs LayoutLMv3 error-message clarity." + "reason": "Completely different areas: ONNX import failure vs LayoutLMv3 error-message clarity." }, { "left": "issue:44117", "right": "issue:45588", "accept": false, - "reason": "Unrelated code paths: tokenizer mapping lookup vs flash_attention crash on s_aux=None." + "reason": "Tokenizer-mapping fallback bug and flash-attention crash are unrelated." }, { "left": "issue:43827", "right": "issue:45446", "accept": false, - "reason": "Docs reference cleanup and a PyTorch version check bug are not the same underlying issue." + "reason": "Docs cleanup for removed pipelines is unrelated to a flex_attention version-check bug." }, { "left": "issue:43381", "right": "issue:44945", "accept": false, - "reason": "Gradient checkpointing eval-mode behavior is unrelated to pipeline-parallelism output corruption." + "reason": "Gradient-checkpointing eval-mode behavior and pipeline-parallel output corruption are different problems." }, { "left": "issue:43937", "right": "issue:44977", "accept": false, - "reason": "Different concrete bugs: invalid generation config vs Qwen3.5 flash-attention generation failure." + "reason": "Different models and failures: GLM generation config validation vs Qwen3.5 flash-attention generation issues." }, { "left": "issue:45405", "right": "issue:45446", "accept": false, - "reason": "Packaging/version pin issue versus an import-version check bug; not the same fix." + "reason": "PEFT version pinning and PyTorch version gating for AuxRequest are unrelated." }, { "left": "issue:43450", "right": "issue:43986", "accept": false, - "reason": "Batched video shape bug and AutoProcessor crash without torchvision are different failure modes." + "reason": "Batched video output shape bug is not the same as an AutoProcessor crash without torchvision." }, { "left": "issue:42673", "right": "issue:45072", "accept": false, - "reason": "VRAM leak in Qwen3ForCausalLM threads is unrelated to dtype mismatches in other models." + "reason": "VRAM leak in multi-threaded inference and bfloat16 dtype mismatches are different bugs." }, { "left": "issue:44117", "right": "issue:45081", "accept": false, - "reason": "TOKENIZER_MAPPING_NAMES None handling is unrelated to the Mistral regex patch crash." + "reason": "TOKENIZER_MAPPING_NAMES returning None is unrelated to the Mistral regex patch crash." }, { "left": "issue:38617", "right": "issue:41628", "accept": false, - "reason": "Both are import errors, but for different exported names and likely unrelated causes." + "reason": "Both are import errors, but they concern different missing APIs and likely different regressions." }, { "left": "issue:39401", "right": "issue:43421", "accept": false, - "reason": "Wrong offset mapping and stale post-processor updates after special-token edits are different tokenizer bugs." + "reason": "Offset mapping correctness and runtime post-processor updates are distinct tokenizer behaviors." }, { "left": "issue:44410", "right": "issue:45310", "accept": false, - "reason": "Different Qwen-family issues: missing projections in qwen3next vs from_pretrained failure in Qwen3.5 MoE." + "reason": "Layer projection wiring in qwen3next is not the same as Qwen3.5 MoE loading failure." }, { "left": "issue:44829", "right": "issue:45216", "accept": false, - "reason": "Flash-attention training degeneration is unrelated to incorrect checkpoint saving in Qwen3.5." + "reason": "Degenerate training with flash_attention_3 and incorrect saved checkpoints are different failure modes." }, { "left": "issue:44291", "right": "issue:45071", "accept": false, - "reason": "init_empty_weights argument mismatch and PretrainedConfig type-checking breakage are separate v5 regressions." + "reason": "init_empty_weights argument handling and PretrainedConfig type checking are separate v5 regressions." }, { "left": "issue:44484", "right": "issue:45310", "accept": false, - "reason": "A save_pretrained shard-size question is unrelated to the Qwen3.5 MoE loading error." + "reason": "save_pretrained shard-size behavior is unrelated to the Qwen3.5 MoE from_pretrained error." }, { "left": "issue:42222", "right": "issue:45542", "accept": false, - "reason": "Different subsystems entirely: VitPose model breakage vs missing TensorFlow backend when only tensorboard is installed." + "reason": "VitPose model breakage and missing TensorFlow backend due to tensorboard-only install are unrelated." }, { "left": "issue:43408", "right": "issue:43742", "accept": false, - "reason": "SAM3 model-type warning and MobileLLM load key error are not the same bug." + "reason": "A model-type warning for sam3 and a MobileLLM loading key error are different issues." }, { "left": "issue:44075", "right": "issue:45656", "accept": false, - "reason": "SGD args ignored and optimizer.step() called twice under deepspeed are different optimizer bugs." + "reason": "Wrong SGD argument usage is not the same as deepspeed calling optimizer.step twice." }, { "left": "issue:44483", "right": "issue:45464", "accept": false, - "reason": "General chat/completions API failure is not the same as the Qwen3.5 streaming-specific failure." + "reason": "Both hit chat/completions, but one is a general API rejection and the other is a streaming-inference failure for a specific model." }, { "left": "issue:44964", "right": "issue:45278", "accept": false, - "reason": "Model-loading failure for Phi-4 multimodal is unrelated to the broad import-error report." + "reason": "Model loading failure for Phi-4 multimodal is not the same as broad import errors after upgrading." }, { "left": "issue:43012", "right": "issue:43577", "accept": false, - "reason": "One is a PyTorch warning during bf16 compilation; the other is incorrect dtype state when loading BLIP2." + "reason": "A compiler warning about bfloat16 precision is not the same as model dtype fields remaining float32 on load." }, { "left": "issue:43066", "right": "issue:43122", "accept": false, - "reason": "Both are tokenizer-v5 regressions, but decoder-type mismatch and changed tokenization output are not the same concrete bug." + "reason": "Tokenizer decoder-type mismatch and changed tokenization output are related at a high level but not clearly the same concrete bug." } ] }, @@ -12763,7 +12768,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 40, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -12824,8 +12829,8 @@ "issue:42371|issue:44261", "issue:38617|issue:44220", "issue:44410|issue:45478", - "issue:43874|issue:44261", "issue:44484|issue:45478", + "issue:43874|issue:44261", "issue:43097|issue:44493", "issue:44263|issue:44485", "issue:42222|issue:45459", @@ -12842,8 +12847,8 @@ "issue:43335|issue:45071", "issue:43976|issue:44945", "issue:43408|issue:44368", - "issue:43874|issue:44263", "issue:43986|issue:44484", + "issue:43874|issue:44263", "issue:44829|issue:45245", "issue:38617|issue:42757", "issue:43064|issue:44315", @@ -12851,20 +12856,20 @@ "issue:38617|issue:44351", "issue:43097|issue:45588", "issue:44062|issue:44117", - "issue:44038|issue:44410", "issue:42673|issue:45200", + "issue:44038|issue:44410", "issue:44964|issue:45071", "issue:44704|issue:45103", "issue:44261|issue:44485", "issue:43931|issue:44410", "issue:44964|issue:45341" ], - "prepared_review_unit_hash": "e0e09981cbd70bb07b71ecfed1ed921744b12c27e3b1d6beec78ebc61d22e8a7", + "prepared_review_unit_hash": "110c070d644d40a58a8cd8e90ed5b92f5d5f702c2843e47158133970386f4cef", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -12872,243 +12877,243 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 37, - "serialized_chars": 38752, - "estimated_input_tokens": 9688, - "estimated_eval_tokens": 19632 + "serialized_chars": 38745, + "estimated_input_tokens": 9687, + "estimated_eval_tokens": 19630 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This is a heterogeneous cluster of unrelated Transformers bug reports; none of the soft pairs look like the same underlying defect, so no duplicate merge is warranted.", - "confidence": 0.71, - "canonical_issue_reason": "No single canonical issue fits this cluster: it mixes unrelated import errors, model-specific regressions, config warnings, and training/runtime bugs.", + "summary": "The cluster is heterogeneous: most items are separate Transformers regressions, import errors, or model-specific bugs rather than duplicates. I would keep one broad API-regression issue as the cluster anchor, but I do not see any soft-edge pair that should be merged as the same underlying defect.", + "confidence": 0.29, + "canonical_issue_reason": "issue:43097 is the broadest, most central regression-style report in this set and has downstream references; it is the best anchor if one issue must represent the cluster.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44704 is the cleanest representative because it is a concrete core API bug with a clear failure mode and broader potential impact.", + "best_issue_reason": "issue:43097 is the most generally phrased user-facing breakage report and the strongest candidate to keep as the representative issue for triage.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:42371", "right": "issue:44261", "accept": false, - "reason": "TF32 settings guidance is unrelated to the MLA rms_norm_eps precision bug." + "reason": "TF32 API-setting guidance vs a multimodal precision bug in MLA layernorm; different symptoms and code paths." }, { "left": "issue:38617", "right": "issue:44220", "accept": false, - "reason": "Different import/pathology: a missing config symbol vs an audio feature-extraction issue." + "reason": "Different import failure and audio feature extraction bug; no shared underlying defect." }, { "left": "issue:44410", "right": "issue:45478", "accept": false, - "reason": "Different Qwen3 model families and different failure modes." + "reason": "Separate Qwen-family model issues: missing projections vs from_pretrained loading error." }, { - "left": "issue:43874", - "right": "issue:44261", + "left": "issue:44484", + "right": "issue:45478", "accept": false, - "reason": "Image patch-count method bug is unrelated to the MLA precision/config issue." + "reason": "Shard-size question is unrelated to the Qwen3.5 MoE loading failure." }, { - "left": "issue:44484", - "right": "issue:45478", + "left": "issue:43874", + "right": "issue:44261", "accept": false, - "reason": "Save-pretrained shard sizing is unrelated to Qwen3.5 MoE loading." + "reason": "Image processor missing method vs MLA precision/config issue; unrelated subsystems." }, { "left": "issue:43097", "right": "issue:44493", "accept": false, - "reason": "Removed tie_embeddings API warning is not the same as unexpected position-id keys." + "reason": "Embedding-tying regression is unrelated to unexpected position-id keys." }, { "left": "issue:44263", "right": "issue:44485", "accept": false, - "reason": "Both are GLM-related, but they describe different code paths and bugs." + "reason": "GLM indexer split behavior and GLM-5 RoPE implementation are different bugs." }, { "left": "issue:42222", "right": "issue:45459", "accept": false, - "reason": "VitPose breakage is unrelated to tokenizer protobuf error masking." + "reason": "VitPose breakage vs tokenizer protobuf-error masking; different failure modes and fixes." }, { "left": "issue:43012", "right": "issue:43408", "accept": false, - "reason": "bfloat16 compile warning and sam3 model-type warning are different issues." + "reason": "bfloat16 precision warning and SAM3 model-type warning are distinct issues." }, { "left": "issue:43441", "right": "issue:44829", "accept": false, - "reason": "Both mention FlashAttention, but one is inference failure and the other is degenerate training." + "reason": "Both involve flash attention, but different models and outcomes: load failure vs degenerate training." }, { "left": "issue:41628", "right": "issue:45071", "accept": false, - "reason": "Missing AutoImageProcessor import is unrelated to PretrainedConfig type checking." + "reason": "Missing AutoImageProcessor import and PretrainedConfig type-checking regression are unrelated." }, { "left": "issue:42673", "right": "issue:44977", "accept": false, - "reason": "VRAM leak in dataloader threads is not the same as flash-attention generation failure." + "reason": "VRAM leak in multi-threaded loading vs flash-attention generation issue; different code paths." }, { "left": "issue:45071", "right": "issue:45542", "accept": false, - "reason": "Type-checking regression is unrelated to the TensorFlow backend import error." + "reason": "Type checking regression is unrelated to TensorFlow backend detection when only tensorboard is installed." }, { "left": "issue:42371", "right": "issue:42831", "accept": false, - "reason": "TF32 settings control is unrelated to FineGrainedFP8 accuracy." + "reason": "TF32 configuration warning is unrelated to FineGrainedFP8 accuracy problems." }, { "left": "issue:42673", "right": "issue:43906", "accept": false, - "reason": "These are different Qwen3-related reports with no shared concrete failure path." + "reason": "VRAM leak report is not the same as the isolated reproduction of a different referenced issue." }, { "left": "issue:43931", "right": "issue:44038", "accept": false, - "reason": "Different model variants and different loading failures." + "reason": "Model weight-shape mismatch and Qwen3-VL-Moe loading issue are distinct model-loading problems." }, { "left": "issue:44117", "right": "issue:44987", "accept": false, - "reason": "Tokenizer mapping returning None is not clearly the same as that model-loading failure." + "reason": "Tokenizer mapping None bug and a specific model load failure are not the same defect." }, { "left": "issue:43097", "right": "issue:43452", "accept": false, - "reason": "API removal warning and gguf_file loading breakage are different bugs." + "reason": "Embedding-tie API removal and gguf_file loading breakage are separate regressions." }, { "left": "issue:43335", "right": "issue:45071", "accept": false, - "reason": "Sparse-layer config creation bug is unrelated to type-checking behavior." + "reason": "SwitchTransformers sparse-layer bug is unrelated to PretrainedConfig type checking." }, { "left": "issue:43976", "right": "issue:44945", "accept": false, - "reason": "Python-version compatibility and pipeline-parallel output corruption are unrelated." + "reason": "Python-version support issue and pipeline-parallelism output corruption are different problems." }, { "left": "issue:43408", "right": "issue:44368", "accept": false, - "reason": "Different warnings in different models; not the same underlying bug." + "reason": "SAM3 config warning and Qwen3.5 LoRA tie-word-embeddings warning are unrelated warnings." }, { - "left": "issue:43874", - "right": "issue:44263", + "left": "issue:43986", + "right": "issue:44484", "accept": false, - "reason": "Both mention GLM, but one is a missing processor method and the other is a torch.split handling issue." + "reason": "AutoProcessor/torchvision crash and save_pretrained shard-size behavior are unrelated." }, { - "left": "issue:43986", - "right": "issue:44484", + "left": "issue:43874", + "right": "issue:44263", "accept": false, - "reason": "AutoProcessor torchvision crash is unrelated to save_pretrained sharding." + "reason": "Missing image-patch method and torch.split return-value issue affect different model components." }, { "left": "issue:44829", "right": "issue:45245", "accept": false, - "reason": "FlashAttention training degeneration is unrelated to category-cardinality limits." + "reason": "FlashAttention training degeneration is unrelated to categorical-cardinality RuntimeError." }, { "left": "issue:38617", "right": "issue:42757", "accept": false, - "reason": "Different missing imports from different modules/symbols." + "reason": "Two separate import errors from different modules and symbols; not the same missing API." }, { "left": "issue:43064", "right": "issue:44315", "accept": false, - "reason": "Wrong optimizer state distribution is not the same as Liger Kernel not being applied." + "reason": "FSDP2 optimizer-state corruption and Liger Kernel not applied with model_init are different training-path bugs." }, { "left": "issue:44410", "right": "issue:45375", "accept": false, - "reason": "Missing projections in qwen3next is unrelated to a silently dropped config field." + "reason": "Missing Qwen3Next projections and missing deepstack_visual_indexes field are unrelated config/model-definition issues." }, { "left": "issue:38617", "right": "issue:44351", "accept": false, - "reason": "Both are import errors, but they involve different missing symbols and code paths." + "reason": "Different missing exports from transformers; no evidence they share one underlying breakage." }, { "left": "issue:43097", "right": "issue:45588", "accept": false, - "reason": "Config API removal and flash_attention.py s_aux=None crash are different bugs." + "reason": "Embedding tying regression is unrelated to flash_attention.py crashing on sink-less models." }, { "left": "issue:44062", "right": "issue:44117", "accept": false, - "reason": "Token AddedToken kwarg duplication is unrelated to tokenizer mapping None handling." + "reason": "AddedToken argument collision and tokenizer mapping None are separate tokenizer bugs." }, { - "left": "issue:44038", - "right": "issue:44410", + "left": "issue:42673", + "right": "issue:45200", "accept": false, - "reason": "Different Qwen3-family model issues with different symptoms." + "reason": "VRAM leak in dataloader threads is unrelated to mm_token_type_ids defaults for text-only fine-tuning." }, { - "left": "issue:42673", - "right": "issue:45200", + "left": "issue:44038", + "right": "issue:44410", "accept": false, - "reason": "VRAM leak in multi-thread loading is unrelated to Gemma 4 mm_token_type_ids defaults." + "reason": "Different Qwen-family model failures: Qwen3-VL-Moe load issue vs Qwen3Next missing projections." }, { "left": "issue:44964", "right": "issue:45071", "accept": false, - "reason": "Phi-4 multimodal load failure is unrelated to a type-checking regression." + "reason": "Phi-4 multimodal loading failure is unrelated to PretrainedConfig type checking." }, { "left": "issue:44704", "right": "issue:45103", "accept": false, - "reason": "cached_file kwargs forwarding and auto_docstring annotation crashes are unrelated." + "reason": "cached_file kwargs forwarding bug and auto-docstring annotations crash are separate utilities issues." }, { "left": "issue:44261", "right": "issue:44485", "accept": false, - "reason": "MLA layernorm epsilon precision and GLM-5 RoPE implementation are different bugs." + "reason": "MLA rms_norm_eps precision bug and GLM-5 RoPE implementation issue are not the same code-path problem." }, { "left": "issue:43931", "right": "issue:44410", "accept": false, - "reason": "Qwen3-VL shape mismatch and qwen3next missing projections are separate model issues." + "reason": "Qwen3-VL weight-shape mismatch and Qwen3Next missing attention projections are different model regressions." }, { "left": "issue:44964", "right": "issue:45341", "accept": false, - "reason": "Phi-4 multimodal loading is unrelated to a testing_utils bug." + "reason": "Model loading failure and a testing_utils bug are unrelated." } ] }, @@ -13124,7 +13129,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 41, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -13217,12 +13222,12 @@ "issue:43867|issue:45216", "issue:42994|issue:44655" ], - "prepared_review_unit_hash": "f958b5cdfbb50b31faa9c1d4ce91eab86b9575f3707d780adf56079b2aeb15f2", + "prepared_review_unit_hash": "16cc998b10556187579de00a0084a93b8b55690705e42711faa2abed4075651f", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -13230,238 +13235,217 @@ "node_count": 47, "item_count": 47, "soft_pair_count": 35, - "serialized_chars": 37419, - "estimated_input_tokens": 9355, - "estimated_eval_tokens": 18966 + "serialized_chars": 37413, + "estimated_input_tokens": 9354, + "estimated_eval_tokens": 18964 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "No soft pair looks like a safe duplicate merge; the set is mostly unrelated regression reports across different models and subsystems.", - "confidence": 0.68, - "canonical_issue_reason": "No safe canonical issue emerges here: the candidate pairs are mostly unrelated, so choosing one as the duplicate anchor would be arbitrary.", + "summary": "This set is mostly a grab-bag of unrelated Transformers issues. The only plausible duplicate pair is the CLIP vision v5 regression around missing optional outputs; everything else appears to target different code paths.", + "confidence": 0.76, + "canonical_issue_reason": "issue:43761 is the strongest representative of the only real duplicate cluster here: a CLIPVisionModel v5 regression with a clear symptom, reproduction context, and broader discussion.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43873 is the strongest standalone anchor among these issues: it is open, broad in scope (quantization/offloading), and has the most surrounding discussion/references.", + "best_issue_reason": "issue:43761 is the most actionable and representative issue in the set, and it best captures the shared CLIP output regression theme.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43502", "right": "issue:43992", "accept": false, - "reason": "Different bugs: local_files_only network leakage vs a missing embed_tokens weight during UMT5 loading." + "reason": "Different failure modes: one is hub/API fetches despite local_files_only, the other is a UMT5 encoder checkpoint weight-loading omission." }, { "left": "issue:45341", "right": "issue:45859", "accept": false, - "reason": "Unrelated subsystems: a testing_utils bug vs Qwen3_5MoeTextRotaryEmbedding CPU offload compatibility." + "reason": "Unrelated components: patched testing utils race vs Qwen3_5MoeTextRotaryEmbedding CPU offload incompatibility." }, { "left": "issue:43986", "right": "issue:44117", "accept": false, - "reason": "Both are loading-related, but one is a missing torchvision dependency path and the other is a tokenizer mapping None-handling bug." + "reason": "Both concern loading, but one is AutoProcessor/torchvision availability and the other is a tokenizer mapping None-handling bug." }, { "left": "issue:43097", "right": "issue:43873", "accept": false, - "reason": "Different problems: a removed API warning vs quantization/offloading behavior." + "reason": "Different subsystems: removed tie_embeddings API vs quantization/offloading not behaving as expected." }, { "left": "issue:43066", "right": "issue:43906", "accept": false, - "reason": "No clear match: tokenizer decoder type regression vs an isolated reproduction of a different issue." + "reason": "Insufficient evidence of the same bug; one is a tokenizer decoder-type regression, the other is only a reproduction of a separate linked issue." }, { "left": "issue:43986", "right": "issue:45290", "accept": false, - "reason": "Different areas: AutoProcessor video-model import failure vs chat template crashes on tool-call assistant messages." + "reason": "Distinct bugs: processor loading without torchvision vs chat-template handling of tool-call assistant messages." }, { "left": "issue:45341", "right": "issue:45561", "accept": false, - "reason": "Shared file name is not enough; one is a generic testing_utils bug and the other is a specific xdist race on captured_info.txt." + "reason": "Testing-utils file race and pytest-xdist worker capture are different issues, not the same underlying defect." }, { "left": "issue:43986", "right": "issue:45372", "accept": false, - "reason": "Different import failures from different dependencies and models." + "reason": "Different import/loading problems with different missing dependencies and code paths." }, { "left": "issue:43097", "right": "issue:43901", "accept": false, - "reason": "Completely unrelated: removed tie_embeddings API vs stale pipeline docs about return_all_scores." + "reason": "API removal versus docs/behavior mismatch in a text classification pipeline." }, { "left": "issue:42617", "right": "issue:45341", "accept": false, - "reason": "Different failures: 3d_parallel.py execution vs a testing_utils bug." + "reason": "3d_parallel.py runtime failure is unrelated to the testing_utils bug." }, { "left": "issue:43986", "right": "issue:45341", "accept": false, - "reason": "Different domains: video-model loading/import path vs testing infrastructure." + "reason": "Processor-loading crash and testing-utils race are unrelated." }, { "left": "issue:43825", "right": "issue:44655", "accept": false, - "reason": "Different surface areas: pipeline task messaging vs saving Pipeline objects." + "reason": "Pipeline task-message behavior issue and pipeline save_pretrained serialization issue are different bugs." }, { "left": "issue:45341", "right": "issue:45588", "accept": false, - "reason": "Testing-utils race bug vs a flash_attention AttributeError in sink-less models." + "reason": "Testing-utils race is unrelated to flash_attention crashing on sink-less models." }, { "left": "issue:43992", "right": "issue:44484", "accept": false, - "reason": "Different save/load concerns: missing embed weight on load vs max_shard_size default behavior." + "reason": "Checkpoint weight loading problem vs save_pretrained shard-size question; not the same defect." }, { "left": "issue:43012", "right": "issue:43550", "accept": false, - "reason": "One is a warning about bfloat16 compilation precision; the other is an actual torch.compile SDPA failure on Bamba." + "reason": "A PyTorch warning during bfloat16 compilation is not the same as an SDPA torch.compile failure." }, { "left": "issue:43208", "right": "issue:43550", "accept": false, - "reason": "xLSTM training bugs are unrelated to a Bamba SDPA compile regression." + "reason": "xLSTM training blockers and Bamba SDPA compile failure are different model-specific bugs." }, { "left": "issue:43012", "right": "issue:44368", "accept": false, - "reason": "Both mention warnings, but they are about different configs and different underlying behaviors." + "reason": "Both mention warnings, but they stem from different causes and different model/config paths." }, { "left": "issue:42886", "right": "issue:43381", "accept": false, - "reason": "Offline cache loading and gradient checkpointing in eval mode are separate bugs." + "reason": "Offline tokenizer caching and gradient-checkpointing eval-mode behavior are unrelated." }, { "left": "issue:42907", "right": "issue:45753", "accept": false, - "reason": "Saving dequantized models and an infinite-generation loop are unrelated." + "reason": "Quantized save failure and Qwen3_5 infinite-loop generation are different problems." }, { "left": "issue:42907", "right": "issue:44655", "accept": false, - "reason": "Both involve saving, but one is quantized model serialization and the other is Pipeline save_pretrained support." + "reason": "Saving dequantized models and saving Pipeline objects are distinct save paths with different failures." }, { "left": "issue:43208", "right": "issue:43526", "accept": false, - "reason": "Different components: xLSTM training bugs vs BeitImageProcessorFast reduce_labels handling." + "reason": "xLSTM training bugs do not match the BeitImageProcessorFast reduce_labels bug." }, { "left": "issue:44483", "right": "issue:44514", "accept": false, - "reason": "Different chat-related failures: OpenAI-style endpoint rejection vs batched apply_chat_template crash." + "reason": "Both involve chat/completions behavior, but one is an API acceptance regression and the other is a chat-template batching crash." }, { "left": "issue:43012", "right": "issue:44683", "accept": false, - "reason": "A warning about bfloat16 precision is not the same bug as flex_attention compilation failure on newer torch." + "reason": "Different attention/compile warnings and failures; no shared concrete bug path." }, { "left": "issue:42757", "right": "issue:43824", "accept": false, - "reason": "Both are ImportErrors, but for different missing symbols and different code paths." + "reason": "Separate import errors from different packages/classes." }, { "left": "issue:38617", "right": "issue:43502", "accept": false, - "reason": "Unrelated imports: layer_type_validation removal vs local_files_only still making API calls." + "reason": "Configuration-utils import error is unrelated to local_files_only network requests." }, { "left": "issue:44483", "right": "issue:45290", "accept": false, - "reason": "Different chat-stack regressions: request validation vs chat template handling of tool-call messages." + "reason": "Different layers: /v1/chat/completions request handling vs apply_chat_template tokenization crash." }, { "left": "issue:44038", "right": "issue:44230", "accept": false, - "reason": "Both mention Qwen3-VL/MoE, but one is a v5 bug report and the other is fp8 inference support." + "reason": "Both mention Qwen3 VL/Moe, but one is a model-loading regression and the other is fp8 inference support." }, { "left": "issue:43618", "right": "issue:43761", - "accept": false, - "reason": "Both are CLIP regressions, but one is missing attentions and the other is hidden_states=None; not the same concrete failure." + "accept": true, + "reason": "Same underlying CLIP vision v5 regression: optional outputs are being dropped from CLIPVisionModel/CLIPOutput in the forward path." }, { "left": "issue:43064", "right": "issue:44380", "accept": false, - "reason": "Trainer/FSDP optimizer-state corruption is unrelated to GPT2 attention scaling being ignored under SDPA/FlashAttention." + "reason": "FSDP2/PEFT optimizer-state mismatch is unrelated to GPT2 attention scaling under SDPA/FlashAttention." }, { "left": "issue:43299", "right": "issue:43867", "accept": false, - "reason": "Different model-loading bugs: Qwen3VL-Moe load failure vs state_dict sorting load error." - }, - { - "left": "issue:44483", - "right": "issue:45381", - "accept": false, - "reason": "OpenAI chat-completions request handling is unrelated to qwen2.5-vl vision_position_ids for video input." - }, - { - "left": "issue:43901", - "right": "issue:44655", - "accept": false, - "reason": "Docs drift about return_all_scores is unrelated to Pipeline save_pretrained failures." - }, - { - "left": "issue:36683", - "right": "issue:43475", - "accept": false, - "reason": "Different missing-attribute errors on different model classes: Gemma3Config vocab_size vs Sam3VisionEncoderOutput fpn_position_embeddings." - }, - { - "left": "issue:43867", - "right": "issue:45216", - "accept": false, - "reason": "Both involve checkpoints, but one is a load-time state_dict ordering error and the other is a save_pretrained regression." + "reason": "Qwen3VL-Moe loading regression and sorted-state_dict load failure are different model-loading issues." }, { "left": "issue:42994", "right": "issue:44655", "accept": false, - "reason": "Both are save-related, but one is quantized model saving and the other is Pipeline object serialization." + "reason": "Quantized model saving failure and pipeline object serialization are different save_pretrained paths." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative: most pairs are clearly unrelated, and the only accepted edge (issue:43618 \u2194 issue:43761) is well supported by the shared CLIP vision v5 optional-output regression. I don\u2019t see overstatement beyond what the issue titles and descriptions justify." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -13470,7 +13454,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 42, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -13478,6 +13462,8 @@ "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ + "issue:28282", + "issue:33453", "issue:36010", "issue:36296", "issue:36683", @@ -13509,7 +13495,6 @@ "issue:44355", "issue:44360", "issue:44380", - "issue:44484", "issue:44485", "issue:44492", "issue:44655", @@ -13560,240 +13545,240 @@ "issue:43064|issue:44655", "issue:36296|issue:43575", "issue:44077|issue:44380", - "issue:43867|issue:44484" + "issue:28282|issue:33453" ], - "prepared_review_unit_hash": "fef0bb11ca8d90e301e94cad4a8a138fb3319207779285c5dd52bd6f9a8653cc", + "prepared_review_unit_hash": "d689830de7829b4778a88b8a71a54832f6a4e21ab0bcaab7f579b11fa020b9ac", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, "budget": { - "node_count": 47, - "item_count": 47, + "node_count": 48, + "item_count": 48, "soft_pair_count": 34, - "serialized_chars": 36869, - "estimated_input_tokens": 9218, - "estimated_eval_tokens": 18692 + "serialized_chars": 37429, + "estimated_input_tokens": 9358, + "estimated_eval_tokens": 18972 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is heterogeneous: most items are distinct Transformers regressions spanning different models, versions, and subsystems. The soft-similarity edges are mostly false positives rather than true duplicates.", - "confidence": 0.94, - "canonical_issue_reason": "No single canonical issue cleanly subsumes this set; the items split into unrelated model-specific loading, config, attention, and tooling regressions. If forced to pick a representative, issue 43097 is the broadest v5 regression, but it does not duplicate the others.", + "summary": "This cluster is noisy: the items share broad Transformers/v5 regression language, but they describe distinct bugs, models, and failure modes rather than true duplicates. I reject all soft-edge matches.", + "confidence": 0.96, + "canonical_issue_reason": "No single issue is a clear duplicate hub; the set spans unrelated loading, config, attention, training, and test failures.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43097 is the best representative issue only because it is a broad, user-facing v5 breakage with clear impact. It is still not a good canonical for the whole cluster, since the rest are mostly separate bugs.", + "best_issue_reason": "No global best issue stands out as a representative duplicate target because the underlying bugs are heterogeneous.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43352", "right": "issue:43937", "accept": false, - "reason": "Different failures: FlashAttention support gap for Nemotron vs invalid GenerationConfig for GLM-5." + "reason": "FlashAttention unsupported for NemotronHForCausalLM is unrelated to GLM-5 generation config validity." }, { "left": "issue:36010", "right": "issue:42757", "accept": false, - "reason": "Both are import errors, but for different symbols from different packages and unrelated code paths." + "reason": "GenerationMixin import failure and is_offline_mode import failure are different missing-symbol regressions." }, { "left": "issue:43066", "right": "issue:45381", "accept": false, - "reason": "Wrong tokenizer decoder type vs Qwen2.5-VL video position ids; different model and bug." + "reason": "Tokenizer decoder type regression is unrelated to Qwen2.5-VL vision_position_ids correctness." }, { "left": "issue:43756", "right": "issue:44485", "accept": false, - "reason": "Smollm3 RoPE layer mismatch vs GLM-5 RoPE implementation discussion; distinct model behaviors." + "reason": "Smollm3 RoPE-layer mismatch and GLM-5 RoPE implementation are different model-specific bugs." }, { "left": "issue:44220", "right": "issue:44655", "accept": false, - "reason": "Audio feature extraction issue vs pipeline save_pretrained failure; unrelated subsystems." + "reason": "Torch fbank feature extraction and Pipeline save_pretrained are unrelated code paths." }, { "left": "issue:44263", "right": "issue:45440", "accept": false, - "reason": "DSA torch.split behavior vs DeepseekV3MoE divergence; not the same bug." + "reason": "GlmMoeDsaIndexer torch.split behavior and DeepseekV3MoE divergence are different model implementations." }, { "left": "issue:36683", "right": "issue:43525", "accept": false, - "reason": "Gemma3 missing vocab_size vs Llama4 missing pad_token_id; same symptom class, different model/config fields." + "reason": "Gemma3Config missing vocab_size and Llama4Config missing pad_token_id are separate config-attribute bugs." }, { "left": "issue:43618", "right": "issue:45216", "accept": false, - "reason": "CLIPOutput attentions omission vs Qwen3.5 save_pretrained regression; unrelated fixes." + "reason": "CLIPOutput attentions assignment and Qwen3.5 save_pretrained checkpoint corruption are unrelated." }, { "left": "issue:43906", "right": "issue:45753", "accept": false, - "reason": "Isolated reproduction of a prior issue vs Qwen3_5 infinite loop on a specific image; not duplicates." + "reason": "An isolated reproduction of issue 38071 is not the same bug as a Qwen3_5 image infinite loop." }, { "left": "issue:36683", "right": "issue:44242", "accept": false, - "reason": "Gemma3 config attribute error vs load balancing loss omission in MoE routing; different code paths." + "reason": "Missing vocab_size in Gemma3Config is unrelated to load-balancing loss handling when output_router_logits=False." }, { "left": "issue:43299", "right": "issue:45753", "accept": false, - "reason": "Qwen3VL MoE model loading breakage vs Qwen3_5 image-specific infinite loop; separate problems." + "reason": "Qwen3VL MoE loading failure and Qwen3_5 image looping are different symptoms and likely different causes." }, { "left": "issue:36683", "right": "issue:43881", "accept": false, - "reason": "Gemma3 config attribute error vs GLM-4V-9B loading failure; different models and failures." + "reason": "Gemma3Config vocab_size absence does not match glm-4v-9b loading failure." }, { "left": "issue:43352", "right": "issue:43976", "accept": false, - "reason": "FlashAttention support bug vs Python version compatibility issue; unrelated." + "reason": "FlashAttention support in Nemotron is unrelated to Python version support in Transformers 5.1.0." }, { "left": "issue:43441", "right": "issue:44380", "accept": false, - "reason": "Ministral FlashAttention failure vs GPT2 attention scaling ignored under SDPA/FlashAttention; different models and fixes." + "reason": "Ministral-3 FlashAttention failure and GPT2 attention scaling ignored are distinct attention-path bugs." }, { "left": "issue:43992", "right": "issue:45310", "accept": false, - "reason": "Missing embed_tokens.weight in UMT5Encoder vs Qwen3.5 Moe from_pretrained error; distinct loading bugs." + "reason": "UMT5Encoder missing embed_tokens.weight and Qwen3.5 MoE from_pretrained error are different loading issues." }, { "left": "issue:43352", "right": "issue:44380", "accept": false, - "reason": "Both involve attention backends, but one is unsupported model/backend, the other ignores a config scaling parameter." + "reason": "Unsupported FlashAttention for Nemotron is not the same as GPT2 scaling being ignored in backend attention implementations." }, { "left": "issue:43867", "right": "issue:45375", "accept": false, - "reason": "State_dict ordering load error vs missing Qwen3_5MoeVisionConfig field; different failure mechanisms." + "reason": "State-dict ordering load error and missing deepstack_visual_indexes are unrelated checkpoint/config problems." }, { "left": "issue:44380", "right": "issue:45479", "accept": false, - "reason": "Attention scaling backend bug vs degenerate zero-loss classification bug; unrelated." + "reason": "Attention scaling bug and degenerate zero-loss classification bug are unrelated." }, { "left": "issue:41669", "right": "issue:44246", "accept": false, - "reason": "Import-time slowdown from import * usage vs intermittent import slowdown; same broad symptom, but not the same concrete bug." + "reason": "Removing import * from models and intermittent import slowdown are different concerns." }, { "left": "issue:43352", "right": "issue:45478", "accept": false, - "reason": "Different Qwen/Nemotron style issue vs Qwen3.5 Moe from_pretrained regression; unrelated model-specific breakages." + "reason": "Nemotron FlashAttention unsupported is different from Qwen3.5 MoE from_pretrained failure." }, { "left": "issue:43618", "right": "issue:44380", "accept": false, - "reason": "CLIP attentions field regression vs GPT2 attention scaling ignored; different affected code and behavior." + "reason": "Missing CLIPOutput attentions assignment is unrelated to GPT2 attention scaling under SDPA/FlashAttention." }, { "left": "issue:44355", "right": "issue:44855", "accept": false, - "reason": "Compiled Python files import errors vs Python 3.13 IndentationError in DebertaV2Model; distinct root causes." + "reason": "Compiled Python file errors and DebertaV2Model import IndentationError are not the same defect." }, { "left": "issue:43064", "right": "issue:44492", "accept": false, - "reason": "FSDP2 optimizer state corruption vs a typo in cache strategies; unrelated." + "reason": "FSDP2/PEFT optimizer-state bug and a cache-strategies typo are unrelated." }, { "left": "issue:36683", "right": "issue:44117", "accept": false, - "reason": "Model config missing vocab_size vs tokenizer mapping sometimes returning None; different layers of the stack." + "reason": "Gemma3Config vocab_size absence and TOKENIZER_MAPPING_NAMES returning None are separate metadata bugs." }, { "left": "issue:42890", "right": "issue:45561", "accept": false, - "reason": "Flaky seed-dependent integration tests vs xdist race on captured_info.txt; both test issues but not the same bug." + "reason": "Missing set_seed in integration tests and xdist race on captured_info.txt are different test flakiness causes." }, { "left": "issue:43097", "right": "issue:43352", "accept": false, - "reason": "Broad removed-API regression vs model-specific FlashAttention support issue; not one underlying change." + "reason": "Removed tie_embeddings_and_encoder_decoder API and FlashAttention support failure are unrelated breakages." }, { "left": "issue:43867", "right": "issue:45357", "accept": false, - "reason": "Generic state_dict loading error vs Qwen3.5 visual encoder key regression; different failure path." + "reason": "Sorted state_dict load failure and incorrect visual encoder keys on save_pretrained are different serialization bugs." }, { "left": "issue:43976", "right": "issue:44938", "accept": false, - "reason": "Python 3.9 compatibility regression vs Python 3.14 load failure; version issues only, not same bug." + "reason": "Python 3.9/3.10 compatibility and Python 3.14 load failure are not the same issue." }, { "left": "issue:43992", "right": "issue:45478", "accept": false, - "reason": "UMT5Encoder missing weight vs Qwen3.5 Moe from_pretrained error; unrelated loading bugs." + "reason": "UMT5Encoder missing embed_tokens.weight is unrelated to Qwen3.5 MoE from_pretrained errors." }, { "left": "issue:44360", "right": "issue:45440", "accept": false, - "reason": "Indexer missing ReLU vs DeepseekV3MoE divergence; different algorithmic issues." + "reason": "DSA indexer ReLU discussion and DeepseekV3MoE divergence are different model internals." }, { "left": "issue:43064", "right": "issue:44655", "accept": false, - "reason": "Optimizer-state corruption in training vs pipeline save_pretrained failure; unrelated subsystems." + "reason": "Trainer/FSDP2 optimizer-state bug and pipeline save_pretrained issue do not share a code path." }, { "left": "issue:36296", "right": "issue:43575", "accept": false, - "reason": "Tensor-parallel training bug vs Qwen2-57B-A14B-Instruct OOM on load; different symptoms and likely causes." + "reason": "Tensor-parallel training bug and tp-induced OOM while loading Qwen2-57B-A14B-Instruct are related broadly only by TP, not by the same bug." }, { "left": "issue:44077", "right": "issue:44380", "accept": false, - "reason": "Optional post_init policy change vs GPT2 attention scaling backend bug; unrelated." + "reason": "patchtsmixer post_init policy and GPT2 attention scaling are unrelated." }, { - "left": "issue:43867", - "right": "issue:44484", + "left": "issue:28282", + "right": "issue:33453", "accept": false, - "reason": "State_dict loading error vs save_pretrained shard size question; not the same bug." + "reason": "AutoModel PyTorch ImportError and tokenizer loading regression are different failure modes." } ] }, @@ -13809,7 +13794,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 43, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -13817,7 +13802,6 @@ "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-392", "nodes": [ - "issue:28282", "issue:30333", "issue:30990", "issue:31795", @@ -13825,15 +13809,14 @@ "issue:34689", "issue:36296", "issue:42548", - "issue:42757", "issue:42831", "issue:42890", "issue:43010", "issue:43502", - "issue:43576", "issue:43618", "issue:43723", "issue:43827", + "issue:43867", "issue:43874", "issue:43901", "issue:44062", @@ -13847,6 +13830,7 @@ "issue:44360", "issue:44368", "issue:44387", + "issue:44484", "issue:44485", "issue:44556", "issue:44655", @@ -13867,7 +13851,7 @@ "issue:45850" ], "soft_pairs": [ - "issue:28282|issue:33453", + "issue:43867|issue:44484", "issue:43618|issue:44857", "issue:43618|issue:44977", "issue:43618|issue:45588", @@ -13878,8 +13862,8 @@ "issue:42890|issue:45600", "issue:43502|issue:44062", "issue:43010|issue:44075", - "issue:42890|issue:45341", "issue:42548|issue:44351", + "issue:42890|issue:45341", "issue:44222|issue:45125", "issue:43502|issue:44485", "issue:44355|issue:44749", @@ -13901,253 +13885,246 @@ "issue:44222|issue:44230", "issue:44355|issue:44655", "issue:43827|issue:44961", - "issue:33453|issue:34689", - "issue:42757|issue:43576" + "issue:33453|issue:34689" ], - "prepared_review_unit_hash": "a36944e34c21615e3afea26aca77962ef1353149f7aa24154a38ffae30e94db3", + "prepared_review_unit_hash": "5dec308bae44c3fd77443a7652868a99c486b2aa5733778b3fc6d8a6afda6d39", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 36, - "serialized_chars": 37954, - "estimated_input_tokens": 9489, - "estimated_eval_tokens": 19234 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 35, + "serialized_chars": 37058, + "estimated_input_tokens": 9265, + "estimated_eval_tokens": 18786 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a loose collection of Transformers v5-era regression/import/load issues, but the proposed soft pairs generally point to different concrete bugs. I would use the broad import-regression report as the representative issue, and reject all soft edges as duplicates.", - "confidence": 0.83, - "canonical_issue_reason": "issue:45278 is the broadest and most representative of the cluster\u2019s recurring theme: breakages after upgrading to v5, especially import/loading regressions.", + "summary": "This cluster is mostly heterogeneous: it mixes broad v5 upgrade/import regressions with unrelated model, FP8, test, and docs issues. No soft pair is clearly the same underlying bug; the best anchor is the broad import-regression report for upgraded installs.", + "confidence": 0.57, + "canonical_issue_reason": "issue:45278 is the broadest and most representative user-facing report here: it describes many import errors after upgrading from 4.57.0 to 5.5.0, which best matches the loose cluster theme of v5 breakages.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 best captures the dominant, user-facing problem pattern in this set and is broad enough to serve as the cluster anchor.", + "best_issue_reason": "issue:45278 is the best overall issue to anchor this cluster because it captures the widest breakage scope, while the others are mostly narrower or unrelated symptoms.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:28282", - "right": "issue:33453", + "left": "issue:43867", + "right": "issue:44484", "accept": false, - "reason": "Different failure classes: missing PyTorch dependency vs tokenizer loading regression." + "reason": "Both involve model loading/saving, but one is a state_dict loading error and the other is a save_pretrained shard-size question; different bugs." }, { "left": "issue:43618", "right": "issue:44857", "accept": false, - "reason": "Unrelated symptoms and code paths; CLIP output attribute handling is not the same as LwDetr AMP crash." + "reason": "CLIP attentions assignment and an AMP/CUDA loss crash are unrelated code paths and symptoms." }, { "left": "issue:43618", "right": "issue:44977", "accept": false, - "reason": "Same broad model family only; one is CLIPOutput attentions, the other is Qwen3.5 flash-attention generation." + "reason": "Different model families and failures; this is not the same underlying bug." }, { "left": "issue:43618", "right": "issue:45588", "accept": false, - "reason": "Both touch attention code, but one is missing attentions assignment and the other is an s_aux=None crash in flash_attention.py." + "reason": "Both touch attention code, but one is about CLIPOutput fields and the other is a flash_attention AttributeError for sink-less models." }, { "left": "issue:43901", "right": "issue:44938", "accept": false, - "reason": "Documentation mismatch vs Python 3.14 import/load failure; not the same bug." + "reason": "Docs wording for return_all_scores versus a Python 3.14 import/load failure are unrelated." }, { "left": "issue:44655", "right": "issue:44938", "accept": false, - "reason": "Saving pipeline objects and loading transformers on Python 3.14 are different issues." + "reason": "Saving Pipeline objects and Python 3.14 load failures are different problems." }, { "left": "issue:42890", "right": "issue:44964", "accept": false, - "reason": "Test seeding flakiness is unrelated to a multimodal model load failure." + "reason": "A flaky SAM HQ integration test is not the same as a Phi-4 multimodal model-loading regression." }, { "left": "issue:42890", "right": "issue:44112", "accept": false, - "reason": "Both are CI/test problems, but they affect different tests and different causes." + "reason": "Both are CI/test failures, but they affect different tests with different root causes." }, { "left": "issue:42890", "right": "issue:45600", "accept": false, - "reason": "Test seed flakiness is not the same as stale auto_mappings config references breaking CI." + "reason": "Different test/model breakages; no clear shared underlying bug." }, { "left": "issue:43502", "right": "issue:44062", "accept": false, - "reason": "local_files_only network leakage and AddedToken keyword collision are unrelated." + "reason": "local_files_only network leakage and AddedToken argument duplication are distinct behaviors." }, { "left": "issue:43010", "right": "issue:44075", "accept": false, - "reason": "Cache no_grad decoration and SGD args not being used are different code paths." + "reason": "Cache update semantics and SGD optimizer args are unrelated." }, { - "left": "issue:42890", - "right": "issue:45341", + "left": "issue:42548", + "right": "issue:44351", "accept": false, - "reason": "A missing set_seed in tests is not the same as a separate testing_utils bug." + "reason": "Both are import errors, but they concern different missing symbols and are not clearly the same fix." }, { - "left": "issue:42548", - "right": "issue:44351", + "left": "issue:42890", + "right": "issue:45341", "accept": false, - "reason": "Both are import errors, but for different symbols and likely different export fixes." + "reason": "Both mention tests, but they are different test cases with different failures." }, { "left": "issue:44222", "right": "issue:45125", "accept": false, - "reason": "FP8 save_pretrained bug and missing tensor-parallel plan are distinct model/serialization problems." + "reason": "FP8 save_pretrained/moe support and tensor-parallel plan support are different code paths." }, { "left": "issue:43502", "right": "issue:44485", "accept": false, - "reason": "local_files_only leakage is unrelated to GLM-5 RoPE implementation." + "reason": "API requests despite local_files_only and GLM-5 RoPE implementation are unrelated." }, { "left": "issue:44355", "right": "issue:44749", "accept": false, - "reason": "Compiled Python file errors and slowed filtering after upgrade are different regressions." + "reason": "Compiled Python file errors and a post-upgrade slowdown are not the same bug." }, { "left": "issue:45125", "right": "issue:45478", "accept": false, - "reason": "Both involve Qwen3.5 MoE, but one is a tensor-parallel plan issue and the other is a broader from_pretrained failure." + "reason": "Both are Qwen3.5 MoE-related, but one is a missing tensor-parallel plan and the other is a generic from_pretrained regression; not enough to treat as the same bug." }, { "left": "issue:30990", "right": "issue:31795", "accept": false, - "reason": "Sentence Transformers loading hang and forward() docs confusion are unrelated." + "reason": "Sentence Transformers loading stall versus a forward-docs clarification are unrelated." }, { "left": "issue:45125", "right": "issue:45375", "accept": false, - "reason": "Missing tensor-parallel plan and missing config field are different Qwen3.5 MoE defects." + "reason": "Tensor-parallel support and a missing config field in Qwen3_5MoeVisionConfig are different issues." }, { "left": "issue:44387", "right": "issue:44556", "accept": false, - "reason": "Int4 CUDA memory/OOM behavior is not the same as checkpoint reload failure after upgrade." + "reason": "Memory/OOM behavior under int4 quantization and checkpoint reload compatibility after upgrade are different regressions." }, { "left": "issue:30333", "right": "issue:33453", "accept": false, - "reason": "MLflow reporting after failed training and tokenizer loading regression are unrelated." + "reason": "MLflow reporting on failed training jobs is unrelated to tokenizer loading regression." }, { "left": "issue:43010", "right": "issue:45278", "accept": false, - "reason": "A cache update no_grad request is not the same as broad import errors after v5.5.0." + "reason": "Cache update no_grad semantics and broad import errors after upgrade are unrelated." }, { "left": "issue:43723", "right": "issue:44556", "accept": false, - "reason": "Tokenizer loading regression and checkpoint reload regression may rhyme, but they are not the same concrete bug." + "reason": "Tokenizer loading failure and checkpoint reload failure are both loading-related, but not clearly the same concrete bug." }, { "left": "issue:43502", "right": "issue:44222", "accept": false, - "reason": "local_files_only network calls and FP8 save_pretrained for MoE are unrelated." + "reason": "Network access despite local_files_only and FP8 MoE save_pretrained are unrelated." }, { "left": "issue:43010", "right": "issue:44368", "accept": false, - "reason": "No_grad on cache updates and a tied-embeddings warning in LoRA fine-tuning are different issues." + "reason": "Cache update decoration and a tie_word_embeddings warning in LoRA fine-tuning are unrelated." }, { "left": "issue:44315", "right": "issue:44360", "accept": false, - "reason": "Liger Kernel application and a DSA indexer ReLU discussion have no shared bug path." + "reason": "Liger Kernel application in model_init and a DSA indexer activation missing ReLU are different subsystems." }, { "left": "issue:43010", "right": "issue:45850", "accept": false, - "reason": "A specific cache mutation bug is not the same as a vague report that v5 breaks too many models." + "reason": "A specific cache-update bug is not the same as a broad complaint that v5 breaks too many models." }, { "left": "issue:43502", "right": "issue:44961", "accept": false, - "reason": "Network requests with local_files_only and an unrelated placeholder issue are not duplicates." + "reason": "local_files_only network leakage has nothing to do with the unrelated 'racoon' issue." }, { "left": "issue:42831", "right": "issue:43874", "accept": false, - "reason": "FineGrainedFP8 accuracy and GLM46V image patch counting are separate model bugs." + "reason": "FineGrainedFP8 accuracy and a missing image-processor method are unrelated." }, { "left": "issue:30333", "right": "issue:36296", "accept": false, - "reason": "Failed-job MLflow reporting and tensor-parallel training are unrelated." + "reason": "MLflow failure reporting and tensor parallel training are different bugs." }, { "left": "issue:44355", "right": "issue:45071", "accept": false, - "reason": "Compiled-file errors and PretrainedConfig type-checking breakage are different regressions." + "reason": "Compiled-file execution errors and PretrainedConfig type-checking regressions are different issues." }, { "left": "issue:44222", "right": "issue:44230", "accept": false, - "reason": "Both are fp8-themed, but one is MoE save_pretrained and the other is fp8 inference support." + "reason": "Both mention FP8 and MoE, but one is about save_pretrained and the other about inference support; not the same bug." }, { "left": "issue:44355", "right": "issue:44655", "accept": false, - "reason": "Compiled Python file failures and pipeline save_pretrained are unrelated." + "reason": "Compiled Python file errors and pipeline save_pretrained support are unrelated." }, { "left": "issue:43827", "right": "issue:44961", "accept": false, - "reason": "Documentation referencing pipeline() and the placeholder racoon issue are not duplicates." + "reason": "Docs still referencing pipeline() and an unrelated issue titled 'racoon' are not duplicates." }, { "left": "issue:33453", "right": "issue:34689", "accept": false, - "reason": "Tokenizer loading regression and Llama 3.2 vision model loading breakage are different model-loading bugs." - }, - { - "left": "issue:42757", - "right": "issue:43576", - "accept": false, - "reason": "Missing is_offline_mode import from huggingface_hub and broken transformers env command are different failures." + "reason": "Tokenizer loading regression and Llama 3.2 vision model loading breakage are both loading issues, but not the same concrete failure." } ] }, @@ -14163,7 +14140,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 44, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -14178,6 +14155,7 @@ "issue:41628", "issue:41669", "issue:42548", + "issue:42757", "issue:42890", "issue:43010", "issue:43299", @@ -14195,7 +14173,6 @@ "issue:44246", "issue:44261", "issue:44273", - "issue:44295", "issue:44297", "issue:44315", "issue:44351", @@ -14221,11 +14198,12 @@ "issue:45850" ], "soft_pairs": [ + "issue:42757|issue:43576", "issue:43299|issue:44556", "issue:43010|issue:45656", "issue:33453|issue:36296", - "issue:43576|issue:43824", "issue:43576|issue:45071", + "issue:43576|issue:43824", "issue:44961|issue:45468", "issue:31795|issue:38617", "issue:41628|issue:42548", @@ -14259,15 +14237,14 @@ "issue:43576|issue:44908", "issue:44908|issue:45071", "issue:44297|issue:45230", - "issue:44295|issue:45230", "issue:41669|issue:44351" ], - "prepared_review_unit_hash": "dd171e46d16a7c9cd02795734c092479224567693fff408c7645f63e5777f74f", + "prepared_review_unit_hash": "2507ad7f6c38cf1687e2322fc80894294d5c7c61d8e0d8d4d4c878b7c9dacf34", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -14275,261 +14252,261 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 40, - "serialized_chars": 38936, - "estimated_input_tokens": 9734, - "estimated_eval_tokens": 19724 + "serialized_chars": 38932, + "estimated_input_tokens": 9733, + "estimated_eval_tokens": 19722 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "No soft pair looks like a safe duplicate merge on titles alone. Most are broad v5 regressions, import/export failures, or unrelated subsystem bugs that share only a loose theme.", - "confidence": 0.58, - "canonical_issue_reason": "issue:44246 is the best standalone representative here: it is a concrete, actionable import-regression report, while most other candidates are either vague or narrower symptoms of different bugs.", + "summary": "Mostly a heterogeneous mix of Transformers v5 regressions, import/export failures, and model-specific bugs; the soft pairs are thematically similar in places but not the same concrete underlying issue. I would not merge any of the candidate pairs as duplicates.", + "confidence": 0.32, + "canonical_issue_reason": "issue:45850 is the broadest umbrella for the overall cluster theme (v5 breaks many models), so it best represents the set even though it is vague.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44246 is the strongest overall issue to anchor the cluster because it describes a specific user-visible failure with a plausible shared area (import/lazy loading) and enough detail to be useful for triage.", + "best_issue_reason": "issue:45850 is the closest global anchor for the cluster, but it is still too generic to serve as a precise duplicate target.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:42757", + "right": "issue:43576", + "accept": false, + "reason": "Different failures: a missing huggingface_hub symbol vs a broken transformers env command." + }, { "left": "issue:43299", "right": "issue:44556", "accept": false, - "reason": "Both are v5 checkpoint-loading regressions, but they hit different model families and likely different failure paths; too broad to treat as the same bug." + "reason": "Both are v5 regressions, but they describe different model-loading breakages and code paths." }, { "left": "issue:43010", "right": "issue:45656", "accept": false, - "reason": "Cache update no_grad decoration and deepspeed double optimizer-step are unrelated code paths." + "reason": "Cache update no_grad semantics and deepspeed double optimizer step are unrelated bugs." }, { "left": "issue:33453", "right": "issue:36296", "accept": false, - "reason": "Tokenizer-loading regression and tensor-parallel training bug are different problems." + "reason": "Tokenizer loading regression is unrelated to tensor-parallel training behavior." }, { "left": "issue:43576", - "right": "issue:43824", + "right": "issue:45071", "accept": false, - "reason": "Broken env command and missing top-level Qwen VL export are unrelated symptoms." + "reason": "Broken env CLI and PretrainedConfig type-checking are separate issues." }, { "left": "issue:43576", - "right": "issue:45071", + "right": "issue:43824", "accept": false, - "reason": "A broken env command is not the same as PreTrainedConfig type-checking breakage." + "reason": "CLI breakage is not the same as a missing top-level model import." }, { "left": "issue:44961", "right": "issue:45468", "accept": false, - "reason": "No meaningful overlap beyond both being generic issue reports." + "reason": "No clear overlap; one is a vague placeholder and the other is a Gemma audio encoding bug." }, { "left": "issue:31795", "right": "issue:38617", "accept": false, - "reason": "Documentation confusion and an ImportError for a missing symbol are not the same bug." + "reason": "Doc confusion about forward args does not match an import error for configuration_utils." }, { "left": "issue:41628", "right": "issue:42548", "accept": false, - "reason": "Both are import failures, but for different missing symbols and likely different export fixes." + "reason": "Both are import errors, but they concern different symbols and likely different missing exports." }, { "left": "issue:38617", "right": "issue:43576", "accept": false, - "reason": "Missing layer_type_validation import and the broken env command are unrelated." + "reason": "ImportError for a config helper is unrelated to the env command regression." }, { "left": "issue:43010", "right": "issue:43976", "accept": false, - "reason": "Decorating cache updates with no_grad and Python-version incompatibility are unrelated." + "reason": "No_grad decoration on cache updates is unrelated to Python-version compatibility." }, { "left": "issue:43576", "right": "issue:44351", "accept": false, - "reason": "Both concern imports, but they refer to different public symbols and different regressions." + "reason": "Broken CLI and missing HybridCache import are different concrete problems." }, { "left": "issue:44908", "right": "issue:44961", "accept": false, - "reason": "Scheduler kwargs handling and an unrelated issue titled 'racoon' do not match." + "reason": "Scheduler kwargs bug is unrelated to the placeholder issue." }, { "left": "issue:36296", "right": "issue:43901", "accept": false, - "reason": "Tensor-parallel training and a pipeline docs mismatch are unrelated." + "reason": "Tensor-parallel training bug and docs mismatch for pipeline output are unrelated." }, { "left": "issue:41628", "right": "issue:44355", "accept": false, - "reason": "Top-level import failure and compiled-file execution errors do not point to the same defect." + "reason": "Top-level import missing and compiled-file runtime errors are not the same bug." }, { "left": "issue:36296", "right": "issue:43526", "accept": false, - "reason": "Tensor parallel training and BeitImageProcessorFast label reduction are unrelated." + "reason": "Tensor-parallel training and BeitImageProcessorFast label reduction are unrelated." }, { "left": "issue:44261", "right": "issue:44360", "accept": false, - "reason": "A precision/config issue in MLA q_a_layernorm is not the same as a DSA indexer activation omission." + "reason": "LayerNorm epsilon precision issue does not match a missing ReLU in the DSA indexer." }, { "left": "issue:44623", "right": "issue:45230", "accept": false, - "reason": "A missing processor.save_pretrained output bug and an empty 'Bug report' title are not enough to establish sameness." + "reason": "Missing files on save_pretrained is unrelated to a generic bug report." }, { "left": "issue:44273", "right": "issue:45542", "accept": false, - "reason": "Lazy loading failures and a TensorBoard-without-TensorFlow backend error are different import-time problems." + "reason": "Lazy loading failure and undefined tf backend error are different code paths." }, { "left": "issue:44273", "right": "issue:45003", "accept": false, - "reason": "Both touch import/lazy-loading machinery, but the reported failures and likely fixes are different." + "reason": "Both touch import mechanics, but one is lazy loading and the other is unsafe sys.modules access." }, { "left": "issue:44393", "right": "issue:45753", "accept": false, - "reason": "Same model family, but different symptoms and repros; not safe to merge as one bug." + "reason": "Different Qwen model symptoms: 2D box hallucination vs infinite loop on a specific image." }, { "left": "issue:43576", "right": "issue:44556", "accept": false, - "reason": "Broken env command and checkpoint reload regressions are unrelated." + "reason": "General CLI breakage and checkpoint reload incompatibility are not the same underlying bug." }, { "left": "issue:44038", "right": "issue:45125", "accept": false, - "reason": "Qwen3-VL/Moe loading trouble and missing tensor-parallel plan are different concrete issues." + "reason": "Related Qwen3-MoE family, but one is a broader model-loading issue and the other is missing tensor-parallel plan support." }, { "left": "issue:44393", "right": "issue:45071", "accept": false, - "reason": "Qwen3-VL hallucination/output issues and PretrainedConfig type checking are unrelated." + "reason": "Model-specific output errors are unrelated to PretrainedConfig type checking." }, { "left": "issue:43525", "right": "issue:45850", "accept": false, - "reason": "A specific missing pad_token_id attribute and a vague 'breaks too many models' complaint are not the same bug." + "reason": "Missing pad_token_id in Llama4Config is a specific config bug, not the generic v5-breaks-many-models report." }, { "left": "issue:44556", "right": "issue:45092", "accept": false, - "reason": "Both mention old-checkpoint incompatibility after v5, but they appear to affect different model/loading paths and are too broad to treat as duplicates." + "reason": "Both are upgrade incompatibilities, but they affect different models and different initialization paths." }, { "left": "issue:41669", "right": "issue:43673", "accept": false, - "reason": "Import-star performance regression and chunked-prefill cache absence are different issues." + "reason": "Import-star performance issue and missing GenerationMixin cache are separate problems." }, { "left": "issue:44373", "right": "issue:44961", "accept": false, - "reason": "Wrong position_ids docstring and an unrelated issue titled 'racoon' are not duplicates." + "reason": "Wrong docstring for position_ids is unrelated to the placeholder issue." }, { "left": "issue:43572", "right": "issue:45850", "accept": false, - "reason": "A specific StableLmConfig field regression and a generic 'too many models' complaint do not match." + "reason": "Specific missing pad_token_idx bug is not the same as the broad v5 regression complaint." }, { "left": "issue:45362", "right": "issue:45850", "accept": false, - "reason": "A Qwen3.5 chat crash and a vague broad regression report are not the same concrete bug." + "reason": "Qwen3.5 chat crash is a specific model/runtime failure, not the generic complaint." }, { "left": "issue:44704", "right": "issue:44908", "accept": false, - "reason": "AutoProcessor cached_file kwargs forwarding and inverse_sqrt scheduler kwargs are different code paths." + "reason": "Passing kwargs to cached_file and scheduler kwargs are unrelated API bugs." }, { "left": "issue:42890", "right": "issue:44908", "accept": false, - "reason": "Missing set_seed in SAM HQ tests and a scheduler kwargs bug are unrelated." + "reason": "Flaky integration tests due to missing seed do not match scheduler kwargs handling." }, { "left": "issue:44246", "right": "issue:44273", "accept": false, - "reason": "Both concern import/lazy-loading behavior, but one reports import slowness and the other a functional lazy-loading failure; not the same concrete bug." + "reason": "Slow import sometimes and lazy loading not working are related only at a high level, not the same concrete bug." }, { "left": "issue:43408", "right": "issue:44315", "accept": false, - "reason": "Model-type mismatch warning and Liger kernel application through model_init are unrelated." + "reason": "sam3 tracker/model-type warning is unrelated to Liger Kernel not being applied in model_init." }, { "left": "issue:43976", "right": "issue:44393", "accept": false, - "reason": "Python version support and Qwen3-VL generation errors are unrelated." + "reason": "Python-version support regression is unrelated to Qwen3-VL bounding-box output errors." }, { "left": "issue:43352", "right": "issue:44393", "accept": false, - "reason": "Flash Attention support gating and Qwen3-VL output errors are different problems." + "reason": "Flash Attention support error for Nemotron and Qwen3-VL output issues are different bugs." }, { "left": "issue:43576", "right": "issue:44908", "accept": false, - "reason": "A broken env command and scheduler kwarg handling are unrelated." + "reason": "Broken env CLI and inverse_sqrt scheduler kwargs are unrelated." }, { "left": "issue:44908", "right": "issue:45071", "accept": false, - "reason": "Scheduler kwargs and PretrainedConfig type checking do not share the same bug." + "reason": "Scheduler kwargs bug and PretrainedConfig type-checking regression are unrelated." }, { "left": "issue:44297", "right": "issue:45230", "accept": false, - "reason": "Tokenizer save_pretrained metadata mismatch and a generic bug report are not duplicates." - }, - { - "left": "issue:44295", - "right": "issue:45230", - "accept": false, - "reason": "Position_ids buffer access error and a generic bug report are not duplicates." + "reason": "Tokenizer_class mismatch in save_pretrained is unrelated to a generic bug report." }, { "left": "issue:41669", "right": "issue:44351", "accept": false, - "reason": "Removing import * for performance and missing HybridCache export are different import-related regressions." + "reason": "Import-star performance issue is unrelated to missing HybridCache import." } ] }, @@ -14545,7 +14522,7 @@ "component_index": 2, "component_count": 16, "review_unit_index": 45, - "review_unit_count": 45, + "review_unit_count": 46, "status": "reviewed", "reason": null, "source": "llm", @@ -14565,7 +14542,6 @@ "issue:42371", "issue:42913", "issue:43066", - "issue:43298", "issue:43502", "issue:43519", "issue:43525", @@ -14581,6 +14557,7 @@ "issue:44261", "issue:44263", "issue:44273", + "issue:44295", "issue:44315", "issue:44360", "issue:44393", @@ -14603,8 +14580,9 @@ "issue:45850" ], "soft_pairs": [ - "issue:43673|issue:44492", + "issue:44295|issue:45230", "issue:41669|issue:45341", + "issue:43673|issue:44492", "issue:45278|issue:45850", "issue:44393|issue:45478", "issue:43874|issue:45850", @@ -14616,8 +14594,8 @@ "issue:41669|issue:44908", "issue:42371|issue:44492", "issue:43576|issue:44273", - "issue:44360|issue:45468", "issue:44655|issue:44861", + "issue:44360|issue:45468", "issue:44492|issue:45850", "issue:44273|issue:44908", "issue:45230|issue:45310", @@ -14652,15 +14630,14 @@ "issue:31515|issue:36296", "issue:31515|issue:31795", "issue:44230|issue:45310", - "issue:31515|issue:33453", - "issue:43298|issue:44230" + "issue:31515|issue:33453" ], - "prepared_review_unit_hash": "b5b487366e22d8d4461b6b6961f025a8714dedee62d4ecb355c8248bf15ab2fc", + "prepared_review_unit_hash": "9d5f0a504e00a7b272480ee3e8a98c95a69f7523819e6acc0adf89e39f3ee21d", "component_budget": { "node_count": 392, "item_count": 392, "soft_pair_count": 1480, - "serialized_chars": 761408, + "serialized_chars": 761406, "estimated_input_tokens": 190352, "estimated_eval_tokens": 380960 }, @@ -14668,321 +14645,390 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 51, - "serialized_chars": 42264, - "estimated_input_tokens": 10566, - "estimated_eval_tokens": 21388 + "serialized_chars": 42295, + "estimated_input_tokens": 10574, + "estimated_eval_tokens": 21404 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This is a loose cluster of mostly unrelated Transformers v5 regression reports. The strongest common thread is broad model-loading / compatibility breakage after version upgrades, but the soft-linked pairs are generally too different to treat as duplicates.", - "confidence": 0.64, - "canonical_issue_reason": "issue:45278 is the best umbrella issue: it concretely reports widespread breakage after upgrading to v5.5.0, which is broader and more representative than the more specific or more vague reports.", + "summary": "The set is a loose collection of Transformers-related issues, mostly v5 migration regressions and a few unrelated model-specific bugs. I did not find any soft pair that clearly describes the same concrete bug/change, so all soft edges are rejected. The most representative issue is the broad v5 upgrade regression report.", + "confidence": 0.71, + "canonical_issue_reason": "issue:45278 is the best representative issue because it clearly captures the broad v5 upgrade regression theme (\u201cmany import errors after update from 4.57.0 to 5.5.0\u201d) that several other items orbit, while still being concrete enough to anchor the cluster.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the most suitable global anchor for this cluster because it captures the recurring upgrade-regression theme without being as vague as 'too many models break'.", + "best_issue_reason": "issue:45278 is the most suitable global issue choice: it is specific, actionable, and broadly representative of the upgrade-related breakage pattern in this set.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43673", - "right": "issue:44492", + "left": "issue:44295", + "right": "issue:45230", "accept": false, - "reason": "Different bugs: missing cache during chunked prefill vs a typo in cache strategy docs/code." + "reason": "Specific position_ids buffer error vs generic bug report; no evidence of the same underlying defect." }, { "left": "issue:41669", "right": "issue:45341", "accept": false, - "reason": "Unrelated: import-star performance issue vs a small testing_utils bug." + "reason": "Import-* performance/refactor issue vs a testing_utils bug; different code paths and symptoms." + }, + { + "left": "issue:43673", + "right": "issue:44492", + "accept": false, + "reason": "Chunked_prefill cache-missing bug vs a typo in cache strategies; not the same bug." }, { "left": "issue:45278", "right": "issue:45850", "accept": false, - "reason": "Same broad complaint about v5 breakage, but not the same concrete bug or fixable change." + "reason": "Both are broad v5 breakage complaints, but they are too umbrella-level to be the same concrete issue." }, { "left": "issue:44393", "right": "issue:45478", "accept": false, - "reason": "Different model families and failures: Qwen3-VL 2D bbox issue vs Qwen3.5 MoE from_pretrained error." + "reason": "Qwen3-VL bbox output problem vs Qwen3.5 MoE from_pretrained error; unrelated failures." }, { "left": "issue:43874", "right": "issue:45850", "accept": false, - "reason": "Specific missing-method multimodal token bug vs a generic meta complaint about v5 breaking models." + "reason": "Missing image-processor method in GLM46V vs a generic \u201ctoo many models break\u201d report; not one bug." }, { "left": "issue:41669", "right": "issue:44492", "accept": false, - "reason": "Import-star cleanup/performance issue is unrelated to cache-strategy typo." + "reason": "Import-* removal/performance issue vs cache-strategy typo; no shared failure." }, { "left": "issue:44315", "right": "issue:44829", "accept": false, - "reason": "Different code paths: Liger kernel application vs flash_attention_3 training degeneration." + "reason": "model_init/Liger Kernel application bug vs flash_attention_3 degenerate training; distinct code paths." }, { "left": "issue:43827", "right": "issue:44908", "accept": false, - "reason": "Docs referencing removed pipeline APIs is unrelated to inverse_sqrt scheduler kwargs handling." + "reason": "Docs still referencing pipeline() vs scheduler kwargs handling; completely different fixes." }, { "left": "issue:44077", "right": "issue:44861", "accept": false, - "reason": "Different failures in different helpers; no shared underlying bug." + "reason": "Optional post_init restriction vs tied-weight-key AttributeError; unrelated model internals." }, { "left": "issue:31795", "right": "issue:33453", "accept": false, - "reason": "Docs confusion vs a tokenizer loading regression." + "reason": "Documentation confusion in model.forward vs tokenizer loading regression; not the same underlying problem." }, { "left": "issue:41669", "right": "issue:44908", "accept": false, - "reason": "Performance/import cleanup is unrelated to scheduler kwargs propagation." + "reason": "Import-* cleanup/perf issue vs inverse_sqrt scheduler kwargs bug; no overlap." }, { "left": "issue:42371", "right": "issue:44492", "accept": false, - "reason": "TF32 API migration issue vs cache-strategy typo." + "reason": "TF32 API guidance vs cache-strategy typo; unrelated." }, { "left": "issue:43576", "right": "issue:44273", "accept": false, - "reason": "Broken env command and lazy-loading failure are separate problems." + "reason": "Broken `transformers env` command vs lazy-loading regression; different CLI/runtime paths." }, { - "left": "issue:44360", - "right": "issue:45468", + "left": "issue:44655", + "right": "issue:44861", "accept": false, - "reason": "Different model implementations and unrelated bugs." + "reason": "Pipeline save_pretrained failure vs tied_weight_keys crash; different serialization bugs." }, { - "left": "issue:44655", - "right": "issue:44861", + "left": "issue:44360", + "right": "issue:45468", "accept": false, - "reason": "Saving Pipeline objects is a different path from tied-weight-key attribute handling." + "reason": "DSA indexer ReLU issue vs Gemma4Audio positional encoding bug; unrelated components." }, { "left": "issue:44492", "right": "issue:45850", "accept": false, - "reason": "A typo in cache strategies is not the same as a broad v5 breakage report." + "reason": "A typo issue vs a broad v5 breakage complaint; not the same defect." }, { "left": "issue:44273", "right": "issue:44908", "accept": false, - "reason": "Lazy loading failure vs scheduler kwargs bug." + "reason": "Lazy-loading regression vs inverse_sqrt scheduler kwargs bug; no common code path." }, { "left": "issue:45230", "right": "issue:45310", "accept": false, - "reason": "Generic bug report vs a specific Qwen3.5 MoE from_pretrained error." + "reason": "Generic bug report placeholder vs specific Qwen3.5 MoE from_pretrained error; insufficient overlap." }, { "left": "issue:43519", "right": "issue:44485", "accept": false, - "reason": "Timestamp calculation bug vs RoPE implementation issue." + "reason": "Incorrect timestamp calculation in Qwen3VL processor vs GLM-5 RoPE implementation; different model subsystems." }, { "left": "issue:41669", "right": "issue:43704", "accept": false, - "reason": "Import-star usage cleanup is unrelated to a VRAM leak." + "reason": "Import-* removal/performance issue vs VRAM leak across dataloader threads; unrelated." }, { "left": "issue:43519", "right": "issue:44908", "accept": false, - "reason": "Timestamp calculation bug vs scheduler keyword handling." + "reason": "Qwen3VL timestamp bug vs scheduler kwargs bug; different areas." }, { "left": "issue:31795", "right": "issue:34689", "accept": false, - "reason": "Documentation confusion vs a specific model-loading regression." + "reason": "Documentation confusion vs model loading breakage for Llama 3.2; not the same bug." }, { "left": "issue:31795", "right": "issue:37428", "accept": false, - "reason": "Docs issue vs an ImportError from a removed symbol." + "reason": "Docs issue vs ImportError for flash attention util; different problem statements." }, { "left": "issue:44315", "right": "issue:45092", "accept": false, - "reason": "Both touch model initialization, but the underlying failures are different." + "reason": "Liger Kernel application bug with model_init vs old InternVL2 remote-code/meta-init incompatibility; separate load-time issues." }, { "left": "issue:43704", "right": "issue:44485", "accept": false, - "reason": "VRAM leak and RoPE implementation are unrelated." + "reason": "VRAM leak in multi-threaded dataloading vs RoPE implementation discussion; unrelated." }, { "left": "issue:44485", "right": "issue:45468", "accept": false, - "reason": "Different positional/rope implementations for different models." + "reason": "GLM-5 RoPE implementation vs Gemma4Audio positional encoding; different models and failures." }, { "left": "issue:42371", "right": "issue:43704", "accept": false, - "reason": "TF32 settings migration vs VRAM leak." + "reason": "TF32 behavior API guidance vs VRAM leak; no shared defect." }, { "left": "issue:43502", "right": "issue:43519", "accept": false, - "reason": "Local-files-only network leakage vs Qwen3VL timestamp math." + "reason": "local_files_only still making requests vs Qwen3VL timestamp calculation; unrelated." }, { "left": "issue:43519", "right": "issue:44623", "accept": false, - "reason": "Different processor bugs: timestamp math vs save_pretrained missing files." + "reason": "Qwen3VL timestamp bug vs missing processor.save_pretrained files; different components." }, { "left": "issue:43519", "right": "issue:43704", "accept": false, - "reason": "Timestamp bug vs VRAM leak." + "reason": "Timestamp calculation bug vs VRAM leak in dataloader threads; not the same bug." }, { "left": "issue:44263", "right": "issue:45468", "accept": false, - "reason": "Different indexer and positional-encoding issues." + "reason": "torch.split return-values issue in DSA indexer vs Gemma4Audio positional encoding; unrelated." }, { "left": "issue:43606", "right": "issue:45468", "accept": false, - "reason": "CPU offload device mismatch vs Gemma audio positional encoding." + "reason": "CPU offload device mismatch vs Gemma4Audio positional encoding; different failures." }, { "left": "issue:44261", "right": "issue:45468", "accept": false, - "reason": "RMS norm epsilon precision issue vs unrelated Gemma audio encoding bug." + "reason": "Missing rms_norm_eps in MLA q_a_layernorm vs Gemma4Audio positional encoding; separate issues." }, { "left": "issue:43704", "right": "issue:45341", "accept": false, - "reason": "VRAM leak vs a testing_utils bug." + "reason": "VRAM leak vs testing_utils bug; no common code path." }, { "left": "issue:42913", "right": "issue:43066", "accept": false, - "reason": "Both are tokenizer-related, but they describe different concrete regressions." + "reason": "Both mention tokenizer behavior in v5, but one is a broad regression and the other a specific decoder-type mismatch; not clearly the same bug." }, { "left": "issue:44908", "right": "issue:44998", "accept": false, - "reason": "Scheduler bug vs an unrelated placeholder issue." + "reason": "Scheduler kwargs bug vs unrelated placeholder issue title; clearly different." }, { "left": "issue:44861", "right": "issue:45290", "accept": false, - "reason": "Different failure modes in different code paths." + "reason": "tied_weight_keys AttributeError vs chat-template crash with tool calls; different code paths." }, { "left": "issue:43704", "right": "issue:44998", "accept": false, - "reason": "VRAM leak vs unrelated placeholder issue." + "reason": "VRAM leak vs unrelated placeholder title; no overlap." }, { "left": "issue:41669", "right": "issue:44998", "accept": false, - "reason": "Import cleanup performance issue vs unrelated placeholder issue." + "reason": "Import-* refactor issue vs unrelated placeholder title; not a duplicate." }, { "left": "issue:43525", "right": "issue:44861", "accept": false, - "reason": "Missing config attribute vs tied-weight-key attribute crash." + "reason": "Missing pad_token_id on Llama4Config vs tied_weight_keys crash; different config/serialization bugs." + }, + { + "left": "issue:43066", + "right": "issue:44998", + "accept": false, + "reason": "Wrong tokenizer decoder type vs unrelated placeholder title; no match." }, { "left": "issue:43572", "right": "issue:44861", "accept": false, - "reason": "StableLm pad_token_idx regression vs tied-weight-key handling." + "reason": "Missing pad_token_idx in StableLmConfig vs tied_weight_keys crash; unrelated." }, { "left": "issue:31515", "right": "issue:38617", "accept": false, - "reason": "Slow checkpoint loading vs an ImportError for a removed config utility." + "reason": "Slow checkpoint loading vs ImportError for layer_type_validation; different symptoms and subsystems." }, { "left": "issue:44360", "right": "issue:44998", "accept": false, - "reason": "DSA indexer bug vs unrelated placeholder issue." + "reason": "DSA indexer bug vs unrelated placeholder title; no shared bug." }, { "left": "issue:44230", "right": "issue:44623", "accept": false, - "reason": "FP8 support request/bug vs processor save_pretrained missing files." + "reason": "fp8 inference support request vs processor.save_pretrained missing files; separate topics." }, { "left": "issue:30333", "right": "issue:31515", "accept": false, - "reason": "MLflow job-reporting issue vs slow from_pretrained loading." + "reason": "MLFlow training-job reporting bug vs slow from_pretrained checkpoint loading; unrelated." }, { "left": "issue:31515", "right": "issue:36296", "accept": false, - "reason": "Checkpoint loading slowdown vs tensor-parallel training bug." + "reason": "Slow checkpoint loading vs tensor parallel training bug; different issues." }, { "left": "issue:31515", "right": "issue:31795", "accept": false, - "reason": "Performance regression vs documentation confusion." + "reason": "Slow loading vs documentation confusion; not the same underlying problem." }, { "left": "issue:44230", "right": "issue:45310", "accept": false, - "reason": "FP8 support issue vs Qwen3.5 MoE from_pretrained error; related model family but different bugs." + "reason": "fp8 support request vs Qwen3.5 MoE from_pretrained error; request vs bug, and different code paths." }, { "left": "issue:31515", "right": "issue:33453", "accept": false, - "reason": "Slow checkpoint loading vs tokenizer loading regression." - }, + "reason": "Slow checkpoint loading vs tokenizer loading regression; different failures." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 46, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:43298", + "issue:44230" + ], + "soft_pairs": [ + "issue:43298|issue:44230" + ], + "prepared_review_unit_hash": "f4b8d4e582d421f4989132f9f9b25da59169bb9c2a138bc5d9f29d2bbb7cdc11", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1467, + "estimated_input_tokens": 367, + "estimated_eval_tokens": 990 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The two issues are about different problems: audio continuous batching support vs. FP8 inference support for Qwen/VL/MoE models. They should not be deduplicated.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "issue:43298 is the better representative issue because it is open and describes a concrete support gap, while issue:44230 is a separate, already-closed FP8-specific request.", + "best_pr_reason": null, + "soft_edge_verdicts": [ { "left": "issue:43298", "right": "issue:44230", "accept": false, - "reason": "Continuous batching audio-model support vs FP8 inference support." + "reason": "Different underlying feature/bug requests with no concrete overlap: one is about continuous batching for audio models, the other about FP8 inference support for specific Qwen models." } ] }, @@ -15012,12 +15058,12 @@ "soft_pairs": [ "issue:26350|issue:33260" ], - "prepared_review_unit_hash": "042c13160c230077e5b466365afd7261046ad29da3a0dfa6022a334d5544917f", + "prepared_review_unit_hash": "3dcd761064374f19c980d4f34926fa32ed40df64045a28aac96ec6507e2e229a", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1590, + "serialized_chars": 1589, "estimated_input_tokens": 398, "estimated_eval_tokens": 1052 }, @@ -15025,7 +15071,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1590, + "serialized_chars": 1589, "estimated_input_tokens": 398, "estimated_eval_tokens": 1052 }, @@ -15034,18 +15080,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are two different community contribution tracking issues for unrelated features (Flash Attention 2 vs GGUF support). The soft similarity is superficial and should not be treated as a duplicate.", - "confidence": 0.96, + "summary": "These are both broad community-contribution feature requests, but they target different capabilities: Flash Attention 2 support vs GGUF support. They are not the same underlying issue.", + "confidence": 0.98, "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:26350 is the stronger representative of the cluster because it has significantly higher discussion activity and is the more established tracking issue, even though it is not a duplicate of issue:33260.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:26350", "right": "issue:33260", "accept": false, - "reason": "Different underlying requests: one is about Flash Attention 2 architecture support, the other is about GGUF architecture support. They share a template and scope style, not the same bug or change." + "reason": "Different requested features and code paths; one is about Flash Attention 2 architecture support, the other about GGUF architecture support. Similar framing does not make them duplicates." } ] }, @@ -15082,12 +15128,12 @@ "issue:43834|issue:44365", "issue:44365|issue:44370" ], - "prepared_review_unit_hash": "70efd57aa823bc8b35dbfe143ecae77709451c4243c4a4a348e3037b2ecd7c5b", + "prepared_review_unit_hash": "d645ab4a25de4ffb69c96ff12779684dc2f22ddf05070fa69bfef5a6342d87ba", "component_budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 4453, + "serialized_chars": 4455, "estimated_input_tokens": 1114, "estimated_eval_tokens": 2484 }, @@ -15095,7 +15141,7 @@ "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 4453, + "serialized_chars": 4455, "estimated_input_tokens": 1114, "estimated_eval_tokens": 2484 }, @@ -15104,48 +15150,48 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are all i18n translation-request issues with highly similar templated wording, but they do not appear to describe the same concrete translation task. The Turkish request is specific, while the others are generic placeholder issues for potentially different languages.", - "confidence": 0.96, - "canonical_issue_reason": "issue:27088 is the only concrete, language-specific request ([i18n-TR] Turkish); the others are templated placeholder issues and are not clearly the same underlying request.", + "summary": "These are translation-docs requests, but they are not the same underlying issue: one is specifically Turkish, while the others are generic placeholder-language requests. No soft duplicate edges should be merged.", + "confidence": 0.91, + "canonical_issue_reason": "issue:27088 is the only concrete, language-specific request; the others read like generic template entries rather than the same bug report.", "canonical_pr_reason": null, - "best_issue_reason": "issue:27088 is the best representative because it is specific and actionable, whereas the others are generic template variants with no concrete language identified.", + "best_issue_reason": "issue:27088 is the best representative because it is specific, actionable, and not just a placeholder title.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:27088", "right": "issue:44370", "accept": false, - "reason": "Same translation-template wording, but no evidence they request the same language; one is Turkish and the other is an unspecified placeholder." + "reason": "Different language requests; same broad translation theme, but not the same underlying issue." }, { "left": "issue:27088", "right": "issue:44365", "accept": false, - "reason": "Superficially similar i18n request, but the concrete Turkish request is distinct from the generic placeholder template." + "reason": "Generic placeholder request versus specific Turkish request; not duplicates." }, { "left": "issue:27088", "right": "issue:43834", "accept": false, - "reason": "Not the same underlying request: Turkish is explicit, while the other issue is a generic language placeholder." + "reason": "One is Turkish-specific, the other is a generic language placeholder; distinct requests." }, { "left": "issue:43834", "right": "issue:44370", "accept": false, - "reason": "Very similar template text, but the placeholders do not establish the same concrete language or translation task." + "reason": "Both are generic translation placeholders, but they still do not identify the same concrete language or task." }, { "left": "issue:43834", "right": "issue:44365", "accept": false, - "reason": "These look like separate language-specific translation requests sharing a template, not duplicates of one concrete issue." + "reason": "Near-identical template wording is not enough; no evidence they target the same exact translation change." }, { "left": "issue:44365", "right": "issue:44370", "accept": false, - "reason": "Identical template structure is not enough to merge them; the actual target language is unknown and may differ." + "reason": "Both are generic placeholders, but they appear to represent separate language translation tasks." } ] }, @@ -15222,244 +15268,244 @@ "issue:37015|issue:45027", "issue:43837|issue:45177" ], - "prepared_review_unit_hash": "f557324d9d0ef7b013b18dbf4ce8c9c20ecb4db0f03ab72b04040ff0a764a899", + "prepared_review_unit_hash": "0f5f3ef2a29172c8f084119bc408a4990292ffea434c456134cccd8a08027603", "component_budget": { "node_count": 15, "item_count": 15, "soft_pair_count": 35, - "serialized_chars": 20707, - "estimated_input_tokens": 5177, - "estimated_eval_tokens": 10610 + "serialized_chars": 20704, + "estimated_input_tokens": 5176, + "estimated_eval_tokens": 10608 }, "budget": { "node_count": 15, "item_count": 15, "soft_pair_count": 35, - "serialized_chars": 20707, - "estimated_input_tokens": 5177, - "estimated_eval_tokens": 10610 + "serialized_chars": 20704, + "estimated_input_tokens": 5176, + "estimated_eval_tokens": 10608 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is a broad false-positive: the issues are all model-add/support requests, but they target different concrete models and often different modalities (BERT-like, detection, OCR, speech, audio, vision). They should not be treated as duplicates.", - "confidence": 0.96, - "canonical_issue_reason": "If forced to pick one representative, issue #42738 is the broadest umbrella-style request and best matches the shared 'model support' theme, though it is not a true duplicate of the rest.", + "summary": "A loose cluster of model-add requests across different models/modalities; they are related in theme but not duplicates of the same concrete change.", + "confidence": 0.74, + "canonical_issue_reason": "issue:43671 is the most central and discussion-rich request in the cluster, so it best serves as the representative issue, though it does not subsume the others.", "canonical_pr_reason": null, - "best_issue_reason": "Issue #42738 is the least specific and most general among the set, so it is the closest single representative of the cluster's theme; however, the cluster is too heterogeneous for a strong canonical issue.", + "best_issue_reason": "issue:43671 is the best single representative of the cluster\u2019s common pattern of model-support requests, with the strongest connectivity among the listed issues.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:36817", "right": "issue:41211", "accept": false, - "reason": "Different model families and domains; only the generic 'add model' framing overlaps." + "reason": "Both are model-add requests, but for different models; no evidence they are the same underlying change." }, { "left": "issue:36817", "right": "issue:43671", "accept": false, - "reason": "EuroBert config support vs Qwen3 text-to-speech support are unrelated code paths." + "reason": "Different model requests (EuroBert vs Qwen3-TTS); related theme only, not the same bug/change." }, { "left": "issue:36817", "right": "issue:36879", "accept": false, - "reason": "BERT config addition vs RF-DETR model support; different concrete models and subsystems." + "reason": "Distinct model requests (EuroBert vs RF-DETR), not a duplicate fix or merged implementation." }, { "left": "issue:36879", "right": "issue:41211", "accept": false, - "reason": "RF-DETR object detection and DEIMv2 are different models; not the same change." + "reason": "Different models and likely different code paths; similarity is only at the request level." }, { "left": "issue:36879", "right": "issue:43909", "accept": false, - "reason": "Object detection request vs audio model request; different integration targets." + "reason": "RF-DETR and LFM2.5 Audio are unrelated concrete model integrations." }, { "left": "issue:36879", "right": "issue:44121", "accept": false, - "reason": "Detector support vs sparse transformer architecture request; unrelated code paths." + "reason": "Object-detection model request versus weight-sparse transformer request; not the same change." }, { "left": "issue:36879", "right": "issue:43837", "accept": false, - "reason": "RF-DETR and Qwen3-ASR are different model types and tasks." + "reason": "RF-DETR and Qwen3-ASR target different models/modalities, so they should not be merged." }, { "left": "issue:36879", "right": "issue:43671", "accept": false, - "reason": "Detector support vs text-to-speech support; not the same underlying bug/change." + "reason": "RF-DETR vs Qwen3-TTS are different integrations with no shared concrete bug." }, { "left": "issue:37015", "right": "issue:43837", "accept": false, - "reason": "NeoBERT support and Qwen3-ASR support are different model integrations." + "reason": "NeoBERT and Qwen3-ASR are separate model requests, not one underlying defect." }, { "left": "issue:37015", "right": "issue:44121", "accept": false, - "reason": "Distinct model families: NeoBERT vs weight-sparse transformer." + "reason": "NeoBERT versus circuit-sparse transformer support are different implementation targets." }, { "left": "issue:37015", "right": "issue:43909", "accept": false, - "reason": "NeoBERT request is unrelated to the LFM2.5 audio model request." + "reason": "Different requested models; no sign of the same code-path problem." }, { "left": "issue:36879", "right": "issue:37015", "accept": false, - "reason": "RF-DETR detection support and NeoBERT support are different concrete additions." + "reason": "RF-DETR and NeoBERT are unrelated model additions, not duplicates." }, { "left": "issue:37015", "right": "issue:42503", "accept": false, - "reason": "Both are model requests, but for different BERT-like families with different implementation needs." + "reason": "NeoBERT and ModernVBERT are distinct BERT-family model requests, not the same change." }, { "left": "issue:41115", "right": "issue:43837", "accept": false, - "reason": "MiniCPM3 architecture support and Qwen3-ASR support are unrelated changes." + "reason": "MiniCPM3 architecture support and Qwen3-ASR support are different model integrations." }, { "left": "issue:41115", "right": "issue:44121", "accept": false, - "reason": "MiniCPM3 model architecture addition vs sparse transformer support; no shared code path." + "reason": "MiniCPM3 and circuit-sparse transformer requests differ in model and implementation scope." }, { "left": "issue:41115", "right": "issue:42503", "accept": false, - "reason": "Different model families and different concrete integration work." + "reason": "MiniCPM3 architecture and ModernVBERT models are separate requests." }, { "left": "issue:41115", "right": "issue:45027", "accept": false, - "reason": "MiniCPM3 architecture request vs Voxtral TTS support are different modalities." + "reason": "MiniCPM3 and Voxtral TTS support are different model families and code paths." }, { "left": "issue:41211", "right": "issue:43671", "accept": false, - "reason": "DEIMv2 and Qwen3-TTS are unrelated model requests." + "reason": "DEIMv2 and Qwen3-TTS are unrelated concrete model requests." }, { "left": "issue:42503", "right": "issue:43837", "accept": false, - "reason": "ModernVBERT and Qwen3-ASR target different model families and tasks." + "reason": "ModernVBERT and Qwen3-ASR are separate integrations, despite both being model-support requests." }, { "left": "issue:42503", "right": "issue:43671", "accept": false, - "reason": "ModernVBERT models and Qwen3 TTS are different integrations, not duplicates." + "reason": "ModernVBERT models and Qwen3-TTS are different model additions, not one merged fix." }, { "left": "issue:42503", "right": "issue:42738", "accept": false, - "reason": "A specific model-family request vs a generic BERT-like-with-RoPE proposal; only thematic overlap." + "reason": "Both mention BERT-like models, but they are not the same specific model or implementation task." }, { "left": "issue:42738", "right": "issue:45027", "accept": false, - "reason": "BERT-like models with RoPE and Voxtral TTS are unrelated model classes." + "reason": "RoPE BERT-like model support and Voxtral TTS support are different requests." }, { "left": "issue:43671", "right": "issue:43837", "accept": false, - "reason": "Both are speech-related, but TTS and ASR are different model support paths." + "reason": "Qwen3-TTS and Qwen3-ASR are closely related, but they are still different concrete model supports and should not be merged." }, { "left": "issue:43671", "right": "issue:45027", "accept": false, - "reason": "Different speech model families; not enough to treat as the same change." + "reason": "Qwen3-TTS and Voxtral-4B-TTS are different TTS model requests, not the same code change." }, { "left": "issue:43671", "right": "issue:45177", "accept": false, - "reason": "Text-to-speech support vs DeepSeek-OCR2 support are different modalities." + "reason": "Qwen3-TTS and DeepSeek-OCR2 are unrelated model integrations." }, { "left": "issue:43671", "right": "issue:44121", "accept": false, - "reason": "Speech model support and sparse transformer support are unrelated." + "reason": "Speech-model support versus weight-sparse transformer support are different changes." }, { "left": "issue:43837", "right": "issue:45322", "accept": false, - "reason": "Qwen3-ASR and EUPE address different model types and tasks." + "reason": "Qwen3-ASR and EUPE are unrelated model requests." }, { "left": "issue:43837", "right": "issue:43909", "accept": false, - "reason": "ASR and audio model requests are related only at a high level, not the same concrete integration." + "reason": "Qwen3-ASR and LFM2.5 Audio are both audio-related, but they are different concrete models and not the same change." }, { "left": "issue:43909", "right": "issue:44205", "accept": false, - "reason": "Audio model support vs SAM3-LiteText support are different changes." + "reason": "Audio model support and SAM3-LiteText are different model requests with no shared concrete bug." }, { "left": "issue:43671", "right": "issue:43909", "accept": false, - "reason": "TTS and audio model support are distinct model integrations." + "reason": "Qwen3-TTS and LFM2.5 Audio are distinct model integrations." }, { "left": "issue:44121", "right": "issue:45322", "accept": false, - "reason": "Weight-sparse transformer support and EUPE support are different architectural requests." + "reason": "Circuit-sparse transformer support and EUPE are separate model requests." }, { "left": "issue:43837", "right": "issue:44121", "accept": false, - "reason": "ASR support and sparse transformer support are unrelated code paths." + "reason": "Qwen3-ASR and weight-sparse transformer support are not the same underlying change." }, { "left": "issue:43837", "right": "issue:45027", "accept": false, - "reason": "Qwen3-ASR and Voxtral TTS are different speech-model integrations." + "reason": "Qwen3-ASR and Voxtral-4B-TTS are different speech-model integrations." }, { "left": "issue:37015", "right": "issue:45027", "accept": false, - "reason": "NeoBERT and Voxtral TTS are unrelated model families." + "reason": "NeoBERT and Voxtral TTS are unrelated model requests." }, { "left": "issue:43837", "right": "issue:45177", "accept": false, - "reason": "ASR support vs OCR2 support; different modalities and implementation work." + "reason": "Qwen3-ASR and DeepSeek-OCR2 are different model families and code paths." } ] }, @@ -15500,12 +15546,12 @@ "issue:43668|issue:44031", "issue:43668|issue:43813" ], - "prepared_review_unit_hash": "997778c65039c2e4781f8743225cd174657d41c0387daddd0097f5f3eccdc4c7", + "prepared_review_unit_hash": "bd1f75549e7e948c4a2059ec3226f3950867ed854b63f64d6768a1548de5ee07", "component_budget": { "node_count": 6, "item_count": 6, "soft_pair_count": 8, - "serialized_chars": 6292, + "serialized_chars": 6291, "estimated_input_tokens": 1573, "estimated_eval_tokens": 3402 }, @@ -15513,7 +15559,7 @@ "node_count": 6, "item_count": 6, "soft_pair_count": 8, - "serialized_chars": 6292, + "serialized_chars": 6291, "estimated_input_tokens": 1573, "estimated_eval_tokens": 3402 }, @@ -15522,8 +15568,8 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The items are not one duplicate cluster; they span unrelated bugs in norms, Mask2Former loss handling, config typing, a typo, and tokenizer warnings. No soft pair looks like the same underlying issue/change.", - "confidence": 0.95, + "summary": "These issues are only loosely text-similar; they describe unrelated bugs across different models/components, so none of the soft duplicate links should be accepted.", + "confidence": 0.93, "canonical_issue_reason": null, "canonical_pr_reason": null, "best_issue_reason": null, @@ -15533,49 +15579,49 @@ "left": "issue:37934", "right": "issue:43668", "accept": false, - "reason": "Both mention normalization details, but one is about whether Llama4TextL2Norm should be RMSNorm and the other is a type-hint problem in ModernBERTConfig; different code paths and fixes." + "reason": "Different problems in different model configs: Llama4TextL2Norm/RMS norm question vs ModernBERT norm_eps type hint." }, { "left": "issue:42936", "right": "issue:43240", "accept": false, - "reason": "Both touch training/loss plumbing, but one is about Mask2Former's ignore_value being unused and the other is about kwargs not reaching the loss function; not the same bug." + "reason": "Mask2Former ignore_value handling is unrelated to kwargs not being forwarded to a loss function." }, { "left": "issue:42936", "right": "issue:44031", "accept": false, - "reason": "Mask2Former loss handling vs tokenizer regex warnings are unrelated subsystems and changes." + "reason": "Mask2Former ignore_value bug is unrelated to a tokenizer regex warning after 4.57.3." }, { "left": "issue:42936", "right": "issue:43813", "accept": false, - "reason": "Mask2Former ignore_value usage and a typo in orig_conversion.quantization_operation are unrelated." + "reason": "Different subsystems and bug types: Mask2Former loss masking vs a quantization attribute typo." }, { "left": "issue:42936", "right": "issue:43668", "accept": false, - "reason": "Mask2Former loss behavior and a ModernBERTConfig type hint issue are unrelated." + "reason": "Unrelated model/config issues: Mask2Former ignore_value usage vs ModernBERT norm_eps typing." }, { "left": "issue:43240", "right": "issue:43668", "accept": false, - "reason": "Passing kwargs to a loss function and correcting a config type hint are different problems." + "reason": "Loss kwargs forwarding bug is not the same as a config type-hint error." }, { "left": "issue:43668", "right": "issue:44031", "accept": false, - "reason": "ModernBERTConfig norm_eps typing and tokenizer regex warnings are unrelated." + "reason": "ModernBERT norm_eps typing and tokenizer regex warnings are distinct issues in different code paths." }, { "left": "issue:43668", "right": "issue:43813", "accept": false, - "reason": "A config type-hint error and a field-name typo in conversion code are not the same underlying issue." + "reason": "A type-hint fix for ModernBERT is unrelated to a quantization typo." } ] }, @@ -15605,7 +15651,7 @@ "soft_pairs": [ "issue:41084|issue:43037" ], - "prepared_review_unit_hash": "fc68dbe90644d4dc1c1a0459868931acecac490e7cc26931b7f76888ec100deb", + "prepared_review_unit_hash": "41e626aafccdbb62551b5b352c4ca3cff4285dd58326f3ee7bec4533316257ec", "component_budget": { "node_count": 2, "item_count": 2, @@ -15627,18 +15673,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two issues are unrelated: one is about block decoding, the other is a DeepSeek v3.2 support request. They should not be clustered as duplicates.", - "confidence": 0.98, - "canonical_issue_reason": null, + "summary": "The two issues are not duplicates: one asks for Set Block Decoding, the other requests DeepSeek v3.2 support. They describe different product areas and different underlying changes.", + "confidence": 0.97, + "canonical_issue_reason": "No canonical issue: 41084 and 43037 are unrelated topics rather than the same bug or request.", "canonical_pr_reason": null, - "best_issue_reason": "Issue #43037 is the more specific and user-facing request, but it is not a duplicate of #41084.", + "best_issue_reason": "Neither issue is a good cluster representative because there is no duplicate relationship to unify.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:41084", "right": "issue:43037", "accept": false, - "reason": "Different underlying topics with no shared code-path or concrete bug/change: block decoding vs model support for DeepSeek v3.2." + "reason": "Different underlying requests: block decoding behavior vs adding support for a specific model version." } ] }, @@ -15668,12 +15714,12 @@ "soft_pairs": [ "issue:43598|issue:43600" ], - "prepared_review_unit_hash": "755a27ca33e0c46cf0c3aafb6bd5c4392550366e38bbc2642a179a6763834cb8", + "prepared_review_unit_hash": "5ed04dc788aaa13b7e27d1b9d2e2bd41f89674a2154719adef789f318415912a", "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 }, @@ -15681,7 +15727,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1583, + "serialized_chars": 1584, "estimated_input_tokens": 396, "estimated_eval_tokens": 1048 }, @@ -15690,18 +15736,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are related in that both mention custom trainers and Trainer behavior, but they describe different problems: one is about `remove_unused_column` customizability, the other about FLOPS estimation. Not a duplicate pair.", - "confidence": 0.91, - "canonical_issue_reason": "Issue 43598 is the cleaner representative of the cluster because it is a more concrete Trainer customization concern.", + "summary": "Both issues concern Trainer behavior with custom trainers, but they address different code paths: column removal vs FLOPs estimation. They are related in theme, not the same underlying bug or change, so I would not merge them as duplicates.", + "confidence": 0.84, + "canonical_issue_reason": "Issue #43598 is the more general customization concern around Trainer internals, so it is the better representative if a single issue must stand in for the cluster.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43598 is the better standalone issue to keep as the cluster representative: it describes a specific behavior in `Trainer` and is easier to action than the broader FLOPS-estimation request.", + "best_issue_reason": "#43598 is the strongest cluster representative because it directly targets a Trainer default that can block custom behavior and is phrased as a reusable design concern.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43598", "right": "issue:43600", "accept": false, - "reason": "Different underlying bugs: one concerns `remove_unused_column` handling, the other FLOPS counting with custom trainers. Shared Trainer/custom trainer context is too broad to treat as the same issue." + "reason": "They share the broad topic of custom trainers, but one is about `remove_unused_column` handling and the other is about FLOPs estimation. These are distinct behaviors and would not plausibly be merged into one issue." } ] }, @@ -15731,7 +15777,7 @@ "soft_pairs": [ "issue:43684|issue:44405" ], - "prepared_review_unit_hash": "111108449c22b443adb6fb6853720c22eda422fdeb4ec4ac7e7ed0c6ee362052", + "prepared_review_unit_hash": "dcf8b463403553c418d1f6b2f3301478bf13e80d26680564f14e37ad94269668", "component_budget": { "node_count": 2, "item_count": 2, @@ -15753,18 +15799,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are two separate feature requests for different Qwen model families and different AutoModel heads. They are related only by a broad theme of model registration, not by the same underlying bug or change.", - "confidence": 0.94, - "canonical_issue_reason": "Issue #43684 is the broader, more general request about registering Qwen3-Omni with AutoModel and AutoModelForConditionalGeneration, so it is the better anchor if this cluster is used as a loose topical grouping.", + "summary": "These are thematically related but distinct feature requests: one asks for Qwen3-Omni auto-class registration, the other for AutoModelForSequenceClassification support for Qwen3.5. They share the same broad area (AutoModel support for Qwen variants) but do not describe the same underlying bug/change.", + "confidence": 0.89, + "canonical_issue_reason": "Issue 43684 is the broader representative of the cluster because it concerns auto-registration for Qwen3-Omni across core auto classes, while 44405 is a narrower, different task for sequence classification on Qwen3.5.", "canonical_pr_reason": null, - "best_issue_reason": "Issue #43684 is the most representative issue in the pair because it describes a broader registration gap, while #44405 is a distinct request for AutoModelForSequenceClassification support on Qwen3.5.", + "best_issue_reason": "43684 is the best issue to represent the cluster theme of missing Qwen auto-model registration support; 44405 is related but targets a different model family and task head.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43684", "right": "issue:44405", "accept": false, - "reason": "Different model families (Qwen3-Omni vs Qwen3.5) and different target heads (conditional generation vs sequence classification); not the same concrete fix." + "reason": "Both are about adding Qwen-related AutoModel support, but they target different model families and different auto classes/tasks (Qwen3-Omni registration vs Qwen3.5 sequence classification). They are not the same change and should not be merged as duplicates." } ] }, @@ -15801,80 +15847,77 @@ "issue:43845|issue:43859", "issue:43846|issue:43859" ], - "prepared_review_unit_hash": "5bc786159cff1dc22217e4a82e3f9732d407c4e8f8a2f54e4ef89453ecd7b958", + "prepared_review_unit_hash": "add8c6290d13a32cccd798ca3a7d3fc49f86a9addee45f16b695be20b6f4f5b4", "component_budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 4263, - "estimated_input_tokens": 1066, - "estimated_eval_tokens": 2388 + "serialized_chars": 4265, + "estimated_input_tokens": 1067, + "estimated_eval_tokens": 2390 }, "budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 4263, - "estimated_input_tokens": 1066, - "estimated_eval_tokens": 2388 + "serialized_chars": 4265, + "estimated_input_tokens": 1067, + "estimated_eval_tokens": 2390 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Three closed issues share the same placeholder title \"huggingface \" and are likely duplicates; the \"Fett\" issue looks unrelated. No PRs are present.", - "confidence": 0.78, - "canonical_issue_reason": "Issue 43845 is the earliest of the near-identical \"huggingface \" reports, so it is the best representative for that duplicate cluster.", + "summary": "These are mostly near-empty issues; three share the same generic title, but there isn\u2019t enough content to confirm a true duplicate beyond superficial similarity. The first huggingface issue is the best representative only by age.", + "confidence": 0.41, + "canonical_issue_reason": "issue:43845 is the earliest of the three identical 'huggingface ' issues, so it is the best placeholder canonical issue for that apparent duplicate set.", "canonical_pr_reason": null, - "best_issue_reason": "43845 is the strongest single issue to keep because it is earliest, has the same title as the other likely duplicates, and there is no evidence that 43835 is related.", + "best_issue_reason": "issue:43845 is the best overall issue because it is one of the repeated-title reports and is the oldest among them; the 'Fett' issue looks unrelated by title.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43835", "right": "issue:43845", "accept": false, - "reason": "Different titles with no supporting body or target overlap; \"Fett\" does not appear to be the same report as \"huggingface \"." + "reason": "Different titles and no body/details to show the same underlying issue; similarity is too weak to merge." }, { "left": "issue:43835", "right": "issue:43846", "accept": false, - "reason": "No evidence these refer to the same underlying issue; the titles are unrelated." + "reason": "Different titles and no concrete problem description; cannot confirm a duplicate." }, { "left": "issue:43835", "right": "issue:43859", "accept": false, - "reason": "No indication of the same bug/change; \"Fett\" is distinct from the repeated \"huggingface \" reports." + "reason": "Different titles and no evidence they describe the same bug or request." }, { "left": "issue:43845", "right": "issue:43846", - "accept": true, - "reason": "Identical title, very close creation times, and no contrary evidence; these look like duplicate reports of the same issue." + "accept": false, + "reason": "Identical generic titles, but the issues are empty enough that I can\u2019t verify they are the same underlying report." }, { "left": "issue:43845", "right": "issue:43859", - "accept": true, - "reason": "Same title and clear thematic overlap with the other \"huggingface \" issues; likely the same underlying report." + "accept": false, + "reason": "Same broad title only; no substantive description or linkage proving a duplicate." }, { "left": "issue:43846", "right": "issue:43859", - "accept": true, - "reason": "Identical title and close cluster context indicate the same duplicate issue." + "accept": false, + "reason": "Same broad title only; insufficient evidence to treat them as the same issue." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet: three issues share the exact same title, the earliest one is correctly chosen as the canonical representative, and the unrelated 'Fett' issue is kept separate. The soft-edge verdicts are conservative overall, and the note that no PRs are present is supported by the packet." - }, - "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 }, @@ -15908,98 +15951,95 @@ "issue:44572|issue:44937", "issue:44573|issue:44937" ], - "prepared_review_unit_hash": "f212e9edab6f94a37e4fcf459fa2c61d7fe84c5c72c43de9d403e057e57aa075", + "prepared_review_unit_hash": "fcf4f4b03494c3aec8fc43a0ead5fb6279d7479ecd1c53ce95528e97496a0fe5", "component_budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 9, - "serialized_chars": 5791, - "estimated_input_tokens": 1448, - "estimated_eval_tokens": 3152 + "serialized_chars": 5788, + "estimated_input_tokens": 1447, + "estimated_eval_tokens": 3150 }, "budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 9, - "serialized_chars": 5791, - "estimated_input_tokens": 1448, - "estimated_eval_tokens": 3152 + "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": "Three issues are exact title matches for \"\" and look like the same spam/duplicate report; the documentation and Google LLC titles do not match that pattern.", - "confidence": 0.91, - "canonical_issue_reason": "issue:44371 is the earliest exact \"\" entry and is the cleanest representative of the repeated spam cluster.", + "summary": "All candidates are extremely low-information or spam-like issues, with no concrete bug report, code path, or change description to support duplicate merging.", + "confidence": 0.08, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:44371 best represents the cluster because it is an exact match for the repeated \"\" issues and appears first chronologically.", + "best_issue_reason": "Issue 44418 is the only non-\"\" item, but it is still far too generic to serve as a reliable canonical representative.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44371", "right": "issue:44572", - "accept": true, - "reason": "Same exact title \"\", same low-information spam pattern, so likely duplicate reports of the same artifact." + "accept": false, + "reason": "Both are just spam placeholders; identical low-information titles are not enough to confirm the same underlying issue." }, { "left": "issue:44371", "right": "issue:44573", - "accept": true, - "reason": "Same exact title \"\" and same spam-like placeholder content." + "accept": false, + "reason": "Both are spam placeholders with no concrete description, so duplicate status cannot be established." }, { "left": "issue:44371", "right": "issue:44418", "accept": false, - "reason": "Different title and different issue type; documentation enhancement is not the same as the spam placeholder issue." + "reason": "Spam placeholder vs. generic documentation suggestion; no shared technical problem is evident." }, { "left": "issue:44371", "right": "issue:44937", "accept": false, - "reason": "\"Check out \\\"Google LLC\\\"\" is a different spam/phishing-style title, not the same exact issue as \"\"." + "reason": "Spam placeholder and an unrelated titled issue; no same underlying bug or change." }, { "left": "issue:44418", "right": "issue:44572", "accept": false, - "reason": "Documentation enhancement suggestion does not match the exact spam placeholder issue." + "reason": "Generic documentation suggestion vs. spam placeholder; no concrete overlap to justify a duplicate merge." }, { "left": "issue:44418", "right": "issue:44573", "accept": false, - "reason": "Different title and different underlying request; not the same issue." + "reason": "Generic documentation suggestion vs. spam placeholder; insufficient evidence of the same issue." }, { "left": "issue:44572", "right": "issue:44573", - "accept": true, - "reason": "Exact title match \"\" with no other distinguishing information, so they appear to be duplicates." + "accept": false, + "reason": "Both are spam placeholders, but there is no substantive report to confirm they are the same issue." }, { "left": "issue:44572", "right": "issue:44937", "accept": false, - "reason": "Different spam wording; no evidence they report the same underlying issue." + "reason": "Spam placeholder vs. unrelated title; no shared bug/change can be inferred." }, { "left": "issue:44573", "right": "issue:44937", "accept": false, - "reason": "Different titles and no shared concrete problem beyond generic spam-like wording." + "reason": "Spam placeholder vs. unrelated title; no evidence they describe the same underlying issue." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet: three items share the exact title \"\" and the other two clearly do not. The soft-edge accepts are conservative enough given the exact title matches and matching low-information metadata, and the rejects avoid overclaiming on the non- issues." - }, - "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 }, @@ -16022,12 +16062,12 @@ "soft_pairs": [ "issue:45145|issue:45151" ], - "prepared_review_unit_hash": "45871a8dfbb2df43a6ce827b7155e31a70bb22f7eecdbfb9434606a3e1ed5de2", + "prepared_review_unit_hash": "482033f6495dbe4d573dc439c5da58257a381a80400e5ee72a5526f27595179c", "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 }, @@ -16035,7 +16075,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1646, + "serialized_chars": 1645, "estimated_input_tokens": 412, "estimated_eval_tokens": 1080 }, @@ -16044,24 +16084,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Likely duplicate issue reports with identical titles and very similar body sizes; #45145 is the better canonical representative because it appeared first and already has an inbound reference.", - "confidence": 0.84, - "canonical_issue_reason": "#45145 is the earliest copy and already has an inbound reference, so it is the best canonical issue among these likely duplicates.", + "summary": "These issues are strong duplicate candidates: they share the exact title and have a soft-similarity signal, so #45145 is the best canonical anchor because it also has an inbound reference. The evidence is suggestive rather than conclusive from the packet alone, so the wording should stay conservative.", + "confidence": 0.78, + "canonical_issue_reason": "#45145 is the better canonical issue because it has the exact same title as #45151 and an inbound reference, making it the more natural deduplication anchor.", "canonical_pr_reason": null, - "best_issue_reason": "#45145 is the best issue representative because it was created first and is already referenced by another issue.", + "best_issue_reason": "#45145 is the best single issue to keep as the primary thread because it has the same title as #45151 and slightly more anchoring evidence via one inbound reference.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45145", "right": "issue:45151", "accept": true, - "reason": "Identical titles and very similar body lengths strongly suggest the same underlying report, though the bodies themselves are not shown." + "reason": "The issues have identical titles and a soft-similarity signal, which is enough to treat them as likely duplicates; the packet does not justify stronger claims about the bodies being identical." } ] }, "evaluator_result": { "accept": false, - "feedback": "The packet supports a strong similarity signal (identical titles, close body lengths, one inbound reference on #45145), but it does not directly show the issue bodies or prove the reports are the same. The writeup is a bit too definitive with phrases like \"near-exact duplicates\" and \"effectively the same issue report.\" A more conservative phrasing such as \"likely duplicate\" would be better grounded." + "feedback": "Rejecting because the analyst overstates the evidence. The packet supports that these two issues have identical titles, similar body lengths, and a soft-similarity signal, so a tentative duplicate/canonicalization choice is reasonable. But it does not ground stronger claims like \u201cequivalent,\u201d \u201csame underlying issue/proposal,\u201d or \u201cnear-identical content,\u201d since the actual bodies are not provided here. The canonical choice based on the inbound reference is plausible, but the explanation should stay conservative and avoid asserting equivalence beyond the available evidence." }, "evaluator_used": true, "retried": true, @@ -16142,40 +16182,40 @@ "soft_pairs": [ "issue:45672|issue:45674" ], - "prepared_review_unit_hash": "85a29aca2afae36fb3e827ddf01fd1cce50d95e4b10b94102bb8a0251fbd53ed", + "prepared_review_unit_hash": "12e0cb68395e80eb51dc8c0d6d32e173e24e6f651f04db123fad82d559359831", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1669, - "estimated_input_tokens": 418, - "estimated_eval_tokens": 1092 + "serialized_chars": 1667, + "estimated_input_tokens": 417, + "estimated_eval_tokens": 1090 }, "budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1669, - "estimated_input_tokens": 418, - "estimated_eval_tokens": 1092 + "serialized_chars": 1667, + "estimated_input_tokens": 417, + "estimated_eval_tokens": 1090 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are related only at a high level (both 4-bit inference failures), but they describe different bugs and failure modes, so they should not be deduplicated.", - "confidence": 0.96, - "canonical_issue_reason": "Issue 45674 is the clearer representative because it states a specific configuration regression in BitsAndBytesConfig with an explicit failure mode and broader actionable scope.", + "summary": "These are two different 4-bit inference bugs in different code paths: one Gemma4/audio-module dtype failure, and one BitsAndBytesConfig skip-module regression that drops the default lm_head exclusion.", + "confidence": 0.97, + "canonical_issue_reason": "No canonical duplicate here: 45672 is a model-/audio-module-specific torch.finfo(uint8) failure, while 45674 is a separate BitsAndBytesConfig behavior bug around llm_int8_skip_modules and lm_head exclusion.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45674 is the better standalone issue to keep as the canonical reference for this cluster since it describes a concrete, reproducible code-path problem rather than a model-specific symptom.", + "best_issue_reason": "If a single representative is needed, 45674 is the better anchor because it describes a broader configuration regression in the 4-bit inference path rather than a Gemma4-specific symptom.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45672", "right": "issue:45674", "accept": false, - "reason": "Different underlying bugs: 45672 is a Gemma4/audio-module torch.finfo TypeError on uint8 weights, while 45674 is an llm_int8_skip_modules / lm_head exclusion AssertionError in 4-bit inference. Same broad area, but not the same fixable code-path." + "reason": "Different underlying bugs and code paths; they share only the broad setting of 4-bit inference, not the same failure mechanism." } ] }, @@ -16205,7 +16245,7 @@ "soft_pairs": [ "issue:45762|issue:45763" ], - "prepared_review_unit_hash": "62b653a03f02e89e38f8b1ac4a30309d040ed04368ae7665f31337cfa82dc629", + "prepared_review_unit_hash": "09ef3629fe4bf4008508129d84ee78175a2ac4742b404487c56d7a68b150b2be", "component_budget": { "node_count": 2, "item_count": 2, @@ -16227,18 +16267,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two closed issues are just separate personal-name entries with different names/dates and no shared bug, feature, or code context, so this is not a duplicate cluster.", - "confidence": 0.98, - "canonical_issue_reason": null, + "summary": "The two closed issues are just person-name/date strings with no body or technical context. They do not appear to describe the same underlying bug or request, so the soft duplicate edge should be rejected.", + "confidence": 0.99, + "canonical_issue_reason": "No clear canonical issue: both issues lack any technical description or evidence of representing the same problem.", "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "Neither issue is a strong representative; if forced, issue:45762 is not meaningfully better than issue:45763 because both are empty and unrelated.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45762", "right": "issue:45763", "accept": false, - "reason": "Same broad surname pattern only; no body, targets, filenames, or discussion linking them to the same underlying issue." + "reason": "The titles are different personal names with different dates, and both issues have no body or shared technical context; they do not look like the same underlying bug or change." } ] }, @@ -16268,40 +16308,40 @@ "soft_pairs": [ "issue:45764|issue:45765" ], - "prepared_review_unit_hash": "d2a692d14b0f6a220670e9ef414cc2c352fe070e58015763ee8a18fb98b62cc4", + "prepared_review_unit_hash": "ecacae9277ea9df8d501f10c11ffd3866b6f7fc70f0cac599b06e1db8d821e00", "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": 1479, + "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": 1479, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are two unrelated, empty closed issues with personal-name/date titles and no substantive content. They do not appear to describe the same bug or request, so they should not be clustered as duplicates.", + "summary": "The cluster contains two closed issues with unrelated name/date-style titles and no bodies or links. There is no evidence they describe the same bug, request, or change.", "confidence": 0.98, - "canonical_issue_reason": "No canonical issue: neither item contains actionable problem description, and the titles are unrelated personal-name/date strings rather than the same report.", + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Neither issue is a good cluster anchor because both are effectively empty/spam-like and provide no meaningful defect or feature context.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45764", "right": "issue:45765", "accept": false, - "reason": "Reject: the titles reference different people and different dates, and there is no body content or shared technical context indicating the same underlying issue." + "reason": "The titles appear to be unrelated personal records with different names and dates; there is no shared technical problem, code path, or issue context." } ] }, @@ -16341,8 +16381,8 @@ ], "soft_pairs": [ "pull_request:39895|pull_request:43424", - "pull_request:41855|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", @@ -16360,154 +16400,154 @@ "pull_request:43823|pull_request:45795", "pull_request:43251|pull_request:43254" ], - "prepared_review_unit_hash": "73a5e5c302f1fa1634d1bc3111598f4913e698dbd6cb4de6353f8f2121035ab5", + "prepared_review_unit_hash": "2c38deedbda50eedb6027b872a1fb5d1586f8d74c2508532735950e8f3452561", "component_budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 19, - "serialized_chars": 35208, - "estimated_input_tokens": 8802, - "estimated_eval_tokens": 17860 + "serialized_chars": 35204, + "estimated_input_tokens": 8801, + "estimated_eval_tokens": 17858 }, "budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 19, - "serialized_chars": 35208, - "estimated_input_tokens": 8802, - "estimated_eval_tokens": 17860 + "serialized_chars": 35204, + "estimated_input_tokens": 8801, + "estimated_eval_tokens": 17858 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is mostly a grab bag of unrelated PRs across model additions, docs, and refactors. The only true duplicate pair is the two fixed_cross_entropy changes (43251/43254), which implement the same kwargs pass-through to nn.functional.cross_entropy.", - "confidence": 0.96, + "summary": "Mostly unrelated PRs spanning new model additions, docs, and small refactors. The only strong duplicate pair is the two `fixed_cross_entropy` changes in `loss_utils.py`, which target the same issue and same code path.", + "confidence": 0.95, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43251 is the better canonical choice for the duplicate loss fix: it covers the same fixed_cross_entropy change as 43254, is a bit more complete, and explicitly links the tracking issue 43240.", + "canonical_pr_reason": "`pull_request:43251` is the clearest representative of the duplicate loss fix: it directly targets issue #43240, has the more explicit description, and includes the same `loss_utils.py` code path as the paired PR.", "best_issue_reason": null, - "best_pr_reason": "PR 43251 is the best representative of the only real duplicate pair in this cluster; the rest are unrelated, and 43251 is the more complete version of the shared cross-entropy kwargs fix.", + "best_pr_reason": "`pull_request:43251` is the best overall PR to represent the only true duplicate cluster here because it is the more complete/explicit version of the shared `fixed_cross_entropy` fix and is tied to the referenced issue.", "soft_edge_verdicts": [ { "left": "pull_request:39895", "right": "pull_request:43424", "accept": false, - "reason": "Different changes: VideoPrism model addition vs an executorch export test." + "reason": "Both are unrelated feature/test PRs; one adds VideoPrism, the other adds an ExecuTorch dynamic-shape test. No shared bug or mergeable code-path overlap." }, { "left": "pull_request:41855", - "right": "pull_request:43424", + "right": "pull_request:43823", "accept": false, - "reason": "Unrelated areas: Mistral tokenizer methods vs executorch dynamic-shape testing." + "reason": "Different tokenizer utility fix vs adding a new model package; not the same underlying change." }, { "left": "pull_request:41855", - "right": "pull_request:43823", + "right": "pull_request:43424", "accept": false, - "reason": "Different workstreams: tokenizer API additions vs adding MobileLLM." + "reason": "A tokenizer helper addition and an ExecuTorch export test are unrelated changes." }, { "left": "pull_request:42668", "right": "pull_request:43823", "accept": false, - "reason": "Processor auto-loading changes are not the same underlying change as adding MobileLLM." + "reason": "Both touch processor/model auto-registration, but they are for different models and different problems, so not duplicates." }, { "left": "pull_request:43251", "right": "pull_request:43823", "accept": false, - "reason": "Cross-entropy kwargs fix and MobileLLM model addition are unrelated." + "reason": "Loss-function kwargs fix versus adding MobileLLM; completely different code paths." }, { "left": "pull_request:43251", "right": "pull_request:44827", "accept": false, - "reason": "Loss helper kwargs fix is unrelated to Mistral4 test fixes and model wiring." + "reason": "`fixed_cross_entropy` kwargs support and Mistral4 test fixes are unrelated." }, { "left": "pull_request:43424", "right": "pull_request:44827", "accept": false, - "reason": "Executorch export tests and Mistral4 test fixes address different code paths." + "reason": "ExecuTorch dynamic export testing and Mistral4 test/model fixes are not the same underlying bug." }, { "left": "pull_request:43424", "right": "pull_request:43823", "accept": false, - "reason": "Different artifacts: executorch export test vs new MobileLLM model implementation." + "reason": "Dynamic-shape export testing is unrelated to adding MobileLLM." }, { "left": "pull_request:43823", "right": "pull_request:45655", "accept": false, - "reason": "New model addition is unrelated to config resolution order in modeling_utils." + "reason": "A new model addition and a Python typing/order fix in `modeling_utils.py` are unrelated." }, { "left": "pull_request:43823", "right": "pull_request:43995", "accept": false, - "reason": "MobileLLM implementation and Falcon output-interface refactor are different changes." + "reason": "New model addition vs Falcon refactor; different models and different issues." }, { "left": "pull_request:43995", "right": "pull_request:44827", "accept": false, - "reason": "Falcon refactor and Mistral4 test fixes do not target the same bug." + "reason": "Falcon output-interface refactor and Mistral4 test fixes do not appear to fix the same concrete bug." }, { "left": "pull_request:43995", "right": "pull_request:45213", "accept": false, - "reason": "Model refactor vs model-creation skill content are not the same underlying change." + "reason": "Falcon refactor and model-creation skill work are unrelated." }, { "left": "pull_request:44827", "right": "pull_request:45170", "accept": false, - "reason": "Mistral4 test fixes and layrnorm->layernorm renaming are different fixes." + "reason": "Mistral4 test fixes and `layrnorm` normalization renaming are different changes, even though both touch model code." }, { "left": "pull_request:44827", "right": "pull_request:45795", "accept": false, - "reason": "Mistral4 test fixes are unrelated to docs for audio/video processors." + "reason": "Mistral4 test fixes and docs for audio/video processors are unrelated." }, { "left": "pull_request:44827", "right": "pull_request:45655", "accept": false, - "reason": "Different problems: Mistral4 tests vs config resolution order bug." + "reason": "Mistral4 test/model work and config-resolution ordering in `modeling_utils.py` are unrelated." }, { "left": "pull_request:44827", "right": "pull_request:45213", "accept": false, - "reason": "Test-fix PR and model-creation skill PR are unrelated." + "reason": "Mistral4 fixes and the model-creation skill PR are unrelated." }, { "left": "pull_request:43823", "right": "pull_request:45213", "accept": false, - "reason": "Adding MobileLLM is not the same underlying change as adding a new-model skill doc." + "reason": "Adding MobileLLM and adding a model-creation skill are not the same underlying change." }, { "left": "pull_request:43823", "right": "pull_request:45795", "accept": false, - "reason": "MobileLLM model addition and docs for processors are different topics." + "reason": "MobileLLM model addition vs documentation for audio/video processors are unrelated." }, { "left": "pull_request:43251", "right": "pull_request:43254", "accept": true, - "reason": "Both PRs patch the same helper, fixed_cross_entropy, to forward the same supported kwargs to nn.functional.cross_entropy; they are mergeable into one change." + "reason": "Both PRs modify `src/transformers/loss/loss_utils.py` to add the same missing `cross_entropy` kwargs (`weight` and `label_smoothing`) for the same issue #43240, so they are the same underlying fix." } ] }, "evaluator_result": { "accept": true, - "feedback": "The analysis is grounded in the packet and stays conservative. The only accepted soft edge, 43251/43254, is well supported by shared file/issue target and the same fixed_cross_entropy kwargs fix, and the other pairs are reasonably rejected as unrelated." + "feedback": "The summary is grounded in the packet, and the soft-edge verdicts stay conservative. The one accepted pair, `pull_request:43251` vs `pull_request:43254`, is well supported by the shared `loss_utils.py` path and common issue target #43240, and the other pairwise rejections do not overclaim evidence." }, "evaluator_used": true, "retried": false, @@ -16534,40 +16574,40 @@ "soft_pairs": [ "pull_request:40546|pull_request:42781" ], - "prepared_review_unit_hash": "186b72b8074839b415d5d697acda9b17f5abdefadee07ba752039a23e06dfa21", + "prepared_review_unit_hash": "407c3cf1d884cf4cac249250539d4964706301de66dca1d4ce64f498f5f2b364", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 7225, - "estimated_input_tokens": 1807, - "estimated_eval_tokens": 3870 + "serialized_chars": 7224, + "estimated_input_tokens": 1806, + "estimated_eval_tokens": 3868 }, "budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 7225, - "estimated_input_tokens": 1807, - "estimated_eval_tokens": 3870 + "serialized_chars": 7224, + "estimated_input_tokens": 1806, + "estimated_eval_tokens": 3868 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both pull requests are about VibeVoice, but they are not duplicates: one is the initial VibeVoice integration and the other adds VibeVoice Realtime plus an acoustic tokenizer and related generation/model changes.", - "confidence": 0.87, + "summary": "Two VibeVoice PRs overlap on shared model scaffolding, but they are distinct changes: one adds the base VibeVoice integration, while the other adds VibeVoice Realtime and the acoustic tokenizer stack.", + "confidence": 0.9, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 40546 is the broader original VibeVoice implementation and appears to be the primary integration PR; PR 42781 is a later, more specialized follow-up for the realtime variant.", + "canonical_pr_reason": "PR #40546 is the broader, earlier VibeVoice integration and has substantial review activity; it is the better representative PR for this cluster.", "best_issue_reason": null, - "best_pr_reason": "PR 40546 is the best representative of the cluster because it introduces the core VibeVoice support that the other PR builds on.", + "best_pr_reason": "PR #40546 is the best single PR to anchor the cluster because it implements the core VibeVoice model support, whereas #42781 is a separate realtime follow-on.", "soft_edge_verdicts": [ { "left": "pull_request:40546", "right": "pull_request:42781", "accept": false, - "reason": "They share the VibeVoice subsystem, but 42781 adds a distinct realtime/acoustic-tokenizer feature set rather than fixing or implementing the same concrete code path as 40546. These are related follow-up changes, not one mergeable duplicate PR." + "reason": "They share VibeVoice infrastructure, but #40546 is the base implementation and #42781 adds realtime/acoustic-tokenizer functionality plus extra generation changes. These are related feature expansions, not the same concrete code change." } ] }, @@ -16597,7 +16637,7 @@ "soft_pairs": [ "pull_request:40755|pull_request:41224" ], - "prepared_review_unit_hash": "9c294abaa62b509f6b7053e1b10763b86dd7da870fb1d14a0563baa59f52460f", + "prepared_review_unit_hash": "20e4a8b28727b317d69e461293750cfb4b3aba73356bf591e2e9cc530f0b2d6c", "component_budget": { "node_count": 2, "item_count": 2, @@ -16619,18 +16659,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two pull requests are about different features in different models: TimesFM covariate forecasting vs. DINOv3 image-classification support. They share only a loose \u201cmodel feature addition\u201d theme, not the same code-path or bug, so they are not duplicates.", - "confidence": 0.98, + "summary": "The two pull requests are not duplicates: one adds TimesFM forecasting with covariates, while the other adds DINOv3 image-classification support. They touch different models, different code paths, and different docs/tests.", + "confidence": 0.99, "canonical_issue_reason": null, - "canonical_pr_reason": "No true canonical PR for this cluster because the PRs target unrelated models and independent changes. If forced to pick a representative, PR 40755 is broader and more feature-complete, but it is not a duplicate of PR 41224.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "PR 40755 is the stronger standalone representative of the cluster only because it has the larger implementation footprint and includes docs/tests for a concrete feature addition. However, it should not be merged with PR 41224 as a duplicate.", + "best_pr_reason": "No canonical PR in this cluster; if forced to pick a representative item, the DINOv3 classification PR is more self-contained, but it is still unrelated to the TimesFM PR.", "soft_edge_verdicts": [ { "left": "pull_request:40755", "right": "pull_request:41224", "accept": false, - "reason": "Different models and different functionality: TimesFM covariate forecasting vs. DINOv3 image classification. No shared code-path or same underlying bug/change." + "reason": "Different features in different model families (TimesFM covariate forecasting vs DINOv3 image classification); they do not describe the same underlying bug or change." } ] }, @@ -16725,7 +16765,7 @@ "pull_request:41797|pull_request:45186", "pull_request:45186|pull_request:45630" ], - "prepared_review_unit_hash": "51307f7b5670046e28b0a785f8298bdea7ec719829f47b5014f713358b1433a5", + "prepared_review_unit_hash": "e1a19f8c3b8362708496e15bc6c804d492d42ab8069491a8c1d2e2e8dbc273af", "component_budget": { "node_count": 3, "item_count": 3, @@ -16747,24 +16787,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "All three items are separate model-addition PRs for different architectures (DeepSeek OCR, Isaac, Kimi2-6). They share boilerplate integration files, but not the same underlying change, so they should not be clustered as duplicates.", - "confidence": 0.98, + "summary": "These are three separate pull requests adding different models (DeepSeek OCR, Isaac, and Kimi2-6). They share only common integration scaffolding and docs/auto-registration updates, not the same underlying bug or change.", + "confidence": 0.99, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45630 is the strongest cluster representative only in the sense that it is the most mature and comprehensive of the three, with the highest review activity and the broadest set of integration updates.", + "canonical_pr_reason": "No canonical PR: the items implement distinct model additions for different architectures, so they are not duplicates of one another.", "best_issue_reason": null, - "best_pr_reason": "PR #45630 is the best single representative if one must be chosen: it is a fully fleshed-out model addition with extensive integration coverage and substantial review attention.", + "best_pr_reason": "If a representative PR is needed, 45630 is the most comprehensive of the three (broadest model integration surface and highest review activity), but it is not a duplicate/canonical merge target for the others.", "soft_edge_verdicts": [ { "left": "pull_request:41797", "right": "pull_request:45186", "accept": false, - "reason": "Different model families and different code paths: DeepSeek OCR vs Isaac. Shared auto-registration/docs scaffolding is boilerplate, not evidence of the same change." + "reason": "DeepSeek OCR and Isaac are different model additions; shared auto-registration/docs files are generic scaffolding, not evidence of the same change or bug fix." }, { "left": "pull_request:45186", "right": "pull_request:45630", "accept": false, - "reason": "These add different models (Isaac vs Kimi2-6) with distinct configurations, processors, and tests. Similar framework integration files do not make them mergeable into one PR." + "reason": "Isaac and Kimi2-6 target different models and code paths; overlap is limited to standard model-adding boilerplate, so they should not be merged as duplicates." } ] }, @@ -16794,7 +16834,7 @@ "soft_pairs": [ "pull_request:42975|pull_request:42976" ], - "prepared_review_unit_hash": "497a04fc187db1ffa0866539390949573186db0b32fbf7d3d5ea9490d24b1fac", + "prepared_review_unit_hash": "9657b54097d3755e2baba74dc3162ee1d9e5761a6ab1869684ff68e46a3b69d6", "component_budget": { "node_count": 2, "item_count": 2, @@ -16816,18 +16856,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two separate workflow-maintenance PRs: one updates multiple GitHub Actions for Node 24 compatibility, the other upgrades Docker build actions to v6. They overlap in workflow files but address different dependencies and problems.", - "confidence": 0.94, + "summary": "Both items are workflow-maintenance PRs that upgrade GitHub Actions, but they update different actions and different code paths: one is for Node 24 compatibility in checkout/cache/upload-artifact, the other is for docker/build-push-action and related workflow pin bumps. They are similar in theme, not the same underlying change.", + "confidence": 0.92, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 42975 is the better canonical representative because it has the clearest, broader purpose (Node 24 compatibility) and covers a wider set of GitHub Actions updates.", + "canonical_pr_reason": "PR 42975 is the better representative of this cluster because it has the broader, clearer objective (Node 24 compatibility across many workflows) and the larger, more coherent action-version bump set.", "best_issue_reason": null, - "best_pr_reason": "PR 42975 is the strongest representative for the cluster since its title and diff clearly describe the main class of change: repository-wide GitHub Actions version upgrades for compatibility.", + "best_pr_reason": "PR 42975 is the strongest PR to represent the group overall: it targets a specific compatibility problem and spans multiple workflows, whereas PR 42976 is a separate dependency/version refresh for docker build workflows.", "soft_edge_verdicts": [ { "left": "pull_request:42975", "right": "pull_request:42976", "accept": false, - "reason": "These are not the same underlying change: 42975 updates checkout/cache/upload-artifact across workflows for Node 24 compatibility, while 42976 only bumps docker/build-push-action to v6 in docker-image workflows. Overlapping files alone is not enough to treat them as duplicates." + "reason": "Reject: they are both GitHub Actions upgrade PRs, but they change different actions and solve different maintenance tasks; no shared concrete bug/change to merge into one PR." } ] }, @@ -16870,12 +16910,12 @@ "pull_request:44601|pull_request:45838", "pull_request:45490|pull_request:45838" ], - "prepared_review_unit_hash": "85c28a5c33abc32549e25199ab3f67c2b6394446237b38dc44512b0736ed7bb7", + "prepared_review_unit_hash": "e85946c296e917a66db1d032dd235a4b647d49ecdbdcf8c6c117a4bd4a8c0864", "component_budget": { "node_count": 7, "item_count": 7, "soft_pair_count": 9, - "serialized_chars": 23515, + "serialized_chars": 23513, "estimated_input_tokens": 5879, "estimated_eval_tokens": 12014 }, @@ -16883,7 +16923,7 @@ "node_count": 7, "item_count": 7, "soft_pair_count": 9, - "serialized_chars": 23515, + "serialized_chars": 23513, "estimated_input_tokens": 5879, "estimated_eval_tokens": 12014 }, @@ -16892,66 +16932,66 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is heterogeneous: several unrelated model-addition PRs plus one distributed pipeline-parallel PR. They share repository plumbing patterns (docs, auto mappings) but do not look like duplicates of the same bug or change.", - "confidence": 0.98, + "summary": "All proposed soft edges look like false positives: the PRs are separate model additions or unrelated infrastructure changes, with only generic docs/registry overlap. None appear to fix the same concrete bug or implement the same mergeable change.", + "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": null, + "canonical_pr_reason": "No single PR is a true duplicate target here; if one representative PR must be picked, 43451 is the most substantial and review-heavy model-addition PR, but it remains distinct from the others.", "best_issue_reason": null, - "best_pr_reason": null, + "best_pr_reason": "43451 is the strongest standalone representative of the model-addition subgroup, but the set does not contain a mergeable duplicate cluster.", "soft_edge_verdicts": [ { "left": "pull_request:42978", "right": "pull_request:43448", "accept": false, - "reason": "Different model integrations (ViT NEPA vs Molmo); shared docs/auto-registry edits are generic model-onboarding boilerplate, not the same change." + "reason": "ViT NEPA and Molmo are different model additions; the overlap is only in shared registration/docs scaffolding." }, { "left": "pull_request:42978", "right": "pull_request:43451", "accept": false, - "reason": "Different model additions (ViT NEPA vs Molmo2) with different files, configs, and tests; not one underlying bug or feature." + "reason": "ViT NEPA vs Molmo2 are unrelated model families, not the same underlying change." }, { "left": "pull_request:42978", "right": "pull_request:45490", "accept": false, - "reason": "ViT NEPA and CTSM are distinct model-support PRs; overlap is only in shared registration/docs scaffolding." + "reason": "ViT NEPA and CTSM are distinct model implementations; shared toctree/auto wiring is boilerplate." }, { "left": "pull_request:43448", "right": "pull_request:43451", "accept": false, - "reason": "Molmo and Molmo2 are related by naming but are separate model families with different codepaths and artifacts; not mergeable as one PR." + "reason": "Molmo and Molmo2 are separate model families/generations, so this is not a duplicate fix or mergeable single PR." }, { "left": "pull_request:43448", "right": "pull_request:45490", "accept": false, - "reason": "Molmo vs CTSM are unrelated model additions; same broad subsystem, but not the same concrete change." + "reason": "Molmo and CTSM address different models and code paths; overlap is limited to generic model-addition plumbing." }, { "left": "pull_request:43451", "right": "pull_request:45490", "accept": false, - "reason": "Molmo2 and CTSM are different model introductions with no shared bug or implementation target." + "reason": "Molmo2 and CTSM are unrelated model additions, not the same concrete change." }, { "left": "pull_request:43973", "right": "pull_request:45838", "accept": false, - "reason": "Lfm2 Audio and PP-OCRv6 are unrelated model-support PRs; both touch docs/auto wiring, but that is not enough to treat them as duplicates." + "reason": "Lfm2 audio support and PP-OCRv6 text recognition are different modalities and model stacks; only docs/index files overlap." }, { "left": "pull_request:44601", "right": "pull_request:45838", "accept": false, - "reason": "Pipeline-parallel core loading support is a distributed-systems change, while PP-OCRv6 is a model support PR; they do not fix the same code-path problem." + "reason": "Native pipeline-parallel loading support is infrastructure work, while PP-OCRv6 is a model support PR; they do not fix the same code-path problem." }, { "left": "pull_request:45490", "right": "pull_request:45838", "accept": false, - "reason": "CTSM and PP-OCRv6 are different model additions; shared repo plumbing does not indicate the same underlying change." + "reason": "CTSM model support and PP-OCRv6 text recognition are different model additions, not duplicate changes." } ] }, @@ -16984,52 +17024,52 @@ "pull_request:43291|pull_request:44815", "pull_request:43665|pull_request:44815" ], - "prepared_review_unit_hash": "29b0f7d250b5dce5d94af3fd00f266b959de8dcb9e623bd2930654d4e8ad0ca4", + "prepared_review_unit_hash": "9c6844e510f4a45023fa4fcee17143709c927e23bdc70db874ff94e864c47cd2", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 7093, - "estimated_input_tokens": 1774, - "estimated_eval_tokens": 3804 + "serialized_chars": 7092, + "estimated_input_tokens": 1773, + "estimated_eval_tokens": 3802 }, "budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 7093, - "estimated_input_tokens": 1774, - "estimated_eval_tokens": 3804 + "serialized_chars": 7092, + "estimated_input_tokens": 1773, + "estimated_eval_tokens": 3802 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The three pull requests are not duplicates of one another. Two are mostly test-only changes, while the third is a substantive dequantization/loading fix in a different subsystem. No soft edge should be merged.", - "confidence": 0.92, + "summary": "These pull requests are not the same change set: one is a Whisper tokenizer/test fix, one is unrelated CLIP/ViT test edits, and one is a broader FP8/dequantization fix across several files. No duplicate cluster emerges here.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "pull_request:44815 is the most substantive and coherent PR: it fixes a concrete dequant/loading path and includes the corresponding implementation and test updates. The other two are narrow test edits without the same underlying code change.", + "canonical_pr_reason": "PR 44815 is the most substantive and coherent change: it fixes a concrete dequantization/loading path and includes targeted code updates plus tests. The others are either narrowly scoped to Whisper or appear to be test-only edits.", "best_issue_reason": null, - "best_pr_reason": "pull_request:44815 is the best standalone PR because it addresses an actual code-path defect rather than only altering tests, and its scope is internally consistent across the touched files.", + "best_pr_reason": "PR 44815 is the best representative of the group because it contains a real cross-file implementation fix, whereas PR 43291 is narrow and PR 43665 looks like unrelated or placeholder test changes rather than a true bug fix.", "soft_edge_verdicts": [ { "left": "pull_request:43291", "right": "pull_request:43665", "accept": false, - "reason": "Both are PRs with test changes, but they target different models and different behavior; there is no shared underlying bug or fix path." + "reason": "Different targets and different problems: Whisper tokenization/decode logic versus CLIP/ViT test files. They do not appear to fix the same underlying bug or code path." }, { "left": "pull_request:43291", "right": "pull_request:44815", "accept": false, - "reason": "Whisper tokenization/test cleanup and FP8 dequant/loading fixes are unrelated changes in different subsystems." + "reason": "Whisper decode behavior and FP8/dequantization/loading are unrelated subsystems with no shared concrete bug path." }, { "left": "pull_request:43665", "right": "pull_request:44815", "accept": false, - "reason": "The CLIP/ViT test-only edits do not match the FP8 dequantization fix; they are not the same bug or mergeable as one PR." + "reason": "Despite superficial similarity in being test-heavy, these PRs address different areas and do not look mergeable as one fix." } ] }, @@ -17059,7 +17099,7 @@ "soft_pairs": [ "pull_request:43488|pull_request:43532" ], - "prepared_review_unit_hash": "5bee5ec7d4b18827eb0a26ce16231d4bbe814ea80d470732b83bb249052830ce", + "prepared_review_unit_hash": "c35da48f9d38520ae515b82be57154402d304ad1e0f1ca1aeabc18ae4fb77730", "component_budget": { "node_count": 2, "item_count": 2, @@ -17081,18 +17121,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two pull requests are not duplicates: one is a synthetic bot-check/version-bump PR, while the other is a larger CI/testing workflow change with unrelated file edits.", - "confidence": 0.95, + "summary": "The two PRs are not duplicates: one is a setup/version/dependency/test tweak, while the other rewires CI workflows and related testing/notification code. Their overlap is superficial (shared test file) and they do not fix the same code-path problem.", + "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43532 is the better canonical representative because it contains the substantive workflow/testing changes; PR 43488 is a narrow repository-bot/test trigger PR and is not a good representative for the cluster.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "PR 43532 is the most meaningful PR in the set, with broader and more realistic code changes across CI and test utilities. PR 43488 is clearly a non-merge bot-check change.", + "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "pull_request:43488", "right": "pull_request:43532", "accept": false, - "reason": "They do not appear to fix the same bug or implement the same change. 43488 is a version/dependency tweak for bot checking, while 43532 changes CI workflow and testing utility code plus related test behavior." + "reason": "Different underlying changes and goals: #43488 touches setup.py, dependency tables, and a ViT test; #43532 changes GitHub workflow files plus testing/notification utilities. Shared filename alone is not enough to treat them as the same PR." } ] }, @@ -17122,7 +17162,7 @@ "soft_pairs": [ "pull_request:43612|pull_request:43613" ], - "prepared_review_unit_hash": "61504846732f3eaccb2ac117b573fc3f190a7473362c23696e8772008dcd10af", + "prepared_review_unit_hash": "15a9b572ed595151d57c0fd90e08e3c2275fe61335d049bd6142a4d5872729be", "component_budget": { "node_count": 2, "item_count": 2, @@ -17144,18 +17184,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are two related but distinct PRs: both introduce new segmentation pipelines and share some registration/docs scaffolding, but they target different tasks, model families, and code paths.", - "confidence": 0.96, + "summary": "The two PRs are closely related in infrastructure and documentation, but they implement different features: promptable concept segmentation vs promptable visual segmentation. They share scaffolding files, but the underlying models, tests, and task docs are distinct, so this is not a duplicate pair.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR: 43612 adds Promptable Concept Segmentation, while 43613 adds Promptable Visual Segmentation; the overlap is mostly shared pipeline/documentation plumbing, not the same underlying change.", + "canonical_pr_reason": "PR 43613 is the better representative only in the sense that it is the broader, more model-backed feature, but it is not a duplicate of 43612 because it targets a different segmentation task and code path.", "best_issue_reason": null, - "best_pr_reason": "No single best PR for a duplicate cluster here; they are separate feature additions rather than one concrete bug fix or mergeable duplicate change.", + "best_pr_reason": "PR 43613 is the stronger anchor for the cluster because it covers the more general visual-segmentation feature with more backend/model integrations, but it should not be merged with 43612 as a duplicate.", "soft_edge_verdicts": [ { "left": "pull_request:43612", "right": "pull_request:43613", "accept": false, - "reason": "Reject: both are new pipeline additions, but they implement different segmentation tasks with different model/test targets, so they are not the same underlying change and should not be merged as duplicates." + "reason": "Shared docs/pipeline plumbing is not enough: one adds promptable concept segmentation and the other adds promptable visual segmentation, with different task docs, model integrations, and test files. They are separate features, not the same underlying change." } ] }, @@ -17185,7 +17225,7 @@ "soft_pairs": [ "pull_request:43651|pull_request:43663" ], - "prepared_review_unit_hash": "9c35be50e5843627e3c42b5f0553aeba729f0636e8483de637ed7b81ec403ab2", + "prepared_review_unit_hash": "23639f2037b88fcb98692c71b0bbf9ee15deef849357ce991a3238d96807ff49", "component_budget": { "node_count": 2, "item_count": 2, @@ -17207,18 +17247,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open PRs in `trainer.py`, but they address different Trainer extension points: gradient-accumulation loss scaling vs. signature-column filtering for custom trainers/PEFT. They share a file and broad subsystem, but not the same underlying change.", + "summary": "These are two separate Trainer extensibility PRs in the same file, but they address different code paths: one changes gradient-accumulation loss scaling, the other makes signature-column filtering overrideable. Related area, not the same underlying change.", "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "No single canonical PR: these are separate trainer customizations with different code paths and behavior changes.", + "canonical_pr_reason": "No true canonical duplicate exists here; the PRs solve different Trainer behaviors rather than one shared bug or feature.", "best_issue_reason": null, - "best_pr_reason": "PR #43651 is the more concrete correctness fix, since it changes actual loss-scaling behavior; PR #43663 is a separate extensibility refactor.", + "best_pr_reason": "PR #43651 is the more central representative of the cluster only in the sense that it adds a broader trainer hook, but it should not be treated as a duplicate of #43663.", "soft_edge_verdicts": [ { "left": "pull_request:43651", "right": "pull_request:43663", "accept": false, - "reason": "Different features and code paths: #43651 controls gradient-accumulation loss scaling, while #43663 adds an override hook for signature-column filtering. They are not the same bug/change and would not plausibly merge into one PR." + "reason": "Both touch trainer.py, but one is about gradient-accumulation loss scaling and the other about column/signature filtering. Different behavior, different fix, not mergeable into one PR." } ] }, @@ -17250,55 +17290,55 @@ "pull_request:43656|pull_request:43842", "pull_request:43836|pull_request:43842" ], - "prepared_review_unit_hash": "74962995867f55bdf88a3863ad7fb3b7e19e38d3cc68d86af2132354c7ff75d3", + "prepared_review_unit_hash": "f78b626bcd2b1c5055d7d1b12ef7bc1b15019d7aebbcc9186db646cba1d4f189", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 5992, - "estimated_input_tokens": 1498, - "estimated_eval_tokens": 3252 + "serialized_chars": 5993, + "estimated_input_tokens": 1499, + "estimated_eval_tokens": 3254 }, "budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 5992, - "estimated_input_tokens": 1498, - "estimated_eval_tokens": 3252 + "serialized_chars": 5993, + "estimated_input_tokens": 1499, + "estimated_eval_tokens": 3254 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "PR #43842 is the cleanest representative of the TypeAdapter NameError fix in `src/transformers/cli/serve.py`. PR #43836 is plausibly the same underlying issue and shares issue target #43824, but PR #43656 is only loosely similar and is tied to a different target (#43576), so it should not be merged into the same duplicate cluster with the others.", + "summary": "All three PRs are in the same `src/transformers/cli/serve.py` area and appear to address the same import-time `TypeAdapter` annotation problem in the CLI. The most focused representative is the minimal, explicit pydantic-related fix.", "confidence": 0.74, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #43842 is the most direct and narrowly scoped fix for the TypeAdapter NameError, with an explicit link to issue #43824 and no extra refactoring beyond the bug fix.", + "canonical_pr_reason": "PR 43842 is the clearest and most targeted fix: it explicitly addresses the `TypeAdapter` NameError when pydantic is absent, keeps the change minimal, and directly annotates the problematic code path.", "best_issue_reason": null, - "best_pr_reason": "PR #43842 is the best overall representative because it addresses the concrete runtime typing failure with the smallest focused change and the clearest issue linkage.", + "best_pr_reason": "PR 43842 is the best overall representative because it is the most precise and least invasive fix for the concrete `TypeAdapter` NameError in `serve.py`.", "soft_edge_verdicts": [ { "left": "pull_request:43656", "right": "pull_request:43842", - "accept": false, - "reason": "These only share broad similarity in `serve.py`; they point to different issue targets (#43576 vs #43824), so the packet does not support treating them as the same bugfix or one mergeable PR." + "accept": true, + "reason": "Both PRs fix the same underlying `TypeAdapter` annotation/import-time NameError in `src/transformers/cli/serve.py`; the changes are different implementations of the same bug fix and could plausibly be folded into one PR." }, { "left": "pull_request:43836", "right": "pull_request:43842", "accept": true, - "reason": "Both target the same `serve.py` TypeAdapter NameError and share issue target #43824, so they plausibly fix the same underlying code-path problem despite different implementation styles." + "reason": "Both PRs target the same `TypeAdapter` NameError in the CLI serve module. Even though 43836 is broader, its stated workaround and the pydantic-specific fix in 43842 are aimed at the same concrete code-path problem." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The writeup overstates the evidence for PR #43656 vs #43842. Those two only share soft similarity and even point to different explicit issue targets (43576 vs 43824), so the packet does not firmly support treating them as the same bugfix or as cleanly mergeable into one PR. #43836 vs #43842 is better grounded because they share issue target 43824, but the summary still collapses all three PRs into one fix more strongly than the packet justifies." + "accept": true, + "feedback": "The summary is grounded in the packet, and the chosen representative PR is reasonably supported as the most targeted fix. Both soft-edge accepts are conservative enough here: the PRs share the same file and same TypeAdapter-related bug theme, and their fixes are compatible enough to plausibly live in one PR." }, "evaluator_used": true, - "retried": true, + "retried": false, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -17484,12 +17524,12 @@ "pull_request:44044|pull_request:44129", "pull_request:44044|pull_request:44154" ], - "prepared_review_unit_hash": "b51f864156a54e40a217adeb8426dd54ef126b08d3e0e9fa90c1b3ebca12470d", + "prepared_review_unit_hash": "0c9ad5a7d44b1769765c7f0e2eb368375662a59eb4087d189ea12b01d40382ea", "component_budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 78, - "serialized_chars": 84896, + "serialized_chars": 84893, "estimated_input_tokens": 21224, "estimated_eval_tokens": 42704 }, @@ -17497,303 +17537,249 @@ "node_count": 27, "item_count": 27, "soft_pair_count": 72, - "serialized_chars": 75093, - "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 a broad standardized output-tracing refactor umbrella across many model families. The true duplicates are the same-model GPT-J/GPT-Neo PR pairs; most other links are just shared refactor theme. I revised the PR anchor to #44722, which is the clearest GPT-J/CodeGen representative in the packet.", - "confidence": 0.81, - "canonical_issue_reason": "Issue #43979 is the shared umbrella tracker for the standardized output-tracing refactor across these PRs.", - "canonical_pr_reason": "PR #44722 is the strongest representative PR because it explicitly targets #43979 and covers both GPT-J and CodeGen, matching the central code-path change in this cluster.", - "best_issue_reason": "No standalone issue artifact is present; #43979 is the best issue-level anchor because the true duplicate PRs all point back to it.", - "best_pr_reason": "PR #44722 is the clearest anchor for the shared GPT-J/CodeGen refactor: it is explicitly linked to #43979 and spans the same concrete files as the other accepted GPT-J/CodeGen PRs.", + "summary": "This cluster is mostly a batch of model-specific output-tracing refactors. Only a few pairs are true near-duplicates within the same concrete code path (notably GPT-Neo and GPT-J/CodeGen); the rest are the same umbrella theme but different models and should stay separate.", + "confidence": 0.87, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44066 is the clearest canonical representative: it directly targets the GPT-J/CodeGen output-tracing migration, has an explicit #43979 link, and its diff matches the concrete standardized-decorator refactor pattern most cleanly.", + "best_issue_reason": null, + "best_pr_reason": "PR 44066 is the best global representative of the cluster\u2019s duplicate set because it is focused, explicitly linked to the umbrella issue, and closest to the repeated GPT-J/CodeGen refactor change path.", "soft_edge_verdicts": [ { "left": "pull_request:43996", "right": "pull_request:44085", "accept": false, - "reason": "Shared tracker only; CVT/FNet and GPT-J are different concrete code paths." + "reason": "Different model families (CVT/FNet vs GPT-J); same umbrella tracing pattern, but not the same concrete code change." }, { "left": "pull_request:43996", "right": "pull_request:44044", "accept": false, - "reason": "Different model families; the overlap is only the generic output-tracing theme." + "reason": "Different models and code paths; both are output-tracing refactors, but not duplicates of the same change." }, { "left": "pull_request:44066", "right": "pull_request:44085", "accept": true, - "reason": "Same GPT-J output-tracing refactor in the same file; mergeable into one PR." + "reason": "Both are GPT-J output-tracing refactors in the same file and same code path; they look like the same underlying change." }, { "left": "pull_request:44007", "right": "pull_request:44072", "accept": false, - "reason": "RegNet/ResNet-style refactor vs EfficientNet; not the same underlying change." + "reason": "RegNet/ResNet vs EfficientNet are different model implementations; shared decorator migration theme is too broad to merge." }, { "left": "pull_request:44072", "right": "pull_request:44722", "accept": false, - "reason": "EfficientNet and GPT-J/CodeGen are unrelated concrete code paths." + "reason": "EfficientNet and GPT-J/CodeGen are unrelated code paths; only the refactor style matches." }, { "left": "pull_request:44066", "right": "pull_request:44072", "accept": false, - "reason": "GPT-J/CodeGen vs EfficientNet; only the broad refactor pattern overlaps." + "reason": "GPT-J/CodeGen and EfficientNet are different models and different concrete fixes." }, { "left": "pull_request:44013", "right": "pull_request:44044", "accept": false, - "reason": "MobileNetV2 and DeBERTa are separate model implementations." + "reason": "MobileNetV2 vs DeBERTa_v2 are unrelated implementations; same tracing theme is not enough for duplication." }, { "left": "pull_request:44066", "right": "pull_request:44086", "accept": false, - "reason": "GPT-J/CodeGen and MGP-STR are different code paths." + "reason": "GPT-J/CodeGen and MGP-STR are different model paths; not the same bug/change." }, { "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 separate code paths; both use the new tracing API but are not duplicates." }, { "left": "pull_request:44018", "right": "pull_request:44068", "accept": true, - "reason": "Both are GPT-Neo output-tracing refactors against the same file set." + "reason": "Both are GPT-Neo output-tracing refactors on the same model/file, with the same standardized decorator migration." }, { "left": "pull_request:44066", "right": "pull_request:44068", "accept": false, - "reason": "GPT-J/CodeGen vs GPT-Neo; same refactor theme only." + "reason": "GPT-J/CodeGen vs GPT-Neo are different models and different code paths." }, { "left": "pull_request:44018", "right": "pull_request:44066", "accept": false, - "reason": "GPT-Neo and GPT-J/CodeGen are different model code paths." + "reason": "GPT-Neo and GPT-J/CodeGen are distinct model implementations; shared issue target does not make them duplicates." }, { "left": "pull_request:44019", "right": "pull_request:44722", "accept": false, - "reason": "ResNet vs GPT-J/CodeGen; no shared concrete bug or fix." + "reason": "ResNet and GPT-J/CodeGen are unrelated model families and fixes." }, { "left": "pull_request:44086", "right": "pull_request:44722", "accept": false, - "reason": "MGP-STR and GPT-J/CodeGen are unrelated implementations." + "reason": "MGP-STR and GPT-J/CodeGen touch different code paths; same refactor pattern only." }, { "left": "pull_request:44019", "right": "pull_request:44085", "accept": false, - "reason": "ResNet and GPT-J are different model families." + "reason": "ResNet vs GPT-J are different models; not the same underlying change." }, { "left": "pull_request:44018", "right": "pull_request:44019", "accept": false, - "reason": "GPT-Neo and ResNet are unrelated concrete changes." + "reason": "GPT-Neo and ResNet are unrelated model implementations." }, { "left": "pull_request:44019", "right": "pull_request:44071", "accept": false, - "reason": "ResNet vs MPT; only the output-tracing theme matches." + "reason": "ResNet vs MPT are different code paths and different concrete output-handling changes." }, { "left": "pull_request:44068", "right": "pull_request:44116", "accept": false, - "reason": "GPT-Neo and Flaubert/XLM are unrelated model code paths." + "reason": "GPT-Neo and Flaubert are different models; same tracing migration pattern only." }, { "left": "pull_request:44068", "right": "pull_request:44722", "accept": false, - "reason": "GPT-Neo vs GPT-J/CodeGen; same migration pattern, different code." + "reason": "GPT-Neo vs GPT-J/CodeGen are different model families and fixes." }, { "left": "pull_request:44018", "right": "pull_request:44116", "accept": false, - "reason": "GPT-Neo and Flaubert/XLM are different implementations." + "reason": "GPT-Neo and Flaubert are separate model code paths." }, { "left": "pull_request:44071", "right": "pull_request:44722", "accept": false, - "reason": "MPT and GPT-J/CodeGen are different model code paths." + "reason": "MPT and GPT-J/CodeGen are different model implementations." }, { "left": "pull_request:44018", "right": "pull_request:44086", "accept": false, - "reason": "GPT-Neo and MGP-STR are separate model implementations." + "reason": "GPT-Neo and MGP-STR are unrelated model paths." }, { "left": "pull_request:44018", "right": "pull_request:44085", "accept": false, - "reason": "GPT-Neo and GPT-J are different model families." + "reason": "GPT-Neo and GPT-J are different models; not a duplicate change." }, { "left": "pull_request:44068", "right": "pull_request:44086", "accept": false, - "reason": "GPT-Neo and MGP-STR are unrelated concrete code paths." + "reason": "GPT-Neo vs MGP-STR are different code paths." }, { "left": "pull_request:44071", "right": "pull_request:44085", "accept": false, - "reason": "MPT and GPT-J are different models." + "reason": "MPT and GPT-J are separate model fixes." }, { "left": "pull_request:44059", "right": "pull_request:44086", "accept": false, - "reason": "GPT-2 and MGP-STR are unrelated implementations." + "reason": "GPT2 and MGP-STR are different models and different concrete refactors." }, { "left": "pull_request:44085", "right": "pull_request:44086", "accept": false, - "reason": "GPT-J and MGP-STR are different concrete code paths." + "reason": "GPT-J and MGP-STR are unrelated implementations; only the decorator migration theme overlaps." }, { "left": "pull_request:44059", "right": "pull_request:44722", "accept": false, - "reason": "GPT-2 vs GPT-J/CodeGen; only the generic refactor theme overlaps." + "reason": "GPT2 vs GPT-J/CodeGen are different code paths." }, { "left": "pull_request:44098", "right": "pull_request:44101", "accept": false, - "reason": "ViLT and Flaubert/XLM are unrelated model code paths." + "reason": "ViLT and Flaubert/XLM are different model families; too broad to be duplicates." }, { "left": "pull_request:44018", "right": "pull_request:44071", "accept": false, - "reason": "GPT-Neo and MPT are different model implementations." + "reason": "GPT-Neo and MPT are different models; same standardized-output work but not the same change." }, { "left": "pull_request:44017", "right": "pull_request:44161", "accept": false, - "reason": "Segformer and LongT5 are different model families." - }, - { - "left": "pull_request:44017", - "right": "pull_request:44722", - "accept": false, - "reason": "Segformer and GPT-J/CodeGen are unrelated concrete code paths." + "reason": "Segformer and LongT5 are unrelated model implementations." }, { - "left": "pull_request:44017", - "right": "pull_request:44073", + "left": "pull_request:43997", + "right": "pull_request:44017", "accept": false, - "reason": "Segformer and VisualBert are separate implementations." + "reason": "RegNet and Segformer are different models and different concrete fixes." }, { - "left": "pull_request:44068", - "right": "pull_request:44071", + "left": "pull_request:43997", + "right": "pull_request:44056", "accept": false, - "reason": "GPT-Neo and MPT are different models." + "reason": "RegNet and MPNet are separate code paths; same tracing infrastructure change only." }, { "left": "pull_request:44071", - "right": "pull_request:44086", - "accept": false, - "reason": "MPT and MGP-STR are different code paths." - }, - { - "left": "pull_request:43997", - "right": "pull_request:44073", + "right": "pull_request:44076", "accept": false, - "reason": "RegNet and VisualBert are unrelated model implementations." + "reason": "MPT and ImageGPT are different model files and different output-tracing changes." }, { "left": "pull_request:44017", - "right": "pull_request:44071", + "right": "pull_request:44073", "accept": false, - "reason": "Segformer and MPT are different concrete changes." + "reason": "Segformer and VisualBert are unrelated model implementations." }, { "left": "pull_request:44073", "right": "pull_request:44101", "accept": false, - "reason": "VisualBert and Flaubert/XLM are unrelated code paths." - }, - { - "left": "pull_request:44056", - "right": "pull_request:44101", - "accept": false, - "reason": "MPNet and Flaubert/XLM are different model implementations." - }, - { - "left": "pull_request:44059", - "right": "pull_request:44068", - "accept": false, - "reason": "GPT-2 and GPT-Neo are different model families." + "reason": "VisualBert and Flaubert/XLM are different model families." }, { "left": "pull_request:44059", "right": "pull_request:44071", "accept": false, - "reason": "GPT-2 and MPT are unrelated concrete code paths." - }, - { - "left": "pull_request:44101", - "right": "pull_request:44161", - "accept": false, - "reason": "Flaubert/XLM and LongT5 are different model families." - }, - { - "left": "pull_request:43997", - "right": "pull_request:44017", - "accept": false, - "reason": "RegNet and Segformer are different models." - }, - { - "left": "pull_request:43997", - "right": "pull_request:44056", - "accept": false, - "reason": "RegNet and MPNet are unrelated implementations." - }, - { - "left": "pull_request:44071", - "right": "pull_request:44076", - "accept": false, - "reason": "MPT and ImageGPT are different concrete code paths." - }, - { - "left": "pull_request:44074", - "right": "pull_request:44101", - "accept": false, - "reason": "TextNet vs Flaubert/XLM; only the broad refactor theme matches." + "reason": "GPT2 and MPT are different code paths and not the same fix." }, { "left": "pull_request:44056", - "right": "pull_request:44161", + "right": "pull_request:44101", "accept": false, - "reason": "MPNet and LongT5 are different model implementations." + "reason": "MPNet and Flaubert/XLM are distinct model implementations." }, { "left": "pull_request:43997", @@ -17805,112 +17791,106 @@ "left": "pull_request:43997", "right": "pull_request:44161", "accept": false, - "reason": "RegNet and LongT5 are different code paths." - }, - { - "left": "pull_request:44074", - "right": "pull_request:44161", - "accept": false, - "reason": "TextNet and LongT5 are different model families." + "reason": "RegNet and LongT5 are different models and fixes." }, { - "left": "pull_request:44018", - "right": "pull_request:44059", + "left": "pull_request:44071", + "right": "pull_request:44129", "accept": false, - "reason": "GPT-Neo and GPT-2 are different model implementations." + "reason": "MPT and SpeechT5 are different code paths; same tracing pattern only." }, { - "left": "pull_request:43997", + "left": "pull_request:44010", "right": "pull_request:44071", "accept": false, - "reason": "RegNet and MPT are unrelated model code paths." + "reason": "SqueezeBert and MPT are unrelated model implementations." }, { - "left": "pull_request:43997", - "right": "pull_request:44074", + "left": "pull_request:44010", + "right": "pull_request:44073", "accept": false, - "reason": "RegNet and TextNet are different models." + "reason": "SqueezeBert and VisualBert are different model paths." }, { - "left": "pull_request:44010", - "right": "pull_request:44071", + "left": "pull_request:44018", + "right": "pull_request:44129", "accept": false, - "reason": "SqueezeBert and MPT are different code paths." + "reason": "GPT-Neo and SpeechT5 are separate model code paths." }, { - "left": "pull_request:44010", - "right": "pull_request:44073", + "left": "pull_request:43996", + "right": "pull_request:44161", "accept": false, - "reason": "SqueezeBert and VisualBert are unrelated implementations." + "reason": "CVT/FNet and LongT5 are different models; same umbrella refactor is not enough." }, { - "left": "pull_request:44010", - "right": "pull_request:44018", + "left": "pull_request:43996", + "right": "pull_request:44017", "accept": false, - "reason": "SqueezeBert vs GPT-Neo; same refactor theme only." + "reason": "CVT/FNet and Segformer are different model implementations." }, { "left": "pull_request:44010", "right": "pull_request:44044", "accept": false, - "reason": "SqueezeBert and DeBERTa are different model code paths." + "reason": "SqueezeBert and DeBERTa_v2 are unrelated code paths." }, { "left": "pull_request:44044", "right": "pull_request:44074", "accept": false, - "reason": "DeBERTa and TextNet are unrelated models." + "reason": "DeBERTa_v2 and TextNet are different models and fixes." }, { "left": "pull_request:44066", "right": "pull_request:44722", "accept": true, - "reason": "Same GPT-J/CodeGen output-tracing refactor; these are effectively duplicate PRs." + "reason": "Both center on the same GPT-J/CodeGen output-tracing refactor; the later PR looks like the same change family." }, { "left": "pull_request:44085", "right": "pull_request:44722", "accept": true, - "reason": "Both touch the same GPT-J output-tracing code path; 44722 just includes an extra CodeGen slice." + "reason": "Both touch GPT-J output tracing in the same file and are the same underlying refactor, despite 44722 also carrying the CodeGen companion change." }, { "left": "pull_request:44085", "right": "pull_request:44129", "accept": false, - "reason": "GPT-J and SpeechT5 are different model families." + "reason": "GPT-J and SpeechT5 are different models and different fixes." }, { "left": "pull_request:43996", "right": "pull_request:44007", "accept": false, - "reason": "CVT/FNet and RegNet/ResNet/RT-DETR are different implementations." + "reason": "CVT/FNet and RegNet/ResNet are different model families; no shared concrete bug." }, { "left": "pull_request:43996", "right": "pull_request:44129", "accept": false, - "reason": "Vision backbone refactor vs SpeechT5; not the same change." + "reason": "CVT/FNet and SpeechT5 are unrelated model code paths." }, { "left": "pull_request:44044", "right": "pull_request:44129", "accept": false, - "reason": "DeBERTa and SpeechT5 are unrelated concrete code paths." + "reason": "DeBERTa_v2 and SpeechT5 are different model implementations." }, { "left": "pull_request:44044", "right": "pull_request:44154", "accept": false, - "reason": "DeBERTa and Vits are different models; same theme only." + "reason": "DeBERTa_v2 and Vits are different models; only the tracing refactor theme overlaps." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The cluster summary is mostly conservative, but the PR anchoring overreaches. In particular, the claim that PR #44066 is broader/more central than later GPT-J-only follow-ups is not supported by the packet: PR #44722 also touches both `codegen` and `gptj`, is explicitly linked to #43979, and looks at least as central. That makes the canonical PR reasoning insufficiently grounded. The true duplicate/mergeable pairs you marked are plausible, but the canonical PR justification should be revised to avoid overstating evidence." + "accept": true, + "feedback": "The summary is grounded in the packet and the soft-edge verdicts are mostly conservative. The accepted pairs are all same-model/same-file refactor variants that plausibly merge into a single bugfix PR, while the rejected pairs correctly stay away from cross-model overreach. No clear evidence of overstating duplicate status." }, "evaluator_used": true, - "retried": true, + "retried": false, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -17945,12 +17925,12 @@ "pull_request:43997|pull_request:44010", "pull_request:44010|pull_request:44129" ], - "prepared_review_unit_hash": "4b81b849860b1ba480643613dfc0b5209e578a2815cd6d3b2c4ee6c8d995e3b5", + "prepared_review_unit_hash": "d503011584788ee1b2a5bef08291a8550059ddd93010f4af300af5db0559ed27", "component_budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 78, - "serialized_chars": 84896, + "serialized_chars": 84893, "estimated_input_tokens": 21224, "estimated_eval_tokens": 42704 }, @@ -17958,57 +17938,57 @@ "node_count": 8, "item_count": 8, "soft_pair_count": 6, - "serialized_chars": 17124, - "estimated_input_tokens": 4281, - "estimated_eval_tokens": 8818 + "serialized_chars": 17125, + "estimated_input_tokens": 4282, + "estimated_eval_tokens": 8820 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These PRs are all model-specific output-tracing refactors, but they touch different code paths and should not be deduplicated across models. They look like a family of similar housekeeping changes rather than one shared bug fix.", - "confidence": 0.92, + "summary": "All items are the same broad modernization pattern\u2014model-specific migration to standardized output capture\u2014but they target different architectures and code paths, so none of the soft pairs are true duplicates.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44056 is the clearest representative of the cluster: it has a focused, well-described capture_outputs refactor and adds the model-specific _can_record_outputs wiring in one place.", + "canonical_pr_reason": "PR 44129 is the best representative because it is the only one tied to an explicit issue and shows the standardized output-capture refactor most clearly, but it is still specific to SpeechT5 rather than a shared bugfix.", "best_issue_reason": null, - "best_pr_reason": "PR 44056 is the best overall representative because its title and diff most directly match the common standardized-output-tracing theme without being overly narrow or tangled with unrelated changes.", + "best_pr_reason": "PR 44129 is the strongest single PR to anchor the cluster: explicit issue linkage, clear refactor intent, and a self-contained model-specific implementation.", "soft_edge_verdicts": [ { "left": "pull_request:44024", "right": "pull_request:44076", "accept": false, - "reason": "Same broad refactor theme, but different models and different concrete code paths (FocalNet vs ImageGPT). Not the same underlying change." + "reason": "Different models (FocalNet vs ImageGPT) and different forward paths; same refactor style, not the same underlying change." }, { "left": "pull_request:44073", "right": "pull_request:44074", "accept": false, - "reason": "Both modernize output handling, but VisualBert and TextNet are separate implementations with different behavior changes. Too broad to treat as duplicates." + "reason": "Different models (VisualBert vs TextNet); they share output-tracing cleanup, but the affected code and behavior are unrelated." }, { "left": "pull_request:44056", "right": "pull_request:44073", "accept": false, - "reason": "Both are standardized output tracing refactors, but they target different model internals (MPNet vs VisualBert) and are not mergeable as one PR." + "reason": "MPNet and VisualBert are separate model implementations with distinct output-capture wiring; not mergeable as one PR." }, { "left": "pull_request:44056", "right": "pull_request:44074", "accept": false, - "reason": "Different models and different output-shape/API adjustments; similar pattern, but not the same concrete fix." + "reason": "MPNet vs TextNet touches different model internals and output-return conventions; same theme, not same bug/change." }, { "left": "pull_request:43997", "right": "pull_request:44010", "accept": false, - "reason": "RegNet and SqueezeBert are unrelated model code paths. Shared decorator imports are not enough to make these duplicates." + "reason": "RegNet and SqueezeBert are unrelated model code paths; both standardize outputs, but they do not fix the same concrete problem." }, { "left": "pull_request:44010", "right": "pull_request:44129", "accept": false, - "reason": "SqueezeBert vs SpeechT5 are different model implementations, and only SpeechT5 is explicitly tied to issue 43979. Not a duplicate pair." + "reason": "SqueezeBert and SpeechT5 are different models with different output-tracing implementations; the overlap is only in refactoring approach." } ] }, @@ -18088,12 +18068,12 @@ "pull_request:44028|pull_request:44030", "pull_request:44029|pull_request:44030" ], - "prepared_review_unit_hash": "d8301b178ca7552b2203f761c9b5dfdd10fe089db1d51d63d9b9a4d9820d61f6", + "prepared_review_unit_hash": "7d7011b1878eeec12309620fd4e6e9a88736902d5d528f889aec869820f3c09b", "component_budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 40, - "serialized_chars": 40177, + "serialized_chars": 40178, "estimated_input_tokens": 10045, "estimated_eval_tokens": 20346 }, @@ -18101,7 +18081,7 @@ "node_count": 13, "item_count": 13, "soft_pair_count": 40, - "serialized_chars": 40177, + "serialized_chars": 40178, "estimated_input_tokens": 10045, "estimated_eval_tokens": 20346 }, @@ -18110,246 +18090,252 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are model-specific output-tracing refactors across unrelated architectures, not duplicate fixes for one shared bug or change.", - "confidence": 0.97, + "summary": "These PRs share a common refactor theme (output tracing / can_return_tuple) but target different models and code paths, so they are not duplicates of the same change.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "44003 is the best single representative PR: it has the broadest scope in this set, touching two closely related Mamba-family files with a substantial tracing refactor.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "44003 is the strongest representative of the pattern because it is broader than the other PRs and contains the clearest, most substantial code-path change.", + "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "pull_request:43998", "right": "pull_request:44002", "accept": false, - "reason": "Same refactor theme, but different model implementations and code paths; not the same concrete bug/change." + "reason": "Different model families (`timm_backbone` vs `upernet`); same refactor theme, not the same concrete fix." }, { "left": "pull_request:43998", "right": "pull_request:44000", "accept": false, - "reason": "Different model families and files; only the refactor style matches, not the underlying change." + "reason": "Unrelated model implementations; no shared code path or bug beyond generic output-tracing refactoring." }, { "left": "pull_request:43998", "right": "pull_request:44001", "accept": false, - "reason": "Different architectures and forward paths; these are separate model-local refactors." + "reason": "Different models (`timm_backbone` vs `univnet`); separate forward/output handling changes." }, { "left": "pull_request:43998", "right": "pull_request:44003", "accept": false, - "reason": "Timm backbone vs Mamba/FalconMamba are unrelated code paths; not one mergeable fix." + "reason": "`timm_backbone` and `mamba/falcon_mamba` are distinct subsystems with separate refactors." }, { "left": "pull_request:43998", "right": "pull_request:44029", "accept": false, - "reason": "Different architectures and output-tracing implementations; same theme, not the same change." + "reason": "Different architectures and files; not the same underlying change." }, { "left": "pull_request:43999", "right": "pull_request:44001", "accept": false, - "reason": "MobileNetV1 and UnivNet are unrelated models; these are separate refactors, not duplicates." + "reason": "Different model code paths (`mobilenet_v1` vs `univnet`), only broadly similar tracing refactor." }, { "left": "pull_request:43999", "right": "pull_request:44002", "accept": false, - "reason": "Different model code paths; the shared wording does not indicate one underlying bug." + "reason": "Separate models and forward signatures; not one mergeable duplicate change." }, { "left": "pull_request:43999", "right": "pull_request:44025", "accept": false, - "reason": "MobileNetV1 vs Depth Anything are unrelated implementations; not a single concrete fix." + "reason": "`mobilenet_v1` is unrelated to `depth_anything` / `prompt_depth_anything`; no shared concrete bug." }, { "left": "pull_request:43999", "right": "pull_request:44026", "accept": false, - "reason": "Different model families and files; only a similar tracing cleanup pattern." + "reason": "Different encoder-decoder model families; same theme but not same fix." }, { "left": "pull_request:43999", "right": "pull_request:44027", "accept": false, - "reason": "MobileNetV1 and Speech-Encoder-Decoder are unrelated code paths, so this is not a duplicate." + "reason": "`mobilenet_v1` and `speech_encoder_decoder` touch different implementations and behaviors." }, { "left": "pull_request:44000", "right": "pull_request:44001", "accept": false, - "reason": "Vision-Text Dual Encoder and UnivNet are separate model implementations; same theme, different changes." + "reason": "Different models (`vision_text_dual_encoder` vs `univnet`); no shared code path." }, { "left": "pull_request:44000", "right": "pull_request:44002", "accept": false, - "reason": "Different model families and forward logic; not the same bug or PR-worthy change." + "reason": "Separate model families and APIs; same refactor motif only." }, { "left": "pull_request:44000", "right": "pull_request:44003", "accept": false, - "reason": "Vision-Text Dual Encoder vs Mamba/FalconMamba are unrelated code paths." + "reason": "Different subsystems (`vision_text_dual_encoder` vs `mamba`); not mergeable as one fix." }, { "left": "pull_request:44000", "right": "pull_request:44025", "accept": false, - "reason": "These touch unrelated models; the common output-tracing wording is too broad to merge." + "reason": "Distinct model code paths; similar output-tracing cleanup is not enough for duplication." }, { "left": "pull_request:44001", "right": "pull_request:44002", "accept": false, - "reason": "UnivNet and UperNet are unrelated model paths; no shared concrete fix." + "reason": "`univnet` and `upernet` are unrelated model implementations." }, { "left": "pull_request:44001", "right": "pull_request:44003", "accept": false, - "reason": "Different architectures and files; not one underlying code-path problem." + "reason": "Different architectures and files; no same underlying bug/change." }, { "left": "pull_request:44001", "right": "pull_request:44025", "accept": false, - "reason": "UnivNet vs Depth Anything are separate model-local refactors, not duplicates." + "reason": "`univnet` does not overlap with `depth_anything` code paths." }, { "left": "pull_request:44002", "right": "pull_request:44029", "accept": false, - "reason": "UperNet and RWKV are unrelated code paths; only a generic refactor theme is shared." + "reason": "`upernet` and `rwkv` are unrelated; same refactor pattern only." }, { "left": "pull_request:44002", "right": "pull_request:44003", "accept": false, - "reason": "UperNet and Mamba/FalconMamba are different models with different tracing logic." + "reason": "Different model families with separate forward/output behavior." }, { "left": "pull_request:44003", "right": "pull_request:44028", "accept": false, - "reason": "Mamba/FalconMamba and SuperPoint are unrelated architectures; not the same fix." + "reason": "`mamba` and `superpoint` are unrelated; no common concrete fix." }, { "left": "pull_request:44003", "right": "pull_request:44004", "accept": false, - "reason": "Mamba/FalconMamba vs CodeGen are different code paths; same pattern, not same change." + "reason": "Different code paths (`mamba` vs `codegen`); not the same PR-worthy change." }, { "left": "pull_request:43998", "right": "pull_request:44004", "accept": false, - "reason": "Timm backbone and CodeGen are unrelated model implementations." + "reason": "`timm_backbone` and `codegen` are unrelated implementations." }, { "left": "pull_request:44001", "right": "pull_request:44004", "accept": false, - "reason": "UnivNet and CodeGen are unrelated code paths; not a single bug fix." + "reason": "Separate model classes and forward semantics; no duplicate bug." }, { "left": "pull_request:44002", "right": "pull_request:44004", "accept": false, - "reason": "UperNet and CodeGen are separate model-specific refactors." + "reason": "Different subsystems (`upernet` vs `codegen`); only generic tracing refactor overlap." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44004", + "accept": false, + "reason": "Distinct models and output formats; not the same underlying change." }, { "left": "pull_request:44025", "right": "pull_request:44026", "accept": false, - "reason": "Depth Anything and Vision-Encoder-Decoder are different model families; not one mergeable change." + "reason": "`depth_anything` and `vision_encoder_decoder` are different model families." }, { "left": "pull_request:44025", "right": "pull_request:44027", "accept": false, - "reason": "Depth Anything vs Speech-Encoder-Decoder are unrelated implementations." + "reason": "Different models and APIs; same broad cleanup theme, not one fix." }, { "left": "pull_request:44025", "right": "pull_request:44028", "accept": false, - "reason": "Different model code paths; the shared tracing refactor theme is too broad." + "reason": "`depth_anything` and `superpoint` do not share a concrete code path." }, { "left": "pull_request:44025", "right": "pull_request:44029", "accept": false, - "reason": "Depth Anything and RWKV are unrelated models and would not be merged as one PR." + "reason": "Different model families (`depth_anything` vs `rwkv`); not duplicates." }, { "left": "pull_request:44025", "right": "pull_request:44030", "accept": false, - "reason": "Different architectures and forward logic; not the same underlying change." + "reason": "`depth_anything` and `dpr` are unrelated changes despite similar refactoring." }, { "left": "pull_request:44026", "right": "pull_request:44029", "accept": false, - "reason": "Vision-Encoder-Decoder and RWKV are unrelated code paths." + "reason": "`vision_encoder_decoder` and `rwkv` are unrelated code paths." }, { "left": "pull_request:44026", "right": "pull_request:44027", "accept": false, - "reason": "Vision-Encoder-Decoder and Speech-Encoder-Decoder are similar wrappers, but still separate model-specific changes and not one duplicate fix." + "reason": "Different encoder-decoder stacks; not the same concrete bug/change." }, { "left": "pull_request:44026", "right": "pull_request:44028", "accept": false, - "reason": "Different model families and files; not the same concrete bug/change." + "reason": "`vision_encoder_decoder` and `superpoint` are unrelated models." }, { "left": "pull_request:44026", "right": "pull_request:44030", "accept": false, - "reason": "Vision-Encoder-Decoder and DPR are unrelated implementations." + "reason": "Different model families and output handling; no shared fix." }, { "left": "pull_request:44027", "right": "pull_request:44028", "accept": false, - "reason": "Speech-Encoder-Decoder and SuperPoint are unrelated code paths." + "reason": "`speech_encoder_decoder` and `superpoint` are unrelated implementations." }, { "left": "pull_request:44027", "right": "pull_request:44029", "accept": false, - "reason": "Speech-Encoder-Decoder and RWKV are unrelated models; no shared underlying fix." + "reason": "Different model subsystems; same refactor pattern only." }, { "left": "pull_request:44027", "right": "pull_request:44030", "accept": false, - "reason": "Speech-Encoder-Decoder and DPR are separate model-local refactors." + "reason": "`speech_encoder_decoder` and `dpr` are not the same underlying change." }, { "left": "pull_request:44028", "right": "pull_request:44029", "accept": false, - "reason": "SuperPoint and RWKV are unrelated architectures; same theme only." + "reason": "`superpoint` and `rwkv` have no shared code path." }, { "left": "pull_request:44028", "right": "pull_request:44030", "accept": false, - "reason": "SuperPoint and DPR are different models with different code paths." + "reason": "Different models and behaviors; not mergeable as one PR." }, { "left": "pull_request:44029", "right": "pull_request:44030", "accept": false, - "reason": "RWKV and DPR are unrelated implementations; not a duplicate PR pair." + "reason": "`rwkv` and `dpr` are unrelated model implementations; only the output-tracing cleanup overlaps." } ] }, @@ -18382,7 +18368,7 @@ "pull_request:44662|pull_request:45075", "pull_request:45075|pull_request:45401" ], - "prepared_review_unit_hash": "935bde6d7171664e4aaae23d32e57fe7f588b447534b3c7dc4fc45677024f4e1", + "prepared_review_unit_hash": "d7c4c19dbbeb6e3f5509886139a59b38000defb7f62c93c8d79c48f2cc0a7e5a", "component_budget": { "node_count": 3, "item_count": 3, @@ -18404,30 +18390,30 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are three separate model-addition PRs for different model families. They overlap on registry/docs plumbing, but each introduces a distinct implementation and test suite, so they are not duplicates.", + "summary": "These are three distinct model-addition PRs for different architectures and tasks (PenguinVL, DeepSeek-OCR-2, and Voxtral TTS). They share only common Transformers integration scaffolding, so they are not duplicates.", "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": null, + "canonical_pr_reason": "No single PR is a valid canonical duplicate representative: each PR introduces a different model family with its own config, modeling, processor, and tests.", "best_issue_reason": null, - "best_pr_reason": null, + "best_pr_reason": "None of these PRs should be treated as the cluster\u2019s best duplicate representative, because they do not fix the same underlying bug or implement the same change.", "soft_edge_verdicts": [ { "left": "pull_request:44662", "right": "pull_request:45401", "accept": false, - "reason": "Different models and code paths: PenguinVL vs Voxtral TTS. Shared auto-registry/docs files are just integration plumbing, not the same underlying change." + "reason": "PenguinVL (vision-language) and Voxtral TTS (text-to-speech) are unrelated model implementations; shared auto-registration and docs files are just boilerplate." }, { "left": "pull_request:44662", "right": "pull_request:45075", "accept": false, - "reason": "Different model implementations: PenguinVL vs DeepSeek-OCR-2. Similar framework registration changes do not make these the same PR." + "reason": "PenguinVL and DeepSeek-OCR-2 are different models with different codepaths and files; overlap is only in generic model-registration/docs plumbing." }, { "left": "pull_request:45075", "right": "pull_request:45401", "accept": false, - "reason": "Distinct model families and feature sets: DeepSeek-OCR-2 vs Voxtral TTS. Overlap is limited to common model-registration files." + "reason": "DeepSeek-OCR-2 (OCR/vision) and Voxtral TTS (speech generation) are different concrete features, not the same bug or mergeable change set." } ] }, @@ -18457,12 +18443,12 @@ "soft_pairs": [ "pull_request:44979|pull_request:45363" ], - "prepared_review_unit_hash": "13f14121ee4f5bc5a4a8abeac7d87ffb77157e3133b9410372981e2e1ad30441", + "prepared_review_unit_hash": "becd15cd66a1f1137551d1eba27cb4d209d94fba44c7920633e12a5ad0f59a2a", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4406, + "serialized_chars": 4407, "estimated_input_tokens": 1102, "estimated_eval_tokens": 2460 }, @@ -18470,7 +18456,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4406, + "serialized_chars": 4407, "estimated_input_tokens": 1102, "estimated_eval_tokens": 2460 }, @@ -18479,18 +18465,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two related but distinct open PRs around fusion infrastructure: one introduces a generic Module Fusion API, while the other adds KernelConfig-based n-to-1 kernel fusion integration and an example. They share a theme but not the same concrete change.", - "confidence": 0.88, + "summary": "These PRs are related in the broad theme of module/kernel fusion, but they are not the same change: one introduces a generic module fusion API, while the other wires up n-to-1 kernel fusion through KernelConfig and integration points.", + "confidence": 0.87, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #44979 is the cleaner representative of the shared theme because it introduces the core Module Fusion API abstraction that the other PR appears to build upon.", + "canonical_pr_reason": "PR #44979 is the better canonical representative because it introduces the foundational, general-purpose Module Fusion API and includes dedicated tests. It is broader and more self-contained than the draft PR #45363, which appears to be a downstream, specific integration of that idea.", "best_issue_reason": null, - "best_pr_reason": "PR #44979 is the best cluster representative overall since it defines the foundational API and is the broadest, most reusable change in the set.", + "best_pr_reason": "PR #44979 is the strongest cluster anchor: it is non-draft, API-level, and appears to define the core abstraction that the other PR builds upon. PR #45363 is narrower and likely depends on the concepts introduced here.", "soft_edge_verdicts": [ { "left": "pull_request:44979", "right": "pull_request:45363", "accept": false, - "reason": "Related fusion work, but not the same underlying bug or mergeable change: #44979 adds a generic Module Fusion API, while #45363 wires a specific KernelConfig-based n-to-1 fusion path plus example/integration changes. The scopes and code paths differ too much to treat as duplicates." + "reason": "Reject: these are adjacent but not the same underlying change. #44979 adds a general Module Fusion API, while #45363 implements n-to-1 kernel fusion via KernelConfig and touches different integration code paths. They would not plausibly be merged as one PR." } ] }, @@ -18520,12 +18506,12 @@ "soft_pairs": [ "pull_request:45086|pull_request:45317" ], - "prepared_review_unit_hash": "cf5211ea4d561ac766becc199b0640b55ad7bf2b8f3c1da1eb2a5958e6066ed7", + "prepared_review_unit_hash": "be859ebf09058f3220d163e3a3fbd86a4e273be06c3dbc71a6e525b7382000ef", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4413, + "serialized_chars": 4414, "estimated_input_tokens": 1104, "estimated_eval_tokens": 2464 }, @@ -18533,7 +18519,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4413, + "serialized_chars": 4414, "estimated_input_tokens": 1104, "estimated_eval_tokens": 2464 }, @@ -18542,18 +18528,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both pull requests fix the same concrete Mistral regex patch bug in `tokenization_utils_tokenizers.py`: they replace `backend_tokenizer.pre_tokenizer` with `tokenizer.pre_tokenizer` to avoid an `AttributeError`. PR 45317 is the more complete version because it includes tests.", - "confidence": 0.99, + "summary": "Both PRs target the same Mistral regex patch bug in the same code path (`_patch_mistral_regex`) and share the same issue target. PR #45317 looks like the more complete fix because it includes test coverage in addition to the code change.", + "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45317 is the best canonical PR because it addresses the same underlying bug as 45086 but adds test coverage and appears to be the more complete fix.", + "canonical_pr_reason": "PR #45317 is the stronger canonical PR: it fixes the same AttributeError, has the same file-level change, and adds tests, making it the more complete representation of the fix.", "best_issue_reason": null, - "best_pr_reason": "PR 45317 is the strongest standalone candidate: same fix, same target issue, plus tests validating `fix_mistral_regex=True`.", + "best_pr_reason": "PR #45317 is the best representative of the cluster because it most fully addresses the bug and includes validation via tests.", "soft_edge_verdicts": [ { "left": "pull_request:45086", "right": "pull_request:45317", "accept": true, - "reason": "Same code-path bug fix in `_patch_mistral_regex` with identical core change; 45317 is an expanded version of 45086 rather than a different PR." + "reason": "Same underlying bug and same fix location (`tokenization_utils_tokenizers.py` / `_patch_mistral_regex`), with the later PR extending the earlier one by adding tests; they are effectively duplicate fixes for the same issue." } ] }, @@ -18583,12 +18569,12 @@ "soft_pairs": [ "pull_request:45115|pull_request:45569" ], - "prepared_review_unit_hash": "8175693e52fb9b8141930d3c38cbd4f14ba637a712bead4162024409aaffdd6b", + "prepared_review_unit_hash": "fb109d5fdbf4367650716ec1e9f95fecf68ba89c72481e79ba63480beb923890", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 6066, + "serialized_chars": 6065, "estimated_input_tokens": 1517, "estimated_eval_tokens": 3290 }, @@ -18596,7 +18582,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 6066, + "serialized_chars": 6065, "estimated_input_tokens": 1517, "estimated_eval_tokens": 3290 }, @@ -18605,18 +18591,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open PRs overlap on NemotronH internals, but they address different changes: one is a conversion/mapping and inheritance refactor, the other is a broader model split into NemotronHDense/NemotronHSparse with docs/tests. They are related but not duplicates.", + "summary": "Both PRs touch NemotronH internals, but they address different changes: #45115 is a conversion-mapping/refactor PR, while #45569 is a broader model-splitting and docs/modeling update. They are related but not duplicates.", "confidence": 0.91, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45569 is the broader, more representative NemotronH change: it introduces the dense/sparse model split, updates docs, auto-mappings, and tests, so it better captures the main architectural direction.", + "canonical_pr_reason": "#45569 is the broader, more complete NemotronH change set: it introduces the dense/sparse model split, updates auto/modeling wiring, docs, and tests. It looks like the main implementation PR rather than a narrow supporting refactor.", "best_issue_reason": null, - "best_pr_reason": "PR #45569 is the best global representative because it encompasses the larger user-visible model refactor and package structure changes, whereas #45115 is a narrower conversion-mapping/inheritance cleanup.", + "best_pr_reason": "#45569 is the best representative of the cluster because it covers the actual user-facing/model-architecture rework, whereas #45115 is limited to conversion key renaming and compatibility mapping.", "soft_edge_verdicts": [ { "left": "pull_request:45115", "right": "pull_request:45569", "accept": false, - "reason": "They both touch NemotronH, but the concrete changes differ: #45115 focuses on checkpoint conversion and inheritance/weight-name mapping, while #45569 splits the architecture into dense/sparse variants and updates docs/tests. Not the same underlying bug or mergeable change." + "reason": "They share NemotronH files, but the concrete changes differ: #45115 only adds checkpoint conversion renames and compatibility mappings, while #45569 splits/rewires NemotronH into dense and sparse models with docs and tests. Not the same fix and not plausibly one merged PR." } ] }, @@ -18646,12 +18632,12 @@ "soft_pairs": [ "pull_request:45332|pull_request:45333" ], - "prepared_review_unit_hash": "3ab322e3f27d0e4187329735f60ed3bda4f58c3326b97e870b75603d30039e2f", + "prepared_review_unit_hash": "e1d0c9e5c5f8cf6e5d16091ea97e4aa0a6fd0934135be9a61f71f80c5293c217", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5398, + "serialized_chars": 5397, "estimated_input_tokens": 1350, "estimated_eval_tokens": 2956 }, @@ -18659,7 +18645,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5398, + "serialized_chars": 5397, "estimated_input_tokens": 1350, "estimated_eval_tokens": 2956 }, @@ -18668,18 +18654,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two PRs are related but not duplicates: one adds heterogeneous per-layer configuration support, while the other adds broader heterogeneous model/runtime support built on top of that groundwork.", - "confidence": 0.9, + "summary": "Two open PRs in the same heterogeneous-config feature area, but one is a broader end-to-end heterogeneous model support change and the other is a narrower config-only change. They are related, not duplicates.", + "confidence": 0.81, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45332 is the broader umbrella change, spanning config, cache, masking, modeling, and tests, so it is the best representative of the cluster.", + "canonical_pr_reason": "PR #45332 is the broader umbrella change: it includes per-layer config handling plus modeling/cache/masking updates and tests, so it subsumes the narrower config-only work in #45333.", "best_issue_reason": null, - "best_pr_reason": "PR #45332 is the most suitable global representative because it covers the end-to-end heterogeneous model support rather than only the config layer.", + "best_pr_reason": "PR #45332 is the best standalone candidate because it covers the full heterogeneous model support path, not just configuration plumbing.", "soft_edge_verdicts": [ { "left": "pull_request:45332", "right": "pull_request:45333", "accept": false, - "reason": "They share implementation infrastructure, but #45333 is config-only while #45332 adds model/runtime behavior; they are related pieces of one feature, not the same concrete change or bug fix." + "reason": "Related feature work, but not the same underlying change: #45333 is config support only, while #45332 adds broader modeling/cache behavior. They would not naturally be merged as one duplicate PR." } ] }, @@ -18709,7 +18695,7 @@ "soft_pairs": [ "pull_request:45415|pull_request:45425" ], - "prepared_review_unit_hash": "0746c8e17bfcbb5c5415d646323bdb671022af20e07d24dbacddad2087999fa9", + "prepared_review_unit_hash": "c835e998a8664a515e60034ae4c0d0905862aa8ec1cae81792b4a78cd470c5d2", "component_budget": { "node_count": 2, "item_count": 2, @@ -18731,18 +18717,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs are typing-related, but they are not the same change: #45415 is a broad repository-wide type-checking sweep, while #45425 adds specific typing aliases/protocols to support modeling_utils and PEFT-related code paths.", - "confidence": 0.91, + "summary": "Two open PRs are both typing-related, but they address different changes: PR 45415 is a broad mypy/type-checking sweep across many `src/transformers/*.py` files and config, while PR 45425 adds shared typing protocols/helpers in `_typing.py` and updates a smaller set of typing-related call sites. The overlap in a few files is not enough to treat them as the same change.", + "confidence": 0.92, "canonical_issue_reason": null, - "canonical_pr_reason": "#45425 is the more focused, self-contained typing change; #45415 is a broad sweep across many unrelated files plus type-checker config, so it is not a duplicate of the targeted typing-support PR.", + "canonical_pr_reason": "PR 45415 is the best canonical representative because it is the broader umbrella change: a large type-checking pass across many modules plus config adjustments, rather than a narrower helper/type-annotation refinement.", "best_issue_reason": null, - "best_pr_reason": "#45425 is the best representative of this cluster because it has one concrete typing support theme and a clear scope; #45415 is too heterogeneous to serve as the canonical change.", + "best_pr_reason": "PR 45415 is the strongest standalone representative of the cluster since it covers the widest scope and is the most likely target for deduping related typing-sweep work.", "soft_edge_verdicts": [ { "left": "pull_request:45415", "right": "pull_request:45425", "accept": false, - "reason": "Reject: shared typing files and helpers do not mean the same underlying bug/change. #45415 is a wide type-checking pass across many modules and pyproject settings, while #45425 adds specific typing aliases/protocols for modeling_utils/PEFT and related utilities. They could be merged independently." + "reason": "Reject: both are typing-focused, but they are not the same underlying bug/change. 45415 is a broad repository-wide type-checking sweep, while 45425 introduces shared typing protocols and aliases in `_typing.py` and updates a smaller set of consumers. Shared filenames alone do not make them mergeable into one PR." } ] }, @@ -18777,58 +18763,58 @@ "pull_request:45817|pull_request:45843", "pull_request:45836|pull_request:45843" ], - "prepared_review_unit_hash": "3bf54099e12545853acaaf6c3ec07013099b340b5d01086e471b3110266559d7", + "prepared_review_unit_hash": "ec86b5cee032337369eb62048a6d238280b2fd5487cbf832f9ad34491bd1305e", "component_budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 4, - "serialized_chars": 10387, - "estimated_input_tokens": 2597, - "estimated_eval_tokens": 5450 + "serialized_chars": 10389, + "estimated_input_tokens": 2598, + "estimated_eval_tokens": 5452 }, "budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 4, - "serialized_chars": 10387, - "estimated_input_tokens": 2597, - "estimated_eval_tokens": 5450 + "serialized_chars": 10389, + "estimated_input_tokens": 2598, + "estimated_eval_tokens": 5452 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are related by theme (model-parallel robustness) but they are not duplicate PRs: each targets a different model or a test-only workaround. None should be merged together.", - "confidence": 0.94, + "summary": "These are mostly separate PRs that happen to share a broad \"model parallel\" theme; one is just test skipping. They do not appear to fix the same concrete bug or code path.", + "confidence": 0.9, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45843 is the best representative of the cluster because it contains a concrete model-parallel code fix in the actual modeling path, whereas 45836 is test-only and 45487/45817 are separate model-specific fixes.", + "canonical_pr_reason": "PR #45487 is the most representative cluster anchor because it is an explicit model-parallel fix with concrete code changes across multiple model implementations, not just a test adjustment.", "best_issue_reason": null, - "best_pr_reason": "PR 45843 is the strongest standalone PR to keep as the representative fix: it addresses a real device-placement / no_split_modules propagation bug in Deimv2, with focused code changes and tests.", + "best_pr_reason": "PR #45487 is the clearest canonical representative for the cluster's theme and has the broadest directly relevant fix among the candidates.", "soft_edge_verdicts": [ { "left": "pull_request:45487", "right": "pull_request:45843", "accept": false, - "reason": "Same broad model-parallel theme, but different models and different failure paths; not the same underlying bug or change." + "reason": "Both concern model-parallel behavior, but they fix different models and different code paths (AltCLIP/ChineseCLIP vs Deimv2). Same broad subsystem, not the same underlying bug." }, { "left": "pull_request:45487", "right": "pull_request:45836", "accept": false, - "reason": "45487 fixes runtime model-parallel device placement; 45836 only skips failing tests for QuantizedCache incompatibility." + "reason": "#45836 only skips failing tests for MiniCPM-V/Qwen3.5; it does not fix the model-parallel bug in #45487." }, { "left": "pull_request:45817", "right": "pull_request:45843", "accept": false, - "reason": "Both are model-parallel fixes, but Gemma4 and Deimv2 have distinct code paths and patch mechanics; not mergeable as one PR." + "reason": "Both are model-parallel fixes, but one is Gemma4-specific and the other is Deimv2-specific. They are different concrete fixes and should not be merged as duplicates." }, { "left": "pull_request:45836", "right": "pull_request:45843", "accept": false, - "reason": "Test skip for MiniCPM-V/Qwen cache incompatibility is unrelated to Deimv2's model-parallel code fix." + "reason": "#45836 is a test-skip PR, while #45843 changes Deimv2 model code. They are unrelated fixes." } ] }, @@ -18858,7 +18844,7 @@ "soft_pairs": [ "pull_request:45548|pull_request:45662" ], - "prepared_review_unit_hash": "0412edd54149163229ba62e7516257b6a315206c23787e6d303d1d159b325b8d", + "prepared_review_unit_hash": "57d7464d7b01b6b4c52c9279faaac3f86236cdeef567bce811039bb382a0d884", "component_budget": { "node_count": 2, "item_count": 2, @@ -18880,18 +18866,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs are about expert-parallel (EP) model loading, but they target different failure modes and code paths: PR #45548 focuses on DeepSpeed ZeRO-3 / accelerate launch config handling, while PR #45662 fixes FSDP2/rank-0 broadcast overwriting expert weights during load. They are related but not duplicates.", - "confidence": 0.91, + "summary": "These two PRs both touch expert-parallel loading, but they fix different failure modes: one is about preserving/recognizing distributed_config for EP + DeepSpeed ZeRO-3 loading, while the other is about preventing FSDP2 rank-0 broadcast from overwriting experts during sharded loading.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45662 is the better canonical PR for the cluster because it addresses the more concrete loading corruption bug and includes the broader set of code-path fixes around expert parameter sharding and assignment.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "PR #45662 is the strongest representative overall: it fixes a specific, user-visible correctness issue in EP weight loading and touches the relevant loading/integration paths directly.", + "best_pr_reason": "PR 45662 is the more concrete and self-contained bug fix: it addresses a specific incorrect parameter assignment path during distributed sharded loading, with targeted code changes across the loading stack.", "soft_edge_verdicts": [ { "left": "pull_request:45548", "right": "pull_request:45662", "accept": false, - "reason": "Different underlying bugs: #45548 is about EP + DeepSpeed ZeRO-3 loading via accelerate launch and config serialization/has_ep detection, while #45662 is about EP + FSDP2 where expert weights are silently overwritten by rank-0 broadcast. Shared subsystem is not enough to treat them as the same change." + "reason": "Different underlying bugs and code paths: 45548 focuses on config serialization/EP detection for accelerate+ZeRO-3, while 45662 fixes post-shard parameter wrapping to stop rank-0 broadcast from overwriting experts under FSDP2. They are not mergeable as one PR." } ] }, @@ -18921,40 +18907,40 @@ "soft_pairs": [ "pull_request:45639|pull_request:45645" ], - "prepared_review_unit_hash": "76ab4bed7ab21edeac39cf454fcb8f795104dc0b4ba4f9a5b10487b0fdfd58c4", + "prepared_review_unit_hash": "46b68e240c887eea68e1b9c113d631f2acbe22281dbf5974d0bd2a5c0e502cc0", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4588, - "estimated_input_tokens": 1147, - "estimated_eval_tokens": 2550 + "serialized_chars": 4590, + "estimated_input_tokens": 1148, + "estimated_eval_tokens": 2552 }, "budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4588, - "estimated_input_tokens": 1147, - "estimated_eval_tokens": 2550 + "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 xdist collision in captured_info logging; #45645 is the broader follow-up that includes the core fix from #45639 plus CI artifact handling updates.", + "summary": "Both PRs address the same xdist-related captured_info collision in testing_utils; 45645 is the broader, more complete fix that also updates CI handling for multiple artifact files.", "confidence": 0.91, "canonical_issue_reason": null, - "canonical_pr_reason": "#45645 is the more complete implementation of the shared captured_info xdist fix: it includes the worker-safe output-file change and also updates CI consumption of those logs.", + "canonical_pr_reason": "PR 45645 is the better canonical PR because it includes the core xdist-safe file handling in testing_utils plus the downstream workflow changes needed to read multiple captured_info files in CI.", "best_issue_reason": null, - "best_pr_reason": "#45645 is the best single PR to keep because it covers the core bug fix and the necessary downstream workflow changes, whereas #45639 is only the smaller subset.", + "best_pr_reason": "PR 45645 is the best representative of the change set: it covers the same underlying bug as 45639 and adds the necessary artifact/CI plumbing rather than just the library-side fix.", "soft_edge_verdicts": [ { "left": "pull_request:45639", "right": "pull_request:45645", "accept": true, - "reason": "Same underlying bug/change: making captured_info logging xdist-safe. #45645 extends the same fix path rather than introducing a separate feature." + "reason": "Same underlying bug: xdist workers colliding on captured_info output. 45645 appears to subsume 45639\u2019s fix and extends it with related CI handling, so they are plausibly one merged change." } ] }, diff --git a/analysis/current/manifest.json b/analysis/current/manifest.json index a2a5df2cde11f291ea7dde46eed47c0fd5818240..f373fec53c3b838fd972463eda1611eb731d5f0f 100644 --- a/analysis/current/manifest.json +++ b/analysis/current/manifest.json @@ -1,8 +1,8 @@ { - "analysis_id": "hybrid-model-20260510t120026z", + "analysis_id": "hybrid-model-20260510t180022z", "archived_artifacts": { - "hybrid": "snapshots/20260510T120026Z/analysis-runs/hybrid-model-20260510t120026z/analysis-report-hybrid.json", - "hybrid_reviews": "snapshots/20260510T120026Z/analysis-runs/hybrid-model-20260510t120026z/analysis-report-hybrid.llm-reviews.json" + "hybrid": "snapshots/20260510T180022Z/analysis-runs/hybrid-model-20260510t180022z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260510T180022Z/analysis-runs/hybrid-model-20260510t180022z/analysis-report-hybrid.llm-reviews.json" }, "artifacts": { "hybrid": "analysis/current/analysis-report-hybrid.json", @@ -10,9 +10,9 @@ }, "channel": "canonical", "model": null, - "published_at": "2026-05-10T12:08:02Z", + "published_at": "2026-05-10T18:06:42Z", "repo": "huggingface/transformers", "schema_version": 1, - "snapshot_id": "20260510T120026Z", + "snapshot_id": "20260510T180022Z", "variant": "hybrid" } diff --git a/snapshots/20260510T180022Z/analysis-runs/hybrid-model-20260510t180022z/analysis-report-hybrid.json b/snapshots/20260510T180022Z/analysis-runs/hybrid-model-20260510t180022z/analysis-report-hybrid.json new file mode 100644 index 0000000000000000000000000000000000000000..b9c4e3be547ff6fa840830c80ecca31763b592f5 --- /dev/null +++ b/snapshots/20260510T180022Z/analysis-runs/hybrid-model-20260510t180022z/analysis-report-hybrid.json @@ -0,0 +1,2205 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260510T180022Z", + "generated_at": "2026-05-10T18:06:40Z", + "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-43656-4", + "summary": "Cluster of 1 issues and 3 PRs centered on issue #43824.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 43824, + "canonical_pr_number": 43656, + "issue_numbers": [ + 43824 + ], + "pr_numbers": [ + 43656, + 43836, + 43842 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 43656, + "right_pr_number": 43836, + "code_similarity": 0.36, + "size_similarity": 0.176, + "file_overlap": 1.0, + "area_overlap": 0.051, + "patch_similarity": 0.048, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 30, + 36 + ], + [ + 315, + 323 + ], + [ + 665, + 671 + ], + [ + 931, + 937 + ], + [ + 1843, + 1849 + ], + [ + 1868, + 1874 + ] + ], + "right_ranges": [ + [ + 11, + 18 + ], + [ + 359, + 429 + ], + [ + 584, + 590 + ], + [ + 1892, + 1910 + ], + [ + 1917, + 1923 + ] + ] + } + ] + }, + { + "left_pr_number": 43656, + "right_pr_number": 43842, + "code_similarity": 0.405, + "size_similarity": 0.5, + "file_overlap": 1.0, + "area_overlap": 0.0, + "patch_similarity": 0.036, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 30, + 36 + ], + [ + 315, + 323 + ], + [ + 665, + 671 + ], + [ + 931, + 937 + ], + [ + 1843, + 1849 + ], + [ + 1868, + 1874 + ] + ], + "right_ranges": [ + [ + 54, + 61 + ], + [ + 587, + 593 + ] + ] + } + ] + }, + { + "left_pr_number": 43836, + "right_pr_number": 43842, + "code_similarity": 0.332, + "size_similarity": 0.088, + "file_overlap": 1.0, + "area_overlap": 0.033, + "patch_similarity": 0.017, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 359, + 429 + ], + [ + 584, + 590 + ], + [ + 1892, + 1910 + ], + [ + 1917, + 1923 + ] + ], + "right_ranges": [ + [ + 54, + 61 + ], + [ + 587, + 593 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-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-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-43656-4", + "canonical_pr_number": 43656, + "duplicate_pr_numbers": [ + 43836, + 43842 + ], + "target_issue_number": 43824, + "reason": "PRs in cluster-43656-4 are treated as duplicates because they converge on issue #43824 with closing_reference, shared_issue_target, 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." + } + ], + "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/20260510T180022Z/analysis-runs/hybrid-model-20260510t180022z/analysis-report-hybrid.llm-reviews.json b/snapshots/20260510T180022Z/analysis-runs/hybrid-model-20260510t180022z/analysis-report-hybrid.llm-reviews.json new file mode 100644 index 0000000000000000000000000000000000000000..f7c419e1d8dcacaa95e7a790530821b095afb83f --- /dev/null +++ b/snapshots/20260510T180022Z/analysis-runs/hybrid-model-20260510t180022z/analysis-report-hybrid.llm-reviews.json @@ -0,0 +1,19084 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260510T180022Z", + "generated_at": "2026-05-10T18:06:40Z", + "model": "gpt-5.4-mini?service_tier=flex", + "reviews": [ + { + "label": "issue", + "component_index": 1, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "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": "41162ca8966146067606c22430385a981dd11473ff1460afb248bed227e2be86", + "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": "This cluster is heterogeneous: one tokenization discrepancy issue, one private-model auth/error-message issue, and one generic model-loading failure. None look like true duplicates of each other.", + "confidence": 0.96, + "canonical_issue_reason": "Issue 16618 is the broadest of the three and the only one centered on model loading, so it is the least specific representative if a single canonical issue is needed.", + "canonical_pr_reason": null, + "best_issue_reason": "16618 is the best cluster representative because it is the most general and closest to the apparent model-loading theme, whereas the other two are clearly narrower and unrelated.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:13244", + "right": "issue:16618", + "accept": false, + "reason": "Tapas tokenization mismatch is a tokenizer/behavior discrepancy, not the same underlying problem as being unable to load bert-base-uncased." + }, + { + "left": "issue:15980", + "right": "issue:16618", + "accept": false, + "reason": "Private-model unauthorized download error messaging is a specific auth/UX bug; 16618 is a separate generic model-loading failure." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:24643", + "issue:30277", + "issue:34634", + "issue:34928", + "issue:35545", + "issue:36010", + "issue:36331", + "issue:39290", + "issue:41093", + "issue:41720", + "issue:41762", + "issue:42915", + "issue:43039", + "issue:43404", + "issue:43425", + "issue:43531", + "issue:43541", + "issue:43596", + "issue:43638", + "issue:43716", + "issue:43792", + "issue:43827", + "issue:43828", + "issue:43854", + "issue:43866", + "issue:43901", + "issue:43975", + "issue:44292", + "issue:44322", + "issue:44457", + "issue:44509", + "issue:44512", + "issue:44560", + "issue:44805", + "issue:44841", + "issue:44863", + "issue:44918", + "issue:45070", + "issue:45081", + "issue:45084", + "issue:45161", + "issue:45237", + "issue:45362", + "issue:45464", + "issue:45507", + "issue:45685", + "issue:45800", + "issue:45823" + ], + "soft_pairs": [ + "issue:44322|issue:45464", + "issue:45237|issue:45685", + "issue:43716|issue:45237", + "issue:43828|issue:45237", + "issue:45237|issue:45507", + "issue:44292|issue:45237", + "issue:30277|issue:35545", + "issue:35545|issue:42915", + "issue:35545|issue:41720", + "issue:44509|issue:44512", + "issue:35545|issue:36010", + "issue:44805|issue:45823", + "issue:43638|issue:44805", + "issue:43596|issue:44805", + "issue:44805|issue:45161", + "issue:44805|issue:44918", + "issue:34634|issue:35545", + "issue:30277|issue:43638", + "issue:43596|issue:43638", + "issue:43039|issue:45161", + "issue:43975|issue:44457", + "issue:44292|issue:44457", + "issue:34928|issue:44805", + "issue:24643|issue:30277", + "issue:43638|issue:45161", + "issue:34928|issue:36331", + "issue:43596|issue:45161", + "issue:43716|issue:45507", + "issue:39290|issue:45081", + "issue:43828|issue:45161", + "issue:43425|issue:44292", + "issue:44918|issue:45161", + "issue:34928|issue:41720", + "issue:43716|issue:45685", + "issue:43541|issue:43716", + "issue:43828|issue:44292", + "issue:45507|issue:45685", + "issue:43716|issue:44292", + "issue:44292|issue:44918", + "issue:43039|issue:44918", + "issue:41762|issue:43638", + "issue:43827|issue:44512", + "issue:43716|issue:44560", + "issue:43828|issue:45685", + "issue:44560|issue:45685", + "issue:43039|issue:43828", + "issue:30277|issue:36331", + "issue:34928|issue:36010", + "issue:43039|issue:44805", + "issue:43901|issue:44512", + "issue:41762|issue:43596", + "issue:39290|issue:41720", + "issue:44841|issue:45823", + "issue:43039|issue:44560", + "issue:43866|issue:44863", + "issue:43854|issue:43866", + "issue:39290|issue:43531", + "issue:41093|issue:43638", + "issue:43425|issue:45070", + "issue:43596|issue:45800", + "issue:43792|issue:45070", + "issue:45362|issue:45464", + "issue:43404|issue:43866", + "issue:39290|issue:45823", + "issue:45464|issue:45685", + "issue:43541|issue:45685", + "issue:43541|issue:43828", + "issue:36010|issue:39290", + "issue:44841|issue:45084", + "issue:45800|issue:45823", + "issue:41093|issue:41762" + ], + "prepared_review_unit_hash": "ed47ed91a489038469a84da260f8a7bc40a1bb08d7bfa1c422098b31a263305e", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 71, + "serialized_chars": 48871, + "estimated_input_tokens": 12218, + "estimated_eval_tokens": 24692 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most items are unrelated model-/docs-specific issues. The only clear duplicate-like pair is the DeepSpeed ZeRO-3 + BERT zero-dimension index error reports. The broadest reusable issue in this cluster is the generic mask/shape-mismatch report.", + "confidence": 0.78, + "canonical_issue_reason": "issue:44805 is the most generic and reusable issue in the set, with a broad error signature that can subsume nearby shape/mask failures.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44805 best serves as the umbrella issue because its title is generic, symptom-focused, and likely to attract the most related duplicates.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44322", + "right": "issue:45464", + "accept": false, + "reason": "Different Qwen3.5 failures: missing config attribute vs streaming chat/completions failure." + }, + { + "left": "issue:45237", + "right": "issue:45685", + "accept": false, + "reason": "Different problems: AMD GPU model loading vs MPS histogram kernel failure." + }, + { + "left": "issue:43716", + "right": "issue:45237", + "accept": false, + "reason": "Different code paths: image preprocessor dtype mismatch vs AMD GPU incompatibility." + }, + { + "left": "issue:43828", + "right": "issue:45237", + "accept": false, + "reason": "Both are dtype/device-related, but they describe different models and failure modes." + }, + { + "left": "issue:45237", + "right": "issue:45507", + "accept": false, + "reason": "Different models and failures: AMD GPU load issue vs invalid method call in GraniteMoEHybrid." + }, + { + "left": "issue:44292", + "right": "issue:45237", + "accept": false, + "reason": "Different Qwen3 NVFP4 runtime error vs AMD GPU support issue." + }, + { + "left": "issue:30277", + "right": "issue:35545", + "accept": false, + "reason": "Both are DeepSpeed/model-loading problems, but one is collective mismatch and the other is ONNX export." + }, + { + "left": "issue:35545", + "right": "issue:42915", + "accept": false, + "reason": "Different model/export failure vs FP8 checkpoint execution failure." + }, + { + "left": "issue:35545", + "right": "issue:41720", + "accept": false, + "reason": "ONNX export error and auto device-map CUDA assert are unrelated failures." + }, + { + "left": "issue:44509", + "right": "issue:44512", + "accept": false, + "reason": "Both are v5 docs updates, but they target different removed doc topics and are not the same change." + }, + { + "left": "issue:35545", + "right": "issue:36010", + "accept": false, + "reason": "ONNX export error vs GenerationMixin import regression are distinct issues." + }, + { + "left": "issue:44805", + "right": "issue:45823", + "accept": false, + "reason": "Both mention tensor/device mismatch concepts, but the underlying bugs are different models and different failure modes." + }, + { + "left": "issue:43638", + "right": "issue:44805", + "accept": false, + "reason": "Similar index-style errors, but one is ZeRO-3 BERT loading and the other is a mask/tensor shape mismatch." + }, + { + "left": "issue:43596", + "right": "issue:44805", + "accept": false, + "reason": "Related by index/shape symptoms, but not clearly the same underlying bug." + }, + { + "left": "issue:44805", + "right": "issue:45161", + "accept": false, + "reason": "Mask/tensor shape mismatch and GPT-OSS MoE TP issue are different problems." + }, + { + "left": "issue:44805", + "right": "issue:44918", + "accept": false, + "reason": "Different failures: mask shape mismatch vs Qwen3.5 embedding unpacking with TRL." + }, + { + "left": "issue:34634", + "right": "issue:35545", + "accept": false, + "reason": "BarkProcessor voice_preset bug is unrelated to ModernBERT ONNX export." + }, + { + "left": "issue:30277", + "right": "issue:43638", + "accept": false, + "reason": "Both involve DeepSpeed, but collective mismatch is not the same as the ZeRO-3 Bert index error." + }, + { + "left": "issue:43596", + "right": "issue:43638", + "accept": true, + "reason": "Same ZeRO-3/BERT loading index-out-of-bounds failure, just reported with slightly different model wording." + }, + { + "left": "issue:43039", + "right": "issue:45161", + "accept": false, + "reason": "Liger Kernel cross-entropy call issue is unrelated to GPT-OSS MoE TP failure." + }, + { + "left": "issue:43975", + "right": "issue:44457", + "accept": false, + "reason": "Both involve detokenization/LoRA behavior, but they are not the same bug or code path." + }, + { + "left": "issue:44292", + "right": "issue:44457", + "accept": false, + "reason": "Qwen3 NVFP4 runtime failure and LoRA save/reload output mismatch are unrelated." + }, + { + "left": "issue:34928", + "right": "issue:44805", + "accept": false, + "reason": "Activation-checkpointing/FSDP tensor-size mismatch differs from the mask/index shape mismatch issue." + }, + { + "left": "issue:24643", + "right": "issue:30277", + "accept": false, + "reason": "Both mention DeepSpeed, but the errors are different: weight dimensionality vs collective mismatch." + }, + { + "left": "issue:43638", + "right": "issue:45161", + "accept": false, + "reason": "ZeRO-3 BERT index error is unrelated to GPT-OSS TP failure." + }, + { + "left": "issue:34928", + "right": "issue:36331", + "accept": false, + "reason": "Activation-checkpointing tensor mismatch is unrelated to CustomTrainer compute_loss signature regression." + }, + { + "left": "issue:43596", + "right": "issue:45161", + "accept": false, + "reason": "Different failure classes: ZeRO-3 BERT index error vs GPT-OSS MoE TP issue." + }, + { + "left": "issue:43716", + "right": "issue:45507", + "accept": false, + "reason": "Dtype mismatch in Mistral-3 preprocessing is unrelated to GraniteMoEHybrid invalid method call." + }, + { + "left": "issue:39290", + "right": "issue:45081", + "accept": false, + "reason": "Gemma3 sliding-window/vLLM config error is unrelated to Mistral tokenizer regex patch crash." + }, + { + "left": "issue:43828", + "right": "issue:45161", + "accept": false, + "reason": "Autocast dtype mismatch and GPT-OSS MoE TP failure are distinct." + }, + { + "left": "issue:44918", + "right": "issue:45161", + "accept": false, + "reason": "TRL SFT embedding unpacking error is not the same as GPT-OSS MoE TP failure." + }, + { + "left": "issue:34928", + "right": "issue:41720", + "accept": false, + "reason": "FSDP checkpointing mismatch and Qwen3 auto device-map CUDA assert are different bugs." + }, + { + "left": "issue:43716", + "right": "issue:45685", + "accept": false, + "reason": "Different models and backends: Mistral-3 dtype mismatch vs MPS histogram op failure." + }, + { + "left": "issue:43541", + "right": "issue:43716", + "accept": false, + "reason": "Grouped_mm torch dynamo tracing failure is unrelated to image-preprocessor dtype mismatch." + }, + { + "left": "issue:43828", + "right": "issue:44292", + "accept": false, + "reason": "Both are runtime mismatches, but they involve different models and different root causes." + }, + { + "left": "issue:44292", + "right": "issue:44918", + "accept": false, + "reason": "Qwen3 NVFP4 runtime error and TRL embedding unpacking issue are unrelated." + }, + { + "left": "issue:43039", + "right": "issue:44918", + "accept": false, + "reason": "Liger Kernel cross-entropy call issue is not the same as Qwen3.5 embedding unpacking." + }, + { + "left": "issue:41762", + "right": "issue:43638", + "accept": false, + "reason": "Both are ZeRO-3 loading failures, but Gemma3 and Bert errors differ in symptom and likely cause." + }, + { + "left": "issue:43827", + "right": "issue:44512", + "accept": false, + "reason": "Both are docs regressions after v5 removals, but they cover different removed entry points." + }, + { + "left": "issue:43716", + "right": "issue:44560", + "accept": false, + "reason": "Mistral-3 dtype mismatch is unrelated to Qwen3-vl video StopIteration." + }, + { + "left": "issue:43828", + "right": "issue:45685", + "accept": false, + "reason": "Different backends and failures: autocast dtype mismatch vs MPS unsupported histogram on int." + }, + { + "left": "issue:44560", + "right": "issue:45685", + "accept": false, + "reason": "Video StopIteration in Qwen3-vl embedding is unrelated to the MPS histogram issue." + }, + { + "left": "issue:43039", + "right": "issue:43828", + "accept": false, + "reason": "Same broad dtype/runtime theme, but different concrete failures and code paths." + }, + { + "left": "issue:30277", + "right": "issue:36331", + "accept": false, + "reason": "DeepSpeed collective mismatch and trainer signature regression are unrelated." + }, + { + "left": "issue:34928", + "right": "issue:36010", + "accept": false, + "reason": "FSDP activation checkpointing mismatch is unrelated to GenerationMixin import failure." + }, + { + "left": "issue:43039", + "right": "issue:44805", + "accept": false, + "reason": "Liger Kernel cross-entropy use is unrelated to the mask/tensor shape mismatch bug." + }, + { + "left": "issue:43901", + "right": "issue:44512", + "accept": false, + "reason": "Both are docs issues, but one is about pipeline task docs and the other about the run command." + }, + { + "left": "issue:41762", + "right": "issue:43596", + "accept": false, + "reason": "Both mention ZeRO-3, but Gemma3 loading and Bert loading are different concrete failures." + }, + { + "left": "issue:39290", + "right": "issue:41720", + "accept": false, + "reason": "Gemma3 sliding-window config error is unrelated to Qwen3 auto device-map CUDA assert." + }, + { + "left": "issue:44841", + "right": "issue:45823", + "accept": false, + "reason": "Processor failure for Voxtral is unrelated to Gemma4 device-mapping mismatch." + }, + { + "left": "issue:43039", + "right": "issue:44560", + "accept": false, + "reason": "Liger Kernel cross-entropy issue and Qwen3-vl video StopIteration are unrelated." + }, + { + "left": "issue:43866", + "right": "issue:44863", + "accept": false, + "reason": "Checkpoint corruption and NemotronH load failure are different problems." + }, + { + "left": "issue:43854", + "right": "issue:43866", + "accept": false, + "reason": "Unable to load GLM-4.7-Flash in tests is not the same as a corrupted Ovis2 checkpoint." + }, + { + "left": "issue:39290", + "right": "issue:43531", + "accept": false, + "reason": "Gemma3 config error and Qwen3-MoE sliding_window issue are related only by model family, not the same bug." + }, + { + "left": "issue:41093", + "right": "issue:43638", + "accept": false, + "reason": "Mask/index shape mismatch and ZeRO-3 Bert zero-dimension index error are different concrete failures." + }, + { + "left": "issue:43425", + "right": "issue:45070", + "accept": false, + "reason": "Torch version incompatibility and pydantic PretrainedConfig field regression are unrelated." + }, + { + "left": "issue:43596", + "right": "issue:45800", + "accept": false, + "reason": "ZeRO-3 Bert index error is unrelated to torch/transformers version incompatibility." + }, + { + "left": "issue:43792", + "right": "issue:45070", + "accept": false, + "reason": "Whisper cannot run and pydantic PretrainedConfig field breakage are unrelated." + }, + { + "left": "issue:45362", + "right": "issue:45464", + "accept": false, + "reason": "Qwen3.5 chat crash and streaming inference API failure are different issues." + }, + { + "left": "issue:43404", + "right": "issue:43866", + "accept": false, + "reason": "Mistral3 lm_head tying bug is unrelated to a corrupted checkpoint." + }, + { + "left": "issue:39290", + "right": "issue:45823", + "accept": false, + "reason": "Gemma3 sliding-window/vLLM error is unrelated to Gemma4 device_map mismatch." + }, + { + "left": "issue:45464", + "right": "issue:45685", + "accept": false, + "reason": "Qwen3.5 streaming inference failure is unrelated to the MPS histogram op issue." + }, + { + "left": "issue:43541", + "right": "issue:45685", + "accept": false, + "reason": "Torch dynamo grouped_mm tracing failure is unrelated to the MPS histogram op issue." + }, + { + "left": "issue:43541", + "right": "issue:43828", + "accept": false, + "reason": "Grouped_mm tracing failure and autocast dtype mismatch are different bugs." + }, + { + "left": "issue:36010", + "right": "issue:39290", + "accept": false, + "reason": "GenerationMixin import regression and Gemma3 sliding-window config error are unrelated." + }, + { + "left": "issue:44841", + "right": "issue:45084", + "accept": false, + "reason": "Voxtral processor failure is unrelated to the template-node compile error." + }, + { + "left": "issue:45800", + "right": "issue:45823", + "accept": false, + "reason": "Torch/transformers incompatibility and Gemma4 device mismatch are different problems." + }, + { + "left": "issue:41093", + "right": "issue:41762", + "accept": false, + "reason": "Both are tensor/indexing failures, but they occur in different model-loading paths and are not clearly the same bug." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative overall. The chosen umbrella issue (44805) is generic enough to cover nearby shape/mask failures, and the only accepted soft-edge pair (43596/43638) looks like a plausible duplicate-class match based on nearly identical ZeRO-3/BERT index-error symptoms. I don\u2019t see any 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": 2, + "component_count": 16, + "review_unit_index": 2, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:39186", + "issue:39692", + "issue:40990", + "issue:41093", + "issue:42915", + "issue:43054", + "issue:43296", + "issue:43366", + "issue:43404", + "issue:43531", + "issue:43541", + "issue:43572", + "issue:43596", + "issue:43644", + "issue:43645", + "issue:43716", + "issue:43828", + "issue:43866", + "issue:43873", + "issue:43950", + "issue:43975", + "issue:43994", + "issue:44291", + "issue:44292", + "issue:44360", + "issue:44387", + "issue:44403", + "issue:44492", + "issue:44512", + "issue:44530", + "issue:44534", + "issue:44589", + "issue:44863", + "issue:44918", + "issue:44928", + "issue:44960", + "issue:45005", + "issue:45020", + "issue:45070", + "issue:45161", + "issue:45399", + "issue:45464", + "issue:45507", + "issue:45542", + "issue:45632", + "issue:45685", + "issue:45698", + "issue:45800" + ], + "soft_pairs": [ + "issue:43296|issue:43366", + "issue:43572|issue:45070", + "issue:44387|issue:45005", + "issue:43541|issue:45161", + "issue:43828|issue:45464", + "issue:44291|issue:45070", + "issue:43366|issue:45464", + "issue:45020|issue:45800", + "issue:43531|issue:45070", + "issue:43541|issue:44589", + "issue:41093|issue:43596", + "issue:43054|issue:43994", + "issue:45542|issue:45800", + "issue:43716|issue:44918", + "issue:44918|issue:45685", + "issue:45632|issue:45698", + "issue:43404|issue:45005", + "issue:43645|issue:45399", + "issue:40990|issue:44960", + "issue:44530|issue:45005", + "issue:44360|issue:44512", + "issue:42915|issue:45399", + "issue:44863|issue:45005", + "issue:43873|issue:45005", + "issue:39186|issue:44918", + "issue:44492|issue:44512", + "issue:44918|issue:45507", + "issue:43975|issue:44292", + "issue:43950|issue:44534", + "issue:43644|issue:43950", + "issue:44292|issue:45507", + "issue:39692|issue:43054", + "issue:43828|issue:44928", + "issue:43866|issue:44403" + ], + "prepared_review_unit_hash": "8d78853ac7bb20e8ee5fbf85fd7c3ce0b005ca15fb6b22382827a0a496cce806", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37473, + "estimated_input_tokens": 9369, + "estimated_eval_tokens": 18994 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly heterogeneous, but there is one clear duplicate subgroup around the Transformers 5.x non-persistent-buffer regression, plus a smaller custom-module cache/path collision pair. No PRs are present.", + "confidence": 0.84, + "canonical_issue_reason": "Issue 43950 is the best canonical issue: it states the core v5 regression clearly, is broadly phrased, and matches the strongest duplicate subgroup with 43644 and 44534.", + "canonical_pr_reason": null, + "best_issue_reason": "43950 is the strongest representative of the shared bug because it describes the underlying non-persistent-buffer corruption most explicitly and in a way that can absorb the near-duplicate reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43296", + "right": "issue:43366", + "accept": false, + "reason": "Different models and failures: PaddleOCR-VL load error vs gpt-oss GGUF support request." + }, + { + "left": "issue:43572", + "right": "issue:45070", + "accept": false, + "reason": "Different regressions: missing StableLmConfig field vs pydantic/PretrainedConfig incompatibility." + }, + { + "left": "issue:44387", + "right": "issue:45005", + "accept": false, + "reason": "Different problems: int4 quantization OOM vs tied-weights handling on translation models." + }, + { + "left": "issue:43541", + "right": "issue:45161", + "accept": false, + "reason": "Both involve MoE, but the concrete failures differ: torch dynamo grouped_mm tracing vs TP not working for GPT-OSS." + }, + { + "left": "issue:43828", + "right": "issue:45464", + "accept": false, + "reason": "Different code paths and symptoms: autocast dtype mismatch vs streaming chat/completions failure." + }, + { + "left": "issue:44291", + "right": "issue:45070", + "accept": false, + "reason": "Different loading bugs: init_empty_weights/_is_hf_initialized TypeError vs pydantic field breakage." + }, + { + "left": "issue:43366", + "right": "issue:45464", + "accept": false, + "reason": "Unrelated: gpt-oss GGUF architecture support vs Qwen3.5 streaming inference failure." + }, + { + "left": "issue:45020", + "right": "issue:45800", + "accept": false, + "reason": "Broad version-regression labels, but not the same concrete bug or code path." + }, + { + "left": "issue:43531", + "right": "issue:45070", + "accept": false, + "reason": "Different issues: Qwen3-MoE sliding_window behavior vs PretrainedConfig/pydantic breakage." + }, + { + "left": "issue:43541", + "right": "issue:44589", + "accept": false, + "reason": "Different failures: grouped_mm tracing error vs missing Float8 storage object." + }, + { + "left": "issue:41093", + "right": "issue:43596", + "accept": false, + "reason": "Both are IndexErrors, but in different subsystems and with different shapes/root causes." + }, + { + "left": "issue:43054", + "right": "issue:43994", + "accept": false, + "reason": "Same model family, but the reports describe different symptoms and do not clearly point to one concrete shared bug." + }, + { + "left": "issue:45542", + "right": "issue:45800", + "accept": false, + "reason": "TensorBoard/TensorFlow backend issue is unrelated to torch/transformers version incompatibility." + }, + { + "left": "issue:43716", + "right": "issue:44918", + "accept": false, + "reason": "Different multimodal/training failures: Mistral-3 image-preprocessor dtype mismatch vs Qwen3.5 embedding unpacking in TRL." + }, + { + "left": "issue:44918", + "right": "issue:45685", + "accept": false, + "reason": "Different model/backend problems: TRL embedding unpacking vs MPS histogram kernel not implemented for Int." + }, + { + "left": "issue:45632", + "right": "issue:45698", + "accept": true, + "reason": "Likely the same custom-module loading bug: cache/path collision or wrong module resolution causes from_pretrained to load the wrong code." + }, + { + "left": "issue:43404", + "right": "issue:45005", + "accept": false, + "reason": "Different tied-weight bugs in different model families and usage scenarios." + }, + { + "left": "issue:43645", + "right": "issue:45399", + "accept": false, + "reason": "Notebook custom-model initialization vs flash-attn fallback gating are unrelated." + }, + { + "left": "issue:40990", + "right": "issue:44960", + "accept": false, + "reason": "Unrelated model evaluation/perplexity problem vs a GLM5 issue with no matching concrete path." + }, + { + "left": "issue:44530", + "right": "issue:45005", + "accept": false, + "reason": "PagedAttentionCache linear_attention crash is unrelated to tied-weight translation model issues." + }, + { + "left": "issue:44360", + "right": "issue:44512", + "accept": false, + "reason": "DSA indexer discussion is unrelated to docs about the removed run command." + }, + { + "left": "issue:42915", + "right": "issue:45399", + "accept": false, + "reason": "Qwen3Moe FP8 failure is unrelated to the flash-attn2 fallback checks." + }, + { + "left": "issue:44863", + "right": "issue:45005", + "accept": false, + "reason": "NemotronH checkpoint loading failure is unrelated to tied-weight translation issues." + }, + { + "left": "issue:43873", + "right": "issue:45005", + "accept": false, + "reason": "Quantization/offloading behavior is unrelated to tied-weights handling." + }, + { + "left": "issue:39186", + "right": "issue:44918", + "accept": false, + "reason": "FSDP 2-D weight error and TRL embedding unpacking are different bugs." + }, + { + "left": "issue:44492", + "right": "issue:44512", + "accept": false, + "reason": "A typo in cache strategies is unrelated to removed-command docs drift." + }, + { + "left": "issue:44918", + "right": "issue:45507", + "accept": false, + "reason": "Different failures: TRL embedding unpacking vs GraniteMoEHybrid invalid method call." + }, + { + "left": "issue:43975", + "right": "issue:44292", + "accept": false, + "reason": "Different model-specific failures: detokenization bug vs NVFP4 execution error." + }, + { + "left": "issue:43950", + "right": "issue:44534", + "accept": true, + "reason": "Exact same underlying regression: Transformers v5 corrupts non-persistent buffers during loading." + }, + { + "left": "issue:43644", + "right": "issue:43950", + "accept": true, + "reason": "Same non-persistent-buffer corruption regression in Transformers 5.x." + }, + { + "left": "issue:44292", + "right": "issue:45507", + "accept": false, + "reason": "Different model/runtime failures with no shared concrete code path." + }, + { + "left": "issue:39692", + "right": "issue:43054", + "accept": false, + "reason": "SigLIP2 doc-example errors are not the same as the later text-embedding quality complaint." + }, + { + "left": "issue:43828", + "right": "issue:44928", + "accept": false, + "reason": "Autocast dtype mismatch and SDPA/BF16 gradient explosion are different bugs." + }, + { + "left": "issue:43866", + "right": "issue:44403", + "accept": false, + "reason": "Corrupted checkpoint vs loading-noise issue are not the same underlying bug." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Grounded overall: the non-persistent-buffer regression cluster is well supported by the titles, the custom-module loading pair is a conservative match, and the negative pair verdicts stay cautious. No PR-pair issues to flag." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 3, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:36331", + "issue:38175", + "issue:41553", + "issue:41628", + "issue:41762", + "issue:42491", + "issue:42915", + "issue:42947", + "issue:43054", + "issue:43404", + "issue:43493", + "issue:43638", + "issue:43643", + "issue:43742", + "issue:43782", + "issue:43792", + "issue:43824", + "issue:43827", + "issue:43828", + "issue:43856", + "issue:43872", + "issue:43881", + "issue:43883", + "issue:43950", + "issue:43975", + "issue:44220", + "issue:44368", + "issue:44387", + "issue:44403", + "issue:44451", + "issue:44488", + "issue:44509", + "issue:44589", + "issue:44661", + "issue:44910", + "issue:44960", + "issue:44991", + "issue:45020", + "issue:45081", + "issue:45237", + "issue:45356", + "issue:45399", + "issue:45520", + "issue:45685", + "issue:45701", + "issue:45800", + "issue:45823", + "issue:45859" + ], + "soft_pairs": [ + "issue:36331|issue:41762", + "issue:41628|issue:45800", + "issue:43872|issue:44589", + "issue:41553|issue:43883", + "issue:38175|issue:43054", + "issue:43054|issue:45701", + "issue:44910|issue:45859", + "issue:41553|issue:43881", + "issue:42947|issue:44387", + "issue:44403|issue:44451", + "issue:43643|issue:45020", + "issue:43975|issue:45520", + "issue:43054|issue:43493", + "issue:43975|issue:45237", + "issue:44403|issue:44488", + "issue:42947|issue:43856", + "issue:43881|issue:43883", + "issue:41762|issue:42915", + "issue:42491|issue:44368", + "issue:45685|issue:45823", + "issue:43975|issue:44451", + "issue:43824|issue:43872", + "issue:45020|issue:45823", + "issue:44991|issue:45399", + "issue:44661|issue:45020", + "issue:43828|issue:45823", + "issue:45020|issue:45356", + "issue:43782|issue:44960", + "issue:45081|issue:45399", + "issue:43827|issue:44509", + "issue:43404|issue:43950", + "issue:43792|issue:44220", + "issue:43742|issue:45399", + "issue:42915|issue:45020", + "issue:43638|issue:45823" + ], + "prepared_review_unit_hash": "eb3f48dd383c3bb29d2af30008a5983eb94a673720e5572b2ede3608207d0d22", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 35, + "serialized_chars": 38226, + "estimated_input_tokens": 9557, + "estimated_eval_tokens": 19370 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most suggested pairs are broad text-similarity matches rather than true duplicates. Only the two documentation issues about removed pipeline tasks look like the same cleanup. No PRs were provided.", + "confidence": 0.74, + "canonical_issue_reason": "issue:45020 is the broadest open report in the set and best fits as an umbrella for recent transformers v5 remote_code/loading regressions.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45020 is the best single anchor for this cluster because it is open, explicitly about recent version breakage, and broad enough to absorb related loading regressions.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36331", + "right": "issue:41762", + "accept": false, + "reason": "Different failures: trainer API kwarg mismatch vs Gemma3 DeepSpeed ZeRO-3 loading index error." + }, + { + "left": "issue:41628", + "right": "issue:45800", + "accept": false, + "reason": "Both are compatibility/loading complaints, but they point to different breakages and different root causes." + }, + { + "left": "issue:43872", + "right": "issue:44589", + "accept": false, + "reason": "Both are library incompatibilities, but the underlying errors are unrelated Int8Params vs Float8 storage handling." + }, + { + "left": "issue:41553", + "right": "issue:43883", + "accept": false, + "reason": "Voxtral tokenizer error-message issue is unrelated to Molmo missing all_tied_weights_keys." + }, + { + "left": "issue:38175", + "right": "issue:43054", + "accept": false, + "reason": "Different models and different symptom domains: zero probabilities vs text embedding quality regression." + }, + { + "left": "issue:43054", + "right": "issue:45701", + "accept": false, + "reason": "One is SigLIP2 embedding quality, the other is a generic tokenization version-change report; not the same bug." + }, + { + "left": "issue:44910", + "right": "issue:45859", + "accept": false, + "reason": "Both involve Qwen3.5, but one is flash-attn packed-sequence misinterpretation and the other is CPU offload incompatibility." + }, + { + "left": "issue:41553", + "right": "issue:43881", + "accept": false, + "reason": "Different model-loading failures for different models; only a weak generic similarity." + }, + { + "left": "issue:42947", + "right": "issue:44387", + "accept": false, + "reason": "Both mention training/memory, but one is gradient checkpointing with LoRA and the other is int4 CUDA reserved memory growth." + }, + { + "left": "issue:44403", + "right": "issue:44451", + "accept": false, + "reason": "Generic loading-noise report vs a specific model load failure; not the same underlying bug." + }, + { + "left": "issue:43643", + "right": "issue:45020", + "accept": false, + "reason": "Both touch recent v5 behavior, but one is missing fields from trust_remote_code config loading and the other is broader remote_code breakage." + }, + { + "left": "issue:43975", + "right": "issue:45520", + "accept": false, + "reason": "Detokenization regression and Python 3.13 flash_attn import error are unrelated." + }, + { + "left": "issue:43054", + "right": "issue:43493", + "accept": false, + "reason": "Both concern SigLIP2, but one is text embedding quality and the other is HF vs JAX implementation discrepancy." + }, + { + "left": "issue:43975", + "right": "issue:45237", + "accept": false, + "reason": "Deepseek tokenizer/detokenization and GPT-OSS-on-AMD are unrelated." + }, + { + "left": "issue:44403", + "right": "issue:44488", + "accept": false, + "reason": "Both are model-loading complaints, but they are separate model-specific failures." + }, + { + "left": "issue:42947", + "right": "issue:43856", + "accept": false, + "reason": "Both mention Qwen/LoRA training, but one is ineffective checkpointing and the other is inefficient memory usage." + }, + { + "left": "issue:43881", + "right": "issue:43883", + "accept": false, + "reason": "Both are model-loading failures, but one is glm-4v-9b loading and the other is Molmo missing tied-weights metadata." + }, + { + "left": "issue:41762", + "right": "issue:42915", + "accept": false, + "reason": "Different failures: Gemma3 ZeRO-3 loading vs Qwen3 Moe FineGrainedFP8Config." + }, + { + "left": "issue:42491", + "right": "issue:44368", + "accept": false, + "reason": "LoRA compatibility on hf5.x and a config warning in Qwen3.5 are not the same bug." + }, + { + "left": "issue:45685", + "right": "issue:45823", + "accept": false, + "reason": "MPS histogram-int support in MoE and Gemma4 PLE device mismatch are different issues." + }, + { + "left": "issue:43975", + "right": "issue:44451", + "accept": false, + "reason": "Different model/tokenizer problems; no evidence they share a concrete code path." + }, + { + "left": "issue:43824", + "right": "issue:43872", + "accept": false, + "reason": "Qwen2.5-VL import error and bitsandbytes Int8Params kwarg incompatibility are unrelated." + }, + { + "left": "issue:45020", + "right": "issue:45823", + "accept": false, + "reason": "Broad remote_code breakage vs a Gemma4 device_map forward mismatch; different concrete bugs." + }, + { + "left": "issue:44991", + "right": "issue:45399", + "accept": false, + "reason": "Tokenizer loading failure for one model versus flash-attn fallback gating; unrelated." + }, + { + "left": "issue:44661", + "right": "issue:45020", + "accept": false, + "reason": "Model registration/add-new-model-like failure is not the same as remote_code loading regressions." + }, + { + "left": "issue:43828", + "right": "issue:45823", + "accept": false, + "reason": "Autocast dtype mismatch in Phi-tiny-MoE and Gemma4 PLE device mismatch are different forward-path bugs." + }, + { + "left": "issue:45020", + "right": "issue:45356", + "accept": false, + "reason": "Remote_code breakage is broader; Kimi-K2.5 tokenizer codec/fix_mistral_regex regression is a separate tokenizer bug." + }, + { + "left": "issue:43782", + "right": "issue:44960", + "accept": false, + "reason": "Qwen3VL weight_only loading error and a generic GLM5 issue do not match." + }, + { + "left": "issue:45081", + "right": "issue:45399", + "accept": false, + "reason": "Tokenizer regex crash and flash-attn fallback gating are different code paths." + }, + { + "left": "issue:43827", + "right": "issue:44509", + "accept": true, + "reason": "Both report that v5 docs still reference removed pipeline tasks (summarization/translation/text2text-generation); same documentation cleanup." + }, + { + "left": "issue:43404", + "right": "issue:43950", + "accept": false, + "reason": "Untied lm_head weights in Mistral3 and non-persistent buffer corruption are different state/serialization bugs." + }, + { + "left": "issue:43792", + "right": "issue:44220", + "accept": false, + "reason": "Whisper runtime failure and fbank feature extraction issue are not the same underlying bug." + }, + { + "left": "issue:43742", + "right": "issue:45399", + "accept": false, + "reason": "MobileLLM key error and flash-attn fallback checks are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:45020", + "accept": false, + "reason": "Qwen3Moe FineGrainedFP8Config failure is a specific quantization/config bug, not the broader remote_code loading regression." + }, + { + "left": "issue:43638", + "right": "issue:45823", + "accept": false, + "reason": "ZeRO-3 with non-pretrained Bert index error and Gemma4 device mismatch are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary stays grounded in the packet and the soft-edge calls are conservative. The single accepted pair (43827/44509) is supported by the issue titles as the same docs cleanup around removed pipeline tasks. No PR-pair mergeability concerns apply because no PRs were provided." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 4, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:24643", + "issue:30064", + "issue:36010", + "issue:36331", + "issue:38175", + "issue:41093", + "issue:41553", + "issue:42617", + "issue:42915", + "issue:43257", + "issue:43366", + "issue:43531", + "issue:43550", + "issue:43632", + "issue:43645", + "issue:43646", + "issue:43824", + "issue:43828", + "issue:43854", + "issue:43866", + "issue:43872", + "issue:43940", + "issue:43950", + "issue:43957", + "issue:43994", + "issue:44291", + "issue:44479", + "issue:44488", + "issue:44530", + "issue:44560", + "issue:44589", + "issue:44661", + "issue:44805", + "issue:44863", + "issue:44910", + "issue:44918", + "issue:44928", + "issue:44991", + "issue:45161", + "issue:45305", + "issue:45313", + "issue:45325", + "issue:45538", + "issue:45588", + "issue:45663", + "issue:45823", + "issue:45834" + ], + "soft_pairs": [ + "issue:43257|issue:43866", + "issue:43872|issue:44291", + "issue:45161|issue:45823", + "issue:43940|issue:45313", + "issue:42915|issue:43872", + "issue:43854|issue:44863", + "issue:41553|issue:44991", + "issue:44928|issue:45588", + "issue:36331|issue:41093", + "issue:43257|issue:45305", + "issue:43872|issue:45538", + "issue:41553|issue:44488", + "issue:41093|issue:44805", + "issue:44530|issue:44863", + "issue:44479|issue:44560", + "issue:24643|issue:30064", + "issue:43366|issue:43828", + "issue:45663|issue:45823", + "issue:43366|issue:43531", + "issue:43950|issue:45834", + "issue:43550|issue:44910", + "issue:43645|issue:43646", + "issue:43366|issue:44589", + "issue:43950|issue:45325", + "issue:44560|issue:44918", + "issue:42617|issue:43366", + "issue:43824|issue:43957", + "issue:42915|issue:43957", + "issue:36010|issue:42915", + "issue:44661|issue:45823", + "issue:38175|issue:43994", + "issue:43632|issue:45834" + ], + "prepared_review_unit_hash": "fd04d1498ee93c8bbfcdad2a69e81f962cef5df1d1806dd7f36164cac079099b", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 32, + "serialized_chars": 36774, + "estimated_input_tokens": 9194, + "estimated_eval_tokens": 18644 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a heterogeneous cluster of unrelated Transformers bugs, with a few clear duplicate subgroups: the `_is_hf_initialized` regression, the custom model initialization regression, and the mask-shape IndexError report.", + "confidence": 0.8, + "canonical_issue_reason": "issue:43632 is the broadest and clearest statement of the shared `_is_hf_initialized` Transformers v5 regression that other nearby reports expand on.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43632 is the best representative issue for the cluster\u2019s main shared regression theme; it is general enough to anchor the close duplicates while staying concrete.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43257", + "right": "issue:43866", + "accept": false, + "reason": "Different model families and failures: Qwen3 MoE weight conversion under accelerate/deepspeed vs an Ovis2 checkpoint corruption report." + }, + { + "left": "issue:43872", + "right": "issue:44291", + "accept": true, + "reason": "Same underlying `_is_hf_initialized` compatibility break during loading/init; one surfaces via bitsandbytes, the other via `init_empty_weights`." + }, + { + "left": "issue:45161", + "right": "issue:45823", + "accept": false, + "reason": "Both are model-loading/training problems, but they affect different models and code paths (GPT-OSS MoE TP vs Gemma4 PLE device mismatch)." + }, + { + "left": "issue:43940", + "right": "issue:45313", + "accept": false, + "reason": "Similar DeepSpeed ZeRO-3 weight-loading symptoms, but the model targets and reported failure details differ enough that the underlying bug is not established." + }, + { + "left": "issue:42915", + "right": "issue:43872", + "accept": false, + "reason": "Qwen3Moe FP8 failure is a different issue from the `_is_hf_initialized` bitsandbytes/loading incompatibility." + }, + { + "left": "issue:43854", + "right": "issue:44863", + "accept": false, + "reason": "Different models and failure modes: GLM-4.7-Flash test loading vs NemotronH checkpoint loading." + }, + { + "left": "issue:41553", + "right": "issue:44991", + "accept": false, + "reason": "Both mention tokenizer loading, but they are different models and distinct failure reports." + }, + { + "left": "issue:44928", + "right": "issue:45588", + "accept": false, + "reason": "Different bugs: one is a Qwen3.5 training/SDPA/BF16 regression, the other is an `s_aux=None` crash in flash_attention integration." + }, + { + "left": "issue:36331", + "right": "issue:41093", + "accept": false, + "reason": "Completely different errors: trainer loss API mismatch vs tensor mask shape mismatch." + }, + { + "left": "issue:43257", + "right": "issue:45305", + "accept": false, + "reason": "Different DeepSpeed-related regressions affecting different training semantics; not the same concrete bug." + }, + { + "left": "issue:43872", + "right": "issue:45538", + "accept": false, + "reason": "`_is_hf_initialized`/bitsandbytes loading issue is unrelated to CLIPTokenizer's max length bug." + }, + { + "left": "issue:41553", + "right": "issue:44488", + "accept": false, + "reason": "Different tokenizer-loading reports for different models, with no shared concrete failure path shown." + }, + { + "left": "issue:41093", + "right": "issue:44805", + "accept": true, + "reason": "These appear to be the same mask-shape mismatch IndexError report, just with different concrete dimensions in the error text." + }, + { + "left": "issue:44530", + "right": "issue:44863", + "accept": false, + "reason": "Qwen3.5 PagedAttention crash and NemotronH checkpoint loading are unrelated." + }, + { + "left": "issue:44479", + "right": "issue:44560", + "accept": false, + "reason": "Both are Qwen video-related, but one is a broad v5.3.0 regression and the other is a specific StopIteration report; same root cause is not clear enough." + }, + { + "left": "issue:24643", + "right": "issue:30064", + "accept": false, + "reason": "Training with DeepSpeed and void segmentation map processing are unrelated issues." + }, + { + "left": "issue:43366", + "right": "issue:43828", + "accept": false, + "reason": "GGUF gpt-oss support and Phi MoE autocast dtype mismatch are different features/bugs." + }, + { + "left": "issue:45663", + "right": "issue:45823", + "accept": false, + "reason": "Different Gemma4 failures: FSDP2 shared_kv_states logic vs device_map auto placement mismatch." + }, + { + "left": "issue:43366", + "right": "issue:43531", + "accept": false, + "reason": "Unrelated: GGUF gpt-oss support vs Qwen3-MoE sliding window behavior." + }, + { + "left": "issue:43950", + "right": "issue:45834", + "accept": false, + "reason": "Different regressions: non-persistent buffer corruption vs Kosmos2.5 long OCR input indexing." + }, + { + "left": "issue:43550", + "right": "issue:44910", + "accept": false, + "reason": "Different model/code-path issues: Bamba SDPA torch.compile crash vs Qwen3.5 flash-attention position_ids bug." + }, + { + "left": "issue:43645", + "right": "issue:43646", + "accept": true, + "reason": "Same custom model initialization regression in Transformers 5.0.0; the notebook wording is just a narrower reproduction." + }, + { + "left": "issue:43366", + "right": "issue:44589", + "accept": false, + "reason": "Unrelated failures: GPT-OSS support vs missing Float8 storage object." + }, + { + "left": "issue:43950", + "right": "issue:45325", + "accept": false, + "reason": "Non-persistent buffer corruption is unrelated to the Qwen2.5-VL rope index scaling bug." + }, + { + "left": "issue:44560", + "right": "issue:44918", + "accept": false, + "reason": "Both involve Qwen3.5-ish behavior, but video StopIteration and TRL SFT embedding unpacking are different concrete bugs." + }, + { + "left": "issue:42617", + "right": "issue:43366", + "accept": false, + "reason": "3d_parallel.py runtime failure and GPT-OSS GGUF support are unrelated." + }, + { + "left": "issue:43824", + "right": "issue:43957", + "accept": false, + "reason": "Different issues: missing Qwen2.5-VL export vs meta-device model loading regression." + }, + { + "left": "issue:42915", + "right": "issue:43957", + "accept": false, + "reason": "Qwen3Moe FP8 failure and meta-device loading breakage are different bugs." + }, + { + "left": "issue:36010", + "right": "issue:42915", + "accept": false, + "reason": "Import error for GenerationMixin is unrelated to Qwen3Moe FP8 loading." + }, + { + "left": "issue:44661", + "right": "issue:45823", + "accept": false, + "reason": "Tokenizer mapping failure and Gemma4 device mismatch are unrelated." + }, + { + "left": "issue:38175", + "right": "issue:43994", + "accept": false, + "reason": "Same model family, but the reports are too vague and not clearly the same underlying defect." + }, + { + "left": "issue:43632", + "right": "issue:43872", + "accept": true, + "reason": "Same shared `_is_hf_initialized` regression; 43872 is a specific downstream symptom of the broader bug described in 43632." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: it correctly treats the cluster as mostly heterogeneous while identifying the `_is_hf_initialized`, custom model initialization, and mask-shape duplicate subgroups. The accepted soft-edge pairs are conservative and well supported by the issue titles." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 5, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:36010", + "issue:38175", + "issue:39404", + "issue:39692", + "issue:41720", + "issue:42491", + "issue:42915", + "issue:43257", + "issue:43317", + "issue:43596", + "issue:43638", + "issue:43644", + "issue:43645", + "issue:43708", + "issue:43720", + "issue:43854", + "issue:43856", + "issue:43873", + "issue:43931", + "issue:43994", + "issue:44075", + "issue:44155", + "issue:44387", + "issue:44451", + "issue:44488", + "issue:44534", + "issue:44560", + "issue:44661", + "issue:44756", + "issue:44805", + "issue:44877", + "issue:44910", + "issue:44960", + "issue:44977", + "issue:44991", + "issue:45030", + "issue:45276", + "issue:45292", + "issue:45313", + "issue:45335", + "issue:45357", + "issue:45362", + "issue:45406", + "issue:45488", + "issue:45584", + "issue:45588", + "issue:45812" + ], + "soft_pairs": [ + "issue:44155|issue:45584", + "issue:44877|issue:45030", + "issue:44560|issue:44805", + "issue:43638|issue:44661", + "issue:43317|issue:44756", + "issue:43596|issue:44661", + "issue:44661|issue:44805", + "issue:38175|issue:39692", + "issue:43644|issue:44534", + "issue:45313|issue:45357", + "issue:44960|issue:44977", + "issue:45488|issue:45812", + "issue:44451|issue:44488", + "issue:42491|issue:43720", + "issue:43854|issue:43931", + "issue:41720|issue:42915", + "issue:43708|issue:44075", + "issue:42491|issue:45276", + "issue:43257|issue:43854", + "issue:43856|issue:43873", + "issue:42915|issue:44756", + "issue:39692|issue:43994", + "issue:42491|issue:43931", + "issue:43856|issue:44387", + "issue:43644|issue:43645", + "issue:44910|issue:45588", + "issue:45362|issue:45406", + "issue:42491|issue:45292", + "issue:44488|issue:44991", + "issue:36010|issue:39404", + "issue:45276|issue:45335" + ], + "prepared_review_unit_hash": "c963d638300563b27247fde40aaf85fe7bebd0f7c18539b25793e477079d00b4", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "serialized_chars": 36405, + "estimated_input_tokens": 9102, + "estimated_eval_tokens": 18460 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster contains several small duplicate subgroups, mostly around Transformers v5 regressions in loading/tokenizer/config handling. I\u2019d keep the tokenizer-loading regression issue as the main issue, and reject most cross-model or cross-subsystem pairs as too loose to be true duplicates.", + "confidence": 0.78, + "canonical_issue_reason": "Issue 44488 is the best hub for the tokenizer-loading regression subgroup: it\u2019s broad, already has inbound references, and sits between the more specific model reports.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44991 is the clearest single statement of the underlying bug class: a Transformers >=5.0.0 tokenizer-loading regression. It best represents the shared failure mode across the related reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44155", + "right": "issue:45584", + "accept": false, + "reason": "Different bugs and different models: batched embedding/token leakage vs Whisper empty-transcription generation failure." + }, + { + "left": "issue:44877", + "right": "issue:45030", + "accept": true, + "reason": "Both describe the same underlying v5 config-validation regression blocking model/config loading for different model families." + }, + { + "left": "issue:44560", + "right": "issue:44805", + "accept": false, + "reason": "Unrelated failures: Qwen3-VL video StopIteration vs a mask/tensor shape mismatch." + }, + { + "left": "issue:43638", + "right": "issue:44661", + "accept": false, + "reason": "Different code paths: DeepSpeed ZeRO-3 Bert init vs tokenizer-mapping logic for adding a model-like entry." + }, + { + "left": "issue:43317", + "right": "issue:44756", + "accept": false, + "reason": "Both involve loading/offload/memory, but the concrete failure modes are different (dequantized offload load failure vs mmap OOM)." + }, + { + "left": "issue:43596", + "right": "issue:44661", + "accept": false, + "reason": "Distinct issues: BertModel ZeRO-3 index error vs tokenizer-mapping add-new-model failure." + }, + { + "left": "issue:44661", + "right": "issue:44805", + "accept": false, + "reason": "No shared bug: tokenizer mapping registration vs a tensor-mask indexing mismatch." + }, + { + "left": "issue:38175", + "right": "issue:39692", + "accept": false, + "reason": "Related SigLIP2 area, but not the same bug: zero probabilities vs doc-example/model-processor mismatch and quantization errors." + }, + { + "left": "issue:43644", + "right": "issue:44534", + "accept": true, + "reason": "Same duplicate: Transformers v5 fills non-persistent buffers with junk." + }, + { + "left": "issue:45313", + "right": "issue:45357", + "accept": false, + "reason": "Different concrete problems: ZeRO-3 language_model loading vs incorrect visual-encoder keys saved by pretrained export." + }, + { + "left": "issue:44960", + "right": "issue:44977", + "accept": false, + "reason": "Different models and failure modes: GLM5 issue vs Qwen3.5 flash-attention generation problem." + }, + { + "left": "issue:45488", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different model families and look like separate bugs." + }, + { + "left": "issue:44451", + "right": "issue:44488", + "accept": true, + "reason": "Same underlying regression: current Transformers version fails to load BERT-like tokenizer/model checkpoints for multiple repositories." + }, + { + "left": "issue:42491", + "right": "issue:43720", + "accept": false, + "reason": "Both touch loading/quantization, but the concrete bugs are different: Qwen3 MoE LoRA compatibility vs BitNet packed-weight unpacking." + }, + { + "left": "issue:43854", + "right": "issue:43931", + "accept": false, + "reason": "Different models and root causes: GLM-4.7-Flash test loading vs Qwen3-VL weight-shape mismatch." + }, + { + "left": "issue:41720", + "right": "issue:42915", + "accept": false, + "reason": "Both are Qwen3-family issues, but the failures are unrelated: auto device mapping CUDA assert vs FineGrainedFP8Config failure." + }, + { + "left": "issue:43708", + "right": "issue:44075", + "accept": false, + "reason": "Trainer checkpoint math and optimizer argument handling are unrelated bugs." + }, + { + "left": "issue:42491", + "right": "issue:45276", + "accept": false, + "reason": "Different scope and failure mode: Qwen3 MoE HF5 compatibility vs Gemma4 resize_token_embeddings behavior." + }, + { + "left": "issue:43257", + "right": "issue:43854", + "accept": false, + "reason": "Separate problems: Qwen3 MoE accelerate+deepspeed weight conversion vs GLM-4.7-Flash loading in tests." + }, + { + "left": "issue:43856", + "right": "issue:43873", + "accept": false, + "reason": "Both mention memory/offload, but one is Qwen3 MoE training memory usage and the other is quantization offloading behavior." + }, + { + "left": "issue:42915", + "right": "issue:44756", + "accept": false, + "reason": "Different issues: Qwen3Moe FineGrainedFP8Config failure vs mmap/OOM on Strix Halo." + }, + { + "left": "issue:39692", + "right": "issue:43994", + "accept": false, + "reason": "Both are SigLIP2-related, but one is doc-example errors and the other is nonsensical outputs in AutoModel/pipeline." + }, + { + "left": "issue:42491", + "right": "issue:43931", + "accept": false, + "reason": "Different bugs: Qwen3 MoE HF5 compatibility vs Qwen3-VL shape mismatch on load." + }, + { + "left": "issue:43856", + "right": "issue:44387", + "accept": false, + "reason": "Both are memory-related, but the actual regressions differ: training memory inefficiency vs increased reserved CUDA memory under int4 quantization." + }, + { + "left": "issue:43644", + "right": "issue:43645", + "accept": false, + "reason": "Related v5 breakage theme, but one is non-persistent buffers junk and the other is custom model initialization in notebooks." + }, + { + "left": "issue:44910", + "right": "issue:45588", + "accept": false, + "reason": "Both involve flash attention, but the concrete failures differ: packed-sequence position_ids crash vs s_aux=None AttributeError." + }, + { + "left": "issue:45362", + "right": "issue:45406", + "accept": false, + "reason": "Different components and failures: Qwen3.5 chat crash vs Gemma4Processor missing _tokenizer in serve." + }, + { + "left": "issue:44488", + "right": "issue:44991", + "accept": true, + "reason": "Same tokenizer-loading regression in Transformers v5; the two issues are model-specific reports of the same underlying failure." + }, + { + "left": "issue:36010", + "right": "issue:39404", + "accept": false, + "reason": "Unrelated problems: GenerationMixin import error vs Whisper return_language pipeline behavior." + }, + { + "left": "issue:45276", + "right": "issue:45335", + "accept": true, + "reason": "Same resize_token_embeddings regression affecting output embeddings across different model variants." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays mostly conservative on the soft edges. The main cluster call around Transformers v5 tokenizer/config-loading regressions is supported, 44488 is a reasonable hub choice given its breadth and inbound refs, and the accepted duplicate pairs are plausible from the issue titles. I don\u2019t see an overstatement severe enough to reject." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 6, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:39404", + "issue:39692", + "issue:41720", + "issue:42947", + "issue:43257", + "issue:43335", + "issue:43381", + "issue:43404", + "issue:43425", + "issue:43454", + "issue:43645", + "issue:43646", + "issue:43708", + "issue:43828", + "issue:43854", + "issue:43873", + "issue:43957", + "issue:44155", + "issue:44164", + "issue:44291", + "issue:44292", + "issue:44387", + "issue:44402", + "issue:44451", + "issue:44479", + "issue:44488", + "issue:44589", + "issue:44683", + "issue:44756", + "issue:44863", + "issue:44877", + "issue:44912", + "issue:44928", + "issue:44960", + "issue:45216", + "issue:45276", + "issue:45292", + "issue:45335", + "issue:45588", + "issue:45663", + "issue:45684", + "issue:45698", + "issue:45701", + "issue:45704", + "issue:45759", + "issue:45823", + "issue:45859" + ], + "soft_pairs": [ + "issue:43404|issue:43454", + "issue:44164|issue:44291", + "issue:44402|issue:44488", + "issue:43425|issue:43957", + "issue:39692|issue:44960", + "issue:42947|issue:45704", + "issue:43335|issue:45663", + "issue:43873|issue:44387", + "issue:45663|issue:45759", + "issue:45663|issue:45859", + "issue:44155|issue:45823", + "issue:43854|issue:45216", + "issue:44387|issue:44756", + "issue:44291|issue:44756", + "issue:44292|issue:44912", + "issue:42947|issue:43381", + "issue:45684|issue:45698", + "issue:45276|issue:45292", + "issue:43381|issue:44928", + "issue:44164|issue:44756", + "issue:44479|issue:44877", + "issue:43646|issue:43708", + "issue:41720|issue:44155", + "issue:45588|issue:45663", + "issue:43854|issue:44960", + "issue:43957|issue:44756", + "issue:45292|issue:45335", + "issue:44402|issue:44451", + "issue:43828|issue:43957", + "issue:43645|issue:44164", + "issue:43425|issue:43828", + "issue:43257|issue:44863", + "issue:44589|issue:44756", + "issue:44683|issue:45823", + "issue:39404|issue:45701" + ], + "prepared_review_unit_hash": "fec8c9366a638da6d3772f5adfcf3b494983aec474afee3c9f0d8938ee329678", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 35, + "serialized_chars": 37606, + "estimated_input_tokens": 9402, + "estimated_eval_tokens": 19060 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous, but there is a small duplicate subgroup around `resize_token_embeddings` not propagating to output/decoder embeddings. Most other pairs are related only at a broad subsystem level and should not be merged.", + "confidence": 0.46, + "canonical_issue_reason": "`issue:45292` is the cleanest, most generic report of the shared `resize_token_embeddings` regression and best matches the strongest duplicate subgroup.", + "canonical_pr_reason": null, + "best_issue_reason": "`issue:45292` is the broadest and most reusable anchor for the accepted resize-token-embedding duplicates, with a concise title that captures the common failure mode.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43404", + "right": "issue:43454", + "accept": false, + "reason": "Both mention tied `lm_head` behavior, but they affect different model implementations and do not clearly describe the same code-path bug." + }, + { + "left": "issue:44164", + "right": "issue:44291", + "accept": false, + "reason": "`extra_state` save/load handling and `init_empty_weights` argument errors are different serialization/loading failures." + }, + { + "left": "issue:44402", + "right": "issue:44488", + "accept": false, + "reason": "Both are BERT load problems, but the models and stated failure modes differ; not enough evidence of one shared bug." + }, + { + "left": "issue:43425", + "right": "issue:43957", + "accept": false, + "reason": "One is torch 2.10 incompatibility and the other is meta-device loading breakage; unrelated regressions." + }, + { + "left": "issue:39692", + "right": "issue:44960", + "accept": false, + "reason": "Documentation example errors and a generic GLM5 issue are not the same underlying bug." + }, + { + "left": "issue:42947", + "right": "issue:45704", + "accept": false, + "reason": "Gradient checkpointing with PEFT LoRA and an apex RMSNorm memory leak are different problems." + }, + { + "left": "issue:43335", + "right": "issue:45663", + "accept": false, + "reason": "Sparse-layer config creation and Gemma4 FSDP2 attention state rebuilding are unrelated code paths." + }, + { + "left": "issue:43873", + "right": "issue:44387", + "accept": false, + "reason": "Both are quantization memory issues, but the causes differ (`offloading` vs increased reserved memory/OOM regression)." + }, + { + "left": "issue:45663", + "right": "issue:45759", + "accept": false, + "reason": "FSDP2 `shared_kv_states` rebuilding and `from_config` not unwrapping `text_config` are distinct bugs." + }, + { + "left": "issue:45663", + "right": "issue:45859", + "accept": false, + "reason": "The Gemma4 FSDP2 error and the Qwen3_5 MoE rotary offload incompatibility are different failures." + }, + { + "left": "issue:44155", + "right": "issue:45823", + "accept": false, + "reason": "AudioFlamingo3 batched-token leakage and Gemma4 PLE device mismatch are unrelated." + }, + { + "left": "issue:43854", + "right": "issue:45216", + "accept": false, + "reason": "A model-loading failure in tests and a `save_pretrained` regression are different issues." + }, + { + "left": "issue:44387", + "right": "issue:44756", + "accept": false, + "reason": "Both involve memory pressure, but one is an int4 quantization regression and the other is mmap/OOM on Strix Halo." + }, + { + "left": "issue:44291", + "right": "issue:44756", + "accept": false, + "reason": "Unexpected `_is_hf_initialized` handling and mmap-related OOM are not the same bug." + }, + { + "left": "issue:44292", + "right": "issue:44912", + "accept": false, + "reason": "NVFP4 load errors and MXFP4 fallback behavior are different quantization/load problems." + }, + { + "left": "issue:42947", + "right": "issue:43381", + "accept": false, + "reason": "These are both checkpointing-related, but one is ineffective LoRA checkpointing and the other is an eval-mode limitation." + }, + { + "left": "issue:45684", + "right": "issue:45698", + "accept": false, + "reason": "Custom-model file permissions and wrong custom-module loading after save/load are separate save/load bugs." + }, + { + "left": "issue:45276", + "right": "issue:45292", + "accept": true, + "reason": "These describe the same `resize_token_embeddings` regression: resized embeddings are not propagated to the output path, with `45276` adding Gemma4-specific detail." + }, + { + "left": "issue:43381", + "right": "issue:44928", + "accept": false, + "reason": "Gradient checkpointing in eval mode and RLHF NaN explosions from 3D position IDs are unrelated." + }, + { + "left": "issue:44164", + "right": "issue:44756", + "accept": false, + "reason": "`extra_state` serialization and mmap/OOM on Strix Halo do not share a concrete root cause." + }, + { + "left": "issue:44479", + "right": "issue:44877", + "accept": false, + "reason": "Video-input regression in Qwen models and strict config blocking `granite_speech` are different failures." + }, + { + "left": "issue:43646", + "right": "issue:43708", + "accept": false, + "reason": "Custom model initialization in notebooks and incorrect `max_steps` on resume are separate trainer/model-init issues." + }, + { + "left": "issue:41720", + "right": "issue:44155", + "accept": false, + "reason": "Qwen3 auto-device-map CUDA asserts and AudioFlamingo3 batched inference leakage are unrelated." + }, + { + "left": "issue:45588", + "right": "issue:45663", + "accept": false, + "reason": "A flash-attention `s_aux=None` crash and the Gemma4 FSDP2 shared-state bug are different code paths." + }, + { + "left": "issue:43854", + "right": "issue:44960", + "accept": false, + "reason": "These are different model-loading issues with different targets and symptoms." + }, + { + "left": "issue:43957", + "right": "issue:44756", + "accept": false, + "reason": "Meta-device loading breakage and mmap-induced OOM are not the same problem." + }, + { + "left": "issue:45292", + "right": "issue:45335", + "accept": true, + "reason": "Both report the same underlying `resize_token_embeddings` bug: the resized weights do not update the model's embedding/output path, just on different model variants." + }, + { + "left": "issue:44402", + "right": "issue:44451", + "accept": false, + "reason": "A tokenizer vocab-size mismatch and a later model-load failure for a specific checkpoint are not clearly the same bug." + }, + { + "left": "issue:43828", + "right": "issue:43957", + "accept": false, + "reason": "Autocast dtype mismatch and meta-device loading failures are unrelated." + }, + { + "left": "issue:43645", + "right": "issue:44164", + "accept": false, + "reason": "Notebook custom-model initialization and `extra_state` save/load handling are different issues." + }, + { + "left": "issue:43425", + "right": "issue:43828", + "accept": false, + "reason": "Torch version incompatibility and an autocast dtype mismatch are distinct regressions." + }, + { + "left": "issue:43257", + "right": "issue:44863", + "accept": false, + "reason": "Qwen3 MoE conversion under accelerate+deepspeed and NemotronH checkpoint loading are different model-loading failures." + }, + { + "left": "issue:44589", + "right": "issue:44756", + "accept": false, + "reason": "Missing Float8 storage support and Strix Halo mmap/OOM are unrelated." + }, + { + "left": "issue:44683", + "right": "issue:45823", + "accept": false, + "reason": "Compiled flex_attention failing on torch>=2.9 and Gemma4 PLE device mismatch are not the same bug." + }, + { + "left": "issue:39404", + "right": "issue:45701", + "accept": false, + "reason": "Whisper pipeline `return_language` regression and tokenizer-version-dependent tokenization changes are different issues." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: the only clearly supported duplicate subgroup is the resize_token_embeddings trio (45276/45292/45335), and the other pairings are conservatively rejected. No pair is overstated as mergeable, and the reasoning stays within the evidence shown in titles/body signals." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 7, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:32090", + "issue:36032", + "issue:39404", + "issue:40990", + "issue:42915", + "issue:42947", + "issue:43299", + "issue:43421", + "issue:43425", + "issue:43452", + "issue:43582", + "issue:43596", + "issue:43611", + "issue:43632", + "issue:43644", + "issue:43645", + "issue:43716", + "issue:43856", + "issue:43901", + "issue:43906", + "issue:43931", + "issue:43994", + "issue:44079", + "issue:44164", + "issue:44206", + "issue:44220", + "issue:44265", + "issue:44479", + "issue:44488", + "issue:44509", + "issue:44530", + "issue:44589", + "issue:44661", + "issue:44671", + "issue:44683", + "issue:44737", + "issue:44756", + "issue:44805", + "issue:44863", + "issue:44898", + "issue:44912", + "issue:44918", + "issue:44991", + "issue:45081", + "issue:45084", + "issue:45759", + "issue:45823", + "issue:45859" + ], + "soft_pairs": [ + "issue:43906|issue:44530", + "issue:43425|issue:45823", + "issue:43611|issue:43645", + "issue:43425|issue:43716", + "issue:42915|issue:44863", + "issue:44530|issue:45084", + "issue:43901|issue:44509", + "issue:39404|issue:44912", + "issue:44265|issue:44898", + "issue:43299|issue:43931", + "issue:44479|issue:44805", + "issue:43425|issue:44918", + "issue:44589|issue:45084", + "issue:40990|issue:42947", + "issue:43856|issue:44756", + "issue:39404|issue:44671", + "issue:44164|issue:45759", + "issue:43994|issue:44079", + "issue:36032|issue:43452", + "issue:43596|issue:44683", + "issue:44671|issue:44991", + "issue:44991|issue:45081", + "issue:44737|issue:45859", + "issue:32090|issue:39404", + "issue:44164|issue:44479", + "issue:44488|issue:45081", + "issue:44661|issue:44683", + "issue:43582|issue:43632", + "issue:40990|issue:43421", + "issue:43611|issue:43644", + "issue:43716|issue:45084", + "issue:44206|issue:44220" + ], + "prepared_review_unit_hash": "21b5560eae18a2d8736b63f1f28c1ec0746fcd03a91114734bac35151a68d40d", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37318, + "estimated_input_tokens": 9330, + "estimated_eval_tokens": 18916 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous Transformers regressions and docs issues, not a tight duplicate set. The only clear duplicate-like pair is the audio feature-extraction crash (44206/44220).", + "confidence": 0.58, + "canonical_issue_reason": "Issue 44206 is the clearest representative of the only true duplicate pair here: it states the regression, the failing component, and the crash mode more fully than 44220.", + "canonical_pr_reason": null, + "best_issue_reason": "44206 is the best issue anchor because it is the most explicit, reproducible report among the actual duplicate candidates; the rest of the cluster is too mixed to serve as a single canonical bug.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43906", + "right": "issue:44530", + "accept": false, + "reason": "Different bugs: one is Whisper pipeline behavior, the other is Qwen3.5 cache/template parsing." + }, + { + "left": "issue:43425", + "right": "issue:45823", + "accept": false, + "reason": "Torch-version incompatibility vs Gemma4 PLE device-map mismatch are unrelated failures." + }, + { + "left": "issue:43611", + "right": "issue:43645", + "accept": false, + "reason": "Both are v5 regressions, but they affect different code paths and symptoms." + }, + { + "left": "issue:43425", + "right": "issue:43716", + "accept": false, + "reason": "Different issues: torch compatibility in general vs image preprocessor/model dtype mismatch." + }, + { + "left": "issue:42915", + "right": "issue:44863", + "accept": false, + "reason": "Different model families and different failure modes; not the same underlying bug." + }, + { + "left": "issue:44530", + "right": "issue:45084", + "accept": false, + "reason": "Qwen3.5 linear-attention cache crash is unrelated to template-node compilation errors." + }, + { + "left": "issue:43901", + "right": "issue:44509", + "accept": false, + "reason": "Both are docs-related, but they document different removed/deprecated pipeline behaviors." + }, + { + "left": "issue:39404", + "right": "issue:44912", + "accept": false, + "reason": "Whisper return_language regression and GPT-OSS quantization fallback are unrelated." + }, + { + "left": "issue:44265", + "right": "issue:44898", + "accept": false, + "reason": "torch.export/torch_compilable_check is unrelated to Perceiver non-default-resolution masking." + }, + { + "left": "issue:43299", + "right": "issue:43931", + "accept": false, + "reason": "Both concern Qwen3-VL loading, but one is a version breakage and the other is a checkpoint shape mismatch." + }, + { + "left": "issue:44479", + "right": "issue:44805", + "accept": false, + "reason": "Video-input regression for specific VL models is not the same as a generic mask shape IndexError." + }, + { + "left": "issue:43425", + "right": "issue:44918", + "accept": false, + "reason": "Torch compatibility and Qwen3.5 embedding unpacking under TRL are different problems." + }, + { + "left": "issue:44589", + "right": "issue:45084", + "accept": false, + "reason": "Float8 storage lookup failure is unrelated to non-template-node compilation." + }, + { + "left": "issue:40990", + "right": "issue:42947", + "accept": false, + "reason": "Perplexity anomaly and LoRA gradient-checkpointing behavior are distinct issues." + }, + { + "left": "issue:43856", + "right": "issue:44756", + "accept": false, + "reason": "Qwen3 MoE training memory usage and mmap OOM on Strix Halo are not the same bug." + }, + { + "left": "issue:39404", + "right": "issue:44671", + "accept": false, + "reason": "Whisper pipeline regression and CamemBERT masked-LM prediction regression are unrelated." + }, + { + "left": "issue:44164", + "right": "issue:45759", + "accept": false, + "reason": "Both involve model loading/serialization, but they hit different APIs and failure modes." + }, + { + "left": "issue:43994", + "right": "issue:44079", + "accept": false, + "reason": "SigLIP2 nonsensical outputs and ModelOutput key assignment are different defects." + }, + { + "left": "issue:36032", + "right": "issue:43452", + "accept": false, + "reason": "Tokenizer special-token conflict is unrelated to gguf_file loading failures." + }, + { + "left": "issue:43596", + "right": "issue:44683", + "accept": false, + "reason": "DeepSpeed ZeRO3 BertModel init error is unrelated to compiled flex_attention on newer torch." + }, + { + "left": "issue:44671", + "right": "issue:44991", + "accept": false, + "reason": "CamemBERT masked-LM regression and tokenizer loading failure for est-roberta are different issues." + }, + { + "left": "issue:44991", + "right": "issue:45081", + "accept": false, + "reason": "Different tokenizers/models and different failure causes; not mergeable into one bug." + }, + { + "left": "issue:44737", + "right": "issue:45859", + "accept": false, + "reason": "CPU-device placement bug in XLNet is unrelated to Qwen3.5 MoE rotary embedding offload issues." + }, + { + "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": "Serialization extra_state handling and video-input regression are different code paths." + }, + { + "left": "issue:44488", + "right": "issue:45081", + "accept": false, + "reason": "sleng-bert tokenizer load failure is unrelated to the Mistral regex patch crash." + }, + { + "left": "issue:44661", + "right": "issue:44683", + "accept": false, + "reason": "Tokenizer mapping bug and flex_attention compilation bug are unrelated." + }, + { + "left": "issue:43582", + "right": "issue:43632", + "accept": false, + "reason": "AppleSilicon warmup TypeError and _is_hf_initialized flag regression are different problems." + }, + { + "left": "issue:40990", + "right": "issue:43421", + "accept": false, + "reason": "Perplexity issue and runtime special-token post-processor update are unrelated." + }, + { + "left": "issue:43611", + "right": "issue:43644", + "accept": false, + "reason": "Both are Transformers v5 regressions, but they affect different mechanisms and symptoms." + }, + { + "left": "issue:43716", + "right": "issue:45084", + "accept": false, + "reason": "Multimodal dtype mismatch is unrelated to template-node compilation failure." + }, + { + "left": "issue:44206", + "right": "issue:44220", + "accept": true, + "reason": "Both point to the same audio feature-extraction failure around `_torch_extract_fbank_features`; 44220 looks like the lower-level duplicate." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: it treats the cluster as mostly heterogeneous, and the only accepted pair (44206/44220) is supported by closely related audio feature-extraction titles. The rejected soft pairs are phrased conservatively and do not overclaim duplicate status." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 8, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:34567", + "issue:36032", + "issue:40444", + "issue:42915", + "issue:43262", + "issue:43296", + "issue:43317", + "issue:43322", + "issue:43377", + "issue:43404", + "issue:43452", + "issue:43482", + "issue:43531", + "issue:43540", + "issue:43541", + "issue:43632", + "issue:43643", + "issue:43644", + "issue:43645", + "issue:43646", + "issue:43742", + "issue:43819", + "issue:43883", + "issue:43994", + "issue:44220", + "issue:44265", + "issue:44291", + "issue:44403", + "issue:44451", + "issue:44466", + "issue:44488", + "issue:44530", + "issue:44534", + "issue:44610", + "issue:44683", + "issue:44756", + "issue:44811", + "issue:44849", + "issue:44987", + "issue:44991", + "issue:45081", + "issue:45084", + "issue:45127", + "issue:45216", + "issue:45325", + "issue:45357", + "issue:45507", + "issue:45584" + ], + "soft_pairs": [ + "issue:44488|issue:44987", + "issue:43883|issue:44488", + "issue:43643|issue:44530", + "issue:34567|issue:40444", + "issue:44811|issue:45584", + "issue:43644|issue:43646", + "issue:44451|issue:44987", + "issue:43541|issue:45084", + "issue:36032|issue:42915", + "issue:43452|issue:43482", + "issue:42915|issue:44530", + "issue:43317|issue:43482", + "issue:44849|issue:45325", + "issue:43883|issue:44991", + "issue:43404|issue:44466", + "issue:36032|issue:43645", + "issue:45084|issue:45507", + "issue:43262|issue:43377", + "issue:43646|issue:44534", + "issue:44987|issue:44991", + "issue:43994|issue:44610", + "issue:44403|issue:45081", + "issue:43322|issue:43540", + "issue:43377|issue:43819", + "issue:43645|issue:44534", + "issue:42915|issue:45084", + "issue:44451|issue:45081", + "issue:45216|issue:45357", + "issue:44987|issue:45081", + "issue:44220|issue:44683", + "issue:44265|issue:44610", + "issue:43404|issue:45127", + "issue:43296|issue:43531", + "issue:43632|issue:44756", + "issue:42915|issue:44291", + "issue:36032|issue:43742" + ], + "prepared_review_unit_hash": "e131a590db60c5c88ffd87097fa9dbd320ada125279ce5cdf6a34747b7b189ff", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 36, + "serialized_chars": 38522, + "estimated_input_tokens": 9631, + "estimated_eval_tokens": 19518 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous and centered on separate Transformers v5/model-loading regressions. Only one soft duplicate looks strong enough to merge: the Qwen3.5 save_pretrained checkpoint serialization regression.", + "confidence": 0.66, + "canonical_issue_reason": "Issue 45216 is the clearest duplicate anchor: it reports a concrete Qwen3.5 save_pretrained regression, and 45357 describes the same incorrect checkpoint serialization for visual encoder keys.", + "canonical_pr_reason": null, + "best_issue_reason": "45216 is the most suitable representative issue because it is concrete, versioned, and has a direct near-duplicate in 45357 with the same save_pretrained checkpoint bug.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44488", + "right": "issue:44987", + "accept": false, + "reason": "Both are model-loading failures, but for different checkpoints and likely different root causes." + }, + { + "left": "issue:43883", + "right": "issue:44488", + "accept": false, + "reason": "Different bugs: tied-weights attribute error vs. model loading failure." + }, + { + "left": "issue:43643", + "right": "issue:44530", + "accept": false, + "reason": "Different code paths: AutoConfig field loss vs. PagedAttentionCache group-type crash." + }, + { + "left": "issue:34567", + "right": "issue:40444", + "accept": false, + "reason": "Trainer token accounting and multimodal iterable dataset failures are unrelated." + }, + { + "left": "issue:44811", + "right": "issue:45584", + "accept": false, + "reason": "Both involve Whisper, but one is batch_decode token skipping and the other is empty-transcription generation failure." + }, + { + "left": "issue:43644", + "right": "issue:43646", + "accept": false, + "reason": "Both are v5 regressions, but one is non-persistent buffer corruption and the other is custom model initialization." + }, + { + "left": "issue:44451", + "right": "issue:44987", + "accept": false, + "reason": "Different models and load failures; no clear shared bug." + }, + { + "left": "issue:43541", + "right": "issue:45084", + "accept": false, + "reason": "Unrelated failures: torch dynamo grouped_mm tracing vs. template-node compilation." + }, + { + "left": "issue:36032", + "right": "issue:42915", + "accept": false, + "reason": "Tokenizer attribute conflict and Qwen3Moe FP8 failure are unrelated." + }, + { + "left": "issue:43452", + "right": "issue:43482", + "accept": false, + "reason": "Both mention GGUF, but one is a generic gguf_file loader breakage and the other is a specific Qwen2.5-GGUF v5 loading failure." + }, + { + "left": "issue:42915", + "right": "issue:44530", + "accept": false, + "reason": "Different model families and failure modes." + }, + { + "left": "issue:43317", + "right": "issue:43482", + "accept": false, + "reason": "Different loading paths: device_map/offload dequantization vs. GGUF/v5 failure." + }, + { + "left": "issue:44849", + "right": "issue:45325", + "accept": false, + "reason": "Different Qwen bugs: hidden-state handling vs. RoPE position scaling." + }, + { + "left": "issue:43883", + "right": "issue:44991", + "accept": false, + "reason": "Different model-loading errors with different underlying causes." + }, + { + "left": "issue:43404", + "right": "issue:44466", + "accept": false, + "reason": "Related to tied weights, but one is untied lm_head in a model class and the other is device-dependent serialization." + }, + { + "left": "issue:36032", + "right": "issue:43645", + "accept": false, + "reason": "Tokenizer load conflict and custom model initialization are unrelated." + }, + { + "left": "issue:45084", + "right": "issue:45507", + "accept": false, + "reason": "Different failures in different subsystems; no shared bug." + }, + { + "left": "issue:43262", + "right": "issue:43377", + "accept": false, + "reason": "Audio processor sampling-rate defaulting and MIMI padding-mask mismatch are different issues." + }, + { + "left": "issue:43646", + "right": "issue:44534", + "accept": false, + "reason": "Both are v5 init-related regressions, but the concrete bugs differ: custom model init vs. non-persistent buffer junk." + }, + { + "left": "issue:44987", + "right": "issue:44991", + "accept": false, + "reason": "Both are loader failures, but for different model/tokenizer packages and different symptoms." + }, + { + "left": "issue:43994", + "right": "issue:44610", + "accept": false, + "reason": "Different multimodal models and mismatched preprocessing expectations." + }, + { + "left": "issue:44265", + "right": "issue:44683", + "accept": false, + "reason": "Different export/compile failures with different triggers." + }, + { + "left": "issue:44403", + "right": "issue:45081", + "accept": false, + "reason": "Noise on loading vs. a specific tokenizer regex patch crash are not the same bug." + }, + { + "left": "issue:43322", + "right": "issue:43540", + "accept": false, + "reason": "Different multimodal failures: Llava Next load segfault vs. Qwen3OmniMoe video processing error." + }, + { + "left": "issue:43377", + "right": "issue:43819", + "accept": false, + "reason": "Both are audio-related, but one is padding-mask batching and the other is DAC STE behavior." + }, + { + "left": "issue:43645", + "right": "issue:44534", + "accept": false, + "reason": "Custom model initialization in notebooks is not the same as buffer initialization corruption." + }, + { + "left": "issue:42915", + "right": "issue:45084", + "accept": false, + "reason": "Unrelated model/config problems." + }, + { + "left": "issue:44451", + "right": "issue:45081", + "accept": false, + "reason": "Different model-loading bugs with different failure modes." + }, + { + "left": "issue:45216", + "right": "issue:45357", + "accept": true, + "reason": "Same save_pretrained checkpoint regression for Qwen3.5, with 45357 explicitly describing the same incorrect visual encoder keys." + }, + { + "left": "issue:44987", + "right": "issue:45081", + "accept": false, + "reason": "Different failure surfaces: loading a model vs. tokenizer regex patch crash." + }, + { + "left": "issue:44220", + "right": "issue:44683", + "accept": false, + "reason": "Different low-level feature/export issues." + }, + { + "left": "issue:44265", + "right": "issue:44610", + "accept": false, + "reason": "torch.export checker failure and image-size preprocessing mismatch are unrelated." + }, + { + "left": "issue:43404", + "right": "issue:45127", + "accept": false, + "reason": "Both mention tied weights, but the underlying bugs differ: missing tying vs. LoRA merge collapse." + }, + { + "left": "issue:43296", + "right": "issue:43531", + "accept": false, + "reason": "PaddleOCR-VL load failure and Qwen3-MoE sliding_window issue are unrelated." + }, + { + "left": "issue:43632", + "right": "issue:44756", + "accept": false, + "reason": "Different regressions: _is_hf_initialized flag handling vs. mmap OOM on Strix Halo." + }, + { + "left": "issue:42915", + "right": "issue:44291", + "accept": false, + "reason": "Different FP8/init issues; no shared underlying change." + }, + { + "left": "issue:36032", + "right": "issue:43742", + "accept": false, + "reason": "Tokenizer method conflict and MobileLLM load key error are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet, and the only accepted soft pair (45216/45357) is well supported as the same Qwen3.5 save_pretrained serialization bug. The rejected soft pairs are stated conservatively, with no clear overclaiming beyond what the titles and packet text support." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 9, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:33666", + "issue:36032", + "issue:40444", + "issue:40990", + "issue:41553", + "issue:41720", + "issue:42175", + "issue:42915", + "issue:43296", + "issue:43317", + "issue:43377", + "issue:43421", + "issue:43425", + "issue:43482", + "issue:43525", + "issue:43531", + "issue:43582", + "issue:43611", + "issue:43632", + "issue:43646", + "issue:43792", + "issue:43818", + "issue:43856", + "issue:44062", + "issue:44079", + "issue:44291", + "issue:44403", + "issue:44462", + "issue:44479", + "issue:44534", + "issue:44568", + "issue:44589", + "issue:44683", + "issue:44811", + "issue:44829", + "issue:44877", + "issue:44987", + "issue:44991", + "issue:45020", + "issue:45081", + "issue:45325", + "issue:45357", + "issue:45479", + "issue:45491", + "issue:45538", + "issue:45542", + "issue:45663", + "issue:45812" + ], + "soft_pairs": [ + "issue:44062|issue:44987", + "issue:42915|issue:44589", + "issue:43531|issue:44877", + "issue:43611|issue:44534", + "issue:43317|issue:43856", + "issue:43425|issue:44403", + "issue:44479|issue:45325", + "issue:40990|issue:44811", + "issue:41553|issue:43582", + "issue:42175|issue:45542", + "issue:43818|issue:45357", + "issue:44462|issue:45812", + "issue:36032|issue:41720", + "issue:44079|issue:45663", + "issue:43421|issue:44568", + "issue:43792|issue:44589", + "issue:43632|issue:44534", + "issue:44403|issue:44991", + "issue:44683|issue:45020", + "issue:43482|issue:45538", + "issue:44829|issue:45479", + "issue:33666|issue:40444", + "issue:44291|issue:44589", + "issue:43482|issue:43525", + "issue:40444|issue:45325", + "issue:43377|issue:45491", + "issue:41720|issue:45081", + "issue:42175|issue:43296", + "issue:43531|issue:44291", + "issue:43611|issue:43646" + ], + "prepared_review_unit_hash": "9ec3342a576e5ba4fb5095e8c3df47a53d8ae4ff3eabc407f727ffabc048a4e0", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36778, + "estimated_input_tokens": 9195, + "estimated_eval_tokens": 18646 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab bag of Transformers regression reports across unrelated models/subsystems. The soft pairs are thematically similar in places, but none look like the same concrete bug/change; I would not merge any of them.", + "confidence": 0.86, + "canonical_issue_reason": "issue:45020 is the broadest umbrella report here: it captures the general class of recent-version regressions breaking model loading/behavior for remote-code/custom-model cases, which best matches the cluster\u2019s overall theme.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45020 is the strongest single representative because it is broad, open, and describes the overarching regression pattern rather than one model-specific symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44062", + "right": "issue:44987", + "accept": false, + "reason": "Both are loading regressions in recent Transformers, but they describe different failure modes and models; not the same concrete tokenizer/model bug." + }, + { + "left": "issue:42915", + "right": "issue:44589", + "accept": false, + "reason": "Qwen3MoE FP8 failure vs missing Float8 storage class are different low-level errors and likely different code paths." + }, + { + "left": "issue:43531", + "right": "issue:44877", + "accept": false, + "reason": "One is a Qwen3-MoE sliding-window bug, the other is strict config handling for granite_speech; unrelated subsystems." + }, + { + "left": "issue:43611", + "right": "issue:44534", + "accept": false, + "reason": "Base-model-prefix loading breakage and non-persistent-buffer corruption are distinct issues." + }, + { + "left": "issue:43317", + "right": "issue:43856", + "accept": false, + "reason": "Device-map/offload loading failure and Qwen3 MoE memory inefficiency are not the same bug." + }, + { + "left": "issue:43425", + "right": "issue:44403", + "accept": false, + "reason": "Torch 2.10 compatibility and noisy model-loading output are unrelated." + }, + { + "left": "issue:44479", + "right": "issue:45325", + "accept": false, + "reason": "Both involve Qwen VL/video behavior, but one is a video-input regression and the other is a rope-index scaling bug for still images." + }, + { + "left": "issue:40990", + "right": "issue:44811", + "accept": false, + "reason": "Perplexity regression on gpt-oss and Whisper batch_decode skip_special_tokens are unrelated." + }, + { + "left": "issue:41553", + "right": "issue:43582", + "accept": false, + "reason": "AutoTokenizer/Voxtral error handling and an Apple Silicon allocator TypeError are different problems." + }, + { + "left": "issue:42175", + "right": "issue:45542", + "accept": false, + "reason": "Both touch TF packaging/backend handling, but one is missing TensorFlow in a torch extra and the other is an undefined backend when only tensorboard is installed." + }, + { + "left": "issue:43818", + "right": "issue:45357", + "accept": false, + "reason": "Video-LLaVA tower/temporal-attention bug and Qwen3.5 save_pretrained key regression are different model-specific defects." + }, + { + "left": "issue:44462", + "right": "issue:45812", + "accept": false, + "reason": "Both are AutoTokenizer regressions, but one ignores tokenizer.json while the other miscomputes Granite token IDs; not the same fix." + }, + { + "left": "issue:36032", + "right": "issue:41720", + "accept": false, + "reason": "Tokenizer method-name conflict and Qwen3 auto-device-map cuda assert are unrelated." + }, + { + "left": "issue:44079", + "right": "issue:45663", + "accept": false, + "reason": "ModelOutput key assignment and Gemma4 shared_kv_states rebuilding are unrelated code paths." + }, + { + "left": "issue:43421", + "right": "issue:44568", + "accept": false, + "reason": "Runtime special-token post-processing update and add_special_tokens not adding BOS/EOS are different tokenizer behaviors." + }, + { + "left": "issue:43792", + "right": "issue:44589", + "accept": false, + "reason": "Whisper runtime failure and missing Float8 storage support are different failures." + }, + { + "left": "issue:43632", + "right": "issue:44534", + "accept": false, + "reason": "_is_hf_initialized flag breakage and junk-filled non-persistent buffers are separate regressions." + }, + { + "left": "issue:44403", + "right": "issue:44991", + "accept": false, + "reason": "Noisy load messages and tokenizer loading failure for EMBEDDIA/est-roberta are unrelated." + }, + { + "left": "issue:44683", + "right": "issue:45020", + "accept": false, + "reason": "Compiled flex_attention on torch>=2.9 is a torch/kernel compatibility issue, not the remote_code loading regression described in 45020." + }, + { + "left": "issue:43482", + "right": "issue:45538", + "accept": false, + "reason": "GGUF loading with transformers v5 and CLIPTokenizer max-length misuse are different tokenizer/model bugs." + }, + { + "left": "issue:44829", + "right": "issue:45479", + "accept": false, + "reason": "Flash-attention training degeneration and zero-loss classification behavior are both training problems but not the same concrete defect." + }, + { + "left": "issue:33666", + "right": "issue:40444", + "accept": false, + "reason": "Qwen2-VL multi-GPU training and iterable-dataset multi-image prompting are different training scenarios and failures." + }, + { + "left": "issue:44291", + "right": "issue:44589", + "accept": false, + "reason": "init_empty_weights unexpected argument and missing Float8 storage are different initialization/storage issues." + }, + { + "left": "issue:43482", + "right": "issue:43525", + "accept": false, + "reason": "GGUF loading failure and missing pad_token_id in Llama4Config are unrelated." + }, + { + "left": "issue:40444", + "right": "issue:45325", + "accept": false, + "reason": "Multi-image iterable dataset failure and Qwen2.5-VL still-image position-id scaling are different multimodal bugs." + }, + { + "left": "issue:43377", + "right": "issue:45491", + "accept": false, + "reason": "Batched-vs-single MIMI output mismatch from missing padding mask and Gemma3 NaNs from sliding-window all-padding windows are different issues." + }, + { + "left": "issue:41720", + "right": "issue:45081", + "accept": false, + "reason": "Qwen3 device-map assert and Mistral tokenizer regex patch crash are unrelated." + }, + { + "left": "issue:42175", + "right": "issue:43296", + "accept": false, + "reason": "TF backend packaging and PaddleOCR-VL load failure in vLLM are different problems." + }, + { + "left": "issue:43531", + "right": "issue:44291", + "accept": false, + "reason": "Qwen3-MoE sliding-window behavior and init_empty_weights argument handling are unrelated." + }, + { + "left": "issue:43611", + "right": "issue:43646", + "accept": false, + "reason": "Both are Transformers v5 loading regressions, but one is specifically base_model_prefix handling and the other is generic custom model initialization; not enough evidence of the same bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 10, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:35707", + "issue:39692", + "issue:40444", + "issue:40990", + "issue:41720", + "issue:42915", + "issue:43262", + "issue:43296", + "issue:43317", + "issue:43377", + "issue:43454", + "issue:43482", + "issue:43526", + "issue:43550", + "issue:43572", + "issue:43606", + "issue:43632", + "issue:43644", + "issue:43701", + "issue:43746", + "issue:43792", + "issue:43819", + "issue:43873", + "issue:43881", + "issue:43883", + "issue:43957", + "issue:43994", + "issue:44079", + "issue:44186", + "issue:44265", + "issue:44291", + "issue:44387", + "issue:44466", + "issue:44479", + "issue:44488", + "issue:44534", + "issue:44610", + "issue:44617", + "issue:44877", + "issue:44898", + "issue:45072", + "issue:45325", + "issue:45381", + "issue:45584", + "issue:45759", + "issue:45800", + "issue:45823", + "issue:45834" + ], + "soft_pairs": [ + "issue:44265|issue:45072", + "issue:43632|issue:45072", + "issue:43454|issue:44466", + "issue:43994|issue:44898", + "issue:44079|issue:44534", + "issue:45325|issue:45834", + "issue:43792|issue:43957", + "issue:42915|issue:43482", + "issue:44079|issue:45072", + "issue:40444|issue:45381", + "issue:43644|issue:44079", + "issue:45325|issue:45381", + "issue:44387|issue:44617", + "issue:43296|issue:45800", + "issue:44479|issue:45823", + "issue:43881|issue:44488", + "issue:35707|issue:40444", + "issue:44291|issue:44877", + "issue:43317|issue:43873", + "issue:43606|issue:44265", + "issue:43701|issue:45325", + "issue:44186|issue:44265", + "issue:43606|issue:43819", + "issue:43262|issue:43746", + "issue:41720|issue:45823", + "issue:43454|issue:43550", + "issue:43377|issue:44610", + "issue:43377|issue:44898", + "issue:43454|issue:45072", + "issue:40990|issue:45584", + "issue:43572|issue:45759", + "issue:39692|issue:40444", + "issue:43526|issue:43883" + ], + "prepared_review_unit_hash": "9f9e616372c5fe7ea2b6e7c39740c8e65212cc8e0bd531526cecc16f6656a11c", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37587, + "estimated_input_tokens": 9397, + "estimated_eval_tokens": 19050 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly unrelated issue reports across different models/code paths. The Qwen2.5-VL position-id reports are the only close pair, but they look related rather than a confirmed duplicate; I\u2019d keep 45325 as the cluster anchor.", + "confidence": 0.78, + "canonical_issue_reason": "issue:45325 is the best anchor because it is earlier and more specific about the likely root path (`get_rope_index` / temporal position-id scaling), while 45381 reads as a related video-input symptom rather than a clearly identical bug.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45325 is the strongest representative for the Qwen2.5-VL position-id regression cluster: it is concrete, root-cause oriented, and precedes the later video report.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44265", + "right": "issue:45072", + "accept": false, + "reason": "Different failures: torch.export/torch_compilable_check vs bfloat16 dtype mismatch." + }, + { + "left": "issue:43632", + "right": "issue:45072", + "accept": false, + "reason": "Unrelated bugs: `_is_hf_initialized` breakage vs bfloat16 inference dtype mismatch." + }, + { + "left": "issue:43454", + "right": "issue:44466", + "accept": false, + "reason": "Both mention tied weights, but one is missing lm_head tying and the other is device-dependent serialization; different code paths." + }, + { + "left": "issue:43994", + "right": "issue:44898", + "accept": false, + "reason": "Different vision-model issues with different symptoms and mechanisms." + }, + { + "left": "issue:44079", + "right": "issue:44534", + "accept": false, + "reason": "ModelOutput key assignment is unrelated to non-persistent-buffer junk serialization." + }, + { + "left": "issue:45325", + "right": "issue:45834", + "accept": false, + "reason": "Both are multimodal indexing bugs, but the concrete models and failure modes differ (Qwen2.5-VL position IDs vs Kosmos2.5 OCR long-input indexing)." + }, + { + "left": "issue:43792", + "right": "issue:43957", + "accept": false, + "reason": "Whisper runtime failure is unrelated to meta-device loading breakage in other models." + }, + { + "left": "issue:42915", + "right": "issue:43482", + "accept": false, + "reason": "Different issues: FineGrainedFP8Config failure vs GGUF loading failure under v5." + }, + { + "left": "issue:44079", + "right": "issue:45072", + "accept": false, + "reason": "ModelOutput key handling is unrelated to dtype mismatches under bfloat16." + }, + { + "left": "issue:40444", + "right": "issue:45381", + "accept": false, + "reason": "Same family (Qwen2.5-VL) but different concrete bugs: multi-image finetuning vs video vision_position_ids." + }, + { + "left": "issue:43644", + "right": "issue:44079", + "accept": false, + "reason": "Non-persistent-buffer junk and ModelOutput key assignment are distinct regressions." + }, + { + "left": "issue:45325", + "right": "issue:45381", + "accept": false, + "reason": "Related Qwen2.5-VL position-id regressions, but the packet only supports plausible relatedness; the surfaces differ (still-image temporal scaling vs video `vision_position_ids`)." + }, + { + "left": "issue:44387", + "right": "issue:44617", + "accept": false, + "reason": "Different resource problems: int4 quantization memory regression vs video OOM." + }, + { + "left": "issue:43296", + "right": "issue:45800", + "accept": false, + "reason": "Different problems: PaddleOCR-VL loading failure vs torch/transformers version incompatibility." + }, + { + "left": "issue:44479", + "right": "issue:45823", + "accept": false, + "reason": "Device-related, but not the same concrete bug: Qwen VL video regression vs Gemma4 PLE forward mismatch." + }, + { + "left": "issue:43881", + "right": "issue:44488", + "accept": false, + "reason": "Different models and different loading failures." + }, + { + "left": "issue:35707", + "right": "issue:40444", + "accept": false, + "reason": "Progressive generation with inputs_embeds/past_key_values is unrelated to Qwen2.5-VL multi-image finetuning." + }, + { + "left": "issue:44291", + "right": "issue:44877", + "accept": false, + "reason": "Both are loading/config issues, but the specific failures are different (`init_empty_weights` argument vs strict granite_speech config)." + }, + { + "left": "issue:43317", + "right": "issue:43873", + "accept": false, + "reason": "Both involve offload/quantization, but the reported failures are not the same code-path bug." + }, + { + "left": "issue:43606", + "right": "issue:44265", + "accept": false, + "reason": "CPU offload device mismatch in bark-small is unrelated to torch.export failures in detection models." + }, + { + "left": "issue:43701", + "right": "issue:45325", + "accept": false, + "reason": "Checkpoint resume key mismatch is unrelated to Qwen2.5-VL position-id scaling." + }, + { + "left": "issue:44186", + "right": "issue:44265", + "accept": false, + "reason": "Tokenizer crashes on NER padding/truncation are unrelated to torch.export/torch_compilable_check." + }, + { + "left": "issue:43606", + "right": "issue:43819", + "accept": false, + "reason": "Different audio-model bugs: CPU-offload device mismatch vs DAC latent/STE mismatch." + }, + { + "left": "issue:43262", + "right": "issue:43746", + "accept": false, + "reason": "Audio processor sample-rate defaulting is unrelated to GraniteSpeech PEFT checkpoint loading." + }, + { + "left": "issue:41720", + "right": "issue:45823", + "accept": false, + "reason": "Different device-mapping failures in different models; no shared concrete bug." + }, + { + "left": "issue:43454", + "right": "issue:43550", + "accept": false, + "reason": "Weight-tying failure is unrelated to Bamba torch.compile SDPA failure." + }, + { + "left": "issue:43377", + "right": "issue:44610", + "accept": false, + "reason": "Missing padding-mask support in MIMI encoder is unrelated to OmDet processor resolution mismatch." + }, + { + "left": "issue:43377", + "right": "issue:44898", + "accept": false, + "reason": "Different models and symptoms; no shared underlying bug." + }, + { + "left": "issue:43454", + "right": "issue:45072", + "accept": false, + "reason": "Weight-tying bug is unrelated to bfloat16 dtype mismatch under CI inference." + }, + { + "left": "issue:40990", + "right": "issue:45584", + "accept": false, + "reason": "GPT-OSS perplexity regression is unrelated to Whisper empty-transcription generation failure." + }, + { + "left": "issue:43572", + "right": "issue:45759", + "accept": false, + "reason": "Missing pad_token_idx in StableLmConfig is unrelated to AutoModelForCausalLM.from_config text_config unwrapping." + }, + { + "left": "issue:39692", + "right": "issue:40444", + "accept": false, + "reason": "SigLIP2 doc-example errors are unrelated to Qwen2.5-VL multi-image finetuning failures." + }, + { + "left": "issue:43526", + "right": "issue:43883", + "accept": false, + "reason": "BEiT Fast label reduction bug is unrelated to Molmo tied-weights attribute failure." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The overall framing is mostly grounded, but the accepted 45325/45381 edge is a bit too strong for the packet alone. The titles show the same model/version and both mention position IDs, yet they describe different surfaces of the bug (still-image temporal scaling vs video `vision_position_ids`) and the packet does not provide explicit duplicate evidence. I would treat that pair as plausible/related rather than a definite duplicate; the rest of the soft-edge rejections look conservative." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 11, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:34634", + "issue:35707", + "issue:36331", + "issue:41720", + "issue:42617", + "issue:42915", + "issue:43296", + "issue:43316", + "issue:43317", + "issue:43322", + "issue:43404", + "issue:43450", + "issue:43454", + "issue:43550", + "issue:43577", + "issue:43606", + "issue:43708", + "issue:43720", + "issue:43749", + "issue:43792", + "issue:43873", + "issue:43881", + "issue:44008", + "issue:44186", + "issue:44387", + "issue:44423", + "issue:44466", + "issue:44479", + "issue:44534", + "issue:44610", + "issue:44683", + "issue:44756", + "issue:44877", + "issue:44898", + "issue:44913", + "issue:44918", + "issue:44977", + "issue:44991", + "issue:45072", + "issue:45081", + "issue:45357", + "issue:45406", + "issue:45632", + "issue:45684", + "issue:45701", + "issue:45704", + "issue:45812", + "issue:45823" + ], + "soft_pairs": [ + "issue:44466|issue:45357", + "issue:43881|issue:44991", + "issue:43792|issue:44683", + "issue:43296|issue:44877", + "issue:43454|issue:43720", + "issue:43873|issue:45701", + "issue:41720|issue:44977", + "issue:44008|issue:45823", + "issue:45632|issue:45684", + "issue:43404|issue:45357", + "issue:34634|issue:35707", + "issue:44423|issue:45406", + "issue:43577|issue:43708", + "issue:44186|issue:45072", + "issue:35707|issue:41720", + "issue:43873|issue:44756", + "issue:44877|issue:44991", + "issue:42617|issue:42915", + "issue:43749|issue:44534", + "issue:43450|issue:45701", + "issue:43550|issue:43720", + "issue:36331|issue:42915", + "issue:44610|issue:44898", + "issue:36331|issue:42617", + "issue:44186|issue:44610", + "issue:44387|issue:45704", + "issue:44479|issue:44918", + "issue:42915|issue:43317", + "issue:43550|issue:43606", + "issue:43316|issue:44913", + "issue:45081|issue:45812", + "issue:41720|issue:43322" + ], + "prepared_review_unit_hash": "480ab5f688ebfa18db4c56a4ed1f88c85378d2bfc88c05e1895bd9ade11d1eb2", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37355, + "estimated_input_tokens": 9339, + "estimated_eval_tokens": 18934 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These issues are mostly unrelated model-specific regressions and loading/runtime failures, with no strong duplicate cluster. I did not find any soft-edge pair that looks like the same underlying bug or change.", + "confidence": 0.9, + "canonical_issue_reason": "issue:43873 is the broadest and most central representative here, covering offloading/quantization behavior that overlaps the cluster\u2019s general loading/runtime theme.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43873 is the best single issue representative because it is open, broadly phrased, and has the strongest evidence of ongoing impact among the set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44466", + "right": "issue:45357", + "accept": false, + "reason": "Different bugs: lm_head tying/serialization by device vs incorrect visual encoder keys in Qwen3.5 save_pretrained." + }, + { + "left": "issue:43881", + "right": "issue:44991", + "accept": false, + "reason": "Different models and failure points: glm-4v-9b load failure vs tokenizer loading regression for EMBEDDIA/est-roberta." + }, + { + "left": "issue:43792", + "right": "issue:44683", + "accept": false, + "reason": "Whisper model runtime failure is unrelated to the torch>=2.9 compiled flex_attention regression." + }, + { + "left": "issue:43296", + "right": "issue:44877", + "accept": false, + "reason": "Different config-loading problems for different models; no shared underlying bug is clear." + }, + { + "left": "issue:43454", + "right": "issue:43720", + "accept": false, + "reason": "One is a weight-tying bug, the other is packed-weight unpacking during accelerate loading." + }, + { + "left": "issue:43873", + "right": "issue:45701", + "accept": false, + "reason": "Quantization/offload behavior and tokenizer changes are different code paths and symptoms." + }, + { + "left": "issue:41720", + "right": "issue:44977", + "accept": false, + "reason": "Both are Qwen family, but one is device-mapping CUDA assert and the other is flash-attention generation regression." + }, + { + "left": "issue:44008", + "right": "issue:45823", + "accept": false, + "reason": "Different Gemma bugs: variable-name collision in forward vs device mismatch with auto device map." + }, + { + "left": "issue:45632", + "right": "issue:45684", + "accept": false, + "reason": "Cache-path collisions and permission propagation are unrelated save/load issues." + }, + { + "left": "issue:43404", + "right": "issue:45357", + "accept": false, + "reason": "Mistral3 lm_head weight tying issue is unrelated to Qwen3.5 visual encoder key serialization." + }, + { + "left": "issue:34634", + "right": "issue:35707", + "accept": false, + "reason": "BarkProcessor voice_preset bug and progressive generation with inputs_embeds/past_key_values are different problems." + }, + { + "left": "issue:44423", + "right": "issue:45406", + "accept": false, + "reason": "Both crash in serve, but with different processors, attributes, and likely different root causes." + }, + { + "left": "issue:43577", + "right": "issue:43708", + "accept": false, + "reason": "BLIP2 dtype loading and trainer resume/max_steps calculation are unrelated." + }, + { + "left": "issue:44186", + "right": "issue:45072", + "accept": false, + "reason": "Tokenizer NER/padding crash and bf16 dtype mismatch are different failure classes." + }, + { + "left": "issue:35707", + "right": "issue:41720", + "accept": false, + "reason": "Generation with inputs_embeds/past_key_values is unrelated to a Qwen3 device-mapping CUDA assert." + }, + { + "left": "issue:43873", + "right": "issue:44756", + "accept": false, + "reason": "Quantization offloading problems are not the same as disabling mmap to avoid OOM on Strix Halo." + }, + { + "left": "issue:44877", + "right": "issue:44991", + "accept": false, + "reason": "Strict config loading for granite_speech and tokenizer loading regression for est-roberta are unrelated." + }, + { + "left": "issue:42617", + "right": "issue:42915", + "accept": false, + "reason": "A 3d_parallel.py runtime problem is unrelated to Qwen3Moe failing with FineGrainedFP8Config." + }, + { + "left": "issue:43749", + "right": "issue:44534", + "accept": false, + "reason": "FSDP CPU-efficient loading and non-persistent buffer junk are different loading bugs." + }, + { + "left": "issue:43450", + "right": "issue:45701", + "accept": false, + "reason": "Batched video processor shape mismatch is unrelated to tokenizer changes across versions." + }, + { + "left": "issue:43550", + "right": "issue:43606", + "accept": false, + "reason": "torch.compile+SDPA failure for Bamba is unrelated to Bark CPU-offload device mismatch." + }, + { + "left": "issue:36331", + "right": "issue:42915", + "accept": false, + "reason": "Trainer compute_loss signature breakage is unrelated to Qwen3Moe FP8 config loading." + }, + { + "left": "issue:44610", + "right": "issue:44898", + "accept": false, + "reason": "Both involve vision input sizing, but they affect different models and different root causes." + }, + { + "left": "issue:36331", + "right": "issue:42617", + "accept": false, + "reason": "Unexpected compute_loss argument and 3d_parallel.py execution failure are unrelated." + }, + { + "left": "issue:44186", + "right": "issue:44610", + "accept": false, + "reason": "Tokenizer crash and processor image-size mismatch do not indicate the same bug." + }, + { + "left": "issue:44387", + "right": "issue:45704", + "accept": false, + "reason": "Int4 quantization OOM from reserved memory growth is unrelated to apex RMSNorm memory leak." + }, + { + "left": "issue:44479", + "right": "issue:44918", + "accept": false, + "reason": "Video-input regression in Qwen models and trl SFT unpacking of input embeddings are different bugs." + }, + { + "left": "issue:42915", + "right": "issue:43317", + "accept": false, + "reason": "Both mention loading/offload, but one is FP8 config failure and the other is gpu+cpu offload with dequantized models." + }, + { + "left": "issue:43550", + "right": "issue:43606", + "accept": false, + "reason": "These are different offload/compile/device-mismatch issues and not the same code-path problem." + }, + { + "left": "issue:43316", + "right": "issue:44913", + "accept": false, + "reason": "Config API discrepancy for Gemma3TextConfig is unrelated to GPTNeoX rotary_pct reload behavior." + }, + { + "left": "issue:45081", + "right": "issue:45812", + "accept": false, + "reason": "Mistral tokenizer regex patch crash and Granite token-id regression are different tokenizer bugs." + }, + { + "left": "issue:41720", + "right": "issue:43322", + "accept": false, + "reason": "Qwen3 device-map CUDA assert and Llava Next segfault are unrelated model-loading failures." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 12, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:30064", + "issue:34567", + "issue:34634", + "issue:35707", + "issue:36010", + "issue:40990", + "issue:41720", + "issue:42617", + "issue:42915", + "issue:43295", + "issue:43322", + "issue:43388", + "issue:43421", + "issue:43526", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43572", + "issue:43606", + "issue:43653", + "issue:43720", + "issue:43782", + "issue:43873", + "issue:43881", + "issue:43927", + "issue:44186", + "issue:44361", + "issue:44368", + "issue:44451", + "issue:44492", + "issue:44509", + "issue:44514", + "issue:44545", + "issue:44671", + "issue:44743", + "issue:44779", + "issue:44991", + "issue:45059", + "issue:45161", + "issue:45357", + "issue:45406", + "issue:45464", + "issue:45701", + "issue:45704", + "issue:45759", + "issue:45812", + "issue:45859" + ], + "soft_pairs": [ + "issue:43295|issue:45701", + "issue:40990|issue:45701", + "issue:43526|issue:43881", + "issue:41720|issue:45161", + "issue:43531|issue:43572", + "issue:43421|issue:45812", + "issue:44671|issue:44743", + "issue:41720|issue:42617", + "issue:36010|issue:42617", + "issue:43540|issue:43782", + "issue:44186|issue:44361", + "issue:45406|issue:45464", + "issue:30064|issue:34634", + "issue:43421|issue:45701", + "issue:44492|issue:44509", + "issue:44779|issue:45812", + "issue:42915|issue:43322", + "issue:43606|issue:43720", + "issue:43550|issue:43653", + "issue:43388|issue:45059", + "issue:44514|issue:44545", + "issue:43531|issue:45759", + "issue:43606|issue:43653", + "issue:43421|issue:43927", + "issue:34567|issue:35707", + "issue:44368|issue:45357", + "issue:44451|issue:44991", + "issue:43873|issue:45704", + "issue:45759|issue:45859" + ], + "prepared_review_unit_hash": "4afc43e7ac7ba007b388b47616ff9143510ebc042bea816ba83c0b296a2412b4", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 35702, + "estimated_input_tokens": 8926, + "estimated_eval_tokens": 18108 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly heterogeneous: many unrelated model-specific bugs and regressions were grouped by broad tokenizer/processor similarity. The only clear duplicate pair is the Qwen2_5_VLProcessor batching crash (issues 44514/44545).", + "confidence": 0.93, + "canonical_issue_reason": "issue:44545 is the best canonical choice because it is an exact duplicate of 44514, has slightly higher activity, and the title/body are the cleaner target for consolidation.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44545 is the only strong duplicate anchor in this cluster; the rest of the items are not the same underlying bug, so it is the safest representative issue.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43295", + "right": "issue:45701", + "accept": false, + "reason": "Both mention tokenization-related regressions, but one is a processor/tokenizer API regression and the other is a broad tokenization behavior change; not the same bug." + }, + { + "left": "issue:40990", + "right": "issue:45701", + "accept": false, + "reason": "High perplexity on a specific model is not the same as a general tokenization change regression." + }, + { + "left": "issue:43526", + "right": "issue:43881", + "accept": false, + "reason": "Different models and failure modes: BeitImageProcessor label reduction vs glm-4v loading failure." + }, + { + "left": "issue:41720", + "right": "issue:45161", + "accept": false, + "reason": "Both involve Qwen3/MoE and device mapping, but one is a CUDA assert and the other is a tensor-parallel-only issue; different code paths." + }, + { + "left": "issue:43531", + "right": "issue:43572", + "accept": false, + "reason": "Sliding-window behavior in Qwen3-MoE is unrelated to a missing pad_token_idx in StableLmConfig." + }, + { + "left": "issue:43421", + "right": "issue:45812", + "accept": false, + "reason": "Both concern tokenizers, but one is runtime post-processor updates and the other is wrong token IDs for Granite models; not the same defect." + }, + { + "left": "issue:44671", + "right": "issue:44743", + "accept": false, + "reason": "CamemBERT masked-LM prediction errors and Qwen recurrent-state reset are different model internals and bugs." + }, + { + "left": "issue:41720", + "right": "issue:42617", + "accept": false, + "reason": "Qwen3 auto device mapping CUDA assert is unrelated to a 3d_parallel.py execution failure." + }, + { + "left": "issue:36010", + "right": "issue:42617", + "accept": false, + "reason": "Importing GenerationMixin and running 3d_parallel.py are unrelated failures." + }, + { + "left": "issue:43540", + "right": "issue:43782", + "accept": false, + "reason": "Video input processing in Qwen3OmniMoe is not the same as a weight_only loading error in Qwen3VL." + }, + { + "left": "issue:44186", + "right": "issue:44361", + "accept": false, + "reason": "Both are tokenizer/task issues, but they affect different tokenizers and failure modes; not a shared underlying bug." + }, + { + "left": "issue:45406", + "right": "issue:45464", + "accept": false, + "reason": "Gemma4Processor missing _tokenizer in serve is unrelated to Qwen3.5 streaming inference failures." + }, + { + "left": "issue:30064", + "right": "issue:34634", + "accept": false, + "reason": "Image processor void segmentation maps and BarkProcessor voice_preset are unrelated processor bugs." + }, + { + "left": "issue:43421", + "right": "issue:45701", + "accept": false, + "reason": "Runtime special-token/post-processor updates do not match a broad tokenization regression across versions." + }, + { + "left": "issue:44492", + "right": "issue:44509", + "accept": false, + "reason": "A typo in cache strategy docs is unrelated to removed pipeline-task documentation." + }, + { + "left": "issue:44779", + "right": "issue:45812", + "accept": false, + "reason": "Deepseek tokenizer regression and Granite tokenizer regression are separate model-specific bugs." + }, + { + "left": "issue:42915", + "right": "issue:43322", + "accept": false, + "reason": "Qwen3Moe FP8 config failure and Llava Next segmentation fault are different failures in different subsystems." + }, + { + "left": "issue:43606", + "right": "issue:43720", + "accept": false, + "reason": "CPU offload device mismatch in Bark is unrelated to BitNet packed-weight unpacking during accelerate loading." + }, + { + "left": "issue:43550", + "right": "issue:43653", + "accept": false, + "reason": "Bamba torch.compile SDPA failure and BigBird tokenizer special-token registration are unrelated." + }, + { + "left": "issue:43388", + "right": "issue:45059", + "accept": false, + "reason": "Metric gathering label truncation and SAM3 text/bounding-box behavior are different bugs." + }, + { + "left": "issue:44514", + "right": "issue:44545", + "accept": true, + "reason": "Same title and same crash scenario; 44545 is a clear duplicate of 44514." + }, + { + "left": "issue:43531", + "right": "issue:45759", + "accept": false, + "reason": "Qwen3-MoE sliding-window behavior and unwrapping text_config for composite configs are distinct generation/model-construction bugs." + }, + { + "left": "issue:43606", + "right": "issue:43653", + "accept": false, + "reason": "Bark CPU offload device mismatch and BigBird mask-token registration are unrelated issues." + }, + { + "left": "issue:43421", + "right": "issue:43927", + "accept": false, + "reason": "Updating post-processors when special tokens change is different from saving/loading DiaConfig custom token IDs." + }, + { + "left": "issue:34567", + "right": "issue:35707", + "accept": false, + "reason": "TrainerState token counter not updating and progressive generation with inputs_embeds/past_key_values are unrelated." + }, + { + "left": "issue:44368", + "right": "issue:45357", + "accept": false, + "reason": "A config warning about tie_word_embeddings is not the same as saving incorrect visual encoder keys." + }, + { + "left": "issue:44451", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer-loading regressions, but they affect different models and likely different tokenizer files/code paths." + }, + { + "left": "issue:43873", + "right": "issue:45704", + "accept": false, + "reason": "Quantization/offloading problems are unrelated to a T5 apex RMSNorm memory leak." + }, + { + "left": "issue:45759", + "right": "issue:45859", + "accept": false, + "reason": "Composite-config unwrapping and CPU-offload incompatibility in rotary embedding are different bugs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Grounded and conservative. The cluster summary matches the packet: most items are clearly heterogeneous by title/body, and the 44514/44545 pair is the only obvious duplicate with near-identical titles and consistent activity. The soft-edge rejections are appropriately cautious and do not overclaim beyond the packet." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 13, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:30064", + "issue:33666", + "issue:34634", + "issue:35707", + "issue:36010", + "issue:39692", + "issue:41720", + "issue:42886", + "issue:42915", + "issue:43381", + "issue:43421", + "issue:43525", + "issue:43531", + "issue:43540", + "issue:43596", + "issue:43618", + "issue:43653", + "issue:43697", + "issue:43746", + "issue:43782", + "issue:43844", + "issue:43873", + "issue:43994", + "issue:44008", + "issue:44062", + "issue:44186", + "issue:44220", + "issue:44451", + "issue:44589", + "issue:44610", + "issue:44625", + "issue:44661", + "issue:44671", + "issue:44843", + "issue:44898", + "issue:44918", + "issue:44936", + "issue:44987", + "issue:45042", + "issue:45072", + "issue:45081", + "issue:45356", + "issue:45381", + "issue:45479", + "issue:45588", + "issue:45704", + "issue:45759", + "issue:45859" + ], + "soft_pairs": [ + "issue:44898|issue:45072", + "issue:41720|issue:43746", + "issue:44062|issue:44451", + "issue:44987|issue:45042", + "issue:43531|issue:44589", + "issue:33666|issue:35707", + "issue:43421|issue:43653", + "issue:45588|issue:45759", + "issue:42886|issue:44843", + "issue:43381|issue:43844", + "issue:39692|issue:44610", + "issue:44918|issue:44936", + "issue:43421|issue:44186", + "issue:43525|issue:43531", + "issue:44625|issue:45479", + "issue:45704|issue:45859", + "issue:45081|issue:45356", + "issue:43782|issue:45381", + "issue:34634|issue:41720", + "issue:43994|issue:44671", + "issue:43381|issue:45704", + "issue:39692|issue:43873", + "issue:42915|issue:45759", + "issue:43596|issue:44220", + "issue:43540|issue:44008", + "issue:43618|issue:43697", + "issue:44220|issue:44661", + "issue:30064|issue:36010" + ], + "prepared_review_unit_hash": "d8a87b8a179bbee28fc05bdbf7c2a672e66c418ecea1e494b2d6fef9378def78", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36230, + "estimated_input_tokens": 9058, + "estimated_eval_tokens": 18372 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is a heterogeneous collection of unrelated issues. Several pairs share broad themes like tokenizers, multimodal models, or offloading, but none look like the same concrete bug/change.", + "confidence": 0.94, + "canonical_issue_reason": "issue:43873 is the most broadly scoped and most actively discussed item in the set (offloading/quantization with the highest inbound attention), so it is the least bad representative if one must be chosen. It is not, however, a true duplicate umbrella for the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43873 is the strongest global representative because it has the broadest impact and most discussion, but the cluster is too mixed to treat it as a real canonical duplicate target.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44898", + "right": "issue:45072", + "accept": false, + "reason": "Both involve vision/image-processing behavior, but one is a Perceiver resolution bug and the other is a bfloat16 dtype mismatch in different models/code paths." + }, + { + "left": "issue:41720", + "right": "issue:43746", + "accept": false, + "reason": "These are unrelated model-loading/runtime failures: Qwen3 device-mapping CUDA asserts versus GraniteSpeech PEFT local checkpoint loading." + }, + { + "left": "issue:44062", + "right": "issue:44451", + "accept": false, + "reason": "Both are loading-related, but one is an AddedToken argument clash and the other is a model-specific failure to load ScandiBERT. Different root causes." + }, + { + "left": "issue:44987", + "right": "issue:45042", + "accept": false, + "reason": "One is a failure loading a specific model on newer transformers, the other is an image processor backend dependency regression. Not the same bug." + }, + { + "left": "issue:43531", + "right": "issue:44589", + "accept": false, + "reason": "These are different issues: a Qwen3-MoE sliding-window problem versus a Float8 storage lookup error." + }, + { + "left": "issue:33666", + "right": "issue:35707", + "accept": false, + "reason": "Multi-GPU training for Qwen2-VL is unrelated to progressive generation with inputs_embeds/past_key_values." + }, + { + "left": "issue:43421", + "right": "issue:43653", + "accept": false, + "reason": "Both touch special tokens, but one is runtime post-processor updating and the other is BigBirdTokenizer mask-token registration. Similar area, different bug." + }, + { + "left": "issue:45588", + "right": "issue:45759", + "accept": false, + "reason": "Flash-attention sink handling and composite Qwen config unwrapping are unrelated code paths." + }, + { + "left": "issue:42886", + "right": "issue:44843", + "accept": false, + "reason": "Both mention offline tokenization, but 44843 is specifically the Mistral regex patch calling model_info(), while 42886 is a broader cache-load failure." + }, + { + "left": "issue:43381", + "right": "issue:43844", + "accept": false, + "reason": "Gradient checkpointing in eval mode is not the same as gradients increasing under DeepSpeed ZeRO-3." + }, + { + "left": "issue:39692", + "right": "issue:44610", + "accept": false, + "reason": "Both involve vision processor/model mismatch, but one is a SigLIP2 doc example/quantization issue and the other is OmDet-Turbo input-size mismatch." + }, + { + "left": "issue:44918", + "right": "issue:44936", + "accept": false, + "reason": "Training with Qwen3.5 embeddings/trainer unpacking is unrelated to trainer.evaluate() failing after train()." + }, + { + "left": "issue:43421", + "right": "issue:44186", + "accept": false, + "reason": "Both are tokenizer-related, but NER padding/truncation crashes and runtime special-token post-processing are different concrete failures." + }, + { + "left": "issue:43525", + "right": "issue:43531", + "accept": false, + "reason": "Llama4Config missing pad_token_id and Qwen3-MoE sliding_window behavior are unrelated configuration bugs." + }, + { + "left": "issue:44625", + "right": "issue:45479", + "accept": false, + "reason": "One is propagation of num_labels into text config; the other is degenerate zero loss for single-label classification. Same broad area, different bug." + }, + { + "left": "issue:45704", + "right": "issue:45859", + "accept": false, + "reason": "T5 apex RMSNorm memory leak and Qwen3_5Moe CPU-offload incompatibility are unrelated." + }, + { + "left": "issue:45081", + "right": "issue:45356", + "accept": false, + "reason": "Both involve fix_mistral_regex, but one is an AttributeError crash and the other is a tokenizer regression with codec handling/warning issues. Not the same concrete fix." + }, + { + "left": "issue:43782", + "right": "issue:45381", + "accept": false, + "reason": "Qwen3VL weight_only loading and Qwen2.5-VL video vision_position_ids are distinct multimodal failures." + }, + { + "left": "issue:34634", + "right": "issue:41720", + "accept": false, + "reason": "BarkProcessor voice_preset and Qwen3 auto device mapping are unrelated model/processor bugs." + }, + { + "left": "issue:43994", + "right": "issue:44671", + "accept": false, + "reason": "SigLIP2 inference nonsense and CamemBERT masked-LM predictions in v5 are different model-specific regressions." + }, + { + "left": "issue:43381", + "right": "issue:45704", + "accept": false, + "reason": "Gradient checkpointing eval-mode behavior and T5 RMSNorm memory leak do not share the same underlying code path." + }, + { + "left": "issue:39692", + "right": "issue:43873", + "accept": false, + "reason": "SigLIP2 example/model mismatch and offloading-with-quantization are unrelated issues." + }, + { + "left": "issue:42915", + "right": "issue:45759", + "accept": false, + "reason": "Qwen3Moe FineGrainedFP8Config failure is not the same as composite Qwen config text_config unwrapping." + }, + { + "left": "issue:43596", + "right": "issue:44220", + "accept": false, + "reason": "DeepSpeed ZeRO-3/BertModel index error and _torch_extract_fbank_features() are different runtime failures." + }, + { + "left": "issue:43540", + "right": "issue:44008", + "accept": false, + "reason": "Video processing ValueError in Qwen3OmniMoe and Gemma 3n audio_mel_mask tensor/name collision are unrelated." + }, + { + "left": "issue:43618", + "right": "issue:43697", + "accept": false, + "reason": "CLIPOutput attentions assignment and RTDetrV2 output differences in v5 are separate model behavior changes." + }, + { + "left": "issue:44220", + "right": "issue:44661", + "accept": false, + "reason": "Audio feature extraction and add-new-model-like failing inside TOKENIZER_MAPPING_NAMES are unrelated tokenizer/model registry issues." + }, + { + "left": "issue:30064", + "right": "issue:36010", + "accept": false, + "reason": "Void segmentation map processing and GenerationMixin import failure are completely different subsystems 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": 2, + "component_count": 16, + "review_unit_index": 14, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:42915", + "issue:43295", + "issue:43322", + "issue:43335", + "issue:43421", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43577", + "issue:43643", + "issue:43653", + "issue:43716", + "issue:43720", + "issue:43746", + "issue:43756", + "issue:43782", + "issue:43818", + "issue:43819", + "issue:43825", + "issue:43873", + "issue:43994", + "issue:44008", + "issue:44062", + "issue:44077", + "issue:44186", + "issue:44448", + "issue:44485", + "issue:44488", + "issue:44509", + "issue:44561", + "issue:44625", + "issue:44671", + "issue:44811", + "issue:44821", + "issue:44843", + "issue:44877", + "issue:44898", + "issue:44977", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45084", + "issue:45183", + "issue:45381", + "issue:45479", + "issue:45584", + "issue:45685", + "issue:45834" + ], + "soft_pairs": [ + "issue:43335|issue:43756", + "issue:43720|issue:43819", + "issue:45183|issue:45479", + "issue:44077|issue:44625", + "issue:43653|issue:43720", + "issue:43716|issue:44008", + "issue:42915|issue:43746", + "issue:43295|issue:45834", + "issue:43746|issue:45381", + "issue:43746|issue:43873", + "issue:43550|issue:45072", + "issue:43550|issue:43819", + "issue:44186|issue:44898", + "issue:44843|issue:45081", + "issue:44062|issue:44488", + "issue:43577|issue:43818", + "issue:43531|issue:43643", + "issue:43643|issue:44877", + "issue:43421|issue:44811", + "issue:43540|issue:45381", + "issue:43653|issue:43819", + "issue:44448|issue:44671", + "issue:43782|issue:44977", + "issue:45584|issue:45834", + "issue:44821|issue:45084", + "issue:43322|issue:45685", + "issue:43825|issue:43994", + "issue:44561|issue:45020", + "issue:44485|issue:44509" + ], + "prepared_review_unit_hash": "6100093784cf24e124a8a400cb4b226df7eb428dbce863945a71bce820e991e3", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36668, + "estimated_input_tokens": 9167, + "estimated_eval_tokens": 18590 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a set of unrelated model-specific regressions. I found no convincing duplicate issue/PR pairs; the only broadly representative issue is the open remote_code regression umbrella.", + "confidence": 0.89, + "canonical_issue_reason": "Issue 45020 is the broadest umbrella in the set (\u201cremote_code\u201d regressions) and is the closest thing to a cluster anchor, though most items are not true duplicates.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45020 is the best representative anchor because it captures the only cross-cutting theme in the cluster; the rest are separate model or tokenizer bugs.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43335", + "right": "issue:43756", + "accept": false, + "reason": "Different model families and failures: sparse-layer config bug vs RoPE-layer mismatch." + }, + { + "left": "issue:43720", + "right": "issue:43819", + "accept": false, + "reason": "Different code paths: packed-weight loading in BitNet vs DAC latent decoding/STE mismatch." + }, + { + "left": "issue:45183", + "right": "issue:45479", + "accept": false, + "reason": "Input validation error handling vs single-label loss degeneracy are unrelated bugs." + }, + { + "left": "issue:44077", + "right": "issue:44625", + "accept": false, + "reason": "PatchTSMixer post-init policy and Qwen3.5 num_labels propagation are unrelated model config issues." + }, + { + "left": "issue:43653", + "right": "issue:43720", + "accept": false, + "reason": "Tokenizer special-token registration bug vs BitNet packed-weight loading bug; different subsystems." + }, + { + "left": "issue:43716", + "right": "issue:44008", + "accept": false, + "reason": "Both are multimodal, but one is a dtype mismatch and the other is a variable-name collision causing AttributeError." + }, + { + "left": "issue:42915", + "right": "issue:43746", + "accept": false, + "reason": "Qwen3Moe FP8 loading failure and GraniteSpeech PEFT local-checkpoint loading are unrelated." + }, + { + "left": "issue:43295", + "right": "issue:45834", + "accept": false, + "reason": "Processor/tokenizer regression and Kosmos2.5 long-OCR index error are different failure modes." + }, + { + "left": "issue:43746", + "right": "issue:45381", + "accept": false, + "reason": "GraniteSpeech PEFT loading and Qwen2.5-VL video position IDs are unrelated issues." + }, + { + "left": "issue:43746", + "right": "issue:43873", + "accept": false, + "reason": "PEFT checkpoint loading is unrelated to quantization/offloading behavior." + }, + { + "left": "issue:43550", + "right": "issue:45072", + "accept": false, + "reason": "Different models and bugs: torch.compile+SDPA failure vs dtype mismatch in bfloat16 inference." + }, + { + "left": "issue:43550", + "right": "issue:43819", + "accept": false, + "reason": "No shared concrete code path; Bamba compile/SDPA issue is unrelated to DAC latent mismatch." + }, + { + "left": "issue:44186", + "right": "issue:44898", + "accept": false, + "reason": "Tokenizer NER/padding crash and Perceiver interpolation issue are different subsystems." + }, + { + "left": "issue:44843", + "right": "issue:45081", + "accept": false, + "reason": "Both touch _patch_mistral_regex, but one is an offline model_info call and the other is an AttributeError on tokenizer backend; distinct bugs." + }, + { + "left": "issue:44062", + "right": "issue:44488", + "accept": false, + "reason": "AddedToken keyword duplication is unrelated to loading cjvt/sleng-bert." + }, + { + "left": "issue:43577", + "right": "issue:43818", + "accept": false, + "reason": "BLIP2 dtype propagation and Video-LLaVA temporal-attention/weight-sharing are unrelated." + }, + { + "left": "issue:43531", + "right": "issue:43643", + "accept": false, + "reason": "Sliding-window Qwen3-MoE bug and trust_remote_code AutoConfig field loss are unrelated." + }, + { + "left": "issue:43643", + "right": "issue:44877", + "accept": false, + "reason": "Both involve config loading, but one is missing fields from trust_remote_code and the other is strict config rejection; not the same bug." + }, + { + "left": "issue:43421", + "right": "issue:44811", + "accept": false, + "reason": "Runtime special-token post-processing update and Whisper batch_decode skip_special_tokens behavior are different tokenizer bugs." + }, + { + "left": "issue:43540", + "right": "issue:45381", + "accept": false, + "reason": "Qwen3OmniMoe video-input ValueError and Qwen2.5-VL vision_position_ids are different model-specific issues." + }, + { + "left": "issue:43653", + "right": "issue:43819", + "accept": false, + "reason": "Tokenizer special-token decode bug and DAC latent conversion mismatch are unrelated." + }, + { + "left": "issue:44448", + "right": "issue:44671", + "accept": false, + "reason": "Both are regression reports, but on different models and different output paths." + }, + { + "left": "issue:43782", + "right": "issue:44977", + "accept": false, + "reason": "Qwen3VL weight_only loading error and Qwen3.5 flash-attention generation issue are different code paths." + }, + { + "left": "issue:45584", + "right": "issue:45834", + "accept": false, + "reason": "Whisper empty-transcription failure and Kosmos2.5 long OCR input error are unrelated." + }, + { + "left": "issue:44821", + "right": "issue:45084", + "accept": false, + "reason": "AutoImageProcessor URL loading and template-node compilation errors are unrelated." + }, + { + "left": "issue:43322", + "right": "issue:45685", + "accept": false, + "reason": "Llava Next segmentation fault and MPS histogram-on-Int error are unrelated." + }, + { + "left": "issue:43825", + "right": "issue:43994", + "accept": false, + "reason": "Pipeline error messaging and SigLIP2 output quality are unrelated issues." + }, + { + "left": "issue:44561", + "right": "issue:45020", + "accept": false, + "reason": "Issue 44561 is one specific remote_code regression cause; 45020 is a broad umbrella and not the same concrete bug." + }, + { + "left": "issue:44485", + "right": "issue:44509", + "accept": false, + "reason": "GLM-5 RoPE implementation discussion and stale v5 docs are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 15, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:30064", + "issue:34634", + "issue:36010", + "issue:36331", + "issue:39692", + "issue:42175", + "issue:43262", + "issue:43329", + "issue:43404", + "issue:43452", + "issue:43526", + "issue:43577", + "issue:43582", + "issue:43606", + "issue:43644", + "issue:43650", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43749", + "issue:43782", + "issue:43819", + "issue:43825", + "issue:43827", + "issue:43906", + "issue:44060", + "issue:44186", + "issue:44368", + "issue:44442", + "issue:44479", + "issue:44610", + "issue:44671", + "issue:44805", + "issue:44857", + "issue:44936", + "issue:44991", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45084", + "issue:45406", + "issue:45459", + "issue:45538", + "issue:45600", + "issue:45701", + "issue:45803", + "issue:45834" + ], + "soft_pairs": [ + "issue:30064|issue:36331", + "issue:39692|issue:45834", + "issue:44479|issue:45834", + "issue:43825|issue:43827", + "issue:44186|issue:44442", + "issue:43606|issue:45072", + "issue:43577|issue:43582", + "issue:34634|issue:36010", + "issue:44805|issue:44936", + "issue:43452|issue:44991", + "issue:42175|issue:45081", + "issue:44610|issue:45072", + "issue:43720|issue:45072", + "issue:45081|issue:45406", + "issue:43404|issue:43782", + "issue:44060|issue:44368", + "issue:43650|issue:43906", + "issue:44671|issue:45701", + "issue:43582|issue:44857", + "issue:43262|issue:43819", + "issue:43526|issue:43697", + "issue:45459|issue:45803", + "issue:45084|issue:45538", + "issue:43644|issue:43749", + "issue:43329|issue:45600", + "issue:43742|issue:45020" + ], + "prepared_review_unit_hash": "cd5d33c9e4f3c900ea0af7244a23dd49df8a6dd488f43f1723d891277377e330", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 26, + "serialized_chars": 35160, + "estimated_input_tokens": 8790, + "estimated_eval_tokens": 17836 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The candidate pairs are largely false positives: they span unrelated bugs, models, and code paths. No PR pairs are present. If a single issue must anchor this heterogeneous set, the broadest regression report is issue 45020.", + "confidence": 0.71, + "canonical_issue_reason": "Issue 45020 is the broadest, most umbrella-like report in the set and the only one framed as a general recent-version regression affecting remote_code models; it is the closest thing to a cluster anchor, though the cluster itself is heterogeneous.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45020 is the best representative of the set because its scope is broader than the model-specific tokenizer/processor bugs and it captures a version-regression theme that could plausibly subsume nearby reports, even if it is not a true duplicate of them.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:30064", + "right": "issue:36331", + "accept": false, + "reason": "Different failures in different components: image processor segmentation-map handling vs trainer custom loss kwargs." + }, + { + "left": "issue:39692", + "right": "issue:45834", + "accept": false, + "reason": "Unrelated models and symptoms: SigLIP2 doc example errors vs Kosmos2.5 long-OCR index error." + }, + { + "left": "issue:44479", + "right": "issue:45834", + "accept": false, + "reason": "Both are vision/multimodal regressions, but one is a video-input regression and the other is an OCR long-input index error." + }, + { + "left": "issue:43825", + "right": "issue:43827", + "accept": false, + "reason": "Related to pipeline deprecations, but one is an error-message wording bug and the other is stale documentation; not the same underlying issue." + }, + { + "left": "issue:44186", + "right": "issue:44442", + "accept": false, + "reason": "Both are tokenizer-related, but they concern different tokenizers and different failure modes." + }, + { + "left": "issue:43606", + "right": "issue:45072", + "accept": false, + "reason": "Device-mismatch during CPU offload vs dtype mismatches in bfloat16 inference are distinct code paths and bugs." + }, + { + "left": "issue:43577", + "right": "issue:43582", + "accept": false, + "reason": "Blip2 dtype-loading bug is unrelated to an Apple Silicon TypeError in caching allocator warmup." + }, + { + "left": "issue:34634", + "right": "issue:36010", + "accept": false, + "reason": "BarkProcessor voice preset behavior and a GenerationMixin import error are unrelated." + }, + { + "left": "issue:44805", + "right": "issue:44936", + "accept": false, + "reason": "Generic mask-shape IndexError vs trainer.evaluate() failing after train() are not the same failure." + }, + { + "left": "issue:43452", + "right": "issue:44991", + "accept": false, + "reason": "Both are loading failures, but one is gguf_file handling and the other is a tokenizer compatibility regression." + }, + { + "left": "issue:42175", + "right": "issue:45081", + "accept": false, + "reason": "Backend-install packaging issue vs Mistral tokenizer regex crash; no shared underlying bug." + }, + { + "left": "issue:44610", + "right": "issue:45072", + "accept": false, + "reason": "Processor input-size mismatch is unrelated to dtype mismatch inference failures." + }, + { + "left": "issue:43720", + "right": "issue:45072", + "accept": false, + "reason": "Packed-weight loading bug in BitNet is unrelated to dtype mismatches." + }, + { + "left": "issue:45081", + "right": "issue:45406", + "accept": false, + "reason": "Both are attribute errors in loading/serving, but they involve different models, different missing attributes, and different code paths." + }, + { + "left": "issue:43404", + "right": "issue:43782", + "accept": false, + "reason": "Mistral weight tying and Qwen3VL weight_only loading are distinct model bugs." + }, + { + "left": "issue:44060", + "right": "issue:44368", + "accept": false, + "reason": "Both mention tied-weights warnings, but one is an incorrect internal tying bug and the other is a config warning during fine-tuning." + }, + { + "left": "issue:43650", + "right": "issue:43906", + "accept": false, + "reason": "Placeholder issue title and a reproduction of another issue are not the same underlying bug." + }, + { + "left": "issue:44671", + "right": "issue:45701", + "accept": false, + "reason": "Masked-LM prediction regression and tokenization changes are different symptoms and likely different fixes." + }, + { + "left": "issue:43582", + "right": "issue:44857", + "accept": false, + "reason": "Apple Silicon allocator TypeError vs CUDA AMP loss crash are unrelated." + }, + { + "left": "issue:43262", + "right": "issue:43819", + "accept": false, + "reason": "Sampling-rate defaulting in audio chat templates is unrelated to DAC latent reconstruction mismatch." + }, + { + "left": "issue:43526", + "right": "issue:43697", + "accept": false, + "reason": "BEiT label reduction bug and RTDetrV2 output divergence are different model-specific regressions." + }, + { + "left": "issue:45459", + "right": "issue:45803", + "accept": false, + "reason": "Both involve exception handling, but they are separate code paths and separate bugs." + }, + { + "left": "issue:45084", + "right": "issue:45538", + "accept": false, + "reason": "Template compilation TypeError and CLIPTokenizer max length are unrelated." + }, + { + "left": "issue:43644", + "right": "issue:43749", + "accept": false, + "reason": "Non-persistent buffer junk-fill vs FSDP CPU RAM-efficient loading are different loading issues." + }, + { + "left": "issue:43329", + "right": "issue:45600", + "accept": false, + "reason": "Multimodal token counting video-branch bug is unrelated to stale auto_mappings config references." + }, + { + "left": "issue:43742", + "right": "issue:45020", + "accept": false, + "reason": "Specific KeyError for one model load is not the same as a broad remote_code regression." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 16, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:34567", + "issue:34634", + "issue:36010", + "issue:36331", + "issue:38175", + "issue:39692", + "issue:40990", + "issue:43257", + "issue:43262", + "issue:43329", + "issue:43450", + "issue:43454", + "issue:43526", + "issue:43531", + "issue:43550", + "issue:43577", + "issue:43606", + "issue:43638", + "issue:43643", + "issue:43645", + "issue:43653", + "issue:43697", + "issue:43720", + "issue:43746", + "issue:43749", + "issue:43819", + "issue:43854", + "issue:43927", + "issue:43931", + "issue:44291", + "issue:44479", + "issue:44554", + "issue:44568", + "issue:44589", + "issue:44610", + "issue:44811", + "issue:44849", + "issue:44912", + "issue:44936", + "issue:44977", + "issue:45042", + "issue:45356", + "issue:45357", + "issue:45488", + "issue:45701", + "issue:45759", + "issue:45823", + "issue:45859" + ], + "soft_pairs": [ + "issue:43653|issue:44912", + "issue:43638|issue:44936", + "issue:43746|issue:44811", + "issue:44589|issue:45042", + "issue:43854|issue:44977", + "issue:38175|issue:44610", + "issue:39692|issue:44912", + "issue:43526|issue:44554", + "issue:36010|issue:43645", + "issue:34634|issue:36331", + "issue:43819|issue:43927", + "issue:43454|issue:43577", + "issue:43257|issue:43329", + "issue:43720|issue:44610", + "issue:43550|issue:44912", + "issue:44568|issue:45488", + "issue:43749|issue:44291", + "issue:43531|issue:45042", + "issue:43262|issue:44811", + "issue:36010|issue:36331", + "issue:44568|issue:45356", + "issue:43643|issue:45759", + "issue:44849|issue:45701", + "issue:43329|issue:43450", + "issue:34567|issue:40990", + "issue:43329|issue:44479", + "issue:43606|issue:45859", + "issue:43257|issue:43931", + "issue:43697|issue:45357", + "issue:45823|issue:45859", + "issue:44291|issue:45042" + ], + "prepared_review_unit_hash": "0f6e3641d6d29dd4134af980150bc92d1c8a6d098e8b8c3036144cadec304e0e", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37392, + "estimated_input_tokens": 9348, + "estimated_eval_tokens": 18952 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a loose grab-bag of Transformers bug reports, mostly around model loading, tokenization, multimodal processors, and trainer behavior. The soft edges look like topical similarity rather than true duplicates, so I would reject them all.", + "confidence": 0.91, + "canonical_issue_reason": "issue:44912 is the most connected issue in the set and has the broadest relevance to a shared code path (model loading/quantization), making it the best cluster anchor even though it is not a true duplicate hub.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44912 is the strongest single representative of the cluster\u2019s recurring loading/quantization regression theme and has multiple soft links, so it is the best issue to anchor triage.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43653", + "right": "issue:44912", + "accept": false, + "reason": "Different bugs: tokenizer special-token registration/decoding vs MXFP4 quantization fallback during model loading." + }, + { + "left": "issue:43638", + "right": "issue:44936", + "accept": false, + "reason": "Unrelated failure modes: DeepSpeed ZeRO-3/non-pretrained BERT index error vs trainer.evaluate() breaking after train()." + }, + { + "left": "issue:43746", + "right": "issue:44811", + "accept": false, + "reason": "Different code paths: PEFT adapter loading from local checkpoints vs Whisper batch_decode skip_special_tokens behavior." + }, + { + "left": "issue:44589", + "right": "issue:45042", + "accept": false, + "reason": "Both are loader/backend issues, but one is a missing storage object for float8 tensors and the other is PIL image processors wrongly requiring torchvision." + }, + { + "left": "issue:43854", + "right": "issue:44977", + "accept": false, + "reason": "Different symptoms: GLM-4.7 model-loading test failure vs Qwen3.5 flash-attention generation regression." + }, + { + "left": "issue:38175", + "right": "issue:44610", + "accept": false, + "reason": "Different model families and bugs: SIGLIP2 zero probabilities vs OmDet-Turbo processor/model input-size mismatch." + }, + { + "left": "issue:39692", + "right": "issue:44912", + "accept": false, + "reason": "SigLIP2 doc example errors are about model/processor mismatch and quantization example failures, not the same MXFP4 loading fallback bug." + }, + { + "left": "issue:43526", + "right": "issue:44554", + "accept": false, + "reason": "Unrelated issues: BeitImageProcessorFast label reduction bug vs MPS attention correctness when value head dim differs from query." + }, + { + "left": "issue:36010", + "right": "issue:43645", + "accept": false, + "reason": "Both mention GenerationMixin/custom model loading, but one is an import path regression and the other is a Jupyter custom-model initialization regression." + }, + { + "left": "issue:34634", + "right": "issue:36331", + "accept": false, + "reason": "BarkProcessor voice_preset and CustomTrainer.compute_loss are distinct APIs and unrelated failures." + }, + { + "left": "issue:43819", + "right": "issue:43927", + "accept": false, + "reason": "Different mechanisms: DAC from_latents/STE mismatch vs DiaConfig losing custom token IDs after save/load." + }, + { + "left": "issue:43454", + "right": "issue:43577", + "accept": false, + "reason": "AyaVision lm_head tying and BLIP2 dtype propagation are separate model-specific initialization bugs." + }, + { + "left": "issue:43257", + "right": "issue:43329", + "accept": false, + "reason": "Qwen3 MoE accelerate/deepspeed weight conversion and multimodal token counting in the video branch are different problems." + }, + { + "left": "issue:43720", + "right": "issue:44610", + "accept": false, + "reason": "BitNet packed-weight unpacking during accelerate loading is unrelated to OmDet-Turbo processor image \u0906\u0915\u093e\u0930 mismatch." + }, + { + "left": "issue:43550", + "right": "issue:44912", + "accept": false, + "reason": "Bamba torch.compile SDPA failure is an execution-time attention issue, not the same as MXFP4 quantized loading fallback." + }, + { + "left": "issue:44568", + "right": "issue:45488", + "accept": false, + "reason": "Tokenizer special-token addition bug and LlamaTokenizer ByteLevel/Metaspace override are related to tokenization broadly, but they are not the same concrete regression." + }, + { + "left": "issue:43749", + "right": "issue:44291", + "accept": false, + "reason": "Both are loading-related, but FSDP CPU RAM efficient loading and init_empty_weights/_is_hf_initialized are distinct loading paths with different breakages." + }, + { + "left": "issue:43531", + "right": "issue:45042", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior and PIL backend torchvision dependency are unrelated." + }, + { + "left": "issue:43262", + "right": "issue:44811", + "accept": false, + "reason": "Audio apply_chat_template sampling-rate default and Whisper batch_decode skip_special_tokens are different audio-processing bugs." + }, + { + "left": "issue:36010", + "right": "issue:36331", + "accept": false, + "reason": "ImportError for GenerationMixin and compute_loss unexpected kwarg are separate trainer/model API regressions." + }, + { + "left": "issue:44568", + "right": "issue:45356", + "accept": false, + "reason": "Both involve tokenization, but mdeberta BOS/EOS handling and Kimi-K2.5 codec/fix_mistral_regex regression are different tokenizer implementations and failures." + }, + { + "left": "issue:43643", + "right": "issue:45759", + "accept": false, + "reason": "AutoConfig trust_remote_code missing fields and AutoModelForCausalLM.from_config text_config unwrapping are related only at a high level; different objects and failure points." + }, + { + "left": "issue:44849", + "right": "issue:45701", + "accept": false, + "reason": "Qwen3.5 output_hidden_states regression and general tokenization changes are not the same bug." + }, + { + "left": "issue:43329", + "right": "issue:43450", + "accept": false, + "reason": "Undefined video token-count helpers vs batched video processor output shape are both video-related but not the same underlying defect." + }, + { + "left": "issue:34567", + "right": "issue:40990", + "accept": false, + "reason": "TrainerState token-count tracking and GPT-OSS perplexity are unrelated training metrics vs model evaluation issues." + }, + { + "left": "issue:43329", + "right": "issue:44479", + "accept": false, + "reason": "Both concern video inputs, but one is an undefined helper path in token counting and the other is a v5.3.0 video-input regression across specific models." + }, + { + "left": "issue:43606", + "right": "issue:45859", + "accept": false, + "reason": "Both involve CPU offload/device handling in Bark/Qwen3.5-MoE, but they are different models and different failing code paths." + }, + { + "left": "issue:43257", + "right": "issue:43931", + "accept": false, + "reason": "Qwen3 MoE deepspeed weight conversion and Qwen3-VL weight-shape mismatch are separate model-loading bugs." + }, + { + "left": "issue:43697", + "right": "issue:45357", + "accept": false, + "reason": "RTDetrV2 output differences in v5 and Qwen3.5 save_pretrained visual-encoder key issues are unrelated regressions." + }, + { + "left": "issue:45823", + "right": "issue:45859", + "accept": false, + "reason": "Gemma4 PLE device mismatch during forward and Qwen3_5MoeTextRotaryEmbedding CPU-offload incompatibility are different runtime device-placement bugs." + }, + { + "left": "issue:44291", + "right": "issue:45042", + "accept": false, + "reason": "init_empty_weights/_is_hf_initialized handling and PIL backend torchvision dependency are unrelated loading vs image-processing regressions." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 17, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:33357", + "issue:34567", + "issue:36010", + "issue:36331", + "issue:38175", + "issue:41720", + "issue:42175", + "issue:42915", + "issue:43257", + "issue:43317", + "issue:43452", + "issue:43493", + "issue:43540", + "issue:43577", + "issue:43582", + "issue:43643", + "issue:43646", + "issue:43696", + "issue:43742", + "issue:43749", + "issue:43756", + "issue:43824", + "issue:43906", + "issue:43927", + "issue:43994", + "issue:44062", + "issue:44291", + "issue:44479", + "issue:44488", + "issue:44560", + "issue:44737", + "issue:44756", + "issue:44792", + "issue:44821", + "issue:44898", + "issue:44912", + "issue:44964", + "issue:44987", + "issue:44991", + "issue:45072", + "issue:45081", + "issue:45137", + "issue:45375", + "issue:45381", + "issue:45405", + "issue:45538", + "issue:45588", + "issue:45823" + ], + "soft_pairs": [ + "issue:43452|issue:43582", + "issue:42915|issue:43742", + "issue:41720|issue:43540", + "issue:43317|issue:45538", + "issue:33357|issue:34567", + "issue:42915|issue:44821", + "issue:44987|issue:45538", + "issue:42915|issue:45538", + "issue:43927|issue:44912", + "issue:44479|issue:45381", + "issue:43257|issue:43756", + "issue:43540|issue:44560", + "issue:43540|issue:44479", + "issue:43257|issue:43696", + "issue:43577|issue:45072", + "issue:45137|issue:45405", + "issue:38175|issue:44898", + "issue:44737|issue:45588", + "issue:43742|issue:44291", + "issue:44062|issue:44991", + "issue:43540|issue:45823", + "issue:43906|issue:45381", + "issue:43646|issue:43749", + "issue:44062|issue:45081", + "issue:43749|issue:44756", + "issue:34567|issue:36331", + "issue:36010|issue:42175", + "issue:43493|issue:43994", + "issue:43643|issue:45375", + "issue:42175|issue:43824", + "issue:44291|issue:44821", + "issue:43452|issue:44488", + "issue:44792|issue:44964" + ], + "prepared_review_unit_hash": "c932c38ed6589a841fe45a92655e87052943d4644b52ea44cee1d952aff279fd", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37633, + "estimated_input_tokens": 9409, + "estimated_eval_tokens": 19074 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is mostly heterogeneous and does not form one duplicate cluster. Only two soft pairs look like true duplicates: the Qwen video-input regression pair and the SigLIP2 discrepancy pair. The rest are related by broad subsystem or model family only, so they should stay separate.", + "confidence": 0.86, + "canonical_issue_reason": "No single issue cleanly represents the whole mixed set; if a representative is needed, issue 44479 is the best umbrella for the clearest duplicate subcluster (the v5.3.0 Qwen video-input regression), and it is broader than its specific report 45381.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44479 is the strongest global representative because it captures a broad, concrete regression with a likely duplicate (45381) and describes an actionable code-path bug rather than a model-specific symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43452", + "right": "issue:43582", + "accept": false, + "reason": "Different subsystems and failure modes: gguf loading vs Apple Silicon warmup TypeError." + }, + { + "left": "issue:42915", + "right": "issue:43742", + "accept": false, + "reason": "Different models and bugs: Qwen3MoE FP8 conversion vs MobileLLM key error." + }, + { + "left": "issue:41720", + "right": "issue:43540", + "accept": false, + "reason": "Both involve Qwen3, but one is auto device mapping on A800 and the other is video input processing in Qwen3OmniMoe; not the same bug." + }, + { + "left": "issue:43317", + "right": "issue:45538", + "accept": false, + "reason": "Unrelated issues: dequantized model loading/offload vs CLIPTokenizer max length." + }, + { + "left": "issue:33357", + "right": "issue:34567", + "accept": false, + "reason": "Completely different areas: Mac bus error on CLIP model vs TrainerState token counting." + }, + { + "left": "issue:42915", + "right": "issue:44821", + "accept": false, + "reason": "Different model-loading problems in different code paths; not the same underlying defect." + }, + { + "left": "issue:44987", + "right": "issue:45538", + "accept": false, + "reason": "One is a model-loading regression for a specific model; the other is tokenizer max-length behavior." + }, + { + "left": "issue:42915", + "right": "issue:45538", + "accept": false, + "reason": "Different bugs with no shared concrete code path." + }, + { + "left": "issue:43927", + "right": "issue:44912", + "accept": false, + "reason": "Dia config save/load token IDs bug is unrelated to MXFP4 quantization fallback." + }, + { + "left": "issue:44479", + "right": "issue:45381", + "accept": true, + "reason": "Both describe the same Qwen video-input regression; 45381 is a specific manifestation of the broader v5.3.0 video-input bug covered by 44479." + }, + { + "left": "issue:43257", + "right": "issue:43756", + "accept": false, + "reason": "Different model-specific issues: Qwen3 MoE weight conversion vs SmolLM3 RoPE layer mismatch." + }, + { + "left": "issue:43540", + "right": "issue:44560", + "accept": false, + "reason": "Both are video-input issues, but in different Qwen model families with different errors; too broad to merge." + }, + { + "left": "issue:43540", + "right": "issue:44479", + "accept": false, + "reason": "Related to video inputs, but the concrete models and failure modes differ; not clearly one bug." + }, + { + "left": "issue:43257", + "right": "issue:43696", + "accept": false, + "reason": "Qwen3 MoE conversion bug is unrelated to GPT-oss OOM." + }, + { + "left": "issue:43577", + "right": "issue:45072", + "accept": false, + "reason": "Both mention dtype, but one is BLIP2 load-time dtype propagation and the other is CI inference mismatches in different models." + }, + { + "left": "issue:45137", + "right": "issue:45405", + "accept": false, + "reason": "DeepSpeed ZeRO3 deque error and MIN_PEFT_VERSION bump are unrelated." + }, + { + "left": "issue:38175", + "right": "issue:44898", + "accept": false, + "reason": "Different model architectures and symptoms: SigLIP2 zero probabilities vs Perceiver non-default resolution failure." + }, + { + "left": "issue:44737", + "right": "issue:45588", + "accept": false, + "reason": "CPU arange placement bug in XLNet is unrelated to flash_attention s_aux handling." + }, + { + "left": "issue:43742", + "right": "issue:44291", + "accept": false, + "reason": "Both are loading-time errors, but one is a specific model key issue and the other is an init_empty_weights API change." + }, + { + "left": "issue:44062", + "right": "issue:44991", + "accept": false, + "reason": "Both involve tokenizers, but the reported failures and code paths are not clearly the same bug." + }, + { + "left": "issue:43540", + "right": "issue:45823", + "accept": false, + "reason": "Different models and different device-mismatch paths." + }, + { + "left": "issue:43906", + "right": "issue:45381", + "accept": false, + "reason": "No shared concrete bug is evident; one is just a reproduction of another issue." + }, + { + "left": "issue:43646", + "right": "issue:43749", + "accept": false, + "reason": "Generic custom-model initialization breakage is not the same as FSDP CPU RAM efficient loading." + }, + { + "left": "issue:44062", + "right": "issue:45081", + "accept": false, + "reason": "Different tokenizer regression paths: AddedToken special-arg conflict vs Mistral regex patch on a missing backend_tokenizer." + }, + { + "left": "issue:43749", + "right": "issue:44756", + "accept": false, + "reason": "Both relate to memory/loading, but one is FSDP loading and the other is mmap behavior on Strix Halo." + }, + { + "left": "issue:34567", + "right": "issue:36331", + "accept": false, + "reason": "TrainerState token counting and CustomTrainer.compute_loss signature changes are unrelated." + }, + { + "left": "issue:36010", + "right": "issue:42175", + "accept": false, + "reason": "Import surface breakage and packaging backend contents are different issues." + }, + { + "left": "issue:43493", + "right": "issue:43994", + "accept": true, + "reason": "Both point to the same SigLIP2 implementation discrepancy; 43994 is a user-facing symptom of the underlying HF-vs-JAX mismatch in 43493." + }, + { + "left": "issue:43643", + "right": "issue:45375", + "accept": false, + "reason": "Both involve config fields, but one is trust_remote_code return completeness and the other is a specific config field being dropped by strict handling." + }, + { + "left": "issue:42175", + "right": "issue:43824", + "accept": false, + "reason": "Packaging TensorFlow omission and missing Qwen2.5-VL import are unrelated." + }, + { + "left": "issue:44291", + "right": "issue:44821", + "accept": false, + "reason": "init_empty_weights argument handling and AutoImageProcessor URL loading are different code paths." + }, + { + "left": "issue:43452", + "right": "issue:44488", + "accept": false, + "reason": "Different loading issues: gguf support vs a specific model failing to load." + }, + { + "left": "issue:44792", + "right": "issue:44964", + "accept": false, + "reason": "Different multimodal model failures and different symptoms; not the same underlying bug." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays appropriately conservative overall. The two accepted duplicate pairs (44479/45381 and 43493/43994) are plausible from the titles, and the rest of the false verdicts avoid overclaiming similarity. No mergeability or single-PR issue is overstated." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 18, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:24643", + "issue:28282", + "issue:29127", + "issue:34689", + "issue:41762", + "issue:42175", + "issue:43295", + "issue:43452", + "issue:43526", + "issue:43531", + "issue:43577", + "issue:43582", + "issue:43643", + "issue:43653", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43756", + "issue:43819", + "issue:44466", + "issue:44484", + "issue:44514", + "issue:44561", + "issue:44568", + "issue:44589", + "issue:44625", + "issue:44704", + "issue:44811", + "issue:44821", + "issue:44843", + "issue:44877", + "issue:44898", + "issue:44936", + "issue:44938", + "issue:44977", + "issue:45005", + "issue:45042", + "issue:45081", + "issue:45216", + "issue:45290", + "issue:45325", + "issue:45356", + "issue:45381", + "issue:45405", + "issue:45479", + "issue:45600", + "issue:45823" + ], + "soft_pairs": [ + "issue:43526|issue:45479", + "issue:28282|issue:34689", + "issue:45042|issue:45081", + "issue:43756|issue:45325", + "issue:43742|issue:44589", + "issue:45405|issue:45600", + "issue:43531|issue:44821", + "issue:43697|issue:45216", + "issue:28282|issue:29127", + "issue:44514|issue:45381", + "issue:43582|issue:44977", + "issue:44484|issue:44704", + "issue:43643|issue:44561", + "issue:44625|issue:44877", + "issue:43720|issue:44898", + "issue:43452|issue:43577", + "issue:42175|issue:44938", + "issue:41762|issue:44936", + "issue:44514|issue:45290", + "issue:43452|issue:44843", + "issue:44466|issue:45005", + "issue:43295|issue:45356", + "issue:43819|issue:44811", + "issue:43653|issue:44568", + "issue:44936|issue:45823", + "issue:24643|issue:29127" + ], + "prepared_review_unit_hash": "d99a9826a9fd44fed77c1a238e27a2ce9caa0b1de668dee9e5711558969390f8", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 26, + "serialized_chars": 35353, + "estimated_input_tokens": 8839, + "estimated_eval_tokens": 17934 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is highly heterogeneous: the soft-similarity pairs are all false positives spanning unrelated tokenizer, model-loading, config, training, and vision issues. No safe duplicate merge candidate stands out.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43526", + "right": "issue:45479", + "accept": false, + "reason": "Different bugs: BeitImageProcessorFast reduce_labels vs sequence-classification zero-loss behavior across models." + }, + { + "left": "issue:28282", + "right": "issue:34689", + "accept": false, + "reason": "Unrelated loading problems: missing PyTorch dependency vs Llama 3.2 Vision model loading regression." + }, + { + "left": "issue:45042", + "right": "issue:45081", + "accept": false, + "reason": "Different code paths: PIL image processors requiring torchvision vs Mistral tokenizer regex crash." + }, + { + "left": "issue:43756", + "right": "issue:45325", + "accept": false, + "reason": "Both touch RoPE-related behavior, but one is about Smollm3 layer drops and the other about Qwen2.5-VL still-image temporal position ids; not the same bug." + }, + { + "left": "issue:43742", + "right": "issue:44589", + "accept": false, + "reason": "Different failure modes: loading facebook/MobileLLM-125M key error vs Float8 storage deserialization error." + }, + { + "left": "issue:45405", + "right": "issue:45600", + "accept": false, + "reason": "One is a dependency version pin issue, the other is stale auto-mapping references breaking CI." + }, + { + "left": "issue:43531", + "right": "issue:44821", + "accept": false, + "reason": "Both are loading-related, but Qwen3-MoE sliding_window and AutoImageProcessor-from-URL are unrelated." + }, + { + "left": "issue:43697", + "right": "issue:45216", + "accept": false, + "reason": "Different regressions: RTDetrV2 output drift in v5 vs Qwen3.5 save_pretrained checkpoint corruption." + }, + { + "left": "issue:28282", + "right": "issue:29127", + "accept": false, + "reason": "Missing PyTorch install vs LayoutLMv3 box-validation error; different root causes." + }, + { + "left": "issue:44514", + "right": "issue:45381", + "accept": false, + "reason": "Both are Qwen2.5-VL chat/vision issues, but one is batched apply_chat_template with padding=False and the other is incorrect video vision_position_ids." + }, + { + "left": "issue:43582", + "right": "issue:44977", + "accept": false, + "reason": "Different subsystems: Apple Silicon caching_allocator_warmup TypeError vs Qwen3.5 flash-attention generation failure." + }, + { + "left": "issue:44484", + "right": "issue:44704", + "accept": false, + "reason": "save_pretrained shard-size question vs AutoProcessor not forwarding kwargs to cached_file; not duplicates." + }, + { + "left": "issue:43643", + "right": "issue:44561", + "accept": false, + "reason": "Different breakages: missing fields with trust_remote_code in AutoConfig vs removal of is_torch_fx_available breaking remote-code models." + }, + { + "left": "issue:44625", + "right": "issue:44877", + "accept": false, + "reason": "Both involve config handling, but Qwen3.5 num_labels propagation and granite_speech strict-config loading are different bugs." + }, + { + "left": "issue:43720", + "right": "issue:44898", + "accept": false, + "reason": "BitNet packed-weights loading failure is unrelated to Perceiver interpolation at non-default resolution." + }, + { + "left": "issue:43452", + "right": "issue:43577", + "accept": false, + "reason": "Different model-loading issues: gguf_file breaks tokenizer/model loading vs Blip2 dtype not propagating to qformer/model." + }, + { + "left": "issue:42175", + "right": "issue:44938", + "accept": false, + "reason": "TensorFlow missing from a torch install extra vs Python 3.14 transformers import/load failure; not the same bug." + }, + { + "left": "issue:41762", + "right": "issue:44936", + "accept": false, + "reason": "Different training/loading paths: Gemma3ForConditionalGeneration ZeRO-3 load IndexError vs trainer.evaluate() failing after train()." + }, + { + "left": "issue:44514", + "right": "issue:45290", + "accept": false, + "reason": "Both hit apply_chat_template, but one is batched padding=False and the other is assistant tool-call messages with no content; distinct defects." + }, + { + "left": "issue:43452", + "right": "issue:44843", + "accept": false, + "reason": "gguf_file loading regression is unrelated to offline HF_HUB_OFFLINE failure in _patch_mistral_regex." + }, + { + "left": "issue:44466", + "right": "issue:45005", + "accept": false, + "reason": "Both concern tied weights, but one is inconsistent lm_head serialization and the other is translation-model tied-weight issues in v5; not clearly the same concrete bug." + }, + { + "left": "issue:43295", + "right": "issue:45356", + "accept": false, + "reason": "Different regressions: processor.tokenizer / image passing breakage vs Kimi-K2.5 tokenizer codec handling and warning behavior." + }, + { + "left": "issue:43819", + "right": "issue:44811", + "accept": false, + "reason": "Different audio/model behaviors: DAC.from_latents vs forward mismatch and Whisper batch_decode skip_special_tokens handling." + }, + { + "left": "issue:43653", + "right": "issue:44568", + "accept": false, + "reason": "BigBirdTokenizer special-token registration bug is unrelated to mdeberta-v3 BOS/EOS not being added." + }, + { + "left": "issue:44936", + "right": "issue:45823", + "accept": false, + "reason": "Trainer lifecycle failure vs Gemma4 PLE device mismatch during forward; different code paths and symptoms." + }, + { + "left": "issue:24643", + "right": "issue:29127", + "accept": false, + "reason": "DeepSpeed training weight-dimension RuntimeError is unrelated to LayoutLMv3 box-information validation." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 19, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:28282", + "issue:30064", + "issue:32090", + "issue:33666", + "issue:34567", + "issue:35141", + "issue:36010", + "issue:38175", + "issue:41720", + "issue:43122", + "issue:43295", + "issue:43329", + "issue:43452", + "issue:43504", + "issue:43525", + "issue:43531", + "issue:43550", + "issue:43572", + "issue:43577", + "issue:43653", + "issue:43688", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43749", + "issue:43756", + "issue:43906", + "issue:43927", + "issue:44361", + "issue:44442", + "issue:44451", + "issue:44464", + "issue:44568", + "issue:44610", + "issue:44743", + "issue:44821", + "issue:44843", + "issue:44849", + "issue:44913", + "issue:44977", + "issue:44991", + "issue:45325", + "issue:45356", + "issue:45357", + "issue:45440", + "issue:45588", + "issue:45812" + ], + "soft_pairs": [ + "issue:30064|issue:33666", + "issue:38175|issue:43295", + "issue:44361|issue:44442", + "issue:43653|issue:44361", + "issue:43577|issue:43697", + "issue:44464|issue:44743", + "issue:44843|issue:44991", + "issue:41720|issue:43906", + "issue:44977|issue:45356", + "issue:43688|issue:45440", + "issue:43531|issue:43742", + "issue:43653|issue:43927", + "issue:44464|issue:44977", + "issue:43550|issue:43927", + "issue:43577|issue:45588", + "issue:43550|issue:44361", + "issue:32090|issue:34567", + "issue:43504|issue:43550", + "issue:43122|issue:43906", + "issue:43504|issue:43720", + "issue:28282|issue:35141", + "issue:32090|issue:33666", + "issue:43504|issue:44610", + "issue:43452|issue:44451", + "issue:44849|issue:45357", + "issue:43742|issue:44821", + "issue:44568|issue:45812", + "issue:33666|issue:36010", + "issue:41720|issue:44464", + "issue:43329|issue:45325", + "issue:43525|issue:43572", + "issue:43756|issue:44913", + "issue:43688|issue:43749" + ], + "prepared_review_unit_hash": "ae60b74bc6bc23e12d521a9c4095741d160f892db2e08a7ffe645dfd10289b67", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 33, + "serialized_chars": 37180, + "estimated_input_tokens": 9295, + "estimated_eval_tokens": 18846 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous: the soft pairs point to different models, APIs, and failure modes, so I would not merge any of them as duplicates. The strongest standalone issue is the open Granite AutoTokenizer regression, which is concrete and broadly impactful.", + "confidence": 0.74, + "canonical_issue_reason": "issue:45812 is the best representative issue here because it is a concrete, user-facing tokenizer regression with broad model impact and active inbound references.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45812 is the strongest issue to anchor on: it is open, clearly scoped, and describes a likely cross-model regression affecting token IDs.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:30064", + "right": "issue:33666", + "accept": false, + "reason": "Different subsystems: image processor segmentation-map handling vs Qwen2-VL multi-GPU training." + }, + { + "left": "issue:38175", + "right": "issue:43295", + "accept": false, + "reason": "Both are regressions, but they concern different code paths: SigLIP2 zero probabilities vs processor/tokenizer API breakage." + }, + { + "left": "issue:44361", + "right": "issue:44442", + "accept": false, + "reason": "Both are tokenizer/loading failures, but for different tokenizers and unrelated error modes." + }, + { + "left": "issue:43653", + "right": "issue:44361", + "accept": false, + "reason": "BigBird special-token decoding issue is unrelated to MLukeTokenizer task errors." + }, + { + "left": "issue:43577", + "right": "issue:43697", + "accept": false, + "reason": "Different model families and bugs: dtype propagation in BLIP2 vs divergent outputs in RTDetrV2." + }, + { + "left": "issue:44464", + "right": "issue:44743", + "accept": false, + "reason": "Both affect generation, but the concrete failures are different: compiled forward inconsistency vs cache/state reset in Qwen3.5 modular code." + }, + { + "left": "issue:44843", + "right": "issue:44991", + "accept": false, + "reason": "Both involve tokenizer loading, but one is offline model_info misuse and the other is a specific tokenizer regression for EMBEDDIA/est-roberta." + }, + { + "left": "issue:41720", + "right": "issue:43906", + "accept": false, + "reason": "The titles suggest different manifestations; there is not enough evidence they are the same underlying device-mapping bug." + }, + { + "left": "issue:44977", + "right": "issue:45356", + "accept": false, + "reason": "Different failures: flash-attention generation bug vs tokenizer codec/regex regression." + }, + { + "left": "issue:43688", + "right": "issue:45440", + "accept": false, + "reason": "Both are MoE-related, but one is auxiliary-loss normalization and the other is DeepSeekV3 implementation divergence." + }, + { + "left": "issue:43531", + "right": "issue:43742", + "accept": false, + "reason": "Sliding-window behavior in Qwen3-MoE is unrelated to a key error when loading MobileLLM-125M." + }, + { + "left": "issue:43653", + "right": "issue:43927", + "accept": false, + "reason": "BigBird mask-token decode failure and DiaConfig custom token-ID loss are different bug classes." + }, + { + "left": "issue:44464", + "right": "issue:44977", + "accept": false, + "reason": "Both mention generation, but the model families and failure mechanisms differ." + }, + { + "left": "issue:43550", + "right": "issue:43927", + "accept": false, + "reason": "torch.compile/SDPA failure in Bamba is unrelated to DiaConfig save/load token ID corruption." + }, + { + "left": "issue:43577", + "right": "issue:45588", + "accept": false, + "reason": "BLIP2 dtype propagation and flash-attention s_aux=None crash are unrelated bugs." + }, + { + "left": "issue:43550", + "right": "issue:44361", + "accept": false, + "reason": "Different areas: compiled attention failure vs tokenizer AttributeError on tasks." + }, + { + "left": "issue:32090", + "right": "issue:34567", + "accept": false, + "reason": "Trainer distributed broadcast error is unrelated to TrainerState token-count tracking." + }, + { + "left": "issue:43504", + "right": "issue:43550", + "accept": false, + "reason": "Legacy-field loading in BeitForSemanticSegmentation is unrelated to Bamba torch.compile failures." + }, + { + "left": "issue:43122", + "right": "issue:43906", + "accept": false, + "reason": "Different tokenizer regressions with no evidence of the same underlying cause." + }, + { + "left": "issue:43504", + "right": "issue:43720", + "accept": false, + "reason": "Pretrained-model legacy-field loading and BitNet packed-weight unpacking are different code paths." + }, + { + "left": "issue:28282", + "right": "issue:35141", + "accept": false, + "reason": "PyTorch-missing import error and embedding reinitialization bug are unrelated." + }, + { + "left": "issue:32090", + "right": "issue:33666", + "accept": false, + "reason": "Both touch training, but one is a NoneType broadcast error and the other is a multi-GPU Qwen2-VL training request." + }, + { + "left": "issue:43504", + "right": "issue:44610", + "accept": false, + "reason": "Different model-loading/processor issues with no shared failure mechanism." + }, + { + "left": "issue:43452", + "right": "issue:44451", + "accept": false, + "reason": "gguf_file loading breakage is not the same as ScandiBERT tokenizer loading failure." + }, + { + "left": "issue:44849", + "right": "issue:45357", + "accept": false, + "reason": "Qwen3.5 hidden-states bug and save_pretrained visual-key regression are different defects." + }, + { + "left": "issue:43742", + "right": "issue:44821", + "accept": false, + "reason": "Key error loading MobileLLM-125M is unrelated to loading AutoImageProcessor from URL." + }, + { + "left": "issue:44568", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different model families and different tokenization behaviors." + }, + { + "left": "issue:33666", + "right": "issue:36010", + "accept": false, + "reason": "Multi-GPU Qwen2-VL training issue is unrelated to a GenerationMixin import error." + }, + { + "left": "issue:41720", + "right": "issue:44464", + "accept": false, + "reason": "Different bug types: device-mapping CUDA assert vs chunked-generation inconsistency under compiled forward." + }, + { + "left": "issue:43329", + "right": "issue:45325", + "accept": false, + "reason": "Both involve multimodal token calculations, but one is an undefined-video-branch bug and the other is still-image position scaling." + }, + { + "left": "issue:43525", + "right": "issue:43572", + "accept": false, + "reason": "Both are config-field problems, but the missing attributes differ and the affected models are unrelated." + }, + { + "left": "issue:43756", + "right": "issue:44913", + "accept": false, + "reason": "RoPE/rotary-related issues, but one is a model-architecture discrepancy and the other is config reload behavior." + }, + { + "left": "issue:43688", + "right": "issue:43749", + "accept": false, + "reason": "MoE auxiliary-loss normalization is unrelated to FSDP CPU RAM efficient loading." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 20, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:28282", + "issue:32090", + "issue:33357", + "issue:33666", + "issue:36331", + "issue:39692", + "issue:43257", + "issue:43262", + "issue:43278", + "issue:43295", + "issue:43299", + "issue:43334", + "issue:43493", + "issue:43504", + "issue:43540", + "issue:43572", + "issue:43577", + "issue:43606", + "issue:43646", + "issue:43688", + "issue:43720", + "issue:43756", + "issue:43824", + "issue:43825", + "issue:43844", + "issue:43927", + "issue:44291", + "issue:44361", + "issue:44423", + "issue:44466", + "issue:44479", + "issue:44488", + "issue:44554", + "issue:44589", + "issue:44625", + "issue:44734", + "issue:44843", + "issue:44964", + "issue:44977", + "issue:45083", + "issue:45200", + "issue:45229", + "issue:45405", + "issue:45520", + "issue:45701", + "issue:45704", + "issue:45759", + "issue:45823" + ], + "soft_pairs": [ + "issue:43493|issue:43825", + "issue:43262|issue:43295", + "issue:43606|issue:43927", + "issue:43720|issue:43927", + "issue:28282|issue:32090", + "issue:28282|issue:33357", + "issue:43577|issue:44554", + "issue:33666|issue:36331", + "issue:39692|issue:43493", + "issue:43720|issue:44361", + "issue:43688|issue:45704", + "issue:44964|issue:45405", + "issue:43334|issue:43572", + "issue:43540|issue:44977", + "issue:44479|issue:44625", + "issue:43493|issue:43844", + "issue:43756|issue:45083", + "issue:43334|issue:45759", + "issue:45200|issue:45229", + "issue:44488|issue:44843", + "issue:43257|issue:43299", + "issue:43824|issue:44589", + "issue:43646|issue:44466", + "issue:43278|issue:43844", + "issue:45229|issue:45823", + "issue:44589|issue:45520", + "issue:43688|issue:45701", + "issue:39692|issue:43295", + "issue:43572|issue:44291", + "issue:33357|issue:33666", + "issue:43504|issue:43606", + "issue:44423|issue:44734", + "issue:43927|issue:44361" + ], + "prepared_review_unit_hash": "ad43c99914c644be17580e6487fa7d3c1ca1a05c2a54e8e030784177d515307d", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37977, + "estimated_input_tokens": 9495, + "estimated_eval_tokens": 19246 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly heterogeneous, with a small Qwen/multimodal-loading subgroup and many unrelated standalone bugs. No soft edge pair looks like the same underlying bug/change, so all candidate merges are rejected.", + "confidence": 0.27, + "canonical_issue_reason": "issue:44479 is the broadest and most representative item in the only clearly related subgroup: a cross-model Qwen multimodal/video-input regression affecting multiple variants.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44479 is the best global representative because it spans several Qwen model families and reflects a concrete regression with a likely shared code path.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43493", + "right": "issue:43825", + "accept": false, + "reason": "SigLIP2 implementation discrepancies are unrelated to a pipeline error-message regression." + }, + { + "left": "issue:43262", + "right": "issue:43295", + "accept": false, + "reason": "Audio processor sampling-rate defaulting and processor.tokenizer regression are different code paths." + }, + { + "left": "issue:43606", + "right": "issue:43927", + "accept": false, + "reason": "CPU offload device mismatch in Bark is unrelated to DiaConfig token-id persistence." + }, + { + "left": "issue:43720", + "right": "issue:43927", + "accept": false, + "reason": "Packed-weight loading for BitNet is unrelated to custom token ID loss in DiaConfig." + }, + { + "left": "issue:28282", + "right": "issue:32090", + "accept": false, + "reason": "Missing PyTorch import and NoneType GPU broadcast errors are unrelated failures." + }, + { + "left": "issue:28282", + "right": "issue:33357", + "accept": false, + "reason": "PyTorch import failure and MacOS bus error in CLIP are unrelated." + }, + { + "left": "issue:43577", + "right": "issue:44554", + "accept": false, + "reason": "BLIP2 dtype persistence and MPS attention correctness are different bugs." + }, + { + "left": "issue:33666", + "right": "issue:36331", + "accept": false, + "reason": "Qwen2-VL multi-GPU training and CustomTrainer loss signature mismatch are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:43493", + "accept": false, + "reason": "Documentation example errors and SigLIP2 HF-vs-JAX implementation divergence are not the same issue." + }, + { + "left": "issue:43720", + "right": "issue:44361", + "accept": false, + "reason": "BitNet accelerate-loading bug and MLukeTokenizer task AttributeError are unrelated." + }, + { + "left": "issue:43688", + "right": "issue:45704", + "accept": false, + "reason": "Aux-loss normalization and T5 apex memory leak affect different subsystems." + }, + { + "left": "issue:44964", + "right": "issue:45405", + "accept": false, + "reason": "Phi-4 multimodal loading regression and an out-of-date PEFT version pin are unrelated." + }, + { + "left": "issue:43334", + "right": "issue:43572", + "accept": false, + "reason": "Qwen3-VL pad_token_id loading bug and StableLm pad_token_idx regression are different model/config issues." + }, + { + "left": "issue:43540", + "right": "issue:44977", + "accept": false, + "reason": "Qwen3OmniMoe video processing failure and Qwen3.5 flash-attention generation bug do not share the same failure mode." + }, + { + "left": "issue:44479", + "right": "issue:44625", + "accept": false, + "reason": "Video-input regression and num_labels propagation are separate config bugs." + }, + { + "left": "issue:43493", + "right": "issue:43844", + "accept": false, + "reason": "SigLIP2 implementation mismatch and DeepSpeed gradient growth are unrelated." + }, + { + "left": "issue:43756", + "right": "issue:45083", + "accept": false, + "reason": "RoPE-layer dropout in Smollm3 and feat-extract length behavior in qwen3_omni_moe are different bugs." + }, + { + "left": "issue:43334", + "right": "issue:45759", + "accept": false, + "reason": "Missing pad_token_id and text_config unwrapping problems are distinct Qwen config-loading issues." + }, + { + "left": "issue:45200", + "right": "issue:45229", + "accept": false, + "reason": "Missing mm_token_type_ids for fine-tuning and multi-GPU OOM are not the same underlying bug." + }, + { + "left": "issue:44488", + "right": "issue:44843", + "accept": false, + "reason": "Model load failure for a specific checkpoint and offline model_info lookup bug have different root causes." + }, + { + "left": "issue:43257", + "right": "issue:43299", + "accept": false, + "reason": "Qwen3 MOE weight conversion and Qwen3VL MOE loading are related only broadly by model family, not by the same bug." + }, + { + "left": "issue:43824", + "right": "issue:44589", + "accept": false, + "reason": "Import error for Qwen2.5-VL class and missing Float8 storage type are unrelated." + }, + { + "left": "issue:43646", + "right": "issue:44466", + "accept": false, + "reason": "Custom model initialization breakage and device-dependent lm_head serialization are different issues." + }, + { + "left": "issue:43278", + "right": "issue:43844", + "accept": false, + "reason": "Embedding dtype drift and DeepSpeed gradient growth are unrelated training problems." + }, + { + "left": "issue:45229", + "right": "issue:45823", + "accept": false, + "reason": "Gemma4 OOM and Gemma4 PLE device mismatch are different inference failures." + }, + { + "left": "issue:44589", + "right": "issue:45520", + "accept": false, + "reason": "Float8 storage lookup failure and flash_attn KeyError on Python 3.13 are unrelated environment bugs." + }, + { + "left": "issue:43688", + "right": "issue:45701", + "accept": false, + "reason": "Aux-loss normalization and tokenization changes across versions are not the same defect." + }, + { + "left": "issue:39692", + "right": "issue:43295", + "accept": false, + "reason": "Documentation example errors and processor.tokenizer regression are unrelated." + }, + { + "left": "issue:43572", + "right": "issue:44291", + "accept": false, + "reason": "StableLm pad_token_idx regression and init_empty_weights unexpected argument are different config/init bugs." + }, + { + "left": "issue:33357", + "right": "issue:33666", + "accept": false, + "reason": "MacOS bus error in a community CLIP model and Qwen2-VL multi-GPU training are unrelated." + }, + { + "left": "issue:43504", + "right": "issue:43606", + "accept": false, + "reason": "Legacy field load failure in BEiT and Bark CPU-offload device mismatch are different model-loading bugs." + }, + { + "left": "issue:44423", + "right": "issue:44734", + "accept": false, + "reason": "Continuous-batching multimodal crash and KV-cache continuation indexing bug are separate serve-path issues." + }, + { + "left": "issue:43927", + "right": "issue:44361", + "accept": false, + "reason": "DiaConfig custom token IDs and MLukeTokenizer task failure are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 21, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:15354", + "issue:28218", + "issue:29942", + "issue:30333", + "issue:33357", + "issue:34567", + "issue:38175", + "issue:43232", + "issue:43278", + "issue:43295", + "issue:43504", + "issue:43540", + "issue:43575", + "issue:43606", + "issue:43653", + "issue:43688", + "issue:43701", + "issue:43844", + "issue:43873", + "issue:43994", + "issue:44112", + "issue:44315", + "issue:44464", + "issue:44466", + "issue:44493", + "issue:44521", + "issue:44554", + "issue:44568", + "issue:44610", + "issue:44625", + "issue:44792", + "issue:44849", + "issue:44964", + "issue:45072", + "issue:45084", + "issue:45127", + "issue:45198", + "issue:45200", + "issue:45290", + "issue:45325", + "issue:45356", + "issue:45405", + "issue:45446", + "issue:45520", + "issue:45584", + "issue:45701", + "issue:45759", + "issue:45823" + ], + "soft_pairs": [ + "issue:43504|issue:43653", + "issue:43575|issue:45405", + "issue:44625|issue:45759", + "issue:43606|issue:44112", + "issue:44792|issue:45405", + "issue:43994|issue:44493", + "issue:44521|issue:45290", + "issue:29942|issue:30333", + "issue:44464|issue:45584", + "issue:28218|issue:34567", + "issue:43844|issue:44964", + "issue:45084|issue:45520", + "issue:44554|issue:45446", + "issue:43688|issue:43873", + "issue:44568|issue:45701", + "issue:15354|issue:38175", + "issue:43232|issue:44849", + "issue:43540|issue:45200", + "issue:45200|issue:45823", + "issue:45072|issue:45198", + "issue:44315|issue:44849", + "issue:43278|issue:43701", + "issue:28218|issue:33357", + "issue:44554|issue:45356", + "issue:45200|issue:45325", + "issue:43295|issue:44610", + "issue:44466|issue:45127" + ], + "prepared_review_unit_hash": "f3405d36ae18623239229e8124c5dbb2d893d444363bdc6efb4535c3b9b8259d", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "serialized_chars": 35870, + "estimated_input_tokens": 8968, + "estimated_eval_tokens": 18192 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is not a duplicate set: the soft pairs are only superficially similar by keywords, but they describe different models, different subsystems, and different failure modes.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43504", + "right": "issue:43653", + "accept": false, + "reason": "Different tokenization/loading bugs on different models: BEiT legacy-field loading vs BigBirdTokenizer special-token registration." + }, + { + "left": "issue:43575", + "right": "issue:45405", + "accept": false, + "reason": "One is a tensor-parallel OOM on Qwen2 loading; the other is a packaging/version requirement issue for PEFT." + }, + { + "left": "issue:44625", + "right": "issue:45759", + "accept": false, + "reason": "Both mention Qwen multimodal configs, but one is num_labels propagation and the other is AutoModelForCausalLM unwrapping text_config." + }, + { + "left": "issue:43606", + "right": "issue:44112", + "accept": false, + "reason": "Different problems: a real CPU offload device mismatch in bark-small vs a stale GraniteSpeech CI test." + }, + { + "left": "issue:44792", + "right": "issue:45405", + "accept": false, + "reason": "Janus image-generation test failure is unrelated to a minimum PEFT version bump." + }, + { + "left": "issue:43994", + "right": "issue:44493", + "accept": false, + "reason": "Different symptoms and code paths: SigLIP2 nonsensical outputs vs a position-id key warning across many models." + }, + { + "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 with no content." + }, + { + "left": "issue:29942", + "right": "issue:30333", + "accept": false, + "reason": "Flash Attention 2 CI failures are unrelated to MLFlow reporting after training-job failure." + }, + { + "left": "issue:44464", + "right": "issue:45584", + "accept": false, + "reason": "Different generation bugs: compiled-forward chunked generation inconsistency vs Whisper empty-transcription failure after token alignment." + }, + { + "left": "issue:28218", + "right": "issue:34567", + "accept": false, + "reason": "Tokenizer spacing after added tokens is unrelated to TrainerState not updating num_input_tokens_seen." + }, + { + "left": "issue:43844", + "right": "issue:44964", + "accept": false, + "reason": "ZeRO-3 gradient growth during training is unrelated to loading Phi-4 multimodal configs in latest transformers." + }, + { + "left": "issue:45084", + "right": "issue:45520", + "accept": false, + "reason": "Non-template-node compilation error is unrelated to the flash_attn import KeyError on Python 3.13." + }, + { + "left": "issue:44554", + "right": "issue:45446", + "accept": false, + "reason": "Both touch attention-related code, but one is an MPS correctness bug and the other is a PyTorch version gate in flex_attention." + }, + { + "left": "issue:43688", + "right": "issue:43873", + "accept": false, + "reason": "Aux-loss normalization in MoE models is unrelated to offloading not working with quantization." + }, + { + "left": "issue:44568", + "right": "issue:45701", + "accept": false, + "reason": "A specific mdeberta tokenizer special-token regression is not the same as a broad report that transformers version changes tokenization." + }, + { + "left": "issue:15354", + "right": "issue:38175", + "accept": false, + "reason": "TorchScript GeneratorExp export failure for ViT is unrelated to SigLIP2 producing zero probabilities." + }, + { + "left": "issue:43232", + "right": "issue:44849", + "accept": false, + "reason": "Generation kwarg update after sync_gpus is a different bug from Qwen3.5 hidden-states output handling." + }, + { + "left": "issue:43540", + "right": "issue:45200", + "accept": false, + "reason": "Video-input processing in Qwen3OmniMoe is unrelated to Gemma 4 mm_token_type_ids defaulting to zeros." + }, + { + "left": "issue:45200", + "right": "issue:45823", + "accept": false, + "reason": "Gemma 4 token-type defaults and a device mismatch under device_map=auto are different forward-path bugs." + }, + { + "left": "issue:45072", + "right": "issue:45198", + "accept": false, + "reason": "bfloat16 dtype mismatches in inference are unrelated to Wav2Vec2 save_pretrained/tokenization failures." + }, + { + "left": "issue:44315", + "right": "issue:44849", + "accept": false, + "reason": "Liger Kernel not applied with model_init has no overlap with Qwen3.5 output_hidden_states behavior." + }, + { + "left": "issue:43278", + "right": "issue:43701", + "accept": false, + "reason": "BF16-to-FP32 embedding dtype drift during eval is unrelated to resume_from_checkpoint key mismatch." + }, + { + "left": "issue:28218", + "right": "issue:33357", + "accept": false, + "reason": "Tokenizer added-space behavior is unrelated to a MacOS bus error in CLIP." + }, + { + "left": "issue:44554", + "right": "issue:45356", + "accept": false, + "reason": "MPS attention correctness and Kimi tokenizer codec-handling regression are unrelated." + }, + { + "left": "issue:45200", + "right": "issue:45325", + "accept": false, + "reason": "Gemma 4 mm_token_type_ids defaults and Qwen2.5-VL rope-index scaling are different multimodal bugs." + }, + { + "left": "issue:43295", + "right": "issue:44610", + "accept": false, + "reason": "Processor.tokenizer regression with images is unrelated to OmDet-Turbo producing the wrong image size." + }, + { + "left": "issue:44466", + "right": "issue:45127", + "accept": false, + "reason": "LM head serialization by device and LoRA merge collapse with extended vocabulary are different tied-weights problems." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 22, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:37428", + "issue:38175", + "issue:42915", + "issue:43262", + "issue:43278", + "issue:43295", + "issue:43334", + "issue:43425", + "issue:43450", + "issue:43493", + "issue:43525", + "issue:43550", + "issue:43572", + "issue:43575", + "issue:43653", + "issue:43701", + "issue:43819", + "issue:43824", + "issue:43825", + "issue:43827", + "issue:43844", + "issue:43856", + "issue:43873", + "issue:43901", + "issue:43957", + "issue:43975", + "issue:44112", + "issue:44206", + "issue:44360", + "issue:44442", + "issue:44464", + "issue:44514", + "issue:44521", + "issue:44561", + "issue:44610", + "issue:44792", + "issue:44857", + "issue:44898", + "issue:44987", + "issue:45083", + "issue:45127", + "issue:45198", + "issue:45245", + "issue:45412", + "issue:45563", + "issue:45584", + "issue:45593" + ], + "soft_pairs": [ + "issue:44898|issue:45412", + "issue:43493|issue:43701", + "issue:43572|issue:44987", + "issue:37428|issue:43957", + "issue:43572|issue:43957", + "issue:43334|issue:43525", + "issue:43873|issue:44464", + "issue:43295|issue:43450", + "issue:43824|issue:43975", + "issue:43550|issue:43844", + "issue:43295|issue:43873", + "issue:37428|issue:43824", + "issue:38175|issue:45412", + "issue:42915|issue:43824", + "issue:38175|issue:43493", + "issue:44442|issue:45198", + "issue:44514|issue:44521", + "issue:43278|issue:43856", + "issue:43827|issue:43901", + "issue:43653|issue:44112", + "issue:43450|issue:43493", + "issue:43450|issue:43575", + "issue:44792|issue:45563", + "issue:45127|issue:45245", + "issue:44360|issue:44561", + "issue:43819|issue:45083", + "issue:44206|issue:45584", + "issue:43262|issue:43450", + "issue:43819|issue:44112", + "issue:37428|issue:43425", + "issue:44610|issue:44857", + "issue:44857|issue:45593", + "issue:43278|issue:43825" + ], + "prepared_review_unit_hash": "06398aee776703e4995ecf27fc5854bbca24666a4b3a298477d2596bf4f2bf8d", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 33, + "serialized_chars": 36924, + "estimated_input_tokens": 9231, + "estimated_eval_tokens": 18718 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a set of superficially similar but actually distinct Transformers issues, many around processors, configs, and model-loading regressions. None of the soft-pair candidates look like true duplicates, so all should stay separate.", + "confidence": 0.61, + "canonical_issue_reason": "Issue 43295 is the broadest user-facing regression report in the processor/tokenizer area and is the closest thing here to a cluster representative.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43295 has the clearest regression framing and the widest apparent overlap with other processor-related reports in this set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44898", + "right": "issue:45412", + "accept": false, + "reason": "Different bugs: image-classification resolution handling vs RT-DETR model deletion memory release." + }, + { + "left": "issue:43493", + "right": "issue:43701", + "accept": false, + "reason": "SigLIP2 numerical discrepancy and resume checkpoint key mismatch are unrelated failures." + }, + { + "left": "issue:43572", + "right": "issue:44987", + "accept": false, + "reason": "Both involve loading/config regressions, but they affect different models and symptoms." + }, + { + "left": "issue:37428", + "right": "issue:43957", + "accept": false, + "reason": "Import error for a flash-attention helper is not the same as meta-device model-loading breakage." + }, + { + "left": "issue:43572", + "right": "issue:43957", + "accept": false, + "reason": "Missing config attribute in StableLm is distinct from meta-device loading failures." + }, + { + "left": "issue:43334", + "right": "issue:43525", + "accept": false, + "reason": "Same symptom class, but different model families and likely separate config fixes." + }, + { + "left": "issue:43873", + "right": "issue:44464", + "accept": false, + "reason": "Quantized offloading behavior is unrelated to compiled-forward chunked generation output drift." + }, + { + "left": "issue:43295", + "right": "issue:43450", + "accept": false, + "reason": "Both concern processors, but one is a tokenizer/image regression and the other is batched video-shape handling." + }, + { + "left": "issue:43824", + "right": "issue:43975", + "accept": false, + "reason": "Importing a VL model class and detokenization for DeepSeek Coder are different issues." + }, + { + "left": "issue:43550", + "right": "issue:43844", + "accept": false, + "reason": "Torch.compile + SDPA failure is not the same as ZeRO-3 gradient growth during training." + }, + { + "left": "issue:43295", + "right": "issue:43873", + "accept": false, + "reason": "Processor/tokenizer regression and quantized offloading are different code paths." + }, + { + "left": "issue:37428", + "right": "issue:43824", + "accept": false, + "reason": "Different import failures for different model APIs, not the same missing symbol." + }, + { + "left": "issue:38175", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 zero-probabilities bug and RT-DETR memory leak are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:43824", + "accept": false, + "reason": "FineGrainedFP8 Qwen3MoE failure is not the same as Qwen2.5-VL import breakage." + }, + { + "left": "issue:38175", + "right": "issue:43493", + "accept": false, + "reason": "Same model family, but one is zero probabilities and the other is HF-vs-JAX implementation mismatch." + }, + { + "left": "issue:44442", + "right": "issue:45198", + "accept": false, + "reason": "Different tokenizer/audio model failures with different APIs and failure modes." + }, + { + "left": "issue:44514", + "right": "issue:44521", + "accept": false, + "reason": "Both are Qwen2.5-VL chat-template bugs, but one crashes on batched padding=False input while the other returns empty assistant masks." + }, + { + "left": "issue:43278", + "right": "issue:43856", + "accept": false, + "reason": "Embedding dtype drift during eval is not the same as Qwen3 MoE memory inefficiency." + }, + { + "left": "issue:43827", + "right": "issue:43901", + "accept": false, + "reason": "Both are docs issues around pipelines, but they target different docs and different deprecated behaviors." + }, + { + "left": "issue:43653", + "right": "issue:44112", + "accept": false, + "reason": "Tokenizer special-token registration and a stale CI test are not duplicates." + }, + { + "left": "issue:43450", + "right": "issue:43493", + "accept": false, + "reason": "Video batch-shape bug and SigLIP2 implementation discrepancy are unrelated." + }, + { + "left": "issue:43450", + "right": "issue:43575", + "accept": false, + "reason": "Processor shape mismatch is not the same as tensor-parallel OOM on model load." + }, + { + "left": "issue:44792", + "right": "issue:45563", + "accept": false, + "reason": "A failing Janus generation test and a stale warning in paged generate are different issues." + }, + { + "left": "issue:45127", + "right": "issue:45245", + "accept": false, + "reason": "LoRA merge collapse and category-cardinality limit are unrelated errors." + }, + { + "left": "issue:44360", + "right": "issue:44561", + "accept": false, + "reason": "DSA indexer ReLU discussion is unrelated to removal of is_torch_fx_available." + }, + { + "left": "issue:43819", + "right": "issue:45083", + "accept": false, + "reason": "DAC latent/forward mismatch and qwen3_omni_moe length helper behavior are different bugs." + }, + { + "left": "issue:44206", + "right": "issue:45584", + "accept": false, + "reason": "Unsupported center arg in a feature extractor is unrelated to Whisper empty-transcription generation failure." + }, + { + "left": "issue:43262", + "right": "issue:43450", + "accept": false, + "reason": "Audio chat-template sampling-rate defaulting and video batch-shape bugs are different subsystems." + }, + { + "left": "issue:43819", + "right": "issue:44112", + "accept": false, + "reason": "DAC latent mismatch and a GraniteSpeech CI test failure are not the same issue." + }, + { + "left": "issue:37428", + "right": "issue:43425", + "accept": false, + "reason": "A missing import symbol and Torch 2.10 incompatibility are different root causes." + }, + { + "left": "issue:44610", + "right": "issue:44857", + "accept": false, + "reason": "OmDet image-size preprocessing and LwDetr AMP crash are separate model/training failures." + }, + { + "left": "issue:44857", + "right": "issue:45593", + "accept": false, + "reason": "AMP CUDA crash in LwDetrLoss is unrelated to D-FINE auxiliary-loss behavior." + }, + { + "left": "issue:43278", + "right": "issue:43825", + "accept": false, + "reason": "Embedding dtype changes and pipeline translation error messaging are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 23, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:28218", + "issue:29127", + "issue:29942", + "issue:32090", + "issue:35141", + "issue:37428", + "issue:38175", + "issue:39692", + "issue:43335", + "issue:43388", + "issue:43504", + "issue:43526", + "issue:43550", + "issue:43606", + "issue:43611", + "issue:43653", + "issue:43720", + "issue:43819", + "issue:43931", + "issue:44112", + "issue:44206", + "issue:44292", + "issue:44351", + "issue:44448", + "issue:44462", + "issue:44493", + "issue:44561", + "issue:44568", + "issue:44743", + "issue:44779", + "issue:44855", + "issue:44857", + "issue:44977", + "issue:45072", + "issue:45083", + "issue:45200", + "issue:45229", + "issue:45290", + "issue:45310", + "issue:45381", + "issue:45478", + "issue:45491", + "issue:45520", + "issue:45588", + "issue:45593", + "issue:45823", + "issue:45859" + ], + "soft_pairs": [ + "issue:45290|issue:45381", + "issue:43606|issue:45083", + "issue:43335|issue:43550", + "issue:44448|issue:44743", + "issue:37428|issue:44351", + "issue:45200|issue:45588", + "issue:43611|issue:43931", + "issue:39692|issue:43526", + "issue:44206|issue:45823", + "issue:44462|issue:44561", + "issue:44561|issue:44779", + "issue:43388|issue:43526", + "issue:43335|issue:43653", + "issue:43819|issue:44493", + "issue:45310|issue:45478", + "issue:44855|issue:45083", + "issue:45588|issue:45859", + "issue:43550|issue:44112", + "issue:29942|issue:32090", + "issue:43335|issue:43504", + "issue:43335|issue:45083", + "issue:39692|issue:44493", + "issue:44292|issue:45520", + "issue:38175|issue:44493", + "issue:44448|issue:44779", + "issue:28218|issue:35141", + "issue:43335|issue:45072", + "issue:43335|issue:45593", + "issue:43720|issue:44112", + "issue:44977|issue:45229", + "issue:44448|issue:44977", + "issue:43606|issue:44857", + "issue:44568|issue:45491", + "issue:44857|issue:45072", + "issue:29127|issue:32090" + ], + "prepared_review_unit_hash": "90b34757744392ca9dd30e6f65be3e18b362b4d0d36bce85b36d42bd9cb760dd", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 35, + "serialized_chars": 37832, + "estimated_input_tokens": 9458, + "estimated_eval_tokens": 19172 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "One clear duplicate pair stands out: the two \"Qwen3.5 Moe from_pretrained error\" issues are the same underlying loading failure. The rest of the soft pairs are only loosely related by subsystem/version and should stay separate.", + "confidence": 0.95, + "canonical_issue_reason": "issue:45310 is the better canonical for the Qwen3.5 Moe from_pretrained failure: it is the earlier report with more context, and issue:45478 is the same bug with essentially the same title.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45310 is the strongest issue candidate overall because it is the clearest duplicate target among the provided items and has the richest context for that specific bug.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45290", + "right": "issue:45381", + "accept": false, + "reason": "Different bugs: chat template/tool-call handling versus Qwen2.5-VL video position ids." + }, + { + "left": "issue:43606", + "right": "issue:45083", + "accept": false, + "reason": "Different failure modes in different code paths; one is CPU offload device mismatch, the other is a feat-length helper behavior issue." + }, + { + "left": "issue:43335", + "right": "issue:43550", + "accept": false, + "reason": "Unrelated model/config bug versus torch.compile+SDPA failure." + }, + { + "left": "issue:44448", + "right": "issue:44743", + "accept": false, + "reason": "Both mention generation/state behavior changes, but they describe different model paths and different concrete defects." + }, + { + "left": "issue:37428", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but for different missing symbols and likely different broken dependencies/paths." + }, + { + "left": "issue:45200", + "right": "issue:45588", + "accept": false, + "reason": "Different issues: Gemma4 text-only token-type defaults versus flash_attention handling of sink-less models with s_aux=None." + }, + { + "left": "issue:43611", + "right": "issue:43931", + "accept": false, + "reason": "Model-loading problems, but not the same one: base_model_prefix handling versus Qwen3-VL weight-shape mismatch." + }, + { + "left": "issue:39692", + "right": "issue:43526", + "accept": false, + "reason": "Docs/example errors versus a BeitImageProcessorFast label-reduction bug." + }, + { + "left": "issue:44206", + "right": "issue:45823", + "accept": false, + "reason": "Different models and different runtime failures: unsupported center arg versus Gemma4 PLE device mismatch." + }, + { + "left": "issue:44462", + "right": "issue:44561", + "accept": false, + "reason": "Tokenizer config loading issue versus removal of is_torch_fx_available breaking trust_remote_code models." + }, + { + "left": "issue:44561", + "right": "issue:44779", + "accept": false, + "reason": "Both are v5 regressions affecting models, but one is an API removal breakage and the other is tokenizer output correctness for Deepseek." + }, + { + "left": "issue:43388", + "right": "issue:43526", + "accept": false, + "reason": "Both involve labels, but one drops labels in metrics gathering while the other returns only one label in BeitImageProcessorFast." + }, + { + "left": "issue:43335", + "right": "issue:43653", + "accept": false, + "reason": "Different tokenizer/config issues; sparse layer construction is unrelated to BigBirdTokenizer special-token registration." + }, + { + "left": "issue:43819", + "right": "issue:44493", + "accept": false, + "reason": "Different bugs: DAC latent conversion mismatch versus unexpected key handling for position ids." + }, + { + "left": "issue:45310", + "right": "issue:45478", + "accept": true, + "reason": "Same title and same reported from_pretrained error for Qwen3.5 Moe; these are clearly duplicate reports of the same loading bug." + }, + { + "left": "issue:44855", + "right": "issue:45083", + "accept": false, + "reason": "Python 3.13 import/torch.jit parsing issue versus a qwen3_omni_moe helper-function behavior bug." + }, + { + "left": "issue:45588", + "right": "issue:45859", + "accept": false, + "reason": "Both touch Qwen3_5Moe/attention/offload areas, but the concrete failures are different and not safely mergeable into one fix." + }, + { + "left": "issue:43550", + "right": "issue:44112", + "accept": false, + "reason": "Different CI/runtime problems in different models: SDPA compile failure versus stale device override test." + }, + { + "left": "issue:29942", + "right": "issue:32090", + "accept": false, + "reason": "Flash Attention 2 test failures and NoneType broadcast errors are unrelated bugs." + }, + { + "left": "issue:43335", + "right": "issue:43504", + "accept": false, + "reason": "Sparse-layer creation bug versus BEiT semantic-segmentation legacy-field loading failure." + }, + { + "left": "issue:43335", + "right": "issue:45072", + "accept": false, + "reason": "Different model/runtime issues: SwitchTransformers sparse-layer bug versus dtype mismatch in inference." + }, + { + "left": "issue:39692", + "right": "issue:44493", + "accept": false, + "reason": "Docs/example errors versus a broad position-id warning affecting many models." + }, + { + "left": "issue:44292", + "right": "issue:45520", + "accept": false, + "reason": "Different models and different errors: Qwen-3-8B-NVFP4 run failure versus Python 3.13 flash_attn import KeyError." + }, + { + "left": "issue:38175", + "right": "issue:44493", + "accept": false, + "reason": "Unexpected zero probabilities in SigLIP2 is not the same as the position-id key warning." + }, + { + "left": "issue:44448", + "right": "issue:44779", + "accept": false, + "reason": "Pegasus output regression and Deepseek tokenizer regression are distinct model-specific bugs." + }, + { + "left": "issue:28218", + "right": "issue:35141", + "accept": false, + "reason": "Tokenizer spacing after added token is unrelated to embedding reinitialization after resize." + }, + { + "left": "issue:43335", + "right": "issue:45072", + "accept": false, + "reason": "Not the same concrete bug; both are inference/config issues but in different models and code paths." + }, + { + "left": "issue:43335", + "right": "issue:45593", + "accept": false, + "reason": "Sparse-layer config bug versus D-FINE auxiliary-loss behavior are unrelated." + }, + { + "left": "issue:43720", + "right": "issue:44112", + "accept": false, + "reason": "Packed-weight unpacking during accelerate loading is unrelated to GraniteSpeech device override test flakiness." + }, + { + "left": "issue:44977", + "right": "issue:45229", + "accept": false, + "reason": "Different Qwen/Gemma runtime failures: flash-attention generation issue versus CUDA OOM in multi-GPU inference." + }, + { + "left": "issue:44448", + "right": "issue:44977", + "accept": false, + "reason": "Both affect generation outputs, but the model families and concrete defects differ." + }, + { + "left": "issue:43606", + "right": "issue:44857", + "accept": false, + "reason": "Different device/runtime crashes in unrelated models." + }, + { + "left": "issue:44568", + "right": "issue:45491", + "accept": false, + "reason": "Tokenizer special-token behavior is unrelated to Gemma3 sliding-window NaN embeddings." + }, + { + "left": "issue:44857", + "right": "issue:45072", + "accept": false, + "reason": "AMP crash in LwDetrImageLoss is unrelated to dtype mismatch in SwitchTransformers/TimmWrapperModel." + }, + { + "left": "issue:29127", + "right": "issue:32090", + "accept": false, + "reason": "LayoutLMv3 error-message clarity issue is unrelated to the Trainer _gpu_broadcast_one NoneType failure." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The canonical pair 45310/45478 is well supported by the packet: identical titles and very similar issue context. The soft-edge rejections are appropriately conservative overall, with reasons grounded in differing titles and bug descriptions." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 24, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:25251", + "issue:29942", + "issue:32090", + "issue:34689", + "issue:35141", + "issue:36010", + "issue:37428", + "issue:40444", + "issue:42915", + "issue:42994", + "issue:43065", + "issue:43066", + "issue:43278", + "issue:43381", + "issue:43412", + "issue:43526", + "issue:43550", + "issue:43653", + "issue:43701", + "issue:43873", + "issue:43927", + "issue:43976", + "issue:43994", + "issue:44186", + "issue:44361", + "issue:44448", + "issue:44451", + "issue:44462", + "issue:44466", + "issue:44493", + "issue:44743", + "issue:44857", + "issue:44871", + "issue:44977", + "issue:45083", + "issue:45198", + "issue:45245", + "issue:45372", + "issue:45412", + "issue:45440", + "issue:45459", + "issue:45520", + "issue:45563", + "issue:45588", + "issue:45698", + "issue:45712", + "issue:45803", + "issue:45823" + ], + "soft_pairs": [ + "issue:45459|issue:45712", + "issue:43927|issue:45698", + "issue:34689|issue:35141", + "issue:45198|issue:45803", + "issue:44977|issue:45563", + "issue:40444|issue:43526", + "issue:43701|issue:45083", + "issue:43550|issue:45083", + "issue:45372|issue:45588", + "issue:43412|issue:45588", + "issue:45245|issue:45563", + "issue:29942|issue:35141", + "issue:43873|issue:44493", + "issue:36010|issue:37428", + "issue:43066|issue:44462", + "issue:45372|issue:45459", + "issue:44857|issue:45588", + "issue:44448|issue:44466", + "issue:43278|issue:43381", + "issue:43065|issue:45412", + "issue:45588|issue:45823", + "issue:25251|issue:32090", + "issue:43653|issue:44743", + "issue:44451|issue:45520", + "issue:43976|issue:45440", + "issue:44186|issue:45198", + "issue:42915|issue:42994", + "issue:43994|issue:45412", + "issue:44361|issue:45198", + "issue:44871|issue:44977" + ], + "prepared_review_unit_hash": "0fdb572cbfc0458894c57f9c4b8ac03faa16b1b3f606871dc013875a00ed6273", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36647, + "estimated_input_tokens": 9162, + "estimated_eval_tokens": 18580 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous: the paired issues share loose keywords like save/load, tokenizer, or import errors, but they do not look like the same underlying bug. No PRs are present.", + "confidence": 0.39, + "canonical_issue_reason": "issue:45698 is the best canonical issue here because it is open, broadly user-facing, and the most general save/load regression in the set. The other issues are either narrower manifestations or unrelated model/tokenizer failures.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45698 is the best overall issue to keep as the cluster representative for the same reasons: open, active, and broadly phrased enough to serve as the nearest umbrella report. That said, the cluster does not appear to contain true duplicates.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45459", + "right": "issue:45712", + "accept": false, + "reason": "Tokenizer error handling vs leftover dummy classes; same theme of bad exception handling, but not the same bug." + }, + { + "left": "issue:43927", + "right": "issue:45698", + "accept": false, + "reason": "Both involve save/load behavior, but one is custom token IDs and generation, the other is wrong custom module resolution; different failure modes." + }, + { + "left": "issue:34689", + "right": "issue:35141", + "accept": false, + "reason": "Model loading breakage for Llama Vision vs embedding reinit after resizing; unrelated code paths." + }, + { + "left": "issue:45198", + "right": "issue:45803", + "accept": false, + "reason": "save_pretrained/tokenization failure vs bare except in FuyuBatchFeature; different symptoms and fixes." + }, + { + "left": "issue:44977", + "right": "issue:45563", + "accept": false, + "reason": "Flash-attention generation issue vs stale warning in paged generate; not the same defect." + }, + { + "left": "issue:40444", + "right": "issue:43526", + "accept": false, + "reason": "IterableDataset multi-image finetuning vs BEiT fast processor label reduction; unrelated subsystems." + }, + { + "left": "issue:43701", + "right": "issue:45083", + "accept": false, + "reason": "Checkpoint resume key mismatch vs feature-length helper behavior; no concrete overlap." + }, + { + "left": "issue:43550", + "right": "issue:45083", + "accept": false, + "reason": "torch.compile/SDPA bug vs feature extraction length helper; different code paths." + }, + { + "left": "issue:45372", + "right": "issue:45588", + "accept": false, + "reason": "Gemma processor import failure vs flash-attention crash on s_aux=None; unrelated issues." + }, + { + "left": "issue:43412", + "right": "issue:45588", + "accept": false, + "reason": "ExecuTorch export guard/support problem vs flash-attention sink-less model crash; different layers." + }, + { + "left": "issue:45245", + "right": "issue:45563", + "accept": false, + "reason": "Category-count runtime limit vs paged generate warning; not duplicates." + }, + { + "left": "issue:29942", + "right": "issue:35141", + "accept": false, + "reason": "Flash Attention 2 test failures vs embedding reinitialization after resize; unrelated." + }, + { + "left": "issue:43873", + "right": "issue:44493", + "accept": false, + "reason": "Quantization/offloading behavior vs unexpected position-id keys; no shared concrete bug." + }, + { + "left": "issue:36010", + "right": "issue:37428", + "accept": false, + "reason": "GenerationMixin import removal vs flash_attention_utils import removal; both imports fail, but they are different symbols and fixes." + }, + { + "left": "issue:43066", + "right": "issue:44462", + "accept": false, + "reason": "Tokenizer decoder type mismatch in v5 vs AutoTokenizer ignoring tokenizer.json; both loading-related, but different defects." + }, + { + "left": "issue:45372", + "right": "issue:45459", + "accept": false, + "reason": "Gemma 4 processor import dependency vs tokenizer exception masking; different failures." + }, + { + "left": "issue:44857", + "right": "issue:45588", + "accept": false, + "reason": "LwDetr loss under AMP/CUDA vs flash-attention integration crash; unrelated model paths." + }, + { + "left": "issue:44448", + "right": "issue:44466", + "accept": false, + "reason": "Pegasus output differences across versions vs lm_head serialization inconsistency; both model behavior regressions, but not the same bug." + }, + { + "left": "issue:43278", + "right": "issue:43381", + "accept": false, + "reason": "Embedding dtype drift in eval vs gradient checkpointing in eval mode; different evaluation-time issues." + }, + { + "left": "issue:43065", + "right": "issue:45412", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder vs RT-DETR memory release; unrelated." + }, + { + "left": "issue:45588", + "right": "issue:45823", + "accept": false, + "reason": "Flash-attention aux handling vs Gemma4 PLE device mismatch; both runtime issues, but distinct code paths." + }, + { + "left": "issue:25251", + "right": "issue:32090", + "accept": false, + "reason": "top_k pipeline output nesting vs Trainer _gpu_broadcast_one NoneType error; unrelated behavior." + }, + { + "left": "issue:43653", + "right": "issue:44743", + "accept": false, + "reason": "BigBirdTokenizer special-token decode bug vs Qwen recurrent-state reset; different models and bugs." + }, + { + "left": "issue:44451", + "right": "issue:45520", + "accept": false, + "reason": "Model loading failure for a specific repo vs KeyError for flash_attn on Python 3.13; different root causes." + }, + { + "left": "issue:43976", + "right": "issue:45440", + "accept": false, + "reason": "Python version compatibility issue vs DeepseekV3MoE divergence; unrelated." + }, + { + "left": "issue:44186", + "right": "issue:45198", + "accept": false, + "reason": "LayoutLMv2Tokenizer NER/padding crash vs Wav2Vec2 save_pretrained/tokenization failure; different tokenizers and failures." + }, + { + "left": "issue:42915", + "right": "issue:42994", + "accept": false, + "reason": "Qwen3Moe FP8 config failure vs quantized model saving failure; both quantization-related, but not the same bug." + }, + { + "left": "issue:43994", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 AutoModel/pipeline nonsense output vs RT-DETR memory leak; unrelated." + }, + { + "left": "issue:44361", + "right": "issue:45198", + "accept": false, + "reason": "MLukeTokenizer task AttributeError vs Wav2Vec2 save/tokenization failure; different tokenizer problems." + }, + { + "left": "issue:44871", + "right": "issue:44977", + "accept": false, + "reason": "Gemma eos_token_id config mismatch vs Qwen3.5 flash-attention generation issue; different model configs 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": 2, + "component_count": 16, + "review_unit_index": 25, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:29127", + "issue:29942", + "issue:30064", + "issue:32090", + "issue:33357", + "issue:34567", + "issue:36010", + "issue:39692", + "issue:41720", + "issue:43065", + "issue:43278", + "issue:43329", + "issue:43334", + "issue:43381", + "issue:43421", + "issue:43526", + "issue:43531", + "issue:43575", + "issue:43653", + "issue:43701", + "issue:43723", + "issue:43756", + "issue:43761", + "issue:43824", + "issue:43873", + "issue:43994", + "issue:44186", + "issue:44206", + "issue:44265", + "issue:44279", + "issue:44442", + "issue:44479", + "issue:44554", + "issue:44610", + "issue:44734", + "issue:44977", + "issue:45103", + "issue:45198", + "issue:45229", + "issue:45245", + "issue:45372", + "issue:45406", + "issue:45412", + "issue:45440", + "issue:45491", + "issue:45593", + "issue:45834", + "issue:45859" + ], + "soft_pairs": [ + "issue:43421|issue:45491", + "issue:44206|issue:44479", + "issue:44265|issue:45198", + "issue:29942|issue:30064", + "issue:44734|issue:45406", + "issue:43065|issue:43994", + "issue:33357|issue:39692", + "issue:29127|issue:34567", + "issue:44610|issue:45412", + "issue:45103|issue:45372", + "issue:43756|issue:45440", + "issue:43873|issue:45229", + "issue:43723|issue:44554", + "issue:45372|issue:45406", + "issue:43278|issue:43575", + "issue:43761|issue:45859", + "issue:43526|issue:45834", + "issue:43381|issue:43701", + "issue:43653|issue:44442", + "issue:45440|issue:45593", + "issue:43278|issue:43329", + "issue:29942|issue:36010", + "issue:41720|issue:45229", + "issue:32090|issue:33357", + "issue:43334|issue:43531", + "issue:43526|issue:44186", + "issue:44977|issue:45245", + "issue:43824|issue:44279" + ], + "prepared_review_unit_hash": "952b7ea01fa2df0387d72013d797cd40fa84356061ad2dfd4c96ce14daf32b45", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36201, + "estimated_input_tokens": 9051, + "estimated_eval_tokens": 18358 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a loose grab bag of unrelated Transformers issues rather than a duplicate set. None of the soft pairs look like the same underlying bug/change, and there are no PRs to consider.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "issue:43873 is the broadest and most active report in the set (quantization/offloading runtime bug with inbound references), so it is the best representative issue if one must be chosen.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43421", + "right": "issue:45491", + "accept": false, + "reason": "TokenizersBackend special-token updates vs Gemma3 NaN embeddings; different components and failure modes." + }, + { + "left": "issue:44206", + "right": "issue:44479", + "accept": false, + "reason": "Feature extractor arg validation crash vs Qwen video-input regression; not the same code path." + }, + { + "left": "issue:44265", + "right": "issue:45198", + "accept": false, + "reason": "torch.export/torch_compilable_check failure vs Wav2Vec2 save/tokenization failure; unrelated APIs." + }, + { + "left": "issue:29942", + "right": "issue:30064", + "accept": false, + "reason": "Flash Attention 2 test failures vs void segmentation map processing; different subsystems." + }, + { + "left": "issue:44734", + "right": "issue:45406", + "accept": false, + "reason": "Both are serve-related, but one is KV-cache indexing and the other is a Gemma4Processor init bug." + }, + { + "left": "issue:43065", + "right": "issue:43994", + "accept": false, + "reason": "Sam3PixelDecoder dummy layer vs SigLIP2 AutoModel/pipeline outputs; unrelated model bugs." + }, + { + "left": "issue:33357", + "right": "issue:39692", + "accept": false, + "reason": "MacOS bus error in community CLIP model vs SigLIP2 docs/model mismatch; different underlying issues." + }, + { + "left": "issue:29127", + "right": "issue:34567", + "accept": false, + "reason": "LayoutLMv3 box/error messaging vs TrainerState token counter update; unrelated behavior." + }, + { + "left": "issue:44610", + "right": "issue:45412", + "accept": false, + "reason": "Processor/model input-size mismatch vs RT-DETR memory release; different bug classes." + }, + { + "left": "issue:45103", + "right": "issue:45372", + "accept": false, + "reason": "auto_docstring future-annotations crash vs Gemma4 dependency import failure; unrelated." + }, + { + "left": "issue:43756", + "right": "issue:45440", + "accept": false, + "reason": "Different model implementation divergences (Smollm3 RoPE layers vs DeepseekV3MoE parity)." + }, + { + "left": "issue:43873", + "right": "issue:45229", + "accept": false, + "reason": "Offloading/quantization behavior vs multi-GPU OOM; same broad area, but not the same concrete bug." + }, + { + "left": "issue:43723", + "right": "issue:44554", + "accept": false, + "reason": "Tokenizer loading regression vs MPS attention correctness issue; unrelated." + }, + { + "left": "issue:45372", + "right": "issue:45406", + "accept": false, + "reason": "Gemma4 processor dependency import failure vs serve-side missing _tokenizer attribute; different root causes." + }, + { + "left": "issue:43278", + "right": "issue:43575", + "accept": false, + "reason": "Embedding dtype drift vs tensor-parallel OOM; not the same defect." + }, + { + "left": "issue:43761", + "right": "issue:45859", + "accept": false, + "reason": "CLIPVisionModel hidden_states regression vs Qwen3_5MoE CPU-offload incompatibility; different models and paths." + }, + { + "left": "issue:43526", + "right": "issue:45834", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug vs Kosmos2.5 long-OCR index error; unrelated." + }, + { + "left": "issue:43381", + "right": "issue:43701", + "accept": false, + "reason": "Gradient checkpointing in eval vs resume_from_checkpoint key mismatch; different training-flow issues." + }, + { + "left": "issue:43653", + "right": "issue:44442", + "accept": false, + "reason": "BigBirdTokenizer special-token registration vs FastSpeech2Conformer tokenizer loading; both tokenizer-related but distinct bugs." + }, + { + "left": "issue:45440", + "right": "issue:45593", + "accept": false, + "reason": "DeepseekV3MoE parity gap vs D-FINE auxiliary-loss omission; different models and behaviors." + }, + { + "left": "issue:43278", + "right": "issue:43329", + "accept": false, + "reason": "Embedding dtype mismatch vs multimodal token counting video-branch NameError; unrelated." + }, + { + "left": "issue:29942", + "right": "issue:36010", + "accept": false, + "reason": "Flash Attention test failures vs GenerationMixin import error; no overlap in root cause." + }, + { + "left": "issue:41720", + "right": "issue:45229", + "accept": false, + "reason": "Qwen3 auto-device-map assert on A800 vs Gemma4 multi-GPU OOM; both CUDA, but not the same failure." + }, + { + "left": "issue:32090", + "right": "issue:33357", + "accept": false, + "reason": "Trainer _gpu_broadcast_one NoneType error vs MacOS CLIP bus error; unrelated." + }, + { + "left": "issue:43334", + "right": "issue:43531", + "accept": false, + "reason": "Qwen3-VL pad_token_id loading bug vs Qwen3-MoE sliding_window bug; same family but different concrete issues." + }, + { + "left": "issue:43526", + "right": "issue:44186", + "accept": false, + "reason": "BeitImageProcessorFast label reduction vs LayoutLMv2Tokenizer NER/padding crash; different components." + }, + { + "left": "issue:44977", + "right": "issue:45245", + "accept": false, + "reason": "Qwen3.5 flash-attention generation regression vs category-count limit error; unrelated." + }, + { + "left": "issue:43824", + "right": "issue:44279", + "accept": false, + "reason": "Specific Qwen2_5_VL import failure vs vague dependency issue; not enough evidence of the same bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 26, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:28218", + "issue:29127", + "issue:32090", + "issue:33290", + "issue:33357", + "issue:34567", + "issue:34689", + "issue:35141", + "issue:38175", + "issue:39692", + "issue:42907", + "issue:42915", + "issue:43262", + "issue:43316", + "issue:43381", + "issue:43441", + "issue:43525", + "issue:43526", + "issue:43575", + "issue:43611", + "issue:43646", + "issue:43701", + "issue:43761", + "issue:43873", + "issue:43931", + "issue:44077", + "issue:44079", + "issue:44188", + "issue:44206", + "issue:44387", + "issue:44442", + "issue:44464", + "issue:44479", + "issue:44743", + "issue:44811", + "issue:44857", + "issue:44898", + "issue:44964", + "issue:44977", + "issue:45072", + "issue:45216", + "issue:45290", + "issue:45440", + "issue:45491", + "issue:45584", + "issue:45588", + "issue:45698", + "issue:45803" + ], + "soft_pairs": [ + "issue:43526|issue:44857", + "issue:43262|issue:44206", + "issue:43441|issue:45588", + "issue:42915|issue:43931", + "issue:44442|issue:45072", + "issue:44464|issue:45491", + "issue:44743|issue:44811", + "issue:43575|issue:43701", + "issue:43646|issue:44077", + "issue:29127|issue:35141", + "issue:43575|issue:44387", + "issue:33357|issue:38175", + "issue:44977|issue:45584", + "issue:44442|issue:45803", + "issue:43316|issue:43525", + "issue:44964|issue:45440", + "issue:44479|issue:45290", + "issue:28218|issue:29127", + "issue:43761|issue:44079", + "issue:42907|issue:45698", + "issue:28218|issue:32090", + "issue:43931|issue:45216", + "issue:33290|issue:34567", + "issue:34689|issue:43611", + "issue:44442|issue:44898", + "issue:39692|issue:45491", + "issue:43761|issue:44188", + "issue:43381|issue:43873" + ], + "prepared_review_unit_hash": "2bb8a707f1d21f2c231a08edd017755f4f1e8c187d9f6a7757655df2e0c1e9fb", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36130, + "estimated_input_tokens": 9033, + "estimated_eval_tokens": 18322 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items do not form a coherent duplicate set; they span unrelated bugs across tokenizers, audio, vision, training, quantization, loading/saving, and model-specific regressions. No soft edge pair looks like the same underlying bug/change.", + "confidence": 0.98, + "canonical_issue_reason": "No strong canonical duplicate exists in this heterogeneous set; if a representative issue is needed, issue 43873 is the broadest and most actively discussed report.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43873 is the best single representative because it has the widest impact description and the most discussion/inbound references among these unrelated reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43526", + "right": "issue:44857", + "accept": false, + "reason": "Different subsystems and failures: Beit image processor label reduction vs LwDETR AMP/CUDA crash." + }, + { + "left": "issue:43262", + "right": "issue:44206", + "accept": false, + "reason": "Both are audio-related, but one is a chat-template sampling-rate bug and the other is a feature extractor argument crash." + }, + { + "left": "issue:43441", + "right": "issue:45588", + "accept": false, + "reason": "Both mention flash attention, but they affect different models/code paths and failure modes." + }, + { + "left": "issue:42915", + "right": "issue:43931", + "accept": false, + "reason": "Different models and problems: FP8 config failure vs weight-shape mismatch on model load." + }, + { + "left": "issue:44442", + "right": "issue:45072", + "accept": false, + "reason": "Unrelated areas: tokenizer loading failure vs dtype mismatch in inference." + }, + { + "left": "issue:44464", + "right": "issue:45491", + "accept": false, + "reason": "Different bugs: compiled-forward chunked generation inconsistency vs Gemma3 NaN embeddings with sliding-window attention." + }, + { + "left": "issue:44743", + "right": "issue:44811", + "accept": false, + "reason": "Different features: recurrent-state reset in Qwen3.5 vs Whisper skip_special_tokens handling." + }, + { + "left": "issue:43575", + "right": "issue:43701", + "accept": false, + "reason": "Different failure types: tensor-parallel OOM vs resume-from-checkpoint key mismatch." + }, + { + "left": "issue:43646", + "right": "issue:44077", + "accept": false, + "reason": "Generic custom-model initialization regression vs a specific patchtsmixer post_init policy issue." + }, + { + "left": "issue:29127", + "right": "issue:35141", + "accept": false, + "reason": "LayoutLMv3 error-message clarity and embedding reinitialization are unrelated bugs." + }, + { + "left": "issue:43575", + "right": "issue:44387", + "accept": false, + "reason": "Both are OOM-related, but one is tp load OOM and the other is increased reserved memory under int4 quantization." + }, + { + "left": "issue:33357", + "right": "issue:38175", + "accept": false, + "reason": "Different models and symptoms: MacOS bus error for CLIP vs zero probabilities for SigLIP2." + }, + { + "left": "issue:44977", + "right": "issue:45584", + "accept": false, + "reason": "Different regressions: Qwen3.5 flash-attention generation vs Whisper empty-transcription handling." + }, + { + "left": "issue:44442", + "right": "issue:45803", + "accept": false, + "reason": "Tokenizer loading failure is unrelated to FuyuBatchFeature's bare-except bug." + }, + { + "left": "issue:43316", + "right": "issue:43525", + "accept": false, + "reason": "Both are config/API issues, but they concern different models and different missing/discrepant attributes." + }, + { + "left": "issue:44964", + "right": "issue:45440", + "accept": false, + "reason": "Different model families and problems: Phi-4 multimodal loading vs DeepSeekV3MoE implementation divergence." + }, + { + "left": "issue:44479", + "right": "issue:45290", + "accept": false, + "reason": "Video-input regression across Qwen variants is unrelated to chat-template crashes with tool-call assistant messages." + }, + { + "left": "issue:28218", + "right": "issue:29127", + "accept": false, + "reason": "Tokenizer spacing bug and LayoutLMv3 error-message clarity issue are unrelated." + }, + { + "left": "issue:43761", + "right": "issue:44079", + "accept": false, + "reason": "Possible superficial relation through ModelOutput, but the reports describe different bugs and are not clearly the same code-path issue." + }, + { + "left": "issue:42907", + "right": "issue:45698", + "accept": false, + "reason": "Both involve save/load behavior, but one is saving dequantized models and the other is custom module resolution after save_pretrained." + }, + { + "left": "issue:28218", + "right": "issue:32090", + "accept": false, + "reason": "Tokenizer spacing bug and Trainer broadcast TypeError are unrelated." + }, + { + "left": "issue:43931", + "right": "issue:45216", + "accept": false, + "reason": "Different checkpoint/model-loading failures: shape mismatch on a VL model vs incorrect saved checkpoint for Qwen3.5." + }, + { + "left": "issue:33290", + "right": "issue:34567", + "accept": false, + "reason": "OOM with Adafactor/DeepSpeed is unrelated to TrainerState token counting." + }, + { + "left": "issue:34689", + "right": "issue:43611", + "accept": false, + "reason": "Both concern loading, but they are different regression reports with different root causes and model contexts." + }, + { + "left": "issue:44442", + "right": "issue:44898", + "accept": false, + "reason": "Tokenizer loading and Perceiver image resolution handling are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:45491", + "accept": false, + "reason": "Documentation/example errors and Gemma3 NaN embeddings are different issue types and code paths." + }, + { + "left": "issue:43761", + "right": "issue:44188", + "accept": false, + "reason": "CLIP hidden_states regression and attention-kernel divergence under torch.compile are unrelated." + }, + { + "left": "issue:43381", + "right": "issue:43873", + "accept": false, + "reason": "Gradient checkpointing eval-mode restriction is unrelated to quantization offloading behavior." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 27, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:25251", + "issue:28282", + "issue:29127", + "issue:32090", + "issue:33290", + "issue:33357", + "issue:34689", + "issue:36010", + "issue:41628", + "issue:41950", + "issue:42175", + "issue:43232", + "issue:43295", + "issue:43316", + "issue:43381", + "issue:43388", + "issue:43404", + "issue:43441", + "issue:43475", + "issue:43493", + "issue:43540", + "issue:43550", + "issue:43643", + "issue:43720", + "issue:43742", + "issue:43825", + "issue:43827", + "issue:43856", + "issue:43873", + "issue:44077", + "issue:44162", + "issue:44190", + "issue:44442", + "issue:44479", + "issue:44496", + "issue:44514", + "issue:44568", + "issue:44743", + "issue:44792", + "issue:44855", + "issue:44871", + "issue:44877", + "issue:44913", + "issue:45137", + "issue:45372", + "issue:45479", + "issue:45656", + "issue:45759" + ], + "soft_pairs": [ + "issue:43493|issue:43827", + "issue:43550|issue:44743", + "issue:44568|issue:45479", + "issue:43316|issue:45759", + "issue:41628|issue:45372", + "issue:43720|issue:44442", + "issue:43643|issue:44913", + "issue:32090|issue:33290", + "issue:43873|issue:44871", + "issue:44190|issue:44496", + "issue:34689|issue:36010", + "issue:43381|issue:43856", + "issue:44855|issue:45137", + "issue:44077|issue:44479", + "issue:33290|issue:45656", + "issue:29127|issue:33357", + "issue:43381|issue:43742", + "issue:43540|issue:44514", + "issue:43316|issue:44877", + "issue:42175|issue:43316", + "issue:33290|issue:34689", + "issue:44162|issue:44792", + "issue:25251|issue:28282", + "issue:43404|issue:43441", + "issue:41950|issue:43475", + "issue:43295|issue:43825", + "issue:43232|issue:43388" + ], + "prepared_review_unit_hash": "203f34b80f33e069b7d0d161ce989e16b2067416e8273b769391392a9a3c237e", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "serialized_chars": 36090, + "estimated_input_tokens": 9023, + "estimated_eval_tokens": 18302 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a broad mix of unrelated Transformers issues, mostly around model loading, configs, processors, and distributed/training edge cases. I don\u2019t see any true duplicate pair among the soft candidates.", + "confidence": 0.91, + "canonical_issue_reason": "issue:44479 is the strongest representative because it describes a concrete, high-impact runtime regression spanning multiple Qwen video variants, which is more central than the other narrowly scoped reports.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44479 is the most broadly impactful user-facing bug in the set and best captures the recent multimodal regression theme.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43493", + "right": "issue:43827", + "accept": false, + "reason": "SigLIP2 implementation discrepancy vs documentation still referencing pipeline(); different problems." + }, + { + "left": "issue:43550", + "right": "issue:44743", + "accept": false, + "reason": "Bamba torch.compile/SDPA failure vs Qwen3.5 recurrent-state cache reset; unrelated code paths." + }, + { + "left": "issue:44568", + "right": "issue:45479", + "accept": false, + "reason": "Tokenizer special-token regression vs sequence-classification zero-loss bug; not the same issue." + }, + { + "left": "issue:43316", + "right": "issue:45759", + "accept": false, + "reason": "Gemma3TextConfig API mismatch vs Qwen multimodal from_config text_config unwrapping; different configs/models." + }, + { + "left": "issue:41628", + "right": "issue:45372", + "accept": false, + "reason": "AutoImageProcessor import failure vs missing ReasoningEffort import for Gemma 4 processor loading; unrelated import issues." + }, + { + "left": "issue:43720", + "right": "issue:44442", + "accept": false, + "reason": "BitNet packed-weight loading bug vs FastSpeech2ConformerTokenizer loading failure; separate load paths." + }, + { + "left": "issue:43643", + "right": "issue:44913", + "accept": false, + "reason": "trust_remote_code config field loss vs GPTNeoX rotary_pct not persisting on reload; different config bugs." + }, + { + "left": "issue:32090", + "right": "issue:33290", + "accept": false, + "reason": "NoneType broadcast error in Trainer vs Adafactor OOM under deepspeed; not the same underlying failure." + }, + { + "left": "issue:43873", + "right": "issue:44871", + "accept": false, + "reason": "Quantization/offloading behavior vs Gemma-3 eos_token_id inconsistency; unrelated configuration problems." + }, + { + "left": "issue:44190", + "right": "issue:44496", + "accept": false, + "reason": "Local dataset loading in a training script vs unrecognized model/config loading error; different surfaces." + }, + { + "left": "issue:34689", + "right": "issue:36010", + "accept": false, + "reason": "Llama vision model loading regression vs GenerationMixin import error; unrelated bugs." + }, + { + "left": "issue:43381", + "right": "issue:43856", + "accept": false, + "reason": "Gradient checkpointing in eval mode vs Qwen3 MoE memory inefficiency; different issues." + }, + { + "left": "issue:44855", + "right": "issue:45137", + "accept": false, + "reason": "PyTorch JIT parse/IndentationError on import vs DeepSpeed ZeRO3 deque underflow; unrelated." + }, + { + "left": "issue:44077", + "right": "issue:44479", + "accept": false, + "reason": "patchtsmixer post_init policy change vs Qwen video input regression; different models and code paths." + }, + { + "left": "issue:33290", + "right": "issue:45656", + "accept": false, + "reason": "Both involve deepspeed/optimizer behavior, but one is OOM and the other is double optimizer stepping; not a duplicate." + }, + { + "left": "issue:29127", + "right": "issue:33357", + "accept": false, + "reason": "LayoutLMv3 error-message clarity vs MacOS CLIP bus error; unrelated model-specific bugs." + }, + { + "left": "issue:43381", + "right": "issue:43742", + "accept": false, + "reason": "Gradient-checkpointing eval-mode issue vs MobileLLM config key error; not the same bug." + }, + { + "left": "issue:43540", + "right": "issue:44514", + "accept": false, + "reason": "Both are Qwen video/multimodal processor issues, but the concrete failures differ enough that they should not be merged." + }, + { + "left": "issue:43316", + "right": "issue:44877", + "accept": false, + "reason": "Gemma3TextConfig discrepancy vs strict config blocking granite_speech loading; different config incompatibilities." + }, + { + "left": "issue:42175", + "right": "issue:43316", + "accept": false, + "reason": "Packaging extras missing TensorFlow vs Gemma3TextConfig API discrepancy; unrelated." + }, + { + "left": "issue:33290", + "right": "issue:34689", + "accept": false, + "reason": "Adafactor/deepspeed OOM vs Llama 3.2 vision loading regression; unrelated." + }, + { + "left": "issue:44162", + "right": "issue:44792", + "accept": false, + "reason": "ESM2 broken vs janus test failure; different models and failure modes." + }, + { + "left": "issue:25251", + "right": "issue:28282", + "accept": false, + "reason": "Pipeline top_k nesting behavior vs missing PyTorch import error; unrelated." + }, + { + "left": "issue:43404", + "right": "issue:43441", + "accept": false, + "reason": "Mistral3 lm_head tying bug vs Ministral FlashAttention failure; same family but different concrete defects." + }, + { + "left": "issue:41950", + "right": "issue:43475", + "accept": false, + "reason": "Video-classification pipeline processor lookup bug vs SAM 3 Video missing attribute; unrelated video-model issues." + }, + { + "left": "issue:43295", + "right": "issue:43825", + "accept": false, + "reason": "Processor/tokenizer regression vs pipeline() translation-message regression; different user-visible behaviors." + }, + { + "left": "issue:43232", + "right": "issue:43388", + "accept": false, + "reason": "Generation kwargs sync_gpus bug vs metric-gathering label truncation; unrelated training/eval paths." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 28, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:33290", + "issue:35141", + "issue:36331", + "issue:41720", + "issue:42617", + "issue:43065", + "issue:43295", + "issue:43452", + "issue:43550", + "issue:43575", + "issue:43606", + "issue:43646", + "issue:43673", + "issue:43701", + "issue:43742", + "issue:43761", + "issue:43827", + "issue:43873", + "issue:43906", + "issue:43931", + "issue:43994", + "issue:44060", + "issue:44077", + "issue:44190", + "issue:44242", + "issue:44464", + "issue:44479", + "issue:44496", + "issue:44534", + "issue:44610", + "issue:44617", + "issue:44734", + "issue:44743", + "issue:44792", + "issue:44855", + "issue:44871", + "issue:44913", + "issue:44936", + "issue:44964", + "issue:44977", + "issue:45127", + "issue:45200", + "issue:45245", + "issue:45290", + "issue:45584", + "issue:45588", + "issue:45600", + "issue:45698" + ], + "soft_pairs": [ + "issue:44871|issue:45584", + "issue:45127|issue:45200", + "issue:43550|issue:43701", + "issue:43606|issue:43701", + "issue:43295|issue:44871", + "issue:43065|issue:44617", + "issue:33290|issue:35141", + "issue:33290|issue:36331", + "issue:43761|issue:44479", + "issue:43452|issue:44496", + "issue:43575|issue:43742", + "issue:43646|issue:44913", + "issue:42617|issue:43575", + "issue:43673|issue:44743", + "issue:44936|issue:45698", + "issue:43761|issue:44242", + "issue:43575|issue:43873", + "issue:44077|issue:44534", + "issue:43931|issue:44060", + "issue:44464|issue:44871", + "issue:44479|issue:44734", + "issue:44617|issue:45584", + "issue:44792|issue:44977", + "issue:43906|issue:45290", + "issue:43065|issue:44610", + "issue:43827|issue:43994", + "issue:44534|issue:44913", + "issue:44190|issue:44964", + "issue:41720|issue:45245", + "issue:44792|issue:45600", + "issue:44855|issue:45588" + ], + "prepared_review_unit_hash": "835a8191cf4d1aa7ba31f46569306698c83894d29423863629af39995eb54e10", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36970, + "estimated_input_tokens": 9243, + "estimated_eval_tokens": 18742 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is very heterogeneous: most pairs are only superficially similar and do not look like the same underlying bug/change. No soft edge is strong enough to merge, so the cluster should not be collapsed into duplicates.", + "confidence": 0.56, + "canonical_issue_reason": "Issue 43646 is the broadest umbrella here ('Transformers 5.0.0 breaks custom model initialization') and best matches the recurring v5/custom-loading regression theme, while most other items are narrower model-specific failures.", + "canonical_pr_reason": null, + "best_issue_reason": "43646 is the most reusable anchor for the cluster because it is general, regression-oriented, and closest to several loading/initialization reports; still, the overall cluster is not a clean duplicate set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44871", + "right": "issue:45584", + "accept": false, + "reason": "Different bugs: config eos_token mismatch vs Whisper empty-transcription failure after align_special_tokens." + }, + { + "left": "issue:45127", + "right": "issue:45200", + "accept": false, + "reason": "Different code paths: LoRA/vocab merge collapse on tied embeddings vs mm_token_type_ids defaulting for text-only fine-tuning." + }, + { + "left": "issue:43550", + "right": "issue:43701", + "accept": false, + "reason": "Unrelated failures: torch.compile/SDPA in Bamba vs resume_from_checkpoint key mismatch." + }, + { + "left": "issue:43606", + "right": "issue:43701", + "accept": false, + "reason": "Device offload mismatch in bark-small is not the same as checkpoint key mismatch." + }, + { + "left": "issue:43295", + "right": "issue:44871", + "accept": false, + "reason": "Regression around processor.tokenizer/images is unrelated to eos_token_id config inconsistency." + }, + { + "left": "issue:43065", + "right": "issue:44617", + "accept": false, + "reason": "Both involve Sam3, but one is a dummy Conv2d implementation issue and the other is a CUDA OOM; not the same bug." + }, + { + "left": "issue:33290", + "right": "issue:35141", + "accept": false, + "reason": "OOM in DeepSpeed Adafactor and embedding reinitialization in post_init are distinct issues." + }, + { + "left": "issue:33290", + "right": "issue:36331", + "accept": false, + "reason": "Different training failures: optimizer memory blow-up vs CustomTrainer API signature break." + }, + { + "left": "issue:43761", + "right": "issue:44479", + "accept": false, + "reason": "CLIPVision hidden_states regression and Qwen video-input regression are separate model-path bugs." + }, + { + "left": "issue:43452", + "right": "issue:44496", + "accept": false, + "reason": "GGUF/from_pretrained breakage is not the same as an unrecognized model config error." + }, + { + "left": "issue:43575", + "right": "issue:43742", + "accept": false, + "reason": "Qwen2 TP OOM and MobileLLM key error are different loading problems." + }, + { + "left": "issue:43646", + "right": "issue:44913", + "accept": false, + "reason": "Custom model initialization regression is not the same as GPTNeoX rotary_pct not persisting on reload." + }, + { + "left": "issue:42617", + "right": "issue:43575", + "accept": false, + "reason": "3d_parallel.py failure and Qwen2 TP OOM are unrelated issues." + }, + { + "left": "issue:43673", + "right": "issue:44743", + "accept": false, + "reason": "Both are cache-related, but chunked_prefill cache missing and recurrent states resetting are different concrete bugs." + }, + { + "left": "issue:44936", + "right": "issue:45698", + "accept": false, + "reason": "trainer.evaluate after train and wrong custom module loading after save_pretrained are separate problems." + }, + { + "left": "issue:43761", + "right": "issue:44242", + "accept": false, + "reason": "CLIPVision hidden_states regression does not match router-loss omission when output_router_logits=False." + }, + { + "left": "issue:43575", + "right": "issue:43873", + "accept": false, + "reason": "Both mention memory/offload themes, but tp OOM and quantization offloading misbehavior are not the same issue." + }, + { + "left": "issue:44077", + "right": "issue:44534", + "accept": false, + "reason": "patchtsmixer post_init policy and non-persistent buffer junk are unrelated v5 behavior changes." + }, + { + "left": "issue:43931", + "right": "issue:44060", + "accept": false, + "reason": "Shape mismatch while loading Qwen3-VL is unrelated to the tied-weights warning on Qwen3-Next." + }, + { + "left": "issue:44464", + "right": "issue:44871", + "accept": false, + "reason": "Compiled chunked generation inconsistency is a different failure from eos_token_id configuration mismatch." + }, + { + "left": "issue:44479", + "right": "issue:44734", + "accept": false, + "reason": "Video-input regression in Qwen VL models and KV-cache continuation crash in serve are different code paths." + }, + { + "left": "issue:44617", + "right": "issue:45584", + "accept": false, + "reason": "Sam3Video CUDA OOM and Whisper empty transcription are entirely separate model bugs." + }, + { + "left": "issue:44792", + "right": "issue:44977", + "accept": false, + "reason": "Janus image-generation test failure and Qwen3.5 flash-attention generation bug are not the same underlying issue." + }, + { + "left": "issue:43906", + "right": "issue:45290", + "accept": false, + "reason": "Isolated reproduction of an unrelated issue and apply_chat_template tool-call crash do not share a concrete bug." + }, + { + "left": "issue:43065", + "right": "issue:44610", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder and OmDet processor/model size mismatch are different problems." + }, + { + "left": "issue:43827", + "right": "issue:43994", + "accept": false, + "reason": "Docs still referencing pipeline() and SigLIP2 nonsensical outputs are unrelated." + }, + { + "left": "issue:44534", + "right": "issue:44913", + "accept": false, + "reason": "Non-persistent buffer initialization garbage and rotary_pct reload default are different regressions." + }, + { + "left": "issue:44190", + "right": "issue:44964", + "accept": false, + "reason": "Local dataset loading failure and Phi-4-multimodal model loading error are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:45245", + "accept": false, + "reason": "CUDA assert with auto device mapping and category-count limit error are different runtime failures." + }, + { + "left": "issue:44792", + "right": "issue:45600", + "accept": false, + "reason": "Janus image-generation test failure is unrelated to stale auto_mappings references breaking CI." + }, + { + "left": "issue:44855", + "right": "issue:45588", + "accept": false, + "reason": "Python 3.13 IndentationError in DebertaV2 import is not the same as flash_attention crashing on s_aux=None." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 29, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:36246", + "issue:38175", + "issue:41628", + "issue:43065", + "issue:43116", + "issue:43295", + "issue:43335", + "issue:43404", + "issue:43479", + "issue:43540", + "issue:43550", + "issue:43644", + "issue:43650", + "issue:43976", + "issue:44077", + "issue:44112", + "issue:44186", + "issue:44190", + "issue:44220", + "issue:44464", + "issue:44466", + "issue:44496", + "issue:44521", + "issue:44561", + "issue:44683", + "issue:44734", + "issue:44737", + "issue:44855", + "issue:44877", + "issue:44913", + "issue:44933", + "issue:44938", + "issue:45127", + "issue:45216", + "issue:45245", + "issue:45276", + "issue:45357", + "issue:45362", + "issue:45375", + "issue:45381", + "issue:45446", + "issue:45542", + "issue:45563", + "issue:45584", + "issue:45600", + "issue:45632", + "issue:45803" + ], + "soft_pairs": [ + "issue:44737|issue:45803", + "issue:44521|issue:45381", + "issue:45127|issue:45357", + "issue:43335|issue:44855", + "issue:44938|issue:45542", + "issue:43976|issue:44855", + "issue:43644|issue:44913", + "issue:43550|issue:44190", + "issue:44077|issue:44877", + "issue:44496|issue:45803", + "issue:43540|issue:44734", + "issue:45276|issue:45584", + "issue:44112|issue:45600", + "issue:43650|issue:44220", + "issue:43335|issue:44190", + "issue:43116|issue:44190", + "issue:43295|issue:45276", + "issue:45245|issue:45584", + "issue:43479|issue:45375", + "issue:36246|issue:41628", + "issue:44933|issue:45362", + "issue:44186|issue:44734", + "issue:44464|issue:45563", + "issue:43404|issue:45216", + "issue:44683|issue:45446", + "issue:38175|issue:43065", + "issue:44734|issue:45632", + "issue:44561|issue:45632", + "issue:44466|issue:44913" + ], + "prepared_review_unit_hash": "2dfb3a09ae952b1244d4016266bb62ea7a61e7c9d9400334f4ef74ba5030a0e0", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 35964, + "estimated_input_tokens": 8991, + "estimated_eval_tokens": 18238 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These issues are largely unrelated one-off bugs across different models, configs, and code paths. I found no soft pair that looks like the same underlying defect or change, so all candidate merges should be rejected.", + "confidence": 0.93, + "canonical_issue_reason": "issue:44521 is the strongest general representative here: it is open, has the most inbound references and discussion, and concerns a core library API (`apply_chat_template`) rather than a narrow model-specific edge case.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44521 has the broadest impact and most activity, so it is the best single issue to anchor the cluster even though the cluster does not contain clear duplicates.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44737", + "right": "issue:45803", + "accept": false, + "reason": "Different bugs in different components: XLNet device placement vs. Fuyu tensor conversion error handling." + }, + { + "left": "issue:44521", + "right": "issue:45381", + "accept": false, + "reason": "Both are multimodal-related, but one is assistant mask generation in `apply_chat_template` and the other is video `vision_position_ids`; distinct code paths and symptoms." + }, + { + "left": "issue:45127", + "right": "issue:45357", + "accept": false, + "reason": "One is LoRA merge/tied-weights collapse, the other is incorrect visual encoder keys in `save_pretrained`; not the same defect." + }, + { + "left": "issue:43335", + "right": "issue:44855", + "accept": false, + "reason": "Unrelated: SwitchTransformers sparse-layer construction vs. Python 3.13 import/`torch.jit.script` parsing failure." + }, + { + "left": "issue:44938", + "right": "issue:45542", + "accept": false, + "reason": "Different failures: Python 3.14 import/load breakage vs. tensorboard-without-TF backend handling." + }, + { + "left": "issue:43976", + "right": "issue:44855", + "accept": false, + "reason": "Both mention Python version compatibility, but one is a broad 5.1.0 support issue and the other is a specific DebertaV2 import parsing error." + }, + { + "left": "issue:43644", + "right": "issue:44913", + "accept": false, + "reason": "Non-persistent buffer initialization bug is unrelated to GPTNeoX config reload losing `rotary_pct`." + }, + { + "left": "issue:43550", + "right": "issue:44190", + "accept": false, + "reason": "Different areas entirely: Bamba SDPA/torch.compile vs. image-classification script local dataset loading." + }, + { + "left": "issue:44077", + "right": "issue:44877", + "accept": false, + "reason": "PatchTSMixer `post_init` restriction and GraniteSpeech strict-config loading are separate config-validation problems." + }, + { + "left": "issue:44496", + "right": "issue:45803", + "accept": false, + "reason": "Unrecognized model config loading and Fuyu bare-except error handling are unrelated." + }, + { + "left": "issue:43540", + "right": "issue:44734", + "accept": false, + "reason": "Qwen3OmniMoe video input validation and serve KV-cache continuation indexing are different code paths." + }, + { + "left": "issue:45276", + "right": "issue:45584", + "accept": false, + "reason": "Gemma4 embedding resize bug and Whisper empty-transcription generation failure are unrelated model-specific issues." + }, + { + "left": "issue:44112", + "right": "issue:45600", + "accept": false, + "reason": "CI stale device override test and auto_mappings cleanup for removed Sam3LiteText configs are not the same bug." + }, + { + "left": "issue:43650", + "right": "issue:44220", + "accept": false, + "reason": "Placeholder issue title and `_torch_extract_fbank_features()` failure have no concrete overlap." + }, + { + "left": "issue:43335", + "right": "issue:44190", + "accept": false, + "reason": "SwitchTransformers config construction is unrelated to the image-classification example script's local dataset loading." + }, + { + "left": "issue:43116", + "right": "issue:44190", + "accept": false, + "reason": "Multi-label classification empty results and local dataset loading failure are different example-script bugs." + }, + { + "left": "issue:43295", + "right": "issue:45276", + "accept": false, + "reason": "Processor/tokenizer regression and Gemma4 embedding resize behavior affect different APIs and model paths." + }, + { + "left": "issue:45245", + "right": "issue:45584", + "accept": false, + "reason": "Category-count runtime limit is unrelated to Whisper empty-transcription handling." + }, + { + "left": "issue:43479", + "right": "issue:45375", + "accept": false, + "reason": "Phi4Multimodal default config initialization and Qwen3_5MoeVisionConfig strict-field dropping are separate config issues." + }, + { + "left": "issue:36246", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but for different symbols and modules (`Qwen2_5_VLImageProcessor` vs. `AutoImageProcessor`)." + }, + { + "left": "issue:44933", + "right": "issue:45362", + "accept": false, + "reason": "Removed image_utils import and Qwen3.5 chat crash are unrelated." + }, + { + "left": "issue:44186", + "right": "issue:44734", + "accept": false, + "reason": "Tokenizer crashes on NER/padding versus server KV-cache continuation indexing are distinct bugs." + }, + { + "left": "issue:44464", + "right": "issue:45563", + "accept": false, + "reason": "Compiled forward chunked generation inconsistency is not the same as a stale warning in paged generate()." + }, + { + "left": "issue:43404", + "right": "issue:45216", + "accept": false, + "reason": "Tied `lm_head` weights in Mistral3 vs. incorrect Qwen3.5 checkpoint saving are different serialization/model-weight issues." + }, + { + "left": "issue:44683", + "right": "issue:45446", + "accept": false, + "reason": "Compiled flex_attention failing on torch>=2.9 and a PyTorch version check for AuxRequest import are separate flex_attention problems." + }, + { + "left": "issue:38175", + "right": "issue:43065", + "accept": false, + "reason": "Siglip2 zero probabilities and Sam3PixelDecoder dummy Conv2d are unrelated model bugs." + }, + { + "left": "issue:44734", + "right": "issue:45632", + "accept": false, + "reason": "Serve KV-cache indexing bug and `trust_remote_code` cache-path collision are different subsystems and failure modes." + }, + { + "left": "issue:44561", + "right": "issue:45632", + "accept": false, + "reason": "Removal of `is_torch_fx_available` breaking trust_remote_code models is unrelated to cache-path collisions for local models." + }, + { + "left": "issue:44466", + "right": "issue:44913", + "accept": false, + "reason": "Chunked generation under compilation and GPTNeoX config reload losing `rotary_pct` are separate issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 30, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:36246", + "issue:38617", + "issue:41950", + "issue:42175", + "issue:42907", + "issue:43295", + "issue:43299", + "issue:43381", + "issue:43388", + "issue:43441", + "issue:43526", + "issue:43531", + "issue:43643", + "issue:43673", + "issue:43688", + "issue:43827", + "issue:43854", + "issue:43901", + "issue:43976", + "issue:44016", + "issue:44062", + "issue:44075", + "issue:44112", + "issue:44220", + "issue:44242", + "issue:44246", + "issue:44279", + "issue:44336", + "issue:44351", + "issue:44368", + "issue:44496", + "issue:44964", + "issue:45003", + "issue:45020", + "issue:45042", + "issue:45200", + "issue:45216", + "issue:45278", + "issue:45335", + "issue:45357", + "issue:45405", + "issue:45406", + "issue:45563", + "issue:45584", + "issue:45593", + "issue:45600", + "issue:45632", + "issue:45759" + ], + "soft_pairs": [ + "issue:44246|issue:45003", + "issue:36246|issue:38617", + "issue:43643|issue:44496", + "issue:45406|issue:45632", + "issue:45563|issue:45584", + "issue:44964|issue:45600", + "issue:41950|issue:44016", + "issue:43388|issue:43688", + "issue:44112|issue:44964", + "issue:42907|issue:43441", + "issue:43295|issue:45335", + "issue:43854|issue:44964", + "issue:44016|issue:44220", + "issue:43673|issue:44336", + "issue:44496|issue:45042", + "issue:43299|issue:45216", + "issue:43531|issue:45600", + "issue:43526|issue:43901", + "issue:42175|issue:44279", + "issue:45335|issue:45584", + "issue:44075|issue:44368", + "issue:43381|issue:45593", + "issue:43299|issue:45357", + "issue:43901|issue:44496", + "issue:44496|issue:45759", + "issue:44351|issue:45278", + "issue:44016|issue:44062", + "issue:44242|issue:45200", + "issue:43388|issue:43827", + "issue:41950|issue:45020", + "issue:43976|issue:45405" + ], + "prepared_review_unit_hash": "03fbcace3003f78cc66f2c5617e55847c5004d35a862303f1e89bf7498ed78d8", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37050, + "estimated_input_tokens": 9263, + "estimated_eval_tokens": 18782 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: most items are separate regression reports, import errors, model-loading issues, or docs/test bugs rather than true duplicates. No soft edge looks safe to merge under a strict duplicate policy.", + "confidence": 0.86, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "issue:45020 is the broadest open report and the closest thing to an umbrella for recent remote_code/model-loading regressions, but it is not a true duplicate of the rest.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44246", + "right": "issue:45003", + "accept": false, + "reason": "Both mention import/runtime behavior, but one is about slow import and the other about unsafe sys.modules access; different bugs." + }, + { + "left": "issue:36246", + "right": "issue:38617", + "accept": false, + "reason": "Both are ImportErrors, but for unrelated symbols in different modules; not the same failure path." + }, + { + "left": "issue:43643", + "right": "issue:44496", + "accept": false, + "reason": "Both concern config/model loading, but one is about trust_remote_code dropping fields and the other is an unrecognized model/config issue." + }, + { + "left": "issue:45406", + "right": "issue:45632", + "accept": false, + "reason": "Gemma4Processor _tokenizer access and trust_remote_code cache collisions are different code paths." + }, + { + "left": "issue:45563", + "right": "issue:45584", + "accept": false, + "reason": "A stale generation warning and Whisper empty-transcription failure are unrelated generation bugs." + }, + { + "left": "issue:44964", + "right": "issue:45600", + "accept": false, + "reason": "Both touch model-loading/auto-mapping paths, but they concern different models and different failures." + }, + { + "left": "issue:41950", + "right": "issue:44016", + "accept": false, + "reason": "Pipeline image-processor lookup and a notebook syntax error are unrelated." + }, + { + "left": "issue:43388", + "right": "issue:43688", + "accept": false, + "reason": "Both affect training/metrics behavior, but the label-batching bug and auxiliary-loss normalization bug are distinct." + }, + { + "left": "issue:44112", + "right": "issue:44964", + "accept": false, + "reason": "A GraniteSpeech CI test failure and a GLM-4.7 model-loading issue are unrelated." + }, + { + "left": "issue:42907", + "right": "issue:43441", + "accept": false, + "reason": "Both mention Ministral models, but saving dequantized checkpoints and FlashAttention loading are different problems." + }, + { + "left": "issue:43295", + "right": "issue:45335", + "accept": false, + "reason": "Processor/tokenizer regressions and t5gemma embedding resizing are different code paths." + }, + { + "left": "issue:43854", + "right": "issue:44964", + "accept": false, + "reason": "Different models and different unit-test loading failures; not duplicates." + }, + { + "left": "issue:44016", + "right": "issue:44220", + "accept": false, + "reason": "Notebook syntax error versus audio feature extraction bug; unrelated." + }, + { + "left": "issue:43673", + "right": "issue:44336", + "accept": false, + "reason": "Chunked-prefill cache regression and ANSI color output in loading_report are unrelated." + }, + { + "left": "issue:44496", + "right": "issue:45042", + "accept": false, + "reason": "Model config loading failure and PIL backend torchvision requirement are unrelated." + }, + { + "left": "issue:43299", + "right": "issue:45216", + "accept": false, + "reason": "Both involve Qwen models, but one is a loading regression and the other is an incorrect saved checkpoint." + }, + { + "left": "issue:43531", + "right": "issue:45600", + "accept": false, + "reason": "Qwen3-MoE sliding-window behavior and stale auto_mappings references are unrelated." + }, + { + "left": "issue:43526", + "right": "issue:43901", + "accept": false, + "reason": "BEiT label reduction bug and text-classification docs mismatch are different issues." + }, + { + "left": "issue:42175", + "right": "issue:44279", + "accept": false, + "reason": "A missing tensorflow backend extra and a generic dependency issue are not the same bug." + }, + { + "left": "issue:45335", + "right": "issue:45584", + "accept": false, + "reason": "Embedding resize behavior and Whisper empty-transcription generation failure are unrelated." + }, + { + "left": "issue:44075", + "right": "issue:44368", + "accept": false, + "reason": "Optimizer arguments being ignored and a tie_word_embeddings warning are unrelated." + }, + { + "left": "issue:43381", + "right": "issue:45593", + "accept": false, + "reason": "Gradient checkpointing in eval mode and D-FINE auxiliary-loss handling are different training bugs." + }, + { + "left": "issue:43299", + "right": "issue:45357", + "accept": false, + "reason": "Both are Qwen3.5-related regressions, but one is model loading and the other is save_pretrained key serialization." + }, + { + "left": "issue:43901", + "right": "issue:44496", + "accept": false, + "reason": "Docs mentioning return_all_scores and an unrecognized model/config error are unrelated." + }, + { + "left": "issue:44496", + "right": "issue:45759", + "accept": false, + "reason": "Both involve config/model instantiation, but one is an unrecognized-model error and the other is missing text_config unwrapping." + }, + { + "left": "issue:44351", + "right": "issue:45278", + "accept": false, + "reason": "A specific HybridCache import error and a broad many-import-errors report are not the same concrete bug." + }, + { + "left": "issue:44016", + "right": "issue:44062", + "accept": false, + "reason": "Notebook syntax error and AddedToken keyword collision are unrelated." + }, + { + "left": "issue:44242", + "right": "issue:45200", + "accept": false, + "reason": "Load-balancing loss omission and Gemma 4 mm_token_type_ids defaults are different model-training issues." + }, + { + "left": "issue:43388", + "right": "issue:43827", + "accept": false, + "reason": "Metrics tuple-label truncation and pipeline() docs still mentioned after removals are unrelated." + }, + { + "left": "issue:41950", + "right": "issue:45020", + "accept": false, + "reason": "A video-classification pipeline bug and broad remote_code regressions are not the same underlying issue." + }, + { + "left": "issue:43976", + "right": "issue:45405", + "accept": false, + "reason": "Python version compatibility and an unreleased MIN_PEFT_VERSION bump are unrelated dependency problems." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 31, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:32090", + "issue:35141", + "issue:38175", + "issue:39692", + "issue:41950", + "issue:42994", + "issue:43065", + "issue:43295", + "issue:43299", + "issue:43317", + "issue:43441", + "issue:43450", + "issue:43479", + "issue:43525", + "issue:43577", + "issue:43650", + "issue:43723", + "issue:43824", + "issue:43854", + "issue:43901", + "issue:43976", + "issue:44162", + "issue:44261", + "issue:44263", + "issue:44279", + "issue:44297", + "issue:44462", + "issue:44466", + "issue:44521", + "issue:44617", + "issue:44623", + "issue:44683", + "issue:44779", + "issue:44898", + "issue:44933", + "issue:44987", + "issue:45081", + "issue:45216", + "issue:45276", + "issue:45290", + "issue:45325", + "issue:45397", + "issue:45405", + "issue:45542", + "issue:45600", + "issue:45712", + "issue:45823", + "issue:45834" + ], + "soft_pairs": [ + "issue:43824|issue:44933", + "issue:43577|issue:45216", + "issue:43479|issue:43525", + "issue:41950|issue:45823", + "issue:44683|issue:45542", + "issue:43299|issue:43854", + "issue:44279|issue:45405", + "issue:38175|issue:44617", + "issue:39692|issue:43901", + "issue:32090|issue:35141", + "issue:43295|issue:44779", + "issue:44462|issue:45081", + "issue:44297|issue:44462", + "issue:41950|issue:43650", + "issue:43976|issue:44279", + "issue:43976|issue:44987", + "issue:45600|issue:45712", + "issue:44462|issue:44779", + "issue:44521|issue:45325", + "issue:43441|issue:45834", + "issue:43450|issue:44279", + "issue:42994|issue:43317", + "issue:44261|issue:44263", + "issue:44466|issue:45276", + "issue:43065|issue:44898", + "issue:43650|issue:45290", + "issue:43441|issue:44683", + "issue:43723|issue:44162", + "issue:44623|issue:45397" + ], + "prepared_review_unit_hash": "4dda6bcc98b47429169ef4b5b16f3ba95b424b9dc8bd92267aef8e0104fb3fb1", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36332, + "estimated_input_tokens": 9083, + "estimated_eval_tokens": 18422 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is highly heterogeneous: the soft pairs share broad keywords (tokenizers, multimodal, serialization, attention, loading) but do not appear to be the same underlying bug or change. No soft edge should be merged.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "issue:44462 is the most concrete and self-contained user-facing bug in the set (AutoTokenizer ignoring repository tokenizer.json), but it does not represent the rest of the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43824", + "right": "issue:44933", + "accept": false, + "reason": "Both are import errors, but one is a missing Qwen2.5-VL export and the other is a nonexistent image_utils import; different code paths." + }, + { + "left": "issue:43577", + "right": "issue:45216", + "accept": false, + "reason": "Both involve saving/loading dtype or checkpoints, but Blip2 dtype casting and Qwen3.5 save_pretrained corruption are distinct failures." + }, + { + "left": "issue:43479", + "right": "issue:43525", + "accept": false, + "reason": "Both are config initialization issues, but one concerns multimodal vision/audio defaults and the other a missing Llama4 pad_token_id." + }, + { + "left": "issue:41950", + "right": "issue:45823", + "accept": false, + "reason": "Video-classification processor selection and Gemma4 device placement are unrelated bugs." + }, + { + "left": "issue:44683", + "right": "issue:45542", + "accept": false, + "reason": "One is a torch flex_attention compile regression; the other is a TensorBoard/TensorFlow dependency issue." + }, + { + "left": "issue:43299", + "right": "issue:43854", + "accept": false, + "reason": "Both are model-loading problems, but Qwen3VL MOE loading and GLM-4.7-Flash loading fail for different reasons." + }, + { + "left": "issue:44279", + "right": "issue:45405", + "accept": false, + "reason": "A vague dependency complaint vs. a specific PEFT minimum-version bump; not the same change." + }, + { + "left": "issue:38175", + "right": "issue:44617", + "accept": false, + "reason": "SigLIP2 zero probabilities and Sam3Video OOM are unrelated runtime issues." + }, + { + "left": "issue:39692", + "right": "issue:43901", + "accept": false, + "reason": "Both mention docs, but one is a SigLIP2 example failure and the other is a pipeline docs/behavior mismatch." + }, + { + "left": "issue:32090", + "right": "issue:35141", + "accept": false, + "reason": "Trainer GPU broadcast TypeError and embedding reinitialization after resize are different model-training bugs." + }, + { + "left": "issue:43295", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer regressions, but one is processor/tokenizer API breakage in v4.57.5 and the other is DeepSeek tokenization output corruption." + }, + { + "left": "issue:44462", + "right": "issue:45081", + "accept": false, + "reason": "Both concern tokenizer loading, but one ignores tokenizer.json and the other crashes while patching Mistral regex." + }, + { + "left": "issue:44297", + "right": "issue:44462", + "accept": false, + "reason": "Both touch tokenizer serialization/loading, but tokenizer_class metadata mismatch is not the same as AutoTokenizer ignoring repository tokenizer.json." + }, + { + "left": "issue:41950", + "right": "issue:43650", + "accept": false, + "reason": "Video pipeline processor lookup and an unrelated placeholder issue are not the same bug." + }, + { + "left": "issue:43976", + "right": "issue:44279", + "accept": false, + "reason": "Python version compatibility and a dependency issue are different problems." + }, + { + "left": "issue:43976", + "right": "issue:44987", + "accept": false, + "reason": "Python version support and a model-loading failure on transformers>=5.1.0 are unrelated." + }, + { + "left": "issue:45600", + "right": "issue:45712", + "accept": false, + "reason": "Both are repo hygiene/CI problems, but removed Sam3LiteText references and leftover dummy classes are separate cleanup tasks." + }, + { + "left": "issue:44462", + "right": "issue:44779", + "accept": false, + "reason": "Both involve tokenizers, but one is repository file precedence and the other is DeepSeek tokenization correctness." + }, + { + "left": "issue:44521", + "right": "issue:45325", + "accept": false, + "reason": "Both are multimodal/vision-adjacent, but assistant mask generation and rope index temporal scaling are different code paths." + }, + { + "left": "issue:43441", + "right": "issue:44683", + "accept": false, + "reason": "Both are attention-kernel related, but Ministral-3 flash-attention failure and compiled flex_attention torch>=2.9 regression are distinct." + }, + { + "left": "issue:43450", + "right": "issue:44279", + "accept": false, + "reason": "Video processor batching shape bug and a dependency complaint are unrelated." + }, + { + "left": "issue:42994", + "right": "issue:43317", + "accept": false, + "reason": "Both involve quantization/offload, but save failure and dequantized model loading failure are different phases and bugs." + }, + { + "left": "issue:44261", + "right": "issue:44263", + "accept": false, + "reason": "One is a missing config field causing precision drift; the other is torch.split return handling in a different model." + }, + { + "left": "issue:44466", + "right": "issue:45276", + "accept": false, + "reason": "Both concern weight/embedding serialization, but device-dependent lm_head saving and resize_token_embeddings not updating Gemma4 outputs are separate issues." + }, + { + "left": "issue:43065", + "right": "issue:44898", + "accept": false, + "reason": "Dummy Conv2d cleanup and Perceiver non-default resolution failure are unrelated." + }, + { + "left": "issue:43650", + "right": "issue:45290", + "accept": false, + "reason": "An unclear placeholder issue and apply_chat_template crashing on tool-call messages are unrelated." + }, + { + "left": "issue:43723", + "right": "issue:44162", + "accept": false, + "reason": "AutoTokenizer v5 loading regression and ESM2 breakage are different failures." + }, + { + "left": "issue:45600", + "right": "issue:45712", + "accept": false, + "reason": "Both are CI/repo-check issues, but stale auto_mappings refs and dummy pt objects are separate files/bugs." + }, + { + "left": "issue:44623", + "right": "issue:45397", + "accept": false, + "reason": "processor.save_pretrained missing files and gemma-4 zero3 from_pretrained are different save/load paths." + }, + { + "left": "issue:45834", + "right": "issue:43441", + "accept": false, + "reason": "Kosmos2.5 OCR indexing and Ministral-3 FlashAttention failure are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 32, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:16998", + "issue:22355", + "issue:41628", + "issue:41950", + "issue:42491", + "issue:43122", + "issue:43262", + "issue:43299", + "issue:43352", + "issue:43450", + "issue:43525", + "issue:43643", + "issue:43650", + "issue:43653", + "issue:43673", + "issue:43761", + "issue:43784", + "issue:43881", + "issue:43901", + "issue:43976", + "issue:43994", + "issue:44016", + "issue:44188", + "issue:44220", + "issue:44242", + "issue:44246", + "issue:44291", + "issue:44295", + "issue:44297", + "issue:44336", + "issue:44361", + "issue:44373", + "issue:44496", + "issue:44521", + "issue:44589", + "issue:44617", + "issue:44623", + "issue:44671", + "issue:44749", + "issue:44779", + "issue:44987", + "issue:45250", + "issue:45362", + "issue:45397", + "issue:45542", + "issue:45593", + "issue:45823" + ], + "soft_pairs": [ + "issue:44623|issue:44749", + "issue:43653|issue:45593", + "issue:44671|issue:44779", + "issue:43784|issue:45542", + "issue:44016|issue:45823", + "issue:44361|issue:45593", + "issue:44987|issue:45542", + "issue:43901|issue:43994", + "issue:43122|issue:43650", + "issue:44016|issue:44291", + "issue:43262|issue:44521", + "issue:44188|issue:44336", + "issue:43525|issue:43881", + "issue:43673|issue:43761", + "issue:44297|issue:45397", + "issue:43450|issue:44617", + "issue:43525|issue:43643", + "issue:42491|issue:43299", + "issue:44589|issue:45362", + "issue:41628|issue:43976", + "issue:43901|issue:44246", + "issue:44336|issue:44373", + "issue:44242|issue:45593", + "issue:16998|issue:22355", + "issue:43352|issue:45250", + "issue:44295|issue:45397", + "issue:44246|issue:44496", + "issue:41950|issue:44220" + ], + "prepared_review_unit_hash": "6ba5b88c9f7d719af61ee86d73d52f58108797bea66aba4c97ae39f9e3924f51", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 28, + "serialized_chars": 35155, + "estimated_input_tokens": 8789, + "estimated_eval_tokens": 17834 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items are mostly unrelated bug reports spanning different models, pipelines, tokenizers, and docs; none of the soft links is strong enough to treat as a true duplicate pair.", + "confidence": 0.87, + "canonical_issue_reason": "issue:44521 is the strongest canonical issue: it is a clear, currently open, user-facing regression in a broadly used multimodal API with concrete repro details.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44521 is the best single issue to anchor the cluster because it is specific, well-described, and has the clearest practical impact among the listed issues.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44623", + "right": "issue:44749", + "accept": false, + "reason": "Different bugs: processor save_pretrained file generation vs a token-filtering slowdown regression." + }, + { + "left": "issue:43653", + "right": "issue:45593", + "accept": false, + "reason": "Tokenizer special-token registration/empty decode is unrelated to D-FINE auxiliary loss behavior." + }, + { + "left": "issue:44671", + "right": "issue:44779", + "accept": false, + "reason": "Both are v5 regressions, but one is CamemBERT MLM quality and the other is DeepSeek tokenization; different code paths and symptoms." + }, + { + "left": "issue:43784", + "right": "issue:45542", + "accept": false, + "reason": "Import-time NameError in sentence-transformers is unrelated to TensorFlow backend detection when only tensorboard is installed." + }, + { + "left": "issue:44016", + "right": "issue:45823", + "accept": false, + "reason": "Notebook syntax error and Gemma4 device-map mismatch are unrelated." + }, + { + "left": "issue:44361", + "right": "issue:45593", + "accept": false, + "reason": "MLukeTokenizer task AttributeError does not match D-FINE's missing auxiliary losses." + }, + { + "left": "issue:44987", + "right": "issue:45542", + "accept": false, + "reason": "Model-loading failure for a specific repo is unrelated to the TensorFlow/tensorboard backend error." + }, + { + "left": "issue:43901", + "right": "issue:43994", + "accept": false, + "reason": "Docs mismatch for return_all_scores is not the same as incorrect SigLIP2 model outputs." + }, + { + "left": "issue:43122", + "right": "issue:43650", + "accept": false, + "reason": "Tokenization regression and a placeholder/bodyless issue are not the same underlying bug." + }, + { + "left": "issue:44016", + "right": "issue:44291", + "accept": false, + "reason": "Notebook syntax error is unrelated to the init_empty_weights unexpected argument regression." + }, + { + "left": "issue:43262", + "right": "issue:44521", + "accept": false, + "reason": "Both involve apply_chat_template, but one is an audio sampling-rate default and the other is multimodal assistant mask generation." + }, + { + "left": "issue:44188", + "right": "issue:44336", + "accept": false, + "reason": "Torch.compile attention-kernel divergence and ANSI color emission in loading_report are unrelated." + }, + { + "left": "issue:43525", + "right": "issue:43881", + "accept": false, + "reason": "Missing pad_token_id on Llama4Config is not the same as glm-4v loading failure." + }, + { + "left": "issue:43673", + "right": "issue:43761", + "accept": false, + "reason": "Generation cache regression and CLIPVision hidden_states regression affect different subsystems and outputs." + }, + { + "left": "issue:44297", + "right": "issue:45397", + "accept": false, + "reason": "Tokenizer save metadata mismatch is unrelated to Gemma-4 zero3 loading." + }, + { + "left": "issue:43450", + "right": "issue:44617", + "accept": false, + "reason": "Batched video processor shape error is not the same as Sam3Video CUDA OOM." + }, + { + "left": "issue:43525", + "right": "issue:43643", + "accept": false, + "reason": "Both mention missing fields/config objects, but one is a specific Llama4Config attribute error and the other is a trust_remote_code AutoConfig field-loss issue." + }, + { + "left": "issue:42491", + "right": "issue:43299", + "accept": false, + "reason": "Both concern Qwen3 MoE on newer transformers, but one is LoRA compatibility and the other is base model loading; not clearly one concrete bug." + }, + { + "left": "issue:44589", + "right": "issue:45362", + "accept": false, + "reason": "Float8 storage deserialization failure is unrelated to Qwen3.5 chat crashes." + }, + { + "left": "issue:41628", + "right": "issue:43976", + "accept": false, + "reason": "Importing AutoImageProcessor and Python version compatibility are different issues." + }, + { + "left": "issue:43901", + "right": "issue:44246", + "accept": false, + "reason": "Pipeline docs mismatch is unrelated to intermittent import latency." + }, + { + "left": "issue:44336", + "right": "issue:44373", + "accept": false, + "reason": "ANSI codes in loading_report and a wrong docstring for position_ids are unrelated documentation/formatting issues." + }, + { + "left": "issue:44242", + "right": "issue:45593", + "accept": false, + "reason": "Both are loss-related, but one is router/load-balancing loss and the other is D-FINE auxiliary losses under a different flag." + }, + { + "left": "issue:16998", + "right": "issue:22355", + "accept": false, + "reason": "Model_max_length behavior and missing transformers.onnx are unrelated." + }, + { + "left": "issue:43352", + "right": "issue:45250", + "accept": false, + "reason": "A specific model lacking Flash Attention 2 support is not the same as a generic Flash Attention 2 topic issue." + }, + { + "left": "issue:44295", + "right": "issue:45397", + "accept": false, + "reason": "Position_ids buffer-reading error is unrelated to Gemma-4 zero3 loading." + }, + { + "left": "issue:44246", + "right": "issue:44496", + "accept": false, + "reason": "Slow import timing and unrecognized model/config missing model_type are unrelated." + }, + { + "left": "issue:41950", + "right": "issue:44220", + "accept": false, + "reason": "Video-classification processor choosing image processors and _torch_extract_fbank_features are different pipeline bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 33, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:36246", + "issue:42757", + "issue:43065", + "issue:43232", + "issue:43257", + "issue:43262", + "issue:43408", + "issue:43475", + "issue:43526", + "issue:43540", + "issue:43596", + "issue:43653", + "issue:43673", + "issue:43824", + "issue:43901", + "issue:43976", + "issue:44162", + "issue:44242", + "issue:44246", + "issue:44295", + "issue:44336", + "issue:44351", + "issue:44466", + "issue:44485", + "issue:44496", + "issue:44561", + "issue:44749", + "issue:44779", + "issue:44857", + "issue:44871", + "issue:44877", + "issue:44964", + "issue:44987", + "issue:44995", + "issue:45003", + "issue:45137", + "issue:45200", + "issue:45292", + "issue:45335", + "issue:45362", + "issue:45375", + "issue:45459", + "issue:45561", + "issue:45563", + "issue:45584", + "issue:45588", + "issue:45701", + "issue:45759" + ], + "soft_pairs": [ + "issue:36246|issue:42757", + "issue:36246|issue:44351", + "issue:44336|issue:44485", + "issue:43673|issue:44561", + "issue:43824|issue:43976", + "issue:43976|issue:44964", + "issue:44246|issue:44871", + "issue:44242|issue:44857", + "issue:45362|issue:45375", + "issue:44162|issue:45200", + "issue:44295|issue:44749", + "issue:44779|issue:45292", + "issue:44877|issue:45375", + "issue:45292|issue:45584", + "issue:45292|issue:45701", + "issue:43901|issue:45003", + "issue:45561|issue:45563", + "issue:44987|issue:45459", + "issue:36246|issue:43596", + "issue:43232|issue:44336", + "issue:43526|issue:45003", + "issue:45375|issue:45759", + "issue:44496|issue:45003", + "issue:43065|issue:43408", + "issue:43257|issue:45137", + "issue:44995|issue:45200", + "issue:43262|issue:44246", + "issue:43475|issue:43540", + "issue:44466|issue:45335", + "issue:44995|issue:45588", + "issue:43653|issue:44162" + ], + "prepared_review_unit_hash": "b95e49dd3041b7833f5c574a5eb241c46dcf4f4c19de48c3c8b7c421aad9a54a", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37092, + "estimated_input_tokens": 9273, + "estimated_eval_tokens": 18802 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is heterogeneous: the soft pairs span unrelated import errors, model/config regressions, generation issues, tokenizer bugs, and performance reports. I would reject every proposed duplicate edge. If forced to choose a representative issue, the Qwen2.5-VL import regression (#43824) is the strongest anchor because it is a clear core-package import failure with the most discussion/references among the set.", + "confidence": 0.68, + "canonical_issue_reason": "Issue #43824 is the most central, user-facing core-package import regression in this set and has the strongest discussion/reference signal, so it is the best representative anchor.", + "canonical_pr_reason": null, + "best_issue_reason": "Among these mostly unrelated reports, #43824 is the best duplicate-triage target because it is concrete, broadly impactful, and well-supported by discussion and inbound references.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36246", + "right": "issue:42757", + "accept": false, + "reason": "Different missing symbols in different libraries/modules; not the same bug." + }, + { + "left": "issue:36246", + "right": "issue:44351", + "accept": false, + "reason": "Qwen import error vs HybridCache import error; unrelated symbols and fixes." + }, + { + "left": "issue:44336", + "right": "issue:44485", + "accept": false, + "reason": "ANSI/terminal rendering bug vs GLM-5 RoPE discussion; unrelated." + }, + { + "left": "issue:43673", + "right": "issue:44561", + "accept": false, + "reason": "Generation cache issue vs trust_remote_code import breakage; different code paths." + }, + { + "left": "issue:43824", + "right": "issue:43976", + "accept": false, + "reason": "Missing model export vs Python-version support issue; not the same bug." + }, + { + "left": "issue:43976", + "right": "issue:44964", + "accept": false, + "reason": "Python compatibility issue vs Phi-4 multimodal loading failure; unrelated." + }, + { + "left": "issue:44246", + "right": "issue:44871", + "accept": false, + "reason": "Import-time slowdown vs Gemma-3 EOS config mismatch; unrelated." + }, + { + "left": "issue:44242", + "right": "issue:44857", + "accept": false, + "reason": "Router-loss omission vs CUDA AMP crash; different failures." + }, + { + "left": "issue:45362", + "right": "issue:45375", + "accept": false, + "reason": "Qwen chat crash vs missing vision-config field; not the same concrete bug." + }, + { + "left": "issue:44162", + "right": "issue:45200", + "accept": false, + "reason": "ESM2 model breakage vs Gemma 4 token-type default; unrelated." + }, + { + "left": "issue:44295", + "right": "issue:44749", + "accept": false, + "reason": "Position buffer read error vs performance regression report; unrelated." + }, + { + "left": "issue:44779", + "right": "issue:45292", + "accept": false, + "reason": "Tokenizer correctness bug vs embedding-resize bug; different code paths." + }, + { + "left": "issue:44877", + "right": "issue:45375", + "accept": false, + "reason": "Granite config loading vs Qwen vision-config field handling; unrelated." + }, + { + "left": "issue:45292", + "right": "issue:45584", + "accept": false, + "reason": "Embedding resize bug vs Whisper empty-transcription failure; unrelated." + }, + { + "left": "issue:45292", + "right": "issue:45701", + "accept": false, + "reason": "Embedding resize bug vs tokenization-version behavior change; unrelated." + }, + { + "left": "issue:43901", + "right": "issue:45003", + "accept": false, + "reason": "Docs mismatch vs sys.modules access bug; unrelated." + }, + { + "left": "issue:45561", + "right": "issue:45563", + "accept": false, + "reason": "xdist file race vs stale generation warning; unrelated." + }, + { + "left": "issue:44987", + "right": "issue:45459", + "accept": false, + "reason": "Model loading failure vs protobuf-error masking; unrelated." + }, + { + "left": "issue:36246", + "right": "issue:43596", + "accept": false, + "reason": "Qwen import regression vs Bert/ZeRO3 indexing error; unrelated." + }, + { + "left": "issue:43232", + "right": "issue:44336", + "accept": false, + "reason": "Generation-kwargs bug vs ANSI output bug; unrelated." + }, + { + "left": "issue:43526", + "right": "issue:45003", + "accept": false, + "reason": "BEiT label reduction bug vs sys.modules access bug; unrelated." + }, + { + "left": "issue:45375", + "right": "issue:45759", + "accept": false, + "reason": "Qwen config field issue vs from_config text_config unwrap bug; different fixes." + }, + { + "left": "issue:44496", + "right": "issue:45003", + "accept": false, + "reason": "Missing model_type for a repo vs sys.modules access bug; unrelated." + }, + { + "left": "issue:43065", + "right": "issue:43408", + "accept": false, + "reason": "Same SAM3 family, but dummy Conv2d vs wrong model-type warning are different bugs." + }, + { + "left": "issue:43257", + "right": "issue:45137", + "accept": false, + "reason": "Qwen/DeepSpeed loading bug vs ZeRO3 deque error; different code paths." + }, + { + "left": "issue:44995", + "right": "issue:45200", + "accept": false, + "reason": "Stale indexer cache vs Gemma token-type default; unrelated." + }, + { + "left": "issue:43262", + "right": "issue:44246", + "accept": false, + "reason": "Audio chat-template sampling-rate bug vs import slowdown; unrelated." + }, + { + "left": "issue:43475", + "right": "issue:43540", + "accept": false, + "reason": "SAM3 output-field bug vs Qwen3OmniMoe video-input error; unrelated." + }, + { + "left": "issue:44466", + "right": "issue:45335", + "accept": false, + "reason": "Device-dependent serialization vs T5Gemma embedding resize; different issues." + }, + { + "left": "issue:44995", + "right": "issue:45588", + "accept": false, + "reason": "Stale cache bug vs flash-attention s_aux handling; unrelated." + }, + { + "left": "issue:43653", + "right": "issue:44162", + "accept": false, + "reason": "Tokenizer special-token registration bug vs ESM2 model breakage; unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 34, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:28282", + "issue:30990", + "issue:41628", + "issue:42371", + "issue:42886", + "issue:42994", + "issue:43232", + "issue:43452", + "issue:43475", + "issue:43482", + "issue:43525", + "issue:43643", + "issue:43646", + "issue:43673", + "issue:43827", + "issue:43931", + "issue:44038", + "issue:44060", + "issue:44077", + "issue:44162", + "issue:44297", + "issue:44361", + "issue:44368", + "issue:44623", + "issue:44734", + "issue:44749", + "issue:44869", + "issue:44933", + "issue:44977", + "issue:45003", + "issue:45081", + "issue:45092", + "issue:45103", + "issue:45137", + "issue:45229", + "issue:45230", + "issue:45310", + "issue:45356", + "issue:45375", + "issue:45381", + "issue:45397", + "issue:45459", + "issue:45478", + "issue:45561", + "issue:45563", + "issue:45600", + "issue:45656" + ], + "soft_pairs": [ + "issue:42886|issue:45229", + "issue:44368|issue:45563", + "issue:44368|issue:44977", + "issue:45397|issue:45656", + "issue:44060|issue:44077", + "issue:45003|issue:45561", + "issue:43673|issue:44734", + "issue:45137|issue:45600", + "issue:43931|issue:44368", + "issue:44933|issue:45459", + "issue:44869|issue:45356", + "issue:44297|issue:44623", + "issue:43646|issue:44162", + "issue:44361|issue:44749", + "issue:43232|issue:43673", + "issue:43452|issue:45003", + "issue:43673|issue:43827", + "issue:44623|issue:45656", + "issue:28282|issue:30990", + "issue:42994|issue:43482", + "issue:44749|issue:45310", + "issue:44749|issue:45656", + "issue:43475|issue:43643", + "issue:42371|issue:45092", + "issue:43475|issue:45381", + "issue:45230|issue:45397", + "issue:44038|issue:44623", + "issue:41628|issue:44933", + "issue:45081|issue:45103", + "issue:45375|issue:45478", + "issue:42994|issue:43525" + ], + "prepared_review_unit_hash": "4046ae5a2a2afd5ac3ab4846fa8b1db659cdd0b86baec027aee28a129e8643dd", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "serialized_chars": 36322, + "estimated_input_tokens": 9081, + "estimated_eval_tokens": 18418 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: most items are separate Transformers regressions, model-specific loading bugs, or unrelated docs/testing issues rather than true duplicates. No soft pair looks safe to merge as one underlying bug/change.", + "confidence": 0.21, + "canonical_issue_reason": "No single issue cleanly represents a duplicate set here; the cluster spans many distinct code paths and model families.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43646 is the broadest representative of the dominant theme (Transformers v5 breaking custom model initialization), but it is still not a reliable duplicate anchor for the rest of the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42886", + "right": "issue:45229", + "accept": false, + "reason": "Tokenizer cache/offline loading failure vs multi-GPU inference CUDA OOM; different failure modes and code paths." + }, + { + "left": "issue:44368", + "right": "issue:45563", + "accept": false, + "reason": "A warning about tie_word_embeddings during Qwen3.5 LoRA fine-tuning is unrelated to a stale paging warning in generate()." + }, + { + "left": "issue:44368", + "right": "issue:44977", + "accept": false, + "reason": "Both mention Qwen3.5, but one is a config warning and the other is a flash-attention generation failure; not the same bug." + }, + { + "left": "issue:45397", + "right": "issue:45656", + "accept": false, + "reason": "Gemma-4 ZeRO3 from_pretrained breakage is unrelated to deepspeed causing optimizer.step to run twice." + }, + { + "left": "issue:44060", + "right": "issue:44077", + "accept": false, + "reason": "Qwen3-Next tied-weights warning and PatchTSMixer post_init policy are different API/validation issues." + }, + { + "left": "issue:45003", + "right": "issue:45561", + "accept": false, + "reason": "Unsafe sys.modules access in modeling_utils is unrelated to a pytest-xdist race on captured_info.txt." + }, + { + "left": "issue:43673", + "right": "issue:44734", + "accept": false, + "reason": "GenerationMixin cache handling during chunked_prefill is a different path from serve KV-cache continuation tensor indexing." + }, + { + "left": "issue:45137", + "right": "issue:45600", + "accept": false, + "reason": "DeepSpeed ZeRO3 deque underflow is unrelated to stale auto_mappings references to removed configs." + }, + { + "left": "issue:43931", + "right": "issue:44368", + "accept": false, + "reason": "Qwen3-VL weight-shape mismatch is a model-loading error, not the LoRA tie_word_embeddings warning." + }, + { + "left": "issue:44933", + "right": "issue:45459", + "accept": false, + "reason": "Missing import from image_utils is unrelated to tokenizer error masking when protobuf is absent." + }, + { + "left": "issue:44869", + "right": "issue:45356", + "accept": false, + "reason": "Whisper timestamp decoding crash and Kimi-K2.5 codec handling regression are different tokenizer/decoding bugs." + }, + { + "left": "issue:44297", + "right": "issue:44623", + "accept": false, + "reason": "tokenizer.save_pretrained writing the wrong class is not the same as processor.save_pretrained missing files." + }, + { + "left": "issue:43646", + "right": "issue:44162", + "accept": false, + "reason": "Generic custom model initialization breakage vs ESM2-specific failure impacting scientists; too broad and different root causes." + }, + { + "left": "issue:44361", + "right": "issue:44749", + "accept": false, + "reason": "MLukeTokenizer task AttributeError and a slowdown after upgrade are unrelated issues." + }, + { + "left": "issue:43232", + "right": "issue:43673", + "accept": false, + "reason": "Both are generation internals, but one is sync_gpus keyword update and the other is chunked_prefill cache missing; not the same bug." + }, + { + "left": "issue:43452", + "right": "issue:45003", + "accept": false, + "reason": "gguf_file breaking AutoTokenizer/AutoModel loading is unrelated to unsafe sys.modules access." + }, + { + "left": "issue:43673", + "right": "issue:43827", + "accept": false, + "reason": "Generation cache bug and docs still referencing removed pipeline() are different kinds of changes." + }, + { + "left": "issue:44623", + "right": "issue:45656", + "accept": false, + "reason": "Missing files from processor.save_pretrained is unrelated to optimizer.step being called twice with deepspeed." + }, + { + "left": "issue:28282", + "right": "issue:30990", + "accept": false, + "reason": "PyTorch missing ImportError and Sentence Transformers hanging on load are not the same underlying issue." + }, + { + "left": "issue:42994", + "right": "issue:43482", + "accept": false, + "reason": "Quantized model saving failure and Qwen2.5-GGUF loading failure are opposite directions and distinct code paths." + }, + { + "left": "issue:44749", + "right": "issue:45310", + "accept": false, + "reason": "Data filtering slowdown after upgrade is unrelated to a Qwen3.5 Moe from_pretrained error." + }, + { + "left": "issue:44749", + "right": "issue:45656", + "accept": false, + "reason": "Performance regression in filtering and deepspeed optimizer duplication are unrelated." + }, + { + "left": "issue:43475", + "right": "issue:43643", + "accept": false, + "reason": "SAM3 missing fpn_position_embeddings and trust_remote_code AutoConfig missing fields are different model/config problems." + }, + { + "left": "issue:42371", + "right": "issue:45092", + "accept": false, + "reason": "TF32 settings API guidance is unrelated to InternVL2 remote-code meta-init incompatibility." + }, + { + "left": "issue:43475", + "right": "issue:45381", + "accept": false, + "reason": "SAM3 video encoder attribute error and Qwen2.5-VL vision_position_ids bug are different model-specific failures." + }, + { + "left": "issue:45230", + "right": "issue:45397", + "accept": false, + "reason": "Generic bug report provides no concrete overlap with Gemma-4 ZeRO3 from_pretrained failure." + }, + { + "left": "issue:44038", + "right": "issue:44623", + "accept": false, + "reason": "Qwen3-VL-Moe v5 breakage and processor.save_pretrained missing files do not share a concrete code path." + }, + { + "left": "issue:41628", + "right": "issue:44933", + "accept": false, + "reason": "Cannot import AutoImageProcessor and nonexistent import from image_utils are similar in surface form only; different symbols/modules." + }, + { + "left": "issue:45081", + "right": "issue:45103", + "accept": false, + "reason": "Mistral regex patch crashing on tokenizer internals is unrelated to docstring processing with future annotations." + }, + { + "left": "issue:45375", + "right": "issue:45478", + "accept": false, + "reason": "Qwen3_5MoeVisionConfig missing a field due to @strict and a generic Qwen3.5 Moe from_pretrained error are too weakly connected to treat as the same bug." + }, + { + "left": "issue:42994", + "right": "issue:43525", + "accept": false, + "reason": "Quantized model saving failure and Llama4Config missing pad_token_id are unrelated model/save vs 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": 2, + "component_count": 16, + "review_unit_index": 35, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:30333", + "issue:30990", + "issue:33290", + "issue:35141", + "issue:36010", + "issue:41628", + "issue:42175", + "issue:42222", + "issue:42673", + "issue:42831", + "issue:42898", + "issue:42994", + "issue:43232", + "issue:43278", + "issue:43377", + "issue:43475", + "issue:43704", + "issue:43723", + "issue:43784", + "issue:43824", + "issue:43874", + "issue:43901", + "issue:44038", + "issue:44060", + "issue:44188", + "issue:44222", + "issue:44242", + "issue:44351", + "issue:44373", + "issue:44496", + "issue:44568", + "issue:44623", + "issue:44661", + "issue:44734", + "issue:44792", + "issue:44964", + "issue:45092", + "issue:45103", + "issue:45125", + "issue:45137", + "issue:45200", + "issue:45310", + "issue:45356", + "issue:45375", + "issue:45561", + "issue:45600", + "issue:45712", + "issue:45812" + ], + "soft_pairs": [ + "issue:42673|issue:43704", + "issue:43475|issue:44661", + "issue:45310|issue:45375", + "issue:41628|issue:44351", + "issue:42831|issue:44222", + "issue:42222|issue:45200", + "issue:44222|issue:45310", + "issue:42994|issue:43824", + "issue:42175|issue:45712", + "issue:36010|issue:41628", + "issue:43377|issue:44242", + "issue:44038|issue:45310", + "issue:44496|issue:45561", + "issue:44964|issue:45137", + "issue:45561|issue:45600", + "issue:42898|issue:44568", + "issue:43901|issue:45561", + "issue:43232|issue:44792", + "issue:30990|issue:35141", + "issue:43232|issue:44188", + "issue:42898|issue:45812", + "issue:44188|issue:44373", + "issue:43784|issue:43824", + "issue:44623|issue:45310", + "issue:43278|issue:45137", + "issue:44734|issue:45103", + "issue:30333|issue:33290", + "issue:43723|issue:44568", + "issue:42898|issue:45356", + "issue:44060|issue:45125", + "issue:43874|issue:45092" + ], + "prepared_review_unit_hash": "57ed0a7806103e4d8b88608682f21780839d6b2d4cbf5f519420334548ff8b65", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37034, + "estimated_input_tokens": 9259, + "estimated_eval_tokens": 18774 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous and not a true duplicate group. I only accept one soft edge: the two identically titled Qwen3ForCausalLM VRAM-leak reports. All other pairs describe different code paths, models, or symptoms.", + "confidence": 0.89, + "canonical_issue_reason": "issue:42673 is the original report for the only clear duplicate pair (with issue:43704): same title, same Qwen3ForCausalLM multi-dataloader-thread VRAM leak symptom.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45310 is the broadest representative of the remaining loose Qwen3.5-MoE subtheme, but it is not a duplicate-safe representative for the whole cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42673", + "right": "issue:43704", + "accept": true, + "reason": "Exact same title and same underlying Qwen3ForCausalLM VRAM leak in multi-dataloader-thread use." + }, + { + "left": "issue:43475", + "right": "issue:44661", + "accept": false, + "reason": "Different bug classes: SAM 3 vision encoder attribute error vs tokenizer-mapping/config helper failure." + }, + { + "left": "issue:45310", + "right": "issue:45375", + "accept": false, + "reason": "Same model family, but different concrete failures: from_pretrained/config loading error vs missing config field being dropped." + }, + { + "left": "issue:41628", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but for unrelated symbols and code paths (AutoImageProcessor vs HybridCache)." + }, + { + "left": "issue:42831", + "right": "issue:44222", + "accept": false, + "reason": "Different FP8 issues: training accuracy regression vs save_pretrained/mode-saving failure." + }, + { + "left": "issue:42222", + "right": "issue:45200", + "accept": false, + "reason": "Unrelated models and symptoms: broken vitpose models vs Gemma 4 mm_token_type_ids defaulting." + }, + { + "left": "issue:44222", + "right": "issue:45310", + "accept": false, + "reason": "One is FP8 save_pretrained for MoE, the other is a Qwen3.5-MoE from_pretrained/config error." + }, + { + "left": "issue:42994", + "right": "issue:43824", + "accept": false, + "reason": "Quantized model saving failure and a separate import error for a multimodal class." + }, + { + "left": "issue:42175", + "right": "issue:45712", + "accept": false, + "reason": "Packaging/backend extra mismatch is unrelated to leftover dummy-class cleanup." + }, + { + "left": "issue:36010", + "right": "issue:41628", + "accept": false, + "reason": "Different missing imports: GenerationMixin vs AutoImageProcessor." + }, + { + "left": "issue:43377", + "right": "issue:44242", + "accept": false, + "reason": "Different subsystems: MIMI padding-mask batching bug vs MoE load-balancing-loss gating." + }, + { + "left": "issue:44038", + "right": "issue:45310", + "accept": false, + "reason": "Same broad Qwen area, but the reported failures are different and not mergeable into one fix." + }, + { + "left": "issue:44496", + "right": "issue:45561", + "accept": false, + "reason": "Model config loading error vs pytest-xdist file race; unrelated root causes." + }, + { + "left": "issue:44964", + "right": "issue:45137", + "accept": false, + "reason": "Model loading incompatibility and DeepSpeed ZeRO3 deque underflow are unrelated failures." + }, + { + "left": "issue:45561", + "right": "issue:45600", + "accept": false, + "reason": "Testing race on captured_info.txt vs stale auto_mappings references; different files and bugs." + }, + { + "left": "issue:42898", + "right": "issue:44568", + "accept": false, + "reason": "Both concern tokenizer behavior, but one is cleanup-space semantics and the other is add_special_tokens not emitting BOS/EOS." + }, + { + "left": "issue:43901", + "right": "issue:45561", + "accept": false, + "reason": "Docs mismatch for text classification pipeline vs a pytest-xdist race bug." + }, + { + "left": "issue:43232", + "right": "issue:44792", + "accept": false, + "reason": "Generation kwargs/sync-gpus bug and a janus image-generation test failure are not the same code path." + }, + { + "left": "issue:30990", + "right": "issue:35141", + "accept": false, + "reason": "Sentence-transformers loading stall vs token-embedding reinitialization after resize; unrelated." + }, + { + "left": "issue:43232", + "right": "issue:44188", + "accept": false, + "reason": "Generation-kwargs update bug vs attention-kernel divergence under torch.compile are different issues." + }, + { + "left": "issue:42898", + "right": "issue:45812", + "accept": false, + "reason": "Tokenizer cleanup behavior change is separate from Granite token-ID regression." + }, + { + "left": "issue:44188", + "right": "issue:44373", + "accept": false, + "reason": "Kernel branching bug vs a wrong docstring; no shared bug or fix." + }, + { + "left": "issue:43784", + "right": "issue:43824", + "accept": false, + "reason": "Both are import-related, but they affect different packages/symbols and stem from different causes." + }, + { + "left": "issue:44623", + "right": "issue:45310", + "accept": false, + "reason": "Processor save_pretrained missing files is unrelated to Qwen3.5-MoE loading errors." + }, + { + "left": "issue:43278", + "right": "issue:45137", + "accept": false, + "reason": "Embedding dtype drift during eval and a ZeRO3 deque IndexError are unrelated." + }, + { + "left": "issue:44734", + "right": "issue:45103", + "accept": false, + "reason": "Serve KV-cache indexing crash vs auto_docstring AttributeError under future annotations; different subsystems." + }, + { + "left": "issue:30333", + "right": "issue:33290", + "accept": false, + "reason": "MLflow reporting after failed training job vs DeepSpeed OOM during Adafactor are unrelated." + }, + { + "left": "issue:43723", + "right": "issue:44568", + "accept": false, + "reason": "Tokenizer loading regression in v5 and missing BOS/EOS with add_special_tokens are different failures." + }, + { + "left": "issue:42898", + "right": "issue:45356", + "accept": false, + "reason": "Different tokenizer regressions: clean_up_tokenization_spaces behavior vs Kimi codec/regex handling." + }, + { + "left": "issue:44060", + "right": "issue:45125", + "accept": false, + "reason": "Different Qwen3.5-MoE config bugs: incorrect tied-weights warning vs missing _tp_plan for tensor parallelism." + }, + { + "left": "issue:43874", + "right": "issue:45092", + "accept": false, + "reason": "Multimodal image-patch counting bug and remote-code meta-init incompatibility are not the same issue." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Grounded overall. The canonical duplicate pair (issue:42673 / issue:43704) is well supported by the packet: identical title and matching VRAM-leak symptom. The remaining soft-edge rejections are conservative and stay within the evidence shown in the issue titles/descriptions. The summary correctly characterizes the cluster as mostly heterogeneous and avoids overstating duplicate evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 36, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:28282", + "issue:30333", + "issue:34689", + "issue:35141", + "issue:36331", + "issue:41628", + "issue:42175", + "issue:42757", + "issue:42831", + "issue:42898", + "issue:43232", + "issue:43479", + "issue:43644", + "issue:43723", + "issue:43873", + "issue:43976", + "issue:44079", + "issue:44188", + "issue:44206", + "issue:44222", + "issue:44261", + "issue:44263", + "issue:44295", + "issue:44297", + "issue:44360", + "issue:44373", + "issue:44448", + "issue:44483", + "issue:44484", + "issue:44485", + "issue:44514", + "issue:44623", + "issue:44779", + "issue:44869", + "issue:44871", + "issue:44933", + "issue:44945", + "issue:44964", + "issue:44977", + "issue:45092", + "issue:45103", + "issue:45310", + "issue:45357", + "issue:45405", + "issue:45406", + "issue:45656", + "issue:45712", + "issue:45834" + ], + "soft_pairs": [ + "issue:42898|issue:44779", + "issue:45405|issue:45712", + "issue:42898|issue:44448", + "issue:44188|issue:44964", + "issue:44933|issue:45712", + "issue:43479|issue:44079", + "issue:44295|issue:45656", + "issue:42175|issue:44933", + "issue:44222|issue:44297", + "issue:43976|issue:44933", + "issue:43479|issue:44869", + "issue:44297|issue:45656", + "issue:44206|issue:45103", + "issue:44222|issue:44623", + "issue:42831|issue:44623", + "issue:41628|issue:42757", + "issue:30333|issue:36331", + "issue:30333|issue:34689", + "issue:43232|issue:45834", + "issue:43723|issue:44977", + "issue:44222|issue:44484", + "issue:44297|issue:45310", + "issue:28282|issue:30333", + "issue:43873|issue:44945", + "issue:30333|issue:35141", + "issue:44263|issue:45092", + "issue:44263|issue:44360", + "issue:44483|issue:45406", + "issue:44373|issue:44485", + "issue:44514|issue:45103", + "issue:44295|issue:44623", + "issue:43479|issue:43644", + "issue:43723|issue:44871", + "issue:45092|issue:45357", + "issue:44261|issue:45092" + ], + "prepared_review_unit_hash": "4f6a9ddb6b63efaaab7190afc3b8417dbd9ab1fd4216c19bee7bfe44c122c11c", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 35, + "serialized_chars": 38022, + "estimated_input_tokens": 9506, + "estimated_eval_tokens": 19268 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The items are a mixed set of unrelated issues rather than one duplicate cluster. None of the soft pairs look like the same underlying bug/change, so all are rejected. #43873 is the best issue anchor because it is an active, concrete bug report with multiple references, but the set overall is heterogeneous.", + "confidence": 0.79, + "canonical_issue_reason": "#43873 is the most active open bug report in the set, with the strongest inbound discussion signal and a concrete runtime-failure focus, so it is the best anchor among these mixed issues.", + "canonical_pr_reason": null, + "best_issue_reason": "#43873 has the broadest relevance and highest activity among the issues here; the rest are narrower, model- or component-specific regressions.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42898", + "right": "issue:44779", + "accept": false, + "reason": "Both involve tokenizer behavior in v5, but one is about `clean_up_tokenization_spaces` semantics and the other is a DeepSeek tokenizer correctness regression." + }, + { + "left": "issue:45405", + "right": "issue:45712", + "accept": false, + "reason": "One is a dependency version bump (`MIN_PEFT_VERSION`), the other is cleanup of dummy torch objects; different problems and fixes." + }, + { + "left": "issue:42898", + "right": "issue:44448", + "accept": false, + "reason": "Both are version-regression reports, but they target different behaviors: token cleanup vs Pegasus output drift." + }, + { + "left": "issue:44188", + "right": "issue:44964", + "accept": false, + "reason": "One is a torch.compile attention-kernel branching bug; the other is a Phi-4 multimodal loading failure. Unrelated code paths." + }, + { + "left": "issue:44933", + "right": "issue:45712", + "accept": false, + "reason": "Both mention imports, but one is a missing symbol from `image_utils` and the other is stray dummy classes leaking into `dir(transformers)`." + }, + { + "left": "issue:43479", + "right": "issue:44079", + "accept": false, + "reason": "Both mention `None`, but one is multimodal config initialization and the other is `ModelOutput` key assignment. Different classes and failures." + }, + { + "left": "issue:44295", + "right": "issue:45656", + "accept": false, + "reason": "One concerns reading a registered buffer; the other is double optimizer stepping under deepspeed. Not the same bug." + }, + { + "left": "issue:42175", + "right": "issue:44933", + "accept": false, + "reason": "Different import/package issues: backend extras missing TensorFlow vs a nonexistent image_utils import." + }, + { + "left": "issue:44222", + "right": "issue:44297", + "accept": false, + "reason": "One is FP8 save_pretrained for MoE models; the other is tokenizer config serialization. Same broad area only superficially." + }, + { + "left": "issue:43976", + "right": "issue:44933", + "accept": false, + "reason": "A Python-version compatibility issue and a missing import are unrelated failures." + }, + { + "left": "issue:43232", + "right": "issue:45834", + "accept": false, + "reason": "One is generation-state handling after `sync_gpus`; the other is an OCR index error in Kosmos2.5. Different code paths." + }, + { + "left": "issue:43723", + "right": "issue:44977", + "accept": false, + "reason": "Both are model/tokenizer generation problems, but one is AutoTokenizer loading in v5 and the other is flash-attention generation behavior for Qwen3.5." + }, + { + "left": "issue:44206", + "right": "issue:45103", + "accept": false, + "reason": "One is a feature extractor argument regression; the other is an auto_docstring crash from future annotations. Not the same underlying bug." + }, + { + "left": "issue:44222", + "right": "issue:44623", + "accept": false, + "reason": "Both touch save_pretrained, but one is MoE FP8 serialization and the other is missing processor files." + }, + { + "left": "issue:42831", + "right": "issue:44623", + "accept": false, + "reason": "Accuracy drift from FineGrainedFP8 is unrelated to missing processor artifacts during save_pretrained." + }, + { + "left": "issue:41628", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but they concern different missing symbols from different modules and likely different fixes." + }, + { + "left": "issue:30333", + "right": "issue:36331", + "accept": false, + "reason": "Training-job reporting/MLflow tracking is unrelated to a Trainer API signature change." + }, + { + "left": "issue:30333", + "right": "issue:34689", + "accept": false, + "reason": "MLflow reporting on failed jobs and model loading breakage in Transformers 4.46.2 are different issues." + }, + { + "left": "issue:43232", + "right": "issue:45834", + "accept": false, + "reason": "Same as above: generation kwargs syncing vs long-input OCR indexing are unrelated." + }, + { + "left": "issue:43723", + "right": "issue:44871", + "accept": false, + "reason": "Tokenizer loading in v5 versus an eos_token_id mismatch for Gemma-3 are different bugs." + }, + { + "left": "issue:44222", + "right": "issue:44484", + "accept": false, + "reason": "FP8 MoE save_pretrained and the default 50GB shard size are unrelated save_pretrained concerns." + }, + { + "left": "issue:44297", + "right": "issue:45310", + "accept": false, + "reason": "Tokenizer-class serialization and a Qwen3.5 MoE from_pretrained regression are different failure modes." + }, + { + "left": "issue:28282", + "right": "issue:30333", + "accept": false, + "reason": "A missing PyTorch dependency import error is unrelated to MLflow not reflecting failed training jobs." + }, + { + "left": "issue:43873", + "right": "issue:44945", + "accept": false, + "reason": "Quantization/offloading behavior is unrelated to incorrect LLM output under pipeline parallelism." + }, + { + "left": "issue:30333", + "right": "issue:35141", + "accept": false, + "reason": "Failed-job MLflow reporting and embedding reinitialization after resizing token embeddings are unrelated." + }, + { + "left": "issue:44263", + "right": "issue:45092", + "accept": false, + "reason": "A torch.split return-value issue in an indexer is unrelated to meta-initialization incompatibility for old InternVL2 checkpoints." + }, + { + "left": "issue:44263", + "right": "issue:44360", + "accept": false, + "reason": "Both are DSA/indexer-related, but one is about split outputs and the other about a missing ReLU. Different concrete bugs." + }, + { + "left": "issue:44483", + "right": "issue:45406", + "accept": false, + "reason": "A chat/completions request handling issue and a Gemma4Processor missing `_tokenizer` attribute are unrelated." + }, + { + "left": "issue:44373", + "right": "issue:44485", + "accept": false, + "reason": "This is a docstring issue, while the other is a RoPE implementation bug. No shared fix." + }, + { + "left": "issue:44514", + "right": "issue:45103", + "accept": false, + "reason": "A batched chat-template crash and an auto_docstring AttributeError are unrelated." + }, + { + "left": "issue:44295", + "right": "issue:44623", + "accept": false, + "reason": "Buffer registration/readback and missing processor files are different save/load problems." + }, + { + "left": "issue:43479", + "right": "issue:43644", + "accept": false, + "reason": "Default config initialization for Phi-4 multimodal is unrelated to junk non-persistent buffers in v5.0.0." + }, + { + "left": "issue:43723", + "right": "issue:44871", + "accept": false, + "reason": "Tokenizer loading regressions and an eos_token_id config mismatch are not the same bug." + }, + { + "left": "issue:45092", + "right": "issue:45357", + "accept": false, + "reason": "Meta-init incompatibility for old checkpoints and incorrect visual encoder keys in `save_pretrained` are distinct regressions." + }, + { + "left": "issue:44261", + "right": "issue:45092", + "accept": false, + "reason": "A missing `rms_norm_eps` in MLA q_a_layernorm causing precision error is unrelated to old InternVL2 meta-init incompatibility." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 37, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:22355", + "issue:28282", + "issue:30990", + "issue:33357", + "issue:38175", + "issue:39401", + "issue:41628", + "issue:42371", + "issue:42757", + "issue:42831", + "issue:42886", + "issue:42907", + "issue:42994", + "issue:43066", + "issue:43122", + "issue:43232", + "issue:43408", + "issue:43475", + "issue:43479", + "issue:43576", + "issue:43723", + "issue:43756", + "issue:43784", + "issue:43824", + "issue:43937", + "issue:44038", + "issue:44060", + "issue:44117", + "issue:44261", + "issue:44263", + "issue:44295", + "issue:44297", + "issue:44373", + "issue:44442", + "issue:44514", + "issue:44568", + "issue:44704", + "issue:44779", + "issue:44913", + "issue:44945", + "issue:45245", + "issue:45278", + "issue:45290", + "issue:45310", + "issue:45593", + "issue:45600", + "issue:45753" + ], + "soft_pairs": [ + "issue:30990|issue:38175", + "issue:41628|issue:43824", + "issue:43479|issue:44913", + "issue:39401|issue:44568", + "issue:22355|issue:28282", + "issue:42831|issue:45310", + "issue:44263|issue:44373", + "issue:42886|issue:42994", + "issue:44945|issue:45753", + "issue:42757|issue:45278", + "issue:42831|issue:44038", + "issue:43576|issue:43784", + "issue:42886|issue:43066", + "issue:43232|issue:45593", + "issue:42371|issue:44263", + "issue:43756|issue:44060", + "issue:44117|issue:44704", + "issue:30990|issue:33357", + "issue:42907|issue:44945", + "issue:44704|issue:45290", + "issue:43122|issue:44514", + "issue:44295|issue:44297", + "issue:41628|issue:45278", + "issue:43723|issue:44779", + "issue:43723|issue:44442", + "issue:43784|issue:45600", + "issue:42907|issue:43937", + "issue:43232|issue:45245", + "issue:44261|issue:44373", + "issue:43408|issue:43475" + ], + "prepared_review_unit_hash": "c3ddf83cac4f5aa02788a580a1b214376fc0224cba0acff98899b032c2d11185", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 35651, + "estimated_input_tokens": 8913, + "estimated_eval_tokens": 18082 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These are mostly unrelated closed issues that only share broad Transformers API/regression wording. The soft pairs are not close enough to be duplicates, so I would reject them all.", + "confidence": 0.71, + "canonical_issue_reason": "issue:45278 is the best umbrella candidate because it broadly covers multiple import regressions after upgrading to v5.5.0 and is still open, making it the most natural central triage point among the listed issues.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the strongest representative issue for this cluster: it is broad, current, and framed as a generalized import-breakage report rather than a narrow model-specific symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:30990", + "right": "issue:38175", + "accept": false, + "reason": "Different failure modes: Sentence-Transformers loading hang vs zero-probabilities in SIGLIP2; no shared code-path implied." + }, + { + "left": "issue:41628", + "right": "issue:43824", + "accept": false, + "reason": "Both are import errors, but for different missing symbols/models (`AutoImageProcessor` vs `Qwen2_5_VLForConditionalGeneration`), so they are not the same bug." + }, + { + "left": "issue:43479", + "right": "issue:44913", + "accept": false, + "reason": "One is config initialization with None for multimodal defaults; the other is a rotary_pct persistence/reload issue in GPTNeoXConfig." + }, + { + "left": "issue:39401", + "right": "issue:44568", + "accept": false, + "reason": "Tokenizer offset_mapping corruption and missing BOS/EOS insertion are distinct tokenizer behaviors and likely separate fixes." + }, + { + "left": "issue:22355", + "right": "issue:28282", + "accept": false, + "reason": "`transformers.onnx` missing module and PyTorch-not-found AutoModel import error are different dependency/import issues." + }, + { + "left": "issue:42831", + "right": "issue:45310", + "accept": false, + "reason": "FineGrainedFP8 accuracy concerns and a Qwen3.5-Moe from_pretrained error are unrelated at the code-path level." + }, + { + "left": "issue:44263", + "right": "issue:44373", + "accept": false, + "reason": "A torch.split return-value bug in GLM MoE indexing is not the same as a docstring correction for position_ids." + }, + { + "left": "issue:42886", + "right": "issue:42994", + "accept": false, + "reason": "Offline tokenizer cache loading failure and quantized model saving failure are separate subsystems." + }, + { + "left": "issue:44945", + "right": "issue:45753", + "accept": false, + "reason": "Pipeline-parallelism output corruption and Qwen3_5 infinite-loop behavior are different runtime bugs with no clear common fix." + }, + { + "left": "issue:42757", + "right": "issue:45278", + "accept": false, + "reason": "`is_offline_mode` import failure is a specific symbol-level breakage; 45278 is a broader umbrella of many import errors, not the same underlying bug." + }, + { + "left": "issue:42831", + "right": "issue:44038", + "accept": false, + "reason": "Both mention model behavior regressions, but one is FP8 accuracy and the other is Qwen3-VL-Moe compatibility; not the same defect." + }, + { + "left": "issue:43576", + "right": "issue:43784", + "accept": false, + "reason": "Broken `transformers env` CLI and a sentence-transformers import NameError are unrelated issues." + }, + { + "left": "issue:42886", + "right": "issue:43066", + "accept": false, + "reason": "Offline cache loading and wrong tokenizer decoder type in v5 are different parts of the tokenizer stack." + }, + { + "left": "issue:43232", + "right": "issue:45593", + "accept": false, + "reason": "Generation kwargs update after sync_gpus and D-FINE auxiliary loss handling are unrelated code paths." + }, + { + "left": "issue:42371", + "right": "issue:44263", + "accept": false, + "reason": "TF32 settings warning and GLM MoE indexing bug do not describe the same problem." + }, + { + "left": "issue:43756", + "right": "issue:44060", + "accept": false, + "reason": "Smollm3 RoPE-layer mismatch and Qwen3-Next tied-weights warning are model-specific configuration issues, not duplicates." + }, + { + "left": "issue:44117", + "right": "issue:44704", + "accept": false, + "reason": "TOKENIZER_MAPPING_NAMES returning None and AutoProcessor not passing kwargs to cached_file are different loader bugs." + }, + { + "left": "issue:30990", + "right": "issue:33357", + "accept": false, + "reason": "A loading hang in Sentence Transformers and a MacOS bus error with a CLIP model are different symptoms and likely different root causes." + }, + { + "left": "issue:42907", + "right": "issue:44945", + "accept": false, + "reason": "Saving dequantized models and incorrect pipeline-parallel outputs are separate functionality failures." + }, + { + "left": "issue:44704", + "right": "issue:45290", + "accept": false, + "reason": "AutoProcessor kwargs propagation and chat template crashes on tool-call assistant messages are unrelated." + }, + { + "left": "issue:43122", + "right": "issue:44514", + "accept": false, + "reason": "Tokenization drift across versions and batched chat-template crash with padding=False are different tokenizer/processor bugs." + }, + { + "left": "issue:44295", + "right": "issue:44297", + "accept": false, + "reason": "Reading a buffer-registered position_ids tensor and saving tokenizer_class mismatch are separate save/load issues." + }, + { + "left": "issue:41628", + "right": "issue:45278", + "accept": false, + "reason": "`AutoImageProcessor` import failure is a specific missing export, while 45278 is a broad report of multiple import errors; not the same concrete bug." + }, + { + "left": "issue:43723", + "right": "issue:44779", + "accept": false, + "reason": "AutoTokenizer loading failure in v5 and Deepseek tokenizer output regressions are both tokenizer-related but not the same failure mode." + }, + { + "left": "issue:43723", + "right": "issue:44442", + "accept": false, + "reason": "AutoTokenizer load failure for FastSpeech2ConformerTokenizer and a specific tokenizer class loading issue are distinct incompatibilities." + }, + { + "left": "issue:43784", + "right": "issue:45600", + "accept": false, + "reason": "Importing sentence-transformers with NameError and broken auto_mappings references to removed Sam3LiteText configs are unrelated import-time problems." + }, + { + "left": "issue:42907", + "right": "issue:43937", + "accept": false, + "reason": "Quantized model save failure and GLM-5 GenerationConfig validation are different bug classes." + }, + { + "left": "issue:43232", + "right": "issue:45245", + "accept": false, + "reason": "Generation-state update bug and category-count limit runtime error are not the same underlying defect." + }, + { + "left": "issue:44261", + "right": "issue:44373", + "accept": false, + "reason": "A missing rms_norm_eps precision issue and a docstring error for position_ids are not duplicates." + }, + { + "left": "issue:43408", + "right": "issue:43475", + "accept": false, + "reason": "Wrong model type warning on sam3_tracker instantiation and missing fpn_position_embeddings attribute are separate SAM 3 video issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 38, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:22355", + "issue:28218", + "issue:29127", + "issue:30990", + "issue:36296", + "issue:39401", + "issue:42222", + "issue:42371", + "issue:42757", + "issue:42831", + "issue:42907", + "issue:43066", + "issue:43116", + "issue:43122", + "issue:43441", + "issue:43452", + "issue:43493", + "issue:43784", + "issue:43824", + "issue:43825", + "issue:43874", + "issue:43937", + "issue:43976", + "issue:43992", + "issue:44038", + "issue:44075", + "issue:44222", + "issue:44295", + "issue:44297", + "issue:44351", + "issue:44360", + "issue:44485", + "issue:44488", + "issue:44521", + "issue:44625", + "issue:44704", + "issue:44779", + "issue:44829", + "issue:44936", + "issue:44964", + "issue:44977", + "issue:45083", + "issue:45200", + "issue:45216", + "issue:45446", + "issue:45478", + "issue:45753" + ], + "soft_pairs": [ + "issue:44360|issue:44485", + "issue:43122|issue:44521", + "issue:44625|issue:44829", + "issue:43116|issue:45200", + "issue:29127|issue:30990", + "issue:42907|issue:44964", + "issue:43122|issue:44779", + "issue:44038|issue:44297", + "issue:42907|issue:43452", + "issue:39401|issue:44488", + "issue:43824|issue:44351", + "issue:44038|issue:44295", + "issue:36296|issue:43116", + "issue:44038|issue:44222", + "issue:39401|issue:44521", + "issue:42757|issue:44351", + "issue:45216|issue:45478", + "issue:43066|issue:44779", + "issue:22355|issue:28218", + "issue:42907|issue:44222", + "issue:43122|issue:44977", + "issue:43784|issue:45446", + "issue:43992|issue:44704", + "issue:43937|issue:44485", + "issue:42222|issue:43441", + "issue:42371|issue:43874", + "issue:43976|issue:45446", + "issue:43493|issue:45753", + "issue:44075|issue:44936", + "issue:42831|issue:45753", + "issue:43116|issue:43825", + "issue:44038|issue:45478", + "issue:44222|issue:45478", + "issue:43116|issue:43493", + "issue:45083|issue:45446" + ], + "prepared_review_unit_hash": "f879cba6393c0337c1dcfc504b973f9cbae1e5ed555e3051064f93d518abccdb", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 35, + "serialized_chars": 37088, + "estimated_input_tokens": 9272, + "estimated_eval_tokens": 18800 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly heterogeneous issue cluster. I only see two plausible duplicate families: tokenizer regressions around v5, and Qwen3.5 save/load regressions around 5.4.0. The rest of the soft pairs point to different subsystems or different failure modes and should stay separate.", + "confidence": 0.66, + "canonical_issue_reason": "issue:43122 is the best anchor for the clearest duplicate family: a broad tokenizer regression between v4.57.3 and v5.0, and it can plausibly subsume the Deepseek tokenizer regression in the accepted pair.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43122 is the strongest overall issue to keep as the representative anchor because it is open, user-facing, and describes a broad v5 tokenizer regression with a clear version comparison.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44360", + "right": "issue:44485", + "accept": false, + "reason": "Different topics: DSA indexer/ReLU discussion vs GLM-5 RoPE implementation." + }, + { + "left": "issue:43122", + "right": "issue:44521", + "accept": false, + "reason": "Tokenizer regression vs multimodal assistant-mask bug; different code paths." + }, + { + "left": "issue:44625", + "right": "issue:44829", + "accept": false, + "reason": "Qwen3.5 num_labels propagation is unrelated to flash_attention_3 training degeneration." + }, + { + "left": "issue:43116", + "right": "issue:45200", + "accept": false, + "reason": "Example-script multi-label output issue vs Gemma 4 mm_token_type_ids defaulting." + }, + { + "left": "issue:29127", + "right": "issue:30990", + "accept": false, + "reason": "LayoutLMv3 error-message clarity and sentence-transformers loading are unrelated." + }, + { + "left": "issue:42907", + "right": "issue:44964", + "accept": false, + "reason": "Different bugs: dequantized save_pretrained failure vs model loading failure for Phi-4 multimodal." + }, + { + "left": "issue:43122", + "right": "issue:44779", + "accept": true, + "reason": "Both describe a v5 tokenizer regression relative to v4 behavior; Deepseek looks like a specific instance of the same changed tokenization path." + }, + { + "left": "issue:44038", + "right": "issue:44297", + "accept": false, + "reason": "Qwen3-VL-Moe failure vs tokenizer_config save_pretrained class mismatch; not the same bug." + }, + { + "left": "issue:42907", + "right": "issue:43452", + "accept": false, + "reason": "Quantized save_pretrained failure and gguf_file from_pretrained breakage are different serialization/loading paths." + }, + { + "left": "issue:39401", + "right": "issue:44488", + "accept": false, + "reason": "Wrong offset_mapping for Qwen3 tokenizer is unrelated to loading cjvt/sleng-bert." + }, + { + "left": "issue:43824", + "right": "issue:44351", + "accept": false, + "reason": "Different missing imports for different symbols; not the same underlying issue." + }, + { + "left": "issue:44038", + "right": "issue:44295", + "accept": false, + "reason": "Qwen3-VL-Moe issue vs position_ids buffer read error; separate problems." + }, + { + "left": "issue:36296", + "right": "issue:43116", + "accept": false, + "reason": "Tensor-parallel training bug vs example-script multi-label classification bug." + }, + { + "left": "issue:44038", + "right": "issue:44222", + "accept": false, + "reason": "Both mention MoE/FP8 contexts, but the concrete failures are different and not mergeable into one fix." + }, + { + "left": "issue:39401", + "right": "issue:44521", + "accept": false, + "reason": "Tokenizer offset_mapping regression is different from multimodal assistant_mask generation." + }, + { + "left": "issue:42757", + "right": "issue:44351", + "accept": false, + "reason": "Import errors from different packages/symbols; unrelated." + }, + { + "left": "issue:45216", + "right": "issue:45478", + "accept": true, + "reason": "Both are Qwen3.5 save/load regressions around 5.4.0, and the save_pretrained corruption plausibly explains the from_pretrained failure." + }, + { + "left": "issue:43066", + "right": "issue:44779", + "accept": false, + "reason": "Wrong tokenizer decoder type is a different tokenizer bug than general incorrect tokenization output." + }, + { + "left": "issue:22355", + "right": "issue:28218", + "accept": false, + "reason": "Missing transformers.onnx module and extra-space-after-added-token are unrelated." + }, + { + "left": "issue:42907", + "right": "issue:44222", + "accept": false, + "reason": "Both involve save_pretrained, but one is dequantized Ministral/Devstral and the other is FP8 MoE; different bugs." + }, + { + "left": "issue:43122", + "right": "issue:44977", + "accept": false, + "reason": "Tokenizer regression vs Qwen3.5 flash-attention generation failure; different failure modes." + }, + { + "left": "issue:43784", + "right": "issue:45446", + "accept": false, + "reason": "Sentence-transformers import NameError and flex_attention PyTorch version check are unrelated." + }, + { + "left": "issue:43992", + "right": "issue:44704", + "accept": false, + "reason": "Missing embed_tokens.weight in UMT5Encoder is unrelated to AutoProcessor kwargs forwarding." + }, + { + "left": "issue:43937", + "right": "issue:44485", + "accept": false, + "reason": "GenerationConfig invalid for GLM-5 is unrelated to GLM-5 RoPE implementation." + }, + { + "left": "issue:42222", + "right": "issue:43441", + "accept": false, + "reason": "Broken vitpose models and Ministral-3 flash-attention failure are unrelated." + }, + { + "left": "issue:42371", + "right": "issue:43874", + "accept": false, + "reason": "TF32 API guidance and missing get_number_of_image_patches are different issues." + }, + { + "left": "issue:43976", + "right": "issue:45446", + "accept": false, + "reason": "Python version compatibility complaint vs incorrect PyTorch version check; not the same bug." + }, + { + "left": "issue:43493", + "right": "issue:45753", + "accept": false, + "reason": "SigLIP2 implementation discrepancy and Qwen3_5 image-specific infinite loop are unrelated." + }, + { + "left": "issue:44075", + "right": "issue:44936", + "accept": false, + "reason": "Optimizer SGD args not used vs trainer.evaluate() after train() are different trainer/optimizer bugs." + }, + { + "left": "issue:42831", + "right": "issue:45753", + "accept": false, + "reason": "FineGrainedFP8 accuracy issue is unrelated to the Qwen3_5 image infinite-loop bug." + }, + { + "left": "issue:43116", + "right": "issue:43825", + "accept": false, + "reason": "Example-script multi-label output bug vs pipeline translation-task error-message issue are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The assessment is grounded in the packet and stays conservative. The two accepted soft pairs are the only ones that look plausibly mergeable into a single bugfix family, while the rejected pairs are described at a sufficiently high level and do not overclaim shared root cause. The summary also avoids overstating the cluster cohesion beyond the two noted families." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 39, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:22355", + "issue:29127", + "issue:33453", + "issue:38617", + "issue:39401", + "issue:41628", + "issue:42175", + "issue:42222", + "issue:42673", + "issue:43012", + "issue:43064", + "issue:43066", + "issue:43122", + "issue:43381", + "issue:43408", + "issue:43421", + "issue:43450", + "issue:43577", + "issue:43673", + "issue:43742", + "issue:43827", + "issue:43937", + "issue:43986", + "issue:44075", + "issue:44117", + "issue:44291", + "issue:44410", + "issue:44483", + "issue:44484", + "issue:44496", + "issue:44779", + "issue:44829", + "issue:44945", + "issue:44964", + "issue:44977", + "issue:45071", + "issue:45072", + "issue:45081", + "issue:45216", + "issue:45278", + "issue:45310", + "issue:45405", + "issue:45446", + "issue:45464", + "issue:45542", + "issue:45563", + "issue:45588", + "issue:45656" + ], + "soft_pairs": [ + "issue:43064|issue:43673", + "issue:43937|issue:45563", + "issue:38617|issue:45278", + "issue:39401|issue:44779", + "issue:33453|issue:39401", + "issue:22355|issue:29127", + "issue:44117|issue:45588", + "issue:43827|issue:45446", + "issue:43381|issue:44945", + "issue:43937|issue:44977", + "issue:45405|issue:45446", + "issue:43450|issue:43986", + "issue:42673|issue:45072", + "issue:44117|issue:45081", + "issue:38617|issue:41628", + "issue:39401|issue:43421", + "issue:44410|issue:45310", + "issue:44829|issue:45216", + "issue:44291|issue:45071", + "issue:44484|issue:45310", + "issue:42222|issue:45542", + "issue:43408|issue:43742", + "issue:43937|issue:44496", + "issue:42175|issue:42222", + "issue:44075|issue:45656", + "issue:44483|issue:45464", + "issue:44964|issue:45278", + "issue:43012|issue:43577", + "issue:43066|issue:43122" + ], + "prepared_review_unit_hash": "50d2aa60e5186173bb384f0093ea0b3f19bd4cc63a9888402710b72884edf344", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36331, + "estimated_input_tokens": 9083, + "estimated_eval_tokens": 18422 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly a set of unrelated Transformers bug reports; the only plausible umbrella issue is the broad import-regression report after upgrading to v5.5.0.", + "confidence": 0.79, + "canonical_issue_reason": "issue:45278 is the broadest and most recent umbrella report, describing multiple import errors after upgrading to 5.5.0.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the best global dedupe target because it is open, broadly scoped, and likely to attract related import-regression reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43064", + "right": "issue:43673", + "accept": false, + "reason": "Different subsystems and failure modes: optimizer state placement vs generation cache handling." + }, + { + "left": "issue:43937", + "right": "issue:45563", + "accept": false, + "reason": "Unrelated bugs: invalid GenerationConfig vs a stale warning about num_return_sequences." + }, + { + "left": "issue:38617", + "right": "issue:45278", + "accept": false, + "reason": "Both are import-related, but one is a specific missing symbol while the other is a broad upgrade report; not clearly the same concrete bug." + }, + { + "left": "issue:39401", + "right": "issue:44779", + "accept": false, + "reason": "Different model/tokenizer regressions with distinct symptoms and code paths." + }, + { + "left": "issue:33453", + "right": "issue:39401", + "accept": false, + "reason": "Both mention tokenizer issues, but loading regressions and offset_mapping bugs are not the same defect." + }, + { + "left": "issue:22355", + "right": "issue:29127", + "accept": false, + "reason": "Completely different areas: ONNX import failure vs LayoutLMv3 error-message clarity." + }, + { + "left": "issue:44117", + "right": "issue:45588", + "accept": false, + "reason": "Tokenizer-mapping fallback bug and flash-attention crash are unrelated." + }, + { + "left": "issue:43827", + "right": "issue:45446", + "accept": false, + "reason": "Docs cleanup for removed pipelines is unrelated to a flex_attention version-check bug." + }, + { + "left": "issue:43381", + "right": "issue:44945", + "accept": false, + "reason": "Gradient-checkpointing eval-mode behavior and pipeline-parallel output corruption are different problems." + }, + { + "left": "issue:43937", + "right": "issue:44977", + "accept": false, + "reason": "Different models and failures: GLM generation config validation vs Qwen3.5 flash-attention generation issues." + }, + { + "left": "issue:45405", + "right": "issue:45446", + "accept": false, + "reason": "PEFT version pinning and PyTorch version gating for AuxRequest are unrelated." + }, + { + "left": "issue:43450", + "right": "issue:43986", + "accept": false, + "reason": "Batched video output shape bug is not the same as an AutoProcessor crash without torchvision." + }, + { + "left": "issue:42673", + "right": "issue:45072", + "accept": false, + "reason": "VRAM leak in multi-threaded inference and bfloat16 dtype mismatches are different bugs." + }, + { + "left": "issue:44117", + "right": "issue:45081", + "accept": false, + "reason": "TOKENIZER_MAPPING_NAMES returning None is unrelated to the Mistral regex patch crash." + }, + { + "left": "issue:38617", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but they concern different missing APIs and likely different regressions." + }, + { + "left": "issue:39401", + "right": "issue:43421", + "accept": false, + "reason": "Offset mapping correctness and runtime post-processor updates are distinct tokenizer behaviors." + }, + { + "left": "issue:44410", + "right": "issue:45310", + "accept": false, + "reason": "Layer projection wiring in qwen3next is not the same as Qwen3.5 MoE loading failure." + }, + { + "left": "issue:44829", + "right": "issue:45216", + "accept": false, + "reason": "Degenerate training with flash_attention_3 and incorrect saved checkpoints are different failure modes." + }, + { + "left": "issue:44291", + "right": "issue:45071", + "accept": false, + "reason": "init_empty_weights argument handling and PretrainedConfig type checking are separate v5 regressions." + }, + { + "left": "issue:44484", + "right": "issue:45310", + "accept": false, + "reason": "save_pretrained shard-size behavior is unrelated to the Qwen3.5 MoE from_pretrained error." + }, + { + "left": "issue:42222", + "right": "issue:45542", + "accept": false, + "reason": "VitPose model breakage and missing TensorFlow backend due to tensorboard-only install are unrelated." + }, + { + "left": "issue:43408", + "right": "issue:43742", + "accept": false, + "reason": "A model-type warning for sam3 and a MobileLLM loading key error are different issues." + }, + { + "left": "issue:44075", + "right": "issue:45656", + "accept": false, + "reason": "Wrong SGD argument usage is not the same as deepspeed calling optimizer.step twice." + }, + { + "left": "issue:44483", + "right": "issue:45464", + "accept": false, + "reason": "Both hit chat/completions, but one is a general API rejection and the other is a streaming-inference failure for a specific model." + }, + { + "left": "issue:44964", + "right": "issue:45278", + "accept": false, + "reason": "Model loading failure for Phi-4 multimodal is not the same as broad import errors after upgrading." + }, + { + "left": "issue:43012", + "right": "issue:43577", + "accept": false, + "reason": "A compiler warning about bfloat16 precision is not the same as model dtype fields remaining float32 on load." + }, + { + "left": "issue:43066", + "right": "issue:43122", + "accept": false, + "reason": "Tokenizer decoder-type mismatch and changed tokenization output are related at a high level but not clearly the same concrete bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 40, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:38617", + "issue:41628", + "issue:42222", + "issue:42371", + "issue:42673", + "issue:42757", + "issue:42831", + "issue:43012", + "issue:43064", + "issue:43097", + "issue:43335", + "issue:43408", + "issue:43441", + "issue:43452", + "issue:43874", + "issue:43906", + "issue:43931", + "issue:43976", + "issue:43986", + "issue:44038", + "issue:44062", + "issue:44117", + "issue:44220", + "issue:44261", + "issue:44263", + "issue:44315", + "issue:44351", + "issue:44368", + "issue:44410", + "issue:44484", + "issue:44485", + "issue:44493", + "issue:44704", + "issue:44829", + "issue:44945", + "issue:44964", + "issue:44977", + "issue:44987", + "issue:45071", + "issue:45103", + "issue:45200", + "issue:45245", + "issue:45341", + "issue:45375", + "issue:45459", + "issue:45478", + "issue:45542", + "issue:45588" + ], + "soft_pairs": [ + "issue:42371|issue:44261", + "issue:38617|issue:44220", + "issue:44410|issue:45478", + "issue:44484|issue:45478", + "issue:43874|issue:44261", + "issue:43097|issue:44493", + "issue:44263|issue:44485", + "issue:42222|issue:45459", + "issue:43012|issue:43408", + "issue:43441|issue:44829", + "issue:41628|issue:45071", + "issue:42673|issue:44977", + "issue:45071|issue:45542", + "issue:42371|issue:42831", + "issue:42673|issue:43906", + "issue:43931|issue:44038", + "issue:44117|issue:44987", + "issue:43097|issue:43452", + "issue:43335|issue:45071", + "issue:43976|issue:44945", + "issue:43408|issue:44368", + "issue:43986|issue:44484", + "issue:43874|issue:44263", + "issue:44829|issue:45245", + "issue:38617|issue:42757", + "issue:43064|issue:44315", + "issue:44410|issue:45375", + "issue:38617|issue:44351", + "issue:43097|issue:45588", + "issue:44062|issue:44117", + "issue:42673|issue:45200", + "issue:44038|issue:44410", + "issue:44964|issue:45071", + "issue:44704|issue:45103", + "issue:44261|issue:44485", + "issue:43931|issue:44410", + "issue:44964|issue:45341" + ], + "prepared_review_unit_hash": "110c070d644d40a58a8cd8e90ed5b92f5d5f702c2843e47158133970386f4cef", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 37, + "serialized_chars": 38745, + "estimated_input_tokens": 9687, + "estimated_eval_tokens": 19630 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is heterogeneous: most items are separate Transformers regressions, import errors, or model-specific bugs rather than duplicates. I would keep one broad API-regression issue as the cluster anchor, but I do not see any soft-edge pair that should be merged as the same underlying defect.", + "confidence": 0.29, + "canonical_issue_reason": "issue:43097 is the broadest, most central regression-style report in this set and has downstream references; it is the best anchor if one issue must represent the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43097 is the most generally phrased user-facing breakage report and the strongest candidate to keep as the representative issue for triage.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42371", + "right": "issue:44261", + "accept": false, + "reason": "TF32 API-setting guidance vs a multimodal precision bug in MLA layernorm; different symptoms and code paths." + }, + { + "left": "issue:38617", + "right": "issue:44220", + "accept": false, + "reason": "Different import failure and audio feature extraction bug; no shared underlying defect." + }, + { + "left": "issue:44410", + "right": "issue:45478", + "accept": false, + "reason": "Separate Qwen-family model issues: missing projections vs from_pretrained loading error." + }, + { + "left": "issue:44484", + "right": "issue:45478", + "accept": false, + "reason": "Shard-size question is unrelated to the Qwen3.5 MoE loading failure." + }, + { + "left": "issue:43874", + "right": "issue:44261", + "accept": false, + "reason": "Image processor missing method vs MLA precision/config issue; unrelated subsystems." + }, + { + "left": "issue:43097", + "right": "issue:44493", + "accept": false, + "reason": "Embedding-tying regression is unrelated to unexpected position-id keys." + }, + { + "left": "issue:44263", + "right": "issue:44485", + "accept": false, + "reason": "GLM indexer split behavior and GLM-5 RoPE implementation are different bugs." + }, + { + "left": "issue:42222", + "right": "issue:45459", + "accept": false, + "reason": "VitPose breakage vs tokenizer protobuf-error masking; different failure modes and fixes." + }, + { + "left": "issue:43012", + "right": "issue:43408", + "accept": false, + "reason": "bfloat16 precision warning and SAM3 model-type warning are distinct issues." + }, + { + "left": "issue:43441", + "right": "issue:44829", + "accept": false, + "reason": "Both involve flash attention, but different models and outcomes: load failure vs degenerate training." + }, + { + "left": "issue:41628", + "right": "issue:45071", + "accept": false, + "reason": "Missing AutoImageProcessor import and PretrainedConfig type-checking regression are unrelated." + }, + { + "left": "issue:42673", + "right": "issue:44977", + "accept": false, + "reason": "VRAM leak in multi-threaded loading vs flash-attention generation issue; different code paths." + }, + { + "left": "issue:45071", + "right": "issue:45542", + "accept": false, + "reason": "Type checking regression is unrelated to TensorFlow backend detection when only tensorboard is installed." + }, + { + "left": "issue:42371", + "right": "issue:42831", + "accept": false, + "reason": "TF32 configuration warning is unrelated to FineGrainedFP8 accuracy problems." + }, + { + "left": "issue:42673", + "right": "issue:43906", + "accept": false, + "reason": "VRAM leak report is not the same as the isolated reproduction of a different referenced issue." + }, + { + "left": "issue:43931", + "right": "issue:44038", + "accept": false, + "reason": "Model weight-shape mismatch and Qwen3-VL-Moe loading issue are distinct model-loading problems." + }, + { + "left": "issue:44117", + "right": "issue:44987", + "accept": false, + "reason": "Tokenizer mapping None bug and a specific model load failure are not the same defect." + }, + { + "left": "issue:43097", + "right": "issue:43452", + "accept": false, + "reason": "Embedding-tie API removal and gguf_file loading breakage are separate regressions." + }, + { + "left": "issue:43335", + "right": "issue:45071", + "accept": false, + "reason": "SwitchTransformers sparse-layer bug is unrelated to PretrainedConfig type checking." + }, + { + "left": "issue:43976", + "right": "issue:44945", + "accept": false, + "reason": "Python-version support issue and pipeline-parallelism output corruption are different problems." + }, + { + "left": "issue:43408", + "right": "issue:44368", + "accept": false, + "reason": "SAM3 config warning and Qwen3.5 LoRA tie-word-embeddings warning are unrelated warnings." + }, + { + "left": "issue:43986", + "right": "issue:44484", + "accept": false, + "reason": "AutoProcessor/torchvision crash and save_pretrained shard-size behavior are unrelated." + }, + { + "left": "issue:43874", + "right": "issue:44263", + "accept": false, + "reason": "Missing image-patch method and torch.split return-value issue affect different model components." + }, + { + "left": "issue:44829", + "right": "issue:45245", + "accept": false, + "reason": "FlashAttention training degeneration is unrelated to categorical-cardinality RuntimeError." + }, + { + "left": "issue:38617", + "right": "issue:42757", + "accept": false, + "reason": "Two separate import errors from different modules and symbols; not the same missing API." + }, + { + "left": "issue:43064", + "right": "issue:44315", + "accept": false, + "reason": "FSDP2 optimizer-state corruption and Liger Kernel not applied with model_init are different training-path bugs." + }, + { + "left": "issue:44410", + "right": "issue:45375", + "accept": false, + "reason": "Missing Qwen3Next projections and missing deepstack_visual_indexes field are unrelated config/model-definition issues." + }, + { + "left": "issue:38617", + "right": "issue:44351", + "accept": false, + "reason": "Different missing exports from transformers; no evidence they share one underlying breakage." + }, + { + "left": "issue:43097", + "right": "issue:45588", + "accept": false, + "reason": "Embedding tying regression is unrelated to flash_attention.py crashing on sink-less models." + }, + { + "left": "issue:44062", + "right": "issue:44117", + "accept": false, + "reason": "AddedToken argument collision and tokenizer mapping None are separate tokenizer bugs." + }, + { + "left": "issue:42673", + "right": "issue:45200", + "accept": false, + "reason": "VRAM leak in dataloader threads is unrelated to mm_token_type_ids defaults for text-only fine-tuning." + }, + { + "left": "issue:44038", + "right": "issue:44410", + "accept": false, + "reason": "Different Qwen-family model failures: Qwen3-VL-Moe load issue vs Qwen3Next missing projections." + }, + { + "left": "issue:44964", + "right": "issue:45071", + "accept": false, + "reason": "Phi-4 multimodal loading failure is unrelated to PretrainedConfig type checking." + }, + { + "left": "issue:44704", + "right": "issue:45103", + "accept": false, + "reason": "cached_file kwargs forwarding bug and auto-docstring annotations crash are separate utilities issues." + }, + { + "left": "issue:44261", + "right": "issue:44485", + "accept": false, + "reason": "MLA rms_norm_eps precision bug and GLM-5 RoPE implementation issue are not the same code-path problem." + }, + { + "left": "issue:43931", + "right": "issue:44410", + "accept": false, + "reason": "Qwen3-VL weight-shape mismatch and Qwen3Next missing attention projections are different model regressions." + }, + { + "left": "issue:44964", + "right": "issue:45341", + "accept": false, + "reason": "Model loading failure and a testing_utils bug are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 41, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:36683", + "issue:38617", + "issue:42617", + "issue:42757", + "issue:42886", + "issue:42907", + "issue:42994", + "issue:43012", + "issue:43064", + "issue:43066", + "issue:43097", + "issue:43208", + "issue:43299", + "issue:43381", + "issue:43475", + "issue:43502", + "issue:43526", + "issue:43550", + "issue:43618", + "issue:43761", + "issue:43824", + "issue:43825", + "issue:43867", + "issue:43873", + "issue:43901", + "issue:43906", + "issue:43986", + "issue:43992", + "issue:44038", + "issue:44117", + "issue:44230", + "issue:44368", + "issue:44380", + "issue:44483", + "issue:44484", + "issue:44514", + "issue:44655", + "issue:44683", + "issue:45216", + "issue:45290", + "issue:45341", + "issue:45372", + "issue:45381", + "issue:45561", + "issue:45588", + "issue:45753", + "issue:45859" + ], + "soft_pairs": [ + "issue:43502|issue:43992", + "issue:45341|issue:45859", + "issue:43986|issue:44117", + "issue:43097|issue:43873", + "issue:43066|issue:43906", + "issue:43986|issue:45290", + "issue:45341|issue:45561", + "issue:43986|issue:45372", + "issue:43097|issue:43901", + "issue:42617|issue:45341", + "issue:43986|issue:45341", + "issue:43825|issue:44655", + "issue:45341|issue:45588", + "issue:43992|issue:44484", + "issue:43012|issue:43550", + "issue:43208|issue:43550", + "issue:43012|issue:44368", + "issue:42886|issue:43381", + "issue:42907|issue:45753", + "issue:42907|issue:44655", + "issue:43208|issue:43526", + "issue:44483|issue:44514", + "issue:43012|issue:44683", + "issue:42757|issue:43824", + "issue:38617|issue:43502", + "issue:44483|issue:45290", + "issue:44038|issue:44230", + "issue:43618|issue:43761", + "issue:43064|issue:44380", + "issue:43299|issue:43867", + "issue:44483|issue:45381", + "issue:43901|issue:44655", + "issue:36683|issue:43475", + "issue:43867|issue:45216", + "issue:42994|issue:44655" + ], + "prepared_review_unit_hash": "16cc998b10556187579de00a0084a93b8b55690705e42711faa2abed4075651f", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 35, + "serialized_chars": 37413, + "estimated_input_tokens": 9354, + "estimated_eval_tokens": 18964 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is mostly a grab-bag of unrelated Transformers issues. The only plausible duplicate pair is the CLIP vision v5 regression around missing optional outputs; everything else appears to target different code paths.", + "confidence": 0.76, + "canonical_issue_reason": "issue:43761 is the strongest representative of the only real duplicate cluster here: a CLIPVisionModel v5 regression with a clear symptom, reproduction context, and broader discussion.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43761 is the most actionable and representative issue in the set, and it best captures the shared CLIP output regression theme.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43502", + "right": "issue:43992", + "accept": false, + "reason": "Different failure modes: one is hub/API fetches despite local_files_only, the other is a UMT5 encoder checkpoint weight-loading omission." + }, + { + "left": "issue:45341", + "right": "issue:45859", + "accept": false, + "reason": "Unrelated components: patched testing utils race vs Qwen3_5MoeTextRotaryEmbedding CPU offload incompatibility." + }, + { + "left": "issue:43986", + "right": "issue:44117", + "accept": false, + "reason": "Both concern loading, but one is AutoProcessor/torchvision availability and the other is a tokenizer mapping None-handling bug." + }, + { + "left": "issue:43097", + "right": "issue:43873", + "accept": false, + "reason": "Different subsystems: removed tie_embeddings API vs quantization/offloading not behaving as expected." + }, + { + "left": "issue:43066", + "right": "issue:43906", + "accept": false, + "reason": "Insufficient evidence of the same bug; one is a tokenizer decoder-type regression, the other is only a reproduction of a separate linked issue." + }, + { + "left": "issue:43986", + "right": "issue:45290", + "accept": false, + "reason": "Distinct bugs: processor loading without torchvision vs chat-template handling of tool-call assistant messages." + }, + { + "left": "issue:45341", + "right": "issue:45561", + "accept": false, + "reason": "Testing-utils file race and pytest-xdist worker capture are different issues, not the same underlying defect." + }, + { + "left": "issue:43986", + "right": "issue:45372", + "accept": false, + "reason": "Different import/loading problems with different missing dependencies and code paths." + }, + { + "left": "issue:43097", + "right": "issue:43901", + "accept": false, + "reason": "API removal versus docs/behavior mismatch in a text classification pipeline." + }, + { + "left": "issue:42617", + "right": "issue:45341", + "accept": false, + "reason": "3d_parallel.py runtime failure is unrelated to the testing_utils bug." + }, + { + "left": "issue:43986", + "right": "issue:45341", + "accept": false, + "reason": "Processor-loading crash and testing-utils race are unrelated." + }, + { + "left": "issue:43825", + "right": "issue:44655", + "accept": false, + "reason": "Pipeline task-message behavior issue and pipeline save_pretrained serialization issue are different bugs." + }, + { + "left": "issue:45341", + "right": "issue:45588", + "accept": false, + "reason": "Testing-utils race is unrelated to flash_attention crashing on sink-less models." + }, + { + "left": "issue:43992", + "right": "issue:44484", + "accept": false, + "reason": "Checkpoint weight loading problem vs save_pretrained shard-size question; not the same defect." + }, + { + "left": "issue:43012", + "right": "issue:43550", + "accept": false, + "reason": "A PyTorch warning during bfloat16 compilation is not the same as an SDPA torch.compile failure." + }, + { + "left": "issue:43208", + "right": "issue:43550", + "accept": false, + "reason": "xLSTM training blockers and Bamba SDPA compile failure are different model-specific bugs." + }, + { + "left": "issue:43012", + "right": "issue:44368", + "accept": false, + "reason": "Both mention warnings, but they stem from different causes and different model/config paths." + }, + { + "left": "issue:42886", + "right": "issue:43381", + "accept": false, + "reason": "Offline tokenizer caching and gradient-checkpointing eval-mode behavior are unrelated." + }, + { + "left": "issue:42907", + "right": "issue:45753", + "accept": false, + "reason": "Quantized save failure and Qwen3_5 infinite-loop generation are different problems." + }, + { + "left": "issue:42907", + "right": "issue:44655", + "accept": false, + "reason": "Saving dequantized models and saving Pipeline objects are distinct save paths with different failures." + }, + { + "left": "issue:43208", + "right": "issue:43526", + "accept": false, + "reason": "xLSTM training bugs do not match the BeitImageProcessorFast reduce_labels bug." + }, + { + "left": "issue:44483", + "right": "issue:44514", + "accept": false, + "reason": "Both involve chat/completions behavior, but one is an API acceptance regression and the other is a chat-template batching crash." + }, + { + "left": "issue:43012", + "right": "issue:44683", + "accept": false, + "reason": "Different attention/compile warnings and failures; no shared concrete bug path." + }, + { + "left": "issue:42757", + "right": "issue:43824", + "accept": false, + "reason": "Separate import errors from different packages/classes." + }, + { + "left": "issue:38617", + "right": "issue:43502", + "accept": false, + "reason": "Configuration-utils import error is unrelated to local_files_only network requests." + }, + { + "left": "issue:44483", + "right": "issue:45290", + "accept": false, + "reason": "Different layers: /v1/chat/completions request handling vs apply_chat_template tokenization crash." + }, + { + "left": "issue:44038", + "right": "issue:44230", + "accept": false, + "reason": "Both mention Qwen3 VL/Moe, but one is a model-loading regression and the other is fp8 inference support." + }, + { + "left": "issue:43618", + "right": "issue:43761", + "accept": true, + "reason": "Same underlying CLIP vision v5 regression: optional outputs are being dropped from CLIPVisionModel/CLIPOutput in the forward path." + }, + { + "left": "issue:43064", + "right": "issue:44380", + "accept": false, + "reason": "FSDP2/PEFT optimizer-state mismatch is unrelated to GPT2 attention scaling under SDPA/FlashAttention." + }, + { + "left": "issue:43299", + "right": "issue:43867", + "accept": false, + "reason": "Qwen3VL-Moe loading regression and sorted-state_dict load failure are different model-loading issues." + }, + { + "left": "issue:42994", + "right": "issue:44655", + "accept": false, + "reason": "Quantized model saving failure and pipeline object serialization are different save_pretrained paths." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative: most pairs are clearly unrelated, and the only accepted edge (issue:43618 \u2194 issue:43761) is well supported by the shared CLIP vision v5 optional-output regression. I don\u2019t see overstatement beyond what the issue titles and descriptions justify." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 42, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:28282", + "issue:33453", + "issue:36010", + "issue:36296", + "issue:36683", + "issue:41669", + "issue:42757", + "issue:42890", + "issue:43064", + "issue:43066", + "issue:43097", + "issue:43299", + "issue:43352", + "issue:43441", + "issue:43525", + "issue:43575", + "issue:43618", + "issue:43756", + "issue:43867", + "issue:43881", + "issue:43906", + "issue:43937", + "issue:43976", + "issue:43992", + "issue:44077", + "issue:44117", + "issue:44220", + "issue:44242", + "issue:44246", + "issue:44263", + "issue:44355", + "issue:44360", + "issue:44380", + "issue:44485", + "issue:44492", + "issue:44655", + "issue:44855", + "issue:44938", + "issue:45216", + "issue:45310", + "issue:45357", + "issue:45375", + "issue:45381", + "issue:45440", + "issue:45478", + "issue:45479", + "issue:45561", + "issue:45753" + ], + "soft_pairs": [ + "issue:43352|issue:43937", + "issue:36010|issue:42757", + "issue:43066|issue:45381", + "issue:43756|issue:44485", + "issue:44220|issue:44655", + "issue:44263|issue:45440", + "issue:36683|issue:43525", + "issue:43618|issue:45216", + "issue:43906|issue:45753", + "issue:36683|issue:44242", + "issue:43299|issue:45753", + "issue:36683|issue:43881", + "issue:43352|issue:43976", + "issue:43441|issue:44380", + "issue:43992|issue:45310", + "issue:43352|issue:44380", + "issue:43867|issue:45375", + "issue:44380|issue:45479", + "issue:41669|issue:44246", + "issue:43352|issue:45478", + "issue:43618|issue:44380", + "issue:44355|issue:44855", + "issue:43064|issue:44492", + "issue:36683|issue:44117", + "issue:42890|issue:45561", + "issue:43097|issue:43352", + "issue:43867|issue:45357", + "issue:43976|issue:44938", + "issue:43992|issue:45478", + "issue:44360|issue:45440", + "issue:43064|issue:44655", + "issue:36296|issue:43575", + "issue:44077|issue:44380", + "issue:28282|issue:33453" + ], + "prepared_review_unit_hash": "d689830de7829b4778a88b8a71a54832f6a4e21ab0bcaab7f579b11fa020b9ac", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37429, + "estimated_input_tokens": 9358, + "estimated_eval_tokens": 18972 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is noisy: the items share broad Transformers/v5 regression language, but they describe distinct bugs, models, and failure modes rather than true duplicates. I reject all soft-edge matches.", + "confidence": 0.96, + "canonical_issue_reason": "No single issue is a clear duplicate hub; the set spans unrelated loading, config, attention, training, and test failures.", + "canonical_pr_reason": null, + "best_issue_reason": "No global best issue stands out as a representative duplicate target because the underlying bugs are heterogeneous.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43352", + "right": "issue:43937", + "accept": false, + "reason": "FlashAttention unsupported for NemotronHForCausalLM is unrelated to GLM-5 generation config validity." + }, + { + "left": "issue:36010", + "right": "issue:42757", + "accept": false, + "reason": "GenerationMixin import failure and is_offline_mode import failure are different missing-symbol regressions." + }, + { + "left": "issue:43066", + "right": "issue:45381", + "accept": false, + "reason": "Tokenizer decoder type regression is unrelated to Qwen2.5-VL vision_position_ids correctness." + }, + { + "left": "issue:43756", + "right": "issue:44485", + "accept": false, + "reason": "Smollm3 RoPE-layer mismatch and GLM-5 RoPE implementation are different model-specific bugs." + }, + { + "left": "issue:44220", + "right": "issue:44655", + "accept": false, + "reason": "Torch fbank feature extraction and Pipeline save_pretrained are unrelated code paths." + }, + { + "left": "issue:44263", + "right": "issue:45440", + "accept": false, + "reason": "GlmMoeDsaIndexer torch.split behavior and DeepseekV3MoE divergence are different model implementations." + }, + { + "left": "issue:36683", + "right": "issue:43525", + "accept": false, + "reason": "Gemma3Config missing vocab_size and Llama4Config missing pad_token_id are separate config-attribute bugs." + }, + { + "left": "issue:43618", + "right": "issue:45216", + "accept": false, + "reason": "CLIPOutput attentions assignment and Qwen3.5 save_pretrained checkpoint corruption are unrelated." + }, + { + "left": "issue:43906", + "right": "issue:45753", + "accept": false, + "reason": "An isolated reproduction of issue 38071 is not the same bug as a Qwen3_5 image infinite loop." + }, + { + "left": "issue:36683", + "right": "issue:44242", + "accept": false, + "reason": "Missing vocab_size in Gemma3Config is unrelated to load-balancing loss handling when output_router_logits=False." + }, + { + "left": "issue:43299", + "right": "issue:45753", + "accept": false, + "reason": "Qwen3VL MoE loading failure and Qwen3_5 image looping are different symptoms and likely different causes." + }, + { + "left": "issue:36683", + "right": "issue:43881", + "accept": false, + "reason": "Gemma3Config vocab_size absence does not match glm-4v-9b loading failure." + }, + { + "left": "issue:43352", + "right": "issue:43976", + "accept": false, + "reason": "FlashAttention support in Nemotron is unrelated to Python version support in Transformers 5.1.0." + }, + { + "left": "issue:43441", + "right": "issue:44380", + "accept": false, + "reason": "Ministral-3 FlashAttention failure and GPT2 attention scaling ignored are distinct attention-path bugs." + }, + { + "left": "issue:43992", + "right": "issue:45310", + "accept": false, + "reason": "UMT5Encoder missing embed_tokens.weight and Qwen3.5 MoE from_pretrained error are different loading issues." + }, + { + "left": "issue:43352", + "right": "issue:44380", + "accept": false, + "reason": "Unsupported FlashAttention for Nemotron is not the same as GPT2 scaling being ignored in backend attention implementations." + }, + { + "left": "issue:43867", + "right": "issue:45375", + "accept": false, + "reason": "State-dict ordering load error and missing deepstack_visual_indexes are unrelated checkpoint/config problems." + }, + { + "left": "issue:44380", + "right": "issue:45479", + "accept": false, + "reason": "Attention scaling bug and degenerate zero-loss classification bug are unrelated." + }, + { + "left": "issue:41669", + "right": "issue:44246", + "accept": false, + "reason": "Removing import * from models and intermittent import slowdown are different concerns." + }, + { + "left": "issue:43352", + "right": "issue:45478", + "accept": false, + "reason": "Nemotron FlashAttention unsupported is different from Qwen3.5 MoE from_pretrained failure." + }, + { + "left": "issue:43618", + "right": "issue:44380", + "accept": false, + "reason": "Missing CLIPOutput attentions assignment is unrelated to GPT2 attention scaling under SDPA/FlashAttention." + }, + { + "left": "issue:44355", + "right": "issue:44855", + "accept": false, + "reason": "Compiled Python file errors and DebertaV2Model import IndentationError are not the same defect." + }, + { + "left": "issue:43064", + "right": "issue:44492", + "accept": false, + "reason": "FSDP2/PEFT optimizer-state bug and a cache-strategies typo are unrelated." + }, + { + "left": "issue:36683", + "right": "issue:44117", + "accept": false, + "reason": "Gemma3Config vocab_size absence and TOKENIZER_MAPPING_NAMES returning None are separate metadata bugs." + }, + { + "left": "issue:42890", + "right": "issue:45561", + "accept": false, + "reason": "Missing set_seed in integration tests and xdist race on captured_info.txt are different test flakiness causes." + }, + { + "left": "issue:43097", + "right": "issue:43352", + "accept": false, + "reason": "Removed tie_embeddings_and_encoder_decoder API and FlashAttention support failure are unrelated breakages." + }, + { + "left": "issue:43867", + "right": "issue:45357", + "accept": false, + "reason": "Sorted state_dict load failure and incorrect visual encoder keys on save_pretrained are different serialization bugs." + }, + { + "left": "issue:43976", + "right": "issue:44938", + "accept": false, + "reason": "Python 3.9/3.10 compatibility and Python 3.14 load failure are not the same issue." + }, + { + "left": "issue:43992", + "right": "issue:45478", + "accept": false, + "reason": "UMT5Encoder missing embed_tokens.weight is unrelated to Qwen3.5 MoE from_pretrained errors." + }, + { + "left": "issue:44360", + "right": "issue:45440", + "accept": false, + "reason": "DSA indexer ReLU discussion and DeepseekV3MoE divergence are different model internals." + }, + { + "left": "issue:43064", + "right": "issue:44655", + "accept": false, + "reason": "Trainer/FSDP2 optimizer-state bug and pipeline save_pretrained issue do not share a code path." + }, + { + "left": "issue:36296", + "right": "issue:43575", + "accept": false, + "reason": "Tensor-parallel training bug and tp-induced OOM while loading Qwen2-57B-A14B-Instruct are related broadly only by TP, not by the same bug." + }, + { + "left": "issue:44077", + "right": "issue:44380", + "accept": false, + "reason": "patchtsmixer post_init policy and GPT2 attention scaling are unrelated." + }, + { + "left": "issue:28282", + "right": "issue:33453", + "accept": false, + "reason": "AutoModel PyTorch ImportError and tokenizer loading regression are different failure modes." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 43, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:30333", + "issue:30990", + "issue:31795", + "issue:33453", + "issue:34689", + "issue:36296", + "issue:42548", + "issue:42831", + "issue:42890", + "issue:43010", + "issue:43502", + "issue:43618", + "issue:43723", + "issue:43827", + "issue:43867", + "issue:43874", + "issue:43901", + "issue:44062", + "issue:44075", + "issue:44112", + "issue:44222", + "issue:44230", + "issue:44315", + "issue:44351", + "issue:44355", + "issue:44360", + "issue:44368", + "issue:44387", + "issue:44484", + "issue:44485", + "issue:44556", + "issue:44655", + "issue:44749", + "issue:44857", + "issue:44938", + "issue:44961", + "issue:44964", + "issue:44977", + "issue:45071", + "issue:45125", + "issue:45278", + "issue:45341", + "issue:45375", + "issue:45478", + "issue:45588", + "issue:45600", + "issue:45850" + ], + "soft_pairs": [ + "issue:43867|issue:44484", + "issue:43618|issue:44857", + "issue:43618|issue:44977", + "issue:43618|issue:45588", + "issue:43901|issue:44938", + "issue:44655|issue:44938", + "issue:42890|issue:44964", + "issue:42890|issue:44112", + "issue:42890|issue:45600", + "issue:43502|issue:44062", + "issue:43010|issue:44075", + "issue:42548|issue:44351", + "issue:42890|issue:45341", + "issue:44222|issue:45125", + "issue:43502|issue:44485", + "issue:44355|issue:44749", + "issue:45125|issue:45478", + "issue:30990|issue:31795", + "issue:45125|issue:45375", + "issue:44387|issue:44556", + "issue:30333|issue:33453", + "issue:43010|issue:45278", + "issue:43723|issue:44556", + "issue:43502|issue:44222", + "issue:43010|issue:44368", + "issue:44315|issue:44360", + "issue:43010|issue:45850", + "issue:43502|issue:44961", + "issue:42831|issue:43874", + "issue:30333|issue:36296", + "issue:44355|issue:45071", + "issue:44222|issue:44230", + "issue:44355|issue:44655", + "issue:43827|issue:44961", + "issue:33453|issue:34689" + ], + "prepared_review_unit_hash": "5dec308bae44c3fd77443a7652868a99c486b2aa5733778b3fc6d8a6afda6d39", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 35, + "serialized_chars": 37058, + "estimated_input_tokens": 9265, + "estimated_eval_tokens": 18786 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous: it mixes broad v5 upgrade/import regressions with unrelated model, FP8, test, and docs issues. No soft pair is clearly the same underlying bug; the best anchor is the broad import-regression report for upgraded installs.", + "confidence": 0.57, + "canonical_issue_reason": "issue:45278 is the broadest and most representative user-facing report here: it describes many import errors after upgrading from 4.57.0 to 5.5.0, which best matches the loose cluster theme of v5 breakages.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the best overall issue to anchor this cluster because it captures the widest breakage scope, while the others are mostly narrower or unrelated symptoms.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43867", + "right": "issue:44484", + "accept": false, + "reason": "Both involve model loading/saving, but one is a state_dict loading error and the other is a save_pretrained shard-size question; different bugs." + }, + { + "left": "issue:43618", + "right": "issue:44857", + "accept": false, + "reason": "CLIP attentions assignment and an AMP/CUDA loss crash are unrelated code paths and symptoms." + }, + { + "left": "issue:43618", + "right": "issue:44977", + "accept": false, + "reason": "Different model families and failures; this is not the same underlying bug." + }, + { + "left": "issue:43618", + "right": "issue:45588", + "accept": false, + "reason": "Both touch attention code, but one is about CLIPOutput fields and the other is a flash_attention AttributeError for sink-less models." + }, + { + "left": "issue:43901", + "right": "issue:44938", + "accept": false, + "reason": "Docs wording for return_all_scores versus a Python 3.14 import/load failure are unrelated." + }, + { + "left": "issue:44655", + "right": "issue:44938", + "accept": false, + "reason": "Saving Pipeline objects and Python 3.14 load failures are different problems." + }, + { + "left": "issue:42890", + "right": "issue:44964", + "accept": false, + "reason": "A flaky SAM HQ integration test is not the same as a Phi-4 multimodal model-loading regression." + }, + { + "left": "issue:42890", + "right": "issue:44112", + "accept": false, + "reason": "Both are CI/test failures, but they affect different tests with different root causes." + }, + { + "left": "issue:42890", + "right": "issue:45600", + "accept": false, + "reason": "Different test/model breakages; no clear shared underlying bug." + }, + { + "left": "issue:43502", + "right": "issue:44062", + "accept": false, + "reason": "local_files_only network leakage and AddedToken argument duplication are distinct behaviors." + }, + { + "left": "issue:43010", + "right": "issue:44075", + "accept": false, + "reason": "Cache update semantics and SGD optimizer args are unrelated." + }, + { + "left": "issue:42548", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but they concern different missing symbols and are not clearly the same fix." + }, + { + "left": "issue:42890", + "right": "issue:45341", + "accept": false, + "reason": "Both mention tests, but they are different test cases with different failures." + }, + { + "left": "issue:44222", + "right": "issue:45125", + "accept": false, + "reason": "FP8 save_pretrained/moe support and tensor-parallel plan support are different code paths." + }, + { + "left": "issue:43502", + "right": "issue:44485", + "accept": false, + "reason": "API requests despite local_files_only and GLM-5 RoPE implementation are unrelated." + }, + { + "left": "issue:44355", + "right": "issue:44749", + "accept": false, + "reason": "Compiled Python file errors and a post-upgrade slowdown are not the same bug." + }, + { + "left": "issue:45125", + "right": "issue:45478", + "accept": false, + "reason": "Both are Qwen3.5 MoE-related, but one is a missing tensor-parallel plan and the other is a generic from_pretrained regression; not enough to treat as the same bug." + }, + { + "left": "issue:30990", + "right": "issue:31795", + "accept": false, + "reason": "Sentence Transformers loading stall versus a forward-docs clarification are unrelated." + }, + { + "left": "issue:45125", + "right": "issue:45375", + "accept": false, + "reason": "Tensor-parallel support and a missing config field in Qwen3_5MoeVisionConfig are different issues." + }, + { + "left": "issue:44387", + "right": "issue:44556", + "accept": false, + "reason": "Memory/OOM behavior under int4 quantization and checkpoint reload compatibility after upgrade are different regressions." + }, + { + "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:45278", + "accept": false, + "reason": "Cache update no_grad semantics and broad import errors after upgrade are unrelated." + }, + { + "left": "issue:43723", + "right": "issue:44556", + "accept": false, + "reason": "Tokenizer loading failure and checkpoint reload failure are both loading-related, but not clearly the same concrete bug." + }, + { + "left": "issue:43502", + "right": "issue:44222", + "accept": false, + "reason": "Network access despite local_files_only and FP8 MoE save_pretrained are unrelated." + }, + { + "left": "issue:43010", + "right": "issue:44368", + "accept": false, + "reason": "Cache update decoration and a tie_word_embeddings warning in LoRA fine-tuning are unrelated." + }, + { + "left": "issue:44315", + "right": "issue:44360", + "accept": false, + "reason": "Liger Kernel application in model_init and a DSA indexer activation missing ReLU are different subsystems." + }, + { + "left": "issue:43010", + "right": "issue:45850", + "accept": false, + "reason": "A specific cache-update bug is not the same as a broad complaint that v5 breaks too many models." + }, + { + "left": "issue:43502", + "right": "issue:44961", + "accept": false, + "reason": "local_files_only network leakage has nothing to do with the unrelated 'racoon' issue." + }, + { + "left": "issue:42831", + "right": "issue:43874", + "accept": false, + "reason": "FineGrainedFP8 accuracy and a missing image-processor method are unrelated." + }, + { + "left": "issue:30333", + "right": "issue:36296", + "accept": false, + "reason": "MLflow failure reporting and tensor parallel training are different bugs." + }, + { + "left": "issue:44355", + "right": "issue:45071", + "accept": false, + "reason": "Compiled-file execution errors and PretrainedConfig type-checking regressions are different issues." + }, + { + "left": "issue:44222", + "right": "issue:44230", + "accept": false, + "reason": "Both mention FP8 and MoE, but one is about save_pretrained and the other about inference support; not the same bug." + }, + { + "left": "issue:44355", + "right": "issue:44655", + "accept": false, + "reason": "Compiled Python file errors and pipeline save_pretrained support are unrelated." + }, + { + "left": "issue:43827", + "right": "issue:44961", + "accept": false, + "reason": "Docs still referencing pipeline() and an unrelated issue titled 'racoon' are not duplicates." + }, + { + "left": "issue:33453", + "right": "issue:34689", + "accept": false, + "reason": "Tokenizer loading regression and Llama 3.2 vision model loading breakage are both loading issues, but not the same concrete failure." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 44, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:31795", + "issue:33453", + "issue:36296", + "issue:38617", + "issue:41628", + "issue:41669", + "issue:42548", + "issue:42757", + "issue:42890", + "issue:43010", + "issue:43299", + "issue:43352", + "issue:43408", + "issue:43525", + "issue:43526", + "issue:43572", + "issue:43576", + "issue:43673", + "issue:43824", + "issue:43901", + "issue:43976", + "issue:44038", + "issue:44246", + "issue:44261", + "issue:44273", + "issue:44297", + "issue:44315", + "issue:44351", + "issue:44355", + "issue:44360", + "issue:44373", + "issue:44393", + "issue:44556", + "issue:44623", + "issue:44704", + "issue:44908", + "issue:44961", + "issue:45003", + "issue:45071", + "issue:45092", + "issue:45125", + "issue:45230", + "issue:45362", + "issue:45468", + "issue:45542", + "issue:45656", + "issue:45753", + "issue:45850" + ], + "soft_pairs": [ + "issue:42757|issue:43576", + "issue:43299|issue:44556", + "issue:43010|issue:45656", + "issue:33453|issue:36296", + "issue:43576|issue:45071", + "issue:43576|issue:43824", + "issue:44961|issue:45468", + "issue:31795|issue:38617", + "issue:41628|issue:42548", + "issue:38617|issue:43576", + "issue:43010|issue:43976", + "issue:43576|issue:44351", + "issue:44908|issue:44961", + "issue:36296|issue:43901", + "issue:41628|issue:44355", + "issue:36296|issue:43526", + "issue:44261|issue:44360", + "issue:44623|issue:45230", + "issue:44273|issue:45542", + "issue:44273|issue:45003", + "issue:44393|issue:45753", + "issue:43576|issue:44556", + "issue:44038|issue:45125", + "issue:44393|issue:45071", + "issue:43525|issue:45850", + "issue:44556|issue:45092", + "issue:41669|issue:43673", + "issue:44373|issue:44961", + "issue:43572|issue:45850", + "issue:45362|issue:45850", + "issue:44704|issue:44908", + "issue:42890|issue:44908", + "issue:44246|issue:44273", + "issue:43408|issue:44315", + "issue:43976|issue:44393", + "issue:43352|issue:44393", + "issue:43576|issue:44908", + "issue:44908|issue:45071", + "issue:44297|issue:45230", + "issue:41669|issue:44351" + ], + "prepared_review_unit_hash": "2507ad7f6c38cf1687e2322fc80894294d5c7c61d8e0d8d4d4c878b7c9dacf34", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 40, + "serialized_chars": 38932, + "estimated_input_tokens": 9733, + "estimated_eval_tokens": 19722 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a heterogeneous mix of Transformers v5 regressions, import/export failures, and model-specific bugs; the soft pairs are thematically similar in places but not the same concrete underlying issue. I would not merge any of the candidate pairs as duplicates.", + "confidence": 0.32, + "canonical_issue_reason": "issue:45850 is the broadest umbrella for the overall cluster theme (v5 breaks many models), so it best represents the set even though it is vague.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45850 is the closest global anchor for the cluster, but it is still too generic to serve as a precise duplicate target.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42757", + "right": "issue:43576", + "accept": false, + "reason": "Different failures: a missing huggingface_hub symbol vs a broken transformers env command." + }, + { + "left": "issue:43299", + "right": "issue:44556", + "accept": false, + "reason": "Both are v5 regressions, but they describe different model-loading breakages and code paths." + }, + { + "left": "issue:43010", + "right": "issue:45656", + "accept": false, + "reason": "Cache update no_grad semantics and deepspeed double optimizer step are unrelated bugs." + }, + { + "left": "issue:33453", + "right": "issue:36296", + "accept": false, + "reason": "Tokenizer loading regression is unrelated to tensor-parallel training behavior." + }, + { + "left": "issue:43576", + "right": "issue:45071", + "accept": false, + "reason": "Broken env CLI and PretrainedConfig type-checking are separate issues." + }, + { + "left": "issue:43576", + "right": "issue:43824", + "accept": false, + "reason": "CLI breakage is not the same as a missing top-level model import." + }, + { + "left": "issue:44961", + "right": "issue:45468", + "accept": false, + "reason": "No clear overlap; one is a vague placeholder and the other is a Gemma audio encoding bug." + }, + { + "left": "issue:31795", + "right": "issue:38617", + "accept": false, + "reason": "Doc confusion about forward args does not match an import error for configuration_utils." + }, + { + "left": "issue:41628", + "right": "issue:42548", + "accept": false, + "reason": "Both are import errors, but they concern different symbols and likely different missing exports." + }, + { + "left": "issue:38617", + "right": "issue:43576", + "accept": false, + "reason": "ImportError for a config helper is unrelated to the env command regression." + }, + { + "left": "issue:43010", + "right": "issue:43976", + "accept": false, + "reason": "No_grad decoration on cache updates is unrelated to Python-version compatibility." + }, + { + "left": "issue:43576", + "right": "issue:44351", + "accept": false, + "reason": "Broken CLI and missing HybridCache import are different concrete problems." + }, + { + "left": "issue:44908", + "right": "issue:44961", + "accept": false, + "reason": "Scheduler kwargs bug is unrelated to the placeholder issue." + }, + { + "left": "issue:36296", + "right": "issue:43901", + "accept": false, + "reason": "Tensor-parallel training bug and docs mismatch for pipeline output are unrelated." + }, + { + "left": "issue:41628", + "right": "issue:44355", + "accept": false, + "reason": "Top-level import missing and compiled-file runtime errors are not the same bug." + }, + { + "left": "issue:36296", + "right": "issue:43526", + "accept": false, + "reason": "Tensor-parallel training and BeitImageProcessorFast label reduction are unrelated." + }, + { + "left": "issue:44261", + "right": "issue:44360", + "accept": false, + "reason": "LayerNorm epsilon precision issue does not match a missing ReLU in the DSA indexer." + }, + { + "left": "issue:44623", + "right": "issue:45230", + "accept": false, + "reason": "Missing files on save_pretrained is unrelated to a generic bug report." + }, + { + "left": "issue:44273", + "right": "issue:45542", + "accept": false, + "reason": "Lazy loading failure and undefined tf backend error are different code paths." + }, + { + "left": "issue:44273", + "right": "issue:45003", + "accept": false, + "reason": "Both touch import mechanics, but one is lazy loading and the other is unsafe sys.modules access." + }, + { + "left": "issue:44393", + "right": "issue:45753", + "accept": false, + "reason": "Different Qwen model symptoms: 2D box hallucination vs infinite loop on a specific image." + }, + { + "left": "issue:43576", + "right": "issue:44556", + "accept": false, + "reason": "General CLI breakage and checkpoint reload incompatibility are not the same underlying bug." + }, + { + "left": "issue:44038", + "right": "issue:45125", + "accept": false, + "reason": "Related Qwen3-MoE family, but one is a broader model-loading issue and the other is missing tensor-parallel plan support." + }, + { + "left": "issue:44393", + "right": "issue:45071", + "accept": false, + "reason": "Model-specific output errors are unrelated to PretrainedConfig type checking." + }, + { + "left": "issue:43525", + "right": "issue:45850", + "accept": false, + "reason": "Missing pad_token_id in Llama4Config is a specific config bug, not the generic v5-breaks-many-models report." + }, + { + "left": "issue:44556", + "right": "issue:45092", + "accept": false, + "reason": "Both are upgrade incompatibilities, but they affect different models and different initialization paths." + }, + { + "left": "issue:41669", + "right": "issue:43673", + "accept": false, + "reason": "Import-star performance issue and missing GenerationMixin cache are separate problems." + }, + { + "left": "issue:44373", + "right": "issue:44961", + "accept": false, + "reason": "Wrong docstring for position_ids is unrelated to the placeholder issue." + }, + { + "left": "issue:43572", + "right": "issue:45850", + "accept": false, + "reason": "Specific missing pad_token_idx bug is not the same as the broad v5 regression complaint." + }, + { + "left": "issue:45362", + "right": "issue:45850", + "accept": false, + "reason": "Qwen3.5 chat crash is a specific model/runtime failure, not the generic complaint." + }, + { + "left": "issue:44704", + "right": "issue:44908", + "accept": false, + "reason": "Passing kwargs to cached_file and scheduler kwargs are unrelated API bugs." + }, + { + "left": "issue:42890", + "right": "issue:44908", + "accept": false, + "reason": "Flaky integration tests due to missing seed do not match scheduler kwargs handling." + }, + { + "left": "issue:44246", + "right": "issue:44273", + "accept": false, + "reason": "Slow import sometimes and lazy loading not working are related only at a high level, not the same concrete bug." + }, + { + "left": "issue:43408", + "right": "issue:44315", + "accept": false, + "reason": "sam3 tracker/model-type warning is unrelated to Liger Kernel not being applied in model_init." + }, + { + "left": "issue:43976", + "right": "issue:44393", + "accept": false, + "reason": "Python-version support regression is unrelated to Qwen3-VL bounding-box output errors." + }, + { + "left": "issue:43352", + "right": "issue:44393", + "accept": false, + "reason": "Flash Attention support error for Nemotron and Qwen3-VL output issues are different bugs." + }, + { + "left": "issue:43576", + "right": "issue:44908", + "accept": false, + "reason": "Broken env CLI and inverse_sqrt scheduler kwargs are unrelated." + }, + { + "left": "issue:44908", + "right": "issue:45071", + "accept": false, + "reason": "Scheduler kwargs bug and PretrainedConfig type-checking regression are unrelated." + }, + { + "left": "issue:44297", + "right": "issue:45230", + "accept": false, + "reason": "Tokenizer_class mismatch in save_pretrained is unrelated to a generic bug report." + }, + { + "left": "issue:41669", + "right": "issue:44351", + "accept": false, + "reason": "Import-star performance issue is unrelated to missing HybridCache import." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 45, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:30333", + "issue:31515", + "issue:31795", + "issue:33453", + "issue:34689", + "issue:36296", + "issue:37428", + "issue:38617", + "issue:41669", + "issue:42371", + "issue:42913", + "issue:43066", + "issue:43502", + "issue:43519", + "issue:43525", + "issue:43572", + "issue:43576", + "issue:43606", + "issue:43673", + "issue:43704", + "issue:43827", + "issue:43874", + "issue:44077", + "issue:44230", + "issue:44261", + "issue:44263", + "issue:44273", + "issue:44295", + "issue:44315", + "issue:44360", + "issue:44393", + "issue:44485", + "issue:44492", + "issue:44623", + "issue:44655", + "issue:44829", + "issue:44861", + "issue:44908", + "issue:44998", + "issue:45092", + "issue:45230", + "issue:45278", + "issue:45290", + "issue:45310", + "issue:45341", + "issue:45468", + "issue:45478", + "issue:45850" + ], + "soft_pairs": [ + "issue:44295|issue:45230", + "issue:41669|issue:45341", + "issue:43673|issue:44492", + "issue:45278|issue:45850", + "issue:44393|issue:45478", + "issue:43874|issue:45850", + "issue:41669|issue:44492", + "issue:44315|issue:44829", + "issue:43827|issue:44908", + "issue:44077|issue:44861", + "issue:31795|issue:33453", + "issue:41669|issue:44908", + "issue:42371|issue:44492", + "issue:43576|issue:44273", + "issue:44655|issue:44861", + "issue:44360|issue:45468", + "issue:44492|issue:45850", + "issue:44273|issue:44908", + "issue:45230|issue:45310", + "issue:43519|issue:44485", + "issue:41669|issue:43704", + "issue:43519|issue:44908", + "issue:31795|issue:34689", + "issue:31795|issue:37428", + "issue:44315|issue:45092", + "issue:43704|issue:44485", + "issue:44485|issue:45468", + "issue:42371|issue:43704", + "issue:43502|issue:43519", + "issue:43519|issue:44623", + "issue:43519|issue:43704", + "issue:44263|issue:45468", + "issue:43606|issue:45468", + "issue:44261|issue:45468", + "issue:43704|issue:45341", + "issue:42913|issue:43066", + "issue:44908|issue:44998", + "issue:44861|issue:45290", + "issue:43704|issue:44998", + "issue:41669|issue:44998", + "issue:43525|issue:44861", + "issue:43066|issue:44998", + "issue:43572|issue:44861", + "issue:31515|issue:38617", + "issue:44360|issue:44998", + "issue:44230|issue:44623", + "issue:30333|issue:31515", + "issue:31515|issue:36296", + "issue:31515|issue:31795", + "issue:44230|issue:45310", + "issue:31515|issue:33453" + ], + "prepared_review_unit_hash": "9d5f0a504e00a7b272480ee3e8a98c95a69f7523819e6acc0adf89e39f3ee21d", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 51, + "serialized_chars": 42295, + "estimated_input_tokens": 10574, + "estimated_eval_tokens": 21404 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is a loose collection of Transformers-related issues, mostly v5 migration regressions and a few unrelated model-specific bugs. I did not find any soft pair that clearly describes the same concrete bug/change, so all soft edges are rejected. The most representative issue is the broad v5 upgrade regression report.", + "confidence": 0.71, + "canonical_issue_reason": "issue:45278 is the best representative issue because it clearly captures the broad v5 upgrade regression theme (\u201cmany import errors after update from 4.57.0 to 5.5.0\u201d) that several other items orbit, while still being concrete enough to anchor the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the most suitable global issue choice: it is specific, actionable, and broadly representative of the upgrade-related breakage pattern in this set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44295", + "right": "issue:45230", + "accept": false, + "reason": "Specific position_ids buffer error vs generic bug report; no evidence of the same underlying defect." + }, + { + "left": "issue:41669", + "right": "issue:45341", + "accept": false, + "reason": "Import-* performance/refactor issue vs a testing_utils bug; different code paths and symptoms." + }, + { + "left": "issue:43673", + "right": "issue:44492", + "accept": false, + "reason": "Chunked_prefill cache-missing bug vs a typo in cache strategies; not the same bug." + }, + { + "left": "issue:45278", + "right": "issue:45850", + "accept": false, + "reason": "Both are broad v5 breakage complaints, but they are too umbrella-level to be the same concrete issue." + }, + { + "left": "issue:44393", + "right": "issue:45478", + "accept": false, + "reason": "Qwen3-VL bbox output problem vs Qwen3.5 MoE from_pretrained error; unrelated failures." + }, + { + "left": "issue:43874", + "right": "issue:45850", + "accept": false, + "reason": "Missing image-processor method in GLM46V vs a generic \u201ctoo many models break\u201d report; not one bug." + }, + { + "left": "issue:41669", + "right": "issue:44492", + "accept": false, + "reason": "Import-* removal/performance issue vs cache-strategy typo; no shared failure." + }, + { + "left": "issue:44315", + "right": "issue:44829", + "accept": false, + "reason": "model_init/Liger Kernel application bug vs flash_attention_3 degenerate training; distinct code paths." + }, + { + "left": "issue:43827", + "right": "issue:44908", + "accept": false, + "reason": "Docs still referencing pipeline() vs scheduler kwargs handling; completely different fixes." + }, + { + "left": "issue:44077", + "right": "issue:44861", + "accept": false, + "reason": "Optional post_init restriction vs tied-weight-key AttributeError; unrelated model internals." + }, + { + "left": "issue:31795", + "right": "issue:33453", + "accept": false, + "reason": "Documentation confusion in model.forward vs tokenizer loading regression; not the same underlying problem." + }, + { + "left": "issue:41669", + "right": "issue:44908", + "accept": false, + "reason": "Import-* cleanup/perf issue vs inverse_sqrt scheduler kwargs bug; no overlap." + }, + { + "left": "issue:42371", + "right": "issue:44492", + "accept": false, + "reason": "TF32 API guidance vs cache-strategy typo; unrelated." + }, + { + "left": "issue:43576", + "right": "issue:44273", + "accept": false, + "reason": "Broken `transformers env` command vs lazy-loading regression; different CLI/runtime paths." + }, + { + "left": "issue:44655", + "right": "issue:44861", + "accept": false, + "reason": "Pipeline save_pretrained failure vs tied_weight_keys crash; different serialization bugs." + }, + { + "left": "issue:44360", + "right": "issue:45468", + "accept": false, + "reason": "DSA indexer ReLU issue vs Gemma4Audio positional encoding bug; unrelated components." + }, + { + "left": "issue:44492", + "right": "issue:45850", + "accept": false, + "reason": "A typo issue vs a broad v5 breakage complaint; not the same defect." + }, + { + "left": "issue:44273", + "right": "issue:44908", + "accept": false, + "reason": "Lazy-loading regression vs inverse_sqrt scheduler kwargs bug; no common code path." + }, + { + "left": "issue:45230", + "right": "issue:45310", + "accept": false, + "reason": "Generic bug report placeholder vs specific Qwen3.5 MoE from_pretrained error; insufficient overlap." + }, + { + "left": "issue:43519", + "right": "issue:44485", + "accept": false, + "reason": "Incorrect timestamp calculation in Qwen3VL processor vs GLM-5 RoPE implementation; different model subsystems." + }, + { + "left": "issue:41669", + "right": "issue:43704", + "accept": false, + "reason": "Import-* removal/performance issue vs VRAM leak across dataloader threads; unrelated." + }, + { + "left": "issue:43519", + "right": "issue:44908", + "accept": false, + "reason": "Qwen3VL timestamp bug vs scheduler kwargs bug; different areas." + }, + { + "left": "issue:31795", + "right": "issue:34689", + "accept": false, + "reason": "Documentation confusion vs model loading breakage for Llama 3.2; not the same bug." + }, + { + "left": "issue:31795", + "right": "issue:37428", + "accept": false, + "reason": "Docs issue vs ImportError for flash attention util; different problem statements." + }, + { + "left": "issue:44315", + "right": "issue:45092", + "accept": false, + "reason": "Liger Kernel application bug with model_init vs old InternVL2 remote-code/meta-init incompatibility; separate load-time issues." + }, + { + "left": "issue:43704", + "right": "issue:44485", + "accept": false, + "reason": "VRAM leak in multi-threaded dataloading vs RoPE implementation discussion; unrelated." + }, + { + "left": "issue:44485", + "right": "issue:45468", + "accept": false, + "reason": "GLM-5 RoPE implementation vs Gemma4Audio positional encoding; different models and failures." + }, + { + "left": "issue:42371", + "right": "issue:43704", + "accept": false, + "reason": "TF32 behavior API guidance vs VRAM leak; no shared defect." + }, + { + "left": "issue:43502", + "right": "issue:43519", + "accept": false, + "reason": "local_files_only still making requests vs Qwen3VL timestamp calculation; unrelated." + }, + { + "left": "issue:43519", + "right": "issue:44623", + "accept": false, + "reason": "Qwen3VL timestamp bug vs missing processor.save_pretrained files; different components." + }, + { + "left": "issue:43519", + "right": "issue:43704", + "accept": false, + "reason": "Timestamp calculation bug vs VRAM leak in dataloader threads; not the same bug." + }, + { + "left": "issue:44263", + "right": "issue:45468", + "accept": false, + "reason": "torch.split return-values issue in DSA indexer vs Gemma4Audio positional encoding; unrelated." + }, + { + "left": "issue:43606", + "right": "issue:45468", + "accept": false, + "reason": "CPU offload device mismatch vs Gemma4Audio positional encoding; different failures." + }, + { + "left": "issue:44261", + "right": "issue:45468", + "accept": false, + "reason": "Missing rms_norm_eps in MLA q_a_layernorm vs Gemma4Audio positional encoding; separate issues." + }, + { + "left": "issue:43704", + "right": "issue:45341", + "accept": false, + "reason": "VRAM leak vs testing_utils bug; no common code path." + }, + { + "left": "issue:42913", + "right": "issue:43066", + "accept": false, + "reason": "Both mention tokenizer behavior in v5, but one is a broad regression and the other a specific decoder-type mismatch; not clearly the same bug." + }, + { + "left": "issue:44908", + "right": "issue:44998", + "accept": false, + "reason": "Scheduler kwargs bug vs unrelated placeholder issue title; clearly different." + }, + { + "left": "issue:44861", + "right": "issue:45290", + "accept": false, + "reason": "tied_weight_keys AttributeError vs chat-template crash with tool calls; different code paths." + }, + { + "left": "issue:43704", + "right": "issue:44998", + "accept": false, + "reason": "VRAM leak vs unrelated placeholder title; no overlap." + }, + { + "left": "issue:41669", + "right": "issue:44998", + "accept": false, + "reason": "Import-* refactor issue vs unrelated placeholder title; not a duplicate." + }, + { + "left": "issue:43525", + "right": "issue:44861", + "accept": false, + "reason": "Missing pad_token_id on Llama4Config vs tied_weight_keys crash; different config/serialization bugs." + }, + { + "left": "issue:43066", + "right": "issue:44998", + "accept": false, + "reason": "Wrong tokenizer decoder type vs unrelated placeholder title; no match." + }, + { + "left": "issue:43572", + "right": "issue:44861", + "accept": false, + "reason": "Missing pad_token_idx in StableLmConfig vs tied_weight_keys crash; unrelated." + }, + { + "left": "issue:31515", + "right": "issue:38617", + "accept": false, + "reason": "Slow checkpoint loading vs ImportError for layer_type_validation; different symptoms and subsystems." + }, + { + "left": "issue:44360", + "right": "issue:44998", + "accept": false, + "reason": "DSA indexer bug vs unrelated placeholder title; no shared bug." + }, + { + "left": "issue:44230", + "right": "issue:44623", + "accept": false, + "reason": "fp8 inference support request vs processor.save_pretrained missing files; separate topics." + }, + { + "left": "issue:30333", + "right": "issue:31515", + "accept": false, + "reason": "MLFlow training-job reporting bug vs slow from_pretrained checkpoint loading; unrelated." + }, + { + "left": "issue:31515", + "right": "issue:36296", + "accept": false, + "reason": "Slow checkpoint loading vs tensor parallel training bug; different issues." + }, + { + "left": "issue:31515", + "right": "issue:31795", + "accept": false, + "reason": "Slow loading vs documentation confusion; not the same underlying problem." + }, + { + "left": "issue:44230", + "right": "issue:45310", + "accept": false, + "reason": "fp8 support request vs Qwen3.5 MoE from_pretrained error; request vs bug, and different code paths." + }, + { + "left": "issue:31515", + "right": "issue:33453", + "accept": false, + "reason": "Slow checkpoint loading vs tokenizer loading regression; different failures." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 46, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-392", + "nodes": [ + "issue:43298", + "issue:44230" + ], + "soft_pairs": [ + "issue:43298|issue:44230" + ], + "prepared_review_unit_hash": "f4b8d4e582d421f4989132f9f9b25da59169bb9c2a138bc5d9f29d2bbb7cdc11", + "component_budget": { + "node_count": 392, + "item_count": 392, + "soft_pair_count": 1480, + "serialized_chars": 761406, + "estimated_input_tokens": 190352, + "estimated_eval_tokens": 380960 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1467, + "estimated_input_tokens": 367, + "estimated_eval_tokens": 990 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The two issues are about different problems: audio continuous batching support vs. FP8 inference support for Qwen/VL/MoE models. They should not be deduplicated.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "issue:43298 is the better representative issue because it is open and describes a concrete support gap, while issue:44230 is a separate, already-closed FP8-specific request.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43298", + "right": "issue:44230", + "accept": false, + "reason": "Different underlying feature/bug requests with no concrete overlap: one is about continuous batching for audio models, the other about FP8 inference support for specific Qwen models." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 3, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "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": "3dcd761064374f19c980d4f34926fa32ed40df64045a28aac96ec6507e2e229a", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1589, + "estimated_input_tokens": 398, + "estimated_eval_tokens": 1052 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1589, + "estimated_input_tokens": 398, + "estimated_eval_tokens": 1052 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are both broad community-contribution feature requests, but they target different capabilities: Flash Attention 2 support vs GGUF support. They are not the same underlying issue.", + "confidence": 0.98, + "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 requested features and code paths; one is about Flash Attention 2 architecture support, the other about GGUF architecture support. Similar framing does not make them duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 4, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-27088-4", + "nodes": [ + "issue:27088", + "issue:43834", + "issue:44365", + "issue:44370" + ], + "soft_pairs": [ + "issue:27088|issue:44370", + "issue:27088|issue:44365", + "issue:27088|issue:43834", + "issue:43834|issue:44370", + "issue:43834|issue:44365", + "issue:44365|issue:44370" + ], + "prepared_review_unit_hash": "d645ab4a25de4ffb69c96ff12779684dc2f22ddf05070fa69bfef5a6342d87ba", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4455, + "estimated_input_tokens": 1114, + "estimated_eval_tokens": 2484 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4455, + "estimated_input_tokens": 1114, + "estimated_eval_tokens": 2484 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are translation-docs requests, but they are not the same underlying issue: one is specifically Turkish, while the others are generic placeholder-language requests. No soft duplicate edges should be merged.", + "confidence": 0.91, + "canonical_issue_reason": "issue:27088 is the only concrete, language-specific request; the others read like generic template entries rather than the same bug report.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:27088 is the best representative because it is specific, actionable, and not just a placeholder title.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:27088", + "right": "issue:44370", + "accept": false, + "reason": "Different language requests; same broad translation theme, but not the same underlying issue." + }, + { + "left": "issue:27088", + "right": "issue:44365", + "accept": false, + "reason": "Generic placeholder request versus specific Turkish request; not duplicates." + }, + { + "left": "issue:27088", + "right": "issue:43834", + "accept": false, + "reason": "One is Turkish-specific, the other is a generic language placeholder; distinct requests." + }, + { + "left": "issue:43834", + "right": "issue:44370", + "accept": false, + "reason": "Both are generic translation placeholders, but they still do not identify the same concrete language or task." + }, + { + "left": "issue:43834", + "right": "issue:44365", + "accept": false, + "reason": "Near-identical template wording is not enough; no evidence they target the same exact translation change." + }, + { + "left": "issue:44365", + "right": "issue:44370", + "accept": false, + "reason": "Both are generic placeholders, but they appear to represent separate language translation tasks." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 5, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-36817-15", + "nodes": [ + "issue:36817", + "issue:36879", + "issue:37015", + "issue:41115", + "issue:41211", + "issue:42503", + "issue:42738", + "issue:43671", + "issue:43837", + "issue:43909", + "issue:44121", + "issue:44205", + "issue:45027", + "issue:45177", + "issue:45322" + ], + "soft_pairs": [ + "issue:36817|issue:41211", + "issue:36817|issue:43671", + "issue:36817|issue:36879", + "issue:36879|issue:41211", + "issue:36879|issue:43909", + "issue:36879|issue:44121", + "issue:36879|issue:43837", + "issue:36879|issue:43671", + "issue:37015|issue:43837", + "issue:37015|issue:44121", + "issue:37015|issue:43909", + "issue:36879|issue:37015", + "issue:37015|issue:42503", + "issue:41115|issue:43837", + "issue:41115|issue:44121", + "issue:41115|issue:42503", + "issue:41115|issue:45027", + "issue:41211|issue:43671", + "issue:42503|issue:43837", + "issue:42503|issue:43671", + "issue:42503|issue:42738", + "issue:42738|issue:45027", + "issue:43671|issue:43837", + "issue:43671|issue:45027", + "issue:43671|issue:45177", + "issue:43671|issue:44121", + "issue:43837|issue:45322", + "issue:43837|issue:43909", + "issue:43909|issue:44205", + "issue:43671|issue:43909", + "issue:44121|issue:45322", + "issue:43837|issue:44121", + "issue:43837|issue:45027", + "issue:37015|issue:45027", + "issue:43837|issue:45177" + ], + "prepared_review_unit_hash": "0f5f3ef2a29172c8f084119bc408a4990292ffea434c456134cccd8a08027603", + "component_budget": { + "node_count": 15, + "item_count": 15, + "soft_pair_count": 35, + "serialized_chars": 20704, + "estimated_input_tokens": 5176, + "estimated_eval_tokens": 10608 + }, + "budget": { + "node_count": 15, + "item_count": 15, + "soft_pair_count": 35, + "serialized_chars": 20704, + "estimated_input_tokens": 5176, + "estimated_eval_tokens": 10608 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "A loose cluster of model-add requests across different models/modalities; they are related in theme but not duplicates of the same concrete change.", + "confidence": 0.74, + "canonical_issue_reason": "issue:43671 is the most central and discussion-rich request in the cluster, so it best serves as the representative issue, though it does not subsume the others.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43671 is the best single representative of the cluster\u2019s common pattern of model-support requests, with the strongest connectivity among the listed issues.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36817", + "right": "issue:41211", + "accept": false, + "reason": "Both are model-add requests, but for different models; no evidence they are the same underlying change." + }, + { + "left": "issue:36817", + "right": "issue:43671", + "accept": false, + "reason": "Different model requests (EuroBert vs Qwen3-TTS); related theme only, not the same bug/change." + }, + { + "left": "issue:36817", + "right": "issue:36879", + "accept": false, + "reason": "Distinct model requests (EuroBert vs RF-DETR), not a duplicate fix or merged implementation." + }, + { + "left": "issue:36879", + "right": "issue:41211", + "accept": false, + "reason": "Different models and likely different code paths; similarity is only at the request level." + }, + { + "left": "issue:36879", + "right": "issue:43909", + "accept": false, + "reason": "RF-DETR and LFM2.5 Audio are unrelated concrete model integrations." + }, + { + "left": "issue:36879", + "right": "issue:44121", + "accept": false, + "reason": "Object-detection model request versus weight-sparse transformer request; not the same change." + }, + { + "left": "issue:36879", + "right": "issue:43837", + "accept": false, + "reason": "RF-DETR and Qwen3-ASR target different models/modalities, so they should not be merged." + }, + { + "left": "issue:36879", + "right": "issue:43671", + "accept": false, + "reason": "RF-DETR vs Qwen3-TTS are different integrations with no shared concrete bug." + }, + { + "left": "issue:37015", + "right": "issue:43837", + "accept": false, + "reason": "NeoBERT and Qwen3-ASR are separate model requests, not one underlying defect." + }, + { + "left": "issue:37015", + "right": "issue:44121", + "accept": false, + "reason": "NeoBERT versus circuit-sparse transformer support are different implementation targets." + }, + { + "left": "issue:37015", + "right": "issue:43909", + "accept": false, + "reason": "Different requested models; no sign of the same code-path problem." + }, + { + "left": "issue:36879", + "right": "issue:37015", + "accept": false, + "reason": "RF-DETR and NeoBERT are unrelated model additions, not duplicates." + }, + { + "left": "issue:37015", + "right": "issue:42503", + "accept": false, + "reason": "NeoBERT and ModernVBERT are distinct BERT-family model requests, not the same change." + }, + { + "left": "issue:41115", + "right": "issue:43837", + "accept": false, + "reason": "MiniCPM3 architecture support and Qwen3-ASR support are different model integrations." + }, + { + "left": "issue:41115", + "right": "issue:44121", + "accept": false, + "reason": "MiniCPM3 and circuit-sparse transformer requests differ in model and implementation scope." + }, + { + "left": "issue:41115", + "right": "issue:42503", + "accept": false, + "reason": "MiniCPM3 architecture and ModernVBERT models are separate requests." + }, + { + "left": "issue:41115", + "right": "issue:45027", + "accept": false, + "reason": "MiniCPM3 and Voxtral TTS support are different model families and code paths." + }, + { + "left": "issue:41211", + "right": "issue:43671", + "accept": false, + "reason": "DEIMv2 and Qwen3-TTS are unrelated concrete model requests." + }, + { + "left": "issue:42503", + "right": "issue:43837", + "accept": false, + "reason": "ModernVBERT and Qwen3-ASR are separate integrations, despite both being model-support requests." + }, + { + "left": "issue:42503", + "right": "issue:43671", + "accept": false, + "reason": "ModernVBERT models and Qwen3-TTS are different model additions, not one merged fix." + }, + { + "left": "issue:42503", + "right": "issue:42738", + "accept": false, + "reason": "Both mention BERT-like models, but they are not the same specific model or implementation task." + }, + { + "left": "issue:42738", + "right": "issue:45027", + "accept": false, + "reason": "RoPE BERT-like model support and Voxtral TTS support are different requests." + }, + { + "left": "issue:43671", + "right": "issue:43837", + "accept": false, + "reason": "Qwen3-TTS and Qwen3-ASR are closely related, but they are still different concrete model supports and should not be merged." + }, + { + "left": "issue:43671", + "right": "issue:45027", + "accept": false, + "reason": "Qwen3-TTS and Voxtral-4B-TTS are different TTS model requests, not the same code change." + }, + { + "left": "issue:43671", + "right": "issue:45177", + "accept": false, + "reason": "Qwen3-TTS and DeepSeek-OCR2 are unrelated model integrations." + }, + { + "left": "issue:43671", + "right": "issue:44121", + "accept": false, + "reason": "Speech-model support versus weight-sparse transformer support are different changes." + }, + { + "left": "issue:43837", + "right": "issue:45322", + "accept": false, + "reason": "Qwen3-ASR and EUPE are unrelated model requests." + }, + { + "left": "issue:43837", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-ASR and LFM2.5 Audio are both audio-related, but they are different concrete models and not the same change." + }, + { + "left": "issue:43909", + "right": "issue:44205", + "accept": false, + "reason": "Audio model support and SAM3-LiteText are different model requests with no shared concrete bug." + }, + { + "left": "issue:43671", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-TTS and LFM2.5 Audio are distinct model integrations." + }, + { + "left": "issue:44121", + "right": "issue:45322", + "accept": false, + "reason": "Circuit-sparse transformer support and EUPE are separate model requests." + }, + { + "left": "issue:43837", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3-ASR and weight-sparse transformer support are not the same underlying change." + }, + { + "left": "issue:43837", + "right": "issue:45027", + "accept": false, + "reason": "Qwen3-ASR and Voxtral-4B-TTS are different speech-model integrations." + }, + { + "left": "issue:37015", + "right": "issue:45027", + "accept": false, + "reason": "NeoBERT and Voxtral TTS are unrelated model requests." + }, + { + "left": "issue:43837", + "right": "issue:45177", + "accept": false, + "reason": "Qwen3-ASR and DeepSeek-OCR2 are different model families and 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": 6, + "component_count": 16, + "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-37934-6", + "nodes": [ + "issue:37934", + "issue:42936", + "issue:43240", + "issue:43668", + "issue:43813", + "issue:44031" + ], + "soft_pairs": [ + "issue:37934|issue:43668", + "issue:42936|issue:43240", + "issue:42936|issue:44031", + "issue:42936|issue:43813", + "issue:42936|issue:43668", + "issue:43240|issue:43668", + "issue:43668|issue:44031", + "issue:43668|issue:43813" + ], + "prepared_review_unit_hash": "bd1f75549e7e948c4a2059ec3226f3950867ed854b63f64d6768a1548de5ee07", + "component_budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 8, + "serialized_chars": 6291, + "estimated_input_tokens": 1573, + "estimated_eval_tokens": 3402 + }, + "budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 8, + "serialized_chars": 6291, + "estimated_input_tokens": 1573, + "estimated_eval_tokens": 3402 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These issues are only loosely text-similar; they describe unrelated bugs across different models/components, so none of the soft duplicate links should be accepted.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:37934", + "right": "issue:43668", + "accept": false, + "reason": "Different problems in different model configs: Llama4TextL2Norm/RMS norm question vs ModernBERT norm_eps type hint." + }, + { + "left": "issue:42936", + "right": "issue:43240", + "accept": false, + "reason": "Mask2Former ignore_value handling is unrelated to kwargs not being forwarded to a loss function." + }, + { + "left": "issue:42936", + "right": "issue:44031", + "accept": false, + "reason": "Mask2Former ignore_value bug is unrelated to a tokenizer regex warning after 4.57.3." + }, + { + "left": "issue:42936", + "right": "issue:43813", + "accept": false, + "reason": "Different subsystems and bug types: Mask2Former loss masking vs a quantization attribute typo." + }, + { + "left": "issue:42936", + "right": "issue:43668", + "accept": false, + "reason": "Unrelated model/config issues: Mask2Former ignore_value usage vs ModernBERT norm_eps typing." + }, + { + "left": "issue:43240", + "right": "issue:43668", + "accept": false, + "reason": "Loss kwargs forwarding bug is not the same as a config type-hint error." + }, + { + "left": "issue:43668", + "right": "issue:44031", + "accept": false, + "reason": "ModernBERT norm_eps typing and tokenizer regex warnings are distinct issues in different code paths." + }, + { + "left": "issue:43668", + "right": "issue:43813", + "accept": false, + "reason": "A type-hint fix for ModernBERT is unrelated to a quantization typo." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 7, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "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": "41e626aafccdbb62551b5b352c4ca3cff4285dd58326f3ee7bec4533316257ec", + "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: one asks for Set Block Decoding, the other requests DeepSeek v3.2 support. They describe different product areas and different underlying changes.", + "confidence": 0.97, + "canonical_issue_reason": "No canonical issue: 41084 and 43037 are unrelated topics rather than the same bug or request.", + "canonical_pr_reason": null, + "best_issue_reason": "Neither issue is a good cluster representative because there is no duplicate relationship to unify.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41084", + "right": "issue:43037", + "accept": false, + "reason": "Different underlying requests: block decoding behavior vs adding support for a specific model version." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 8, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "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": "5ed04dc788aaa13b7e27d1b9d2e2bd41f89674a2154719adef789f318415912a", + "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": "Both issues concern Trainer behavior with custom trainers, but they address different code paths: column removal vs FLOPs estimation. They are related in theme, not the same underlying bug or change, so I would not merge them as duplicates.", + "confidence": 0.84, + "canonical_issue_reason": "Issue #43598 is the more general customization concern around Trainer internals, so it is the better representative if a single issue must stand in for the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "#43598 is the strongest cluster representative because it directly targets a Trainer default that can block custom behavior and is phrased as a reusable design concern.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43598", + "right": "issue:43600", + "accept": false, + "reason": "They share the broad topic of custom trainers, but one is about `remove_unused_column` handling and the other is about FLOPs estimation. These are distinct behaviors and would not plausibly be merged into one issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 9, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "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": "dcf8b463403553c418d1f6b2f3301478bf13e80d26680564f14e37ad94269668", + "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 thematically related but distinct feature requests: one asks for Qwen3-Omni auto-class registration, the other for AutoModelForSequenceClassification support for Qwen3.5. They share the same broad area (AutoModel support for Qwen variants) but do not describe the same underlying bug/change.", + "confidence": 0.89, + "canonical_issue_reason": "Issue 43684 is the broader representative of the cluster because it concerns auto-registration for Qwen3-Omni across core auto classes, while 44405 is a narrower, different task for sequence classification on Qwen3.5.", + "canonical_pr_reason": null, + "best_issue_reason": "43684 is the best issue to represent the cluster theme of missing Qwen auto-model registration support; 44405 is related but targets a different model family and task head.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43684", + "right": "issue:44405", + "accept": false, + "reason": "Both are about adding Qwen-related AutoModel support, but they target different model families and different auto classes/tasks (Qwen3-Omni registration vs Qwen3.5 sequence classification). They are not the same change and should not be merged as duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 10, + "component_count": 16, + "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": "add8c6290d13a32cccd798ca3a7d3fc49f86a9addee45f16b695be20b6f4f5b4", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4265, + "estimated_input_tokens": 1067, + "estimated_eval_tokens": 2390 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4265, + "estimated_input_tokens": 1067, + "estimated_eval_tokens": 2390 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are mostly near-empty issues; three share the same generic title, but there isn\u2019t enough content to confirm a true duplicate beyond superficial similarity. The first huggingface issue is the best representative only by age.", + "confidence": 0.41, + "canonical_issue_reason": "issue:43845 is the earliest of the three identical 'huggingface ' issues, so it is the best placeholder canonical issue for that apparent duplicate set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43845 is the best overall issue because it is one of the repeated-title reports and is the oldest among them; the 'Fett' issue looks unrelated by title.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43835", + "right": "issue:43845", + "accept": false, + "reason": "Different titles and no body/details to show the same underlying issue; similarity is too weak to merge." + }, + { + "left": "issue:43835", + "right": "issue:43846", + "accept": false, + "reason": "Different titles and no concrete problem description; cannot confirm a duplicate." + }, + { + "left": "issue:43835", + "right": "issue:43859", + "accept": false, + "reason": "Different titles and no evidence they describe the same bug or request." + }, + { + "left": "issue:43845", + "right": "issue:43846", + "accept": false, + "reason": "Identical generic titles, but the issues are empty enough that I can\u2019t verify they are the same underlying report." + }, + { + "left": "issue:43845", + "right": "issue:43859", + "accept": false, + "reason": "Same broad title only; no substantive description or linkage proving a duplicate." + }, + { + "left": "issue:43846", + "right": "issue:43859", + "accept": false, + "reason": "Same broad title only; insufficient evidence to treat them as the same issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 11, + "component_count": 16, + "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": "fcf4f4b03494c3aec8fc43a0ead5fb6279d7479ecd1c53ce95528e97496a0fe5", + "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": "All candidates are extremely low-information or spam-like issues, with no concrete bug report, code path, or change description to support duplicate merging.", + "confidence": 0.08, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44418 is the only non-\"\" item, but it is still far too generic to serve as a reliable canonical representative.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44371", + "right": "issue:44572", + "accept": false, + "reason": "Both are just spam placeholders; identical low-information titles are not enough to confirm the same underlying issue." + }, + { + "left": "issue:44371", + "right": "issue:44573", + "accept": false, + "reason": "Both are spam placeholders with no concrete description, so duplicate status cannot be established." + }, + { + "left": "issue:44371", + "right": "issue:44418", + "accept": false, + "reason": "Spam placeholder vs. generic documentation suggestion; no shared technical problem is evident." + }, + { + "left": "issue:44371", + "right": "issue:44937", + "accept": false, + "reason": "Spam placeholder and an unrelated titled issue; no same underlying bug or change." + }, + { + "left": "issue:44418", + "right": "issue:44572", + "accept": false, + "reason": "Generic documentation suggestion vs. spam placeholder; no concrete overlap to justify a duplicate merge." + }, + { + "left": "issue:44418", + "right": "issue:44573", + "accept": false, + "reason": "Generic documentation suggestion vs. spam placeholder; insufficient evidence of the same issue." + }, + { + "left": "issue:44572", + "right": "issue:44573", + "accept": false, + "reason": "Both are spam placeholders, but there is no substantive report to confirm they are the same issue." + }, + { + "left": "issue:44572", + "right": "issue:44937", + "accept": false, + "reason": "Spam placeholder vs. unrelated title; no shared bug/change can be inferred." + }, + { + "left": "issue:44573", + "right": "issue:44937", + "accept": false, + "reason": "Spam placeholder vs. unrelated title; no evidence they describe 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": 12, + "component_count": 16, + "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": "482033f6495dbe4d573dc439c5da58257a381a80400e5ee72a5526f27595179c", + "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": "These issues are strong duplicate candidates: they share the exact title and have a soft-similarity signal, so #45145 is the best canonical anchor because it also has an inbound reference. The evidence is suggestive rather than conclusive from the packet alone, so the wording should stay conservative.", + "confidence": 0.78, + "canonical_issue_reason": "#45145 is the better canonical issue because it has the exact same title as #45151 and an inbound reference, making it the more natural deduplication anchor.", + "canonical_pr_reason": null, + "best_issue_reason": "#45145 is the best single issue to keep as the primary thread because it has the same title as #45151 and slightly more anchoring evidence via one inbound reference.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45145", + "right": "issue:45151", + "accept": true, + "reason": "The issues have identical titles and a soft-similarity signal, which is enough to treat them as likely duplicates; the packet does not justify stronger claims about the bodies being identical." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "Rejecting because the analyst overstates the evidence. The packet supports that these two issues have identical titles, similar body lengths, and a soft-similarity signal, so a tentative duplicate/canonicalization choice is reasonable. But it does not ground stronger claims like \u201cequivalent,\u201d \u201csame underlying issue/proposal,\u201d or \u201cnear-identical content,\u201d since the actual bodies are not provided here. The canonical choice based on the inbound reference is plausible, but the explanation should stay conservative and avoid asserting equivalence beyond the available evidence." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 13, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45295-2", + "nodes": [ + "issue:45295", + "issue:45373" + ], + "soft_pairs": [], + "prepared_review_unit_hash": "f5fd95fada2f530ab0999e343c17c16266cde0c7182bb22509972ca44827cd49", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 0, + "serialized_chars": 1286, + "estimated_input_tokens": 322, + "estimated_eval_tokens": 900 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 0, + "serialized_chars": 1286, + "estimated_input_tokens": 322, + "estimated_eval_tokens": 900 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two issues describe the same missing Gemma 4 sequence-classification support; the later, more specific open issue is the better cluster representative.", + "confidence": 0.94, + "canonical_issue_reason": "issue #45373 is the clearest canonical tracker: it is open, explicitly names the missing class `Gemma4ForSequenceClassification`, and states the module-level gap relative to Gemma 2/3.", + "canonical_pr_reason": null, + "best_issue_reason": "issue #45373 best captures the concrete request and likely remaining work, while #45295 is a shorter earlier duplicate with less detail and is already closed.", + "best_pr_reason": null, + "soft_edge_verdicts": [] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 14, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "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": "12e0cb68395e80eb51dc8c0d6d32e173e24e6f651f04db123fad82d559359831", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1667, + "estimated_input_tokens": 417, + "estimated_eval_tokens": 1090 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1667, + "estimated_input_tokens": 417, + "estimated_eval_tokens": 1090 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are two different 4-bit inference bugs in different code paths: one Gemma4/audio-module dtype failure, and one BitsAndBytesConfig skip-module regression that drops the default lm_head exclusion.", + "confidence": 0.97, + "canonical_issue_reason": "No canonical duplicate here: 45672 is a model-/audio-module-specific torch.finfo(uint8) failure, while 45674 is a separate BitsAndBytesConfig behavior bug around llm_int8_skip_modules and lm_head exclusion.", + "canonical_pr_reason": null, + "best_issue_reason": "If a single representative is needed, 45674 is the better anchor because it describes a broader configuration regression in the 4-bit inference path rather than a Gemma4-specific symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45672", + "right": "issue:45674", + "accept": false, + "reason": "Different underlying bugs and code paths; they share only the broad setting of 4-bit inference, not the same failure mechanism." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 15, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "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": "09ef3629fe4bf4008508129d84ee78175a2ac4742b404487c56d7a68b150b2be", + "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 closed issues are just person-name/date strings with no body or technical context. They do not appear to describe the same underlying bug or request, so the soft duplicate edge should be rejected.", + "confidence": 0.99, + "canonical_issue_reason": "No clear canonical issue: both issues lack any technical description or evidence of representing the same problem.", + "canonical_pr_reason": null, + "best_issue_reason": "Neither issue is a strong representative; if forced, issue:45762 is not meaningfully better than issue:45763 because both are empty and unrelated.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45762", + "right": "issue:45763", + "accept": false, + "reason": "The titles are different personal names with different dates, and both issues have no body or shared technical context; they do not look like 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": 16, + "component_count": 16, + "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": "ecacae9277ea9df8d501f10c11ffd3866b6f7fc70f0cac599b06e1db8d821e00", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1479, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1479, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The cluster contains two closed issues with unrelated name/date-style titles and no bodies or links. There is no evidence they describe the same bug, request, or change.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45764", + "right": "issue:45765", + "accept": false, + "reason": "The titles appear to be unrelated personal records with different names and dates; there is no shared technical problem, code path, or issue context." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 1, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-39895-13", + "nodes": [ + "pull_request:39895", + "pull_request:41855", + "pull_request:42668", + "pull_request:43251", + "pull_request:43254", + "pull_request:43424", + "pull_request:43823", + "pull_request:43995", + "pull_request:44827", + "pull_request:45170", + "pull_request:45213", + "pull_request:45655", + "pull_request:45795" + ], + "soft_pairs": [ + "pull_request:39895|pull_request:43424", + "pull_request:41855|pull_request: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:45795", + "pull_request:44827|pull_request:45655", + "pull_request:44827|pull_request:45213", + "pull_request:43823|pull_request:45213", + "pull_request:43823|pull_request:45795", + "pull_request:43251|pull_request:43254" + ], + "prepared_review_unit_hash": "2c38deedbda50eedb6027b872a1fb5d1586f8d74c2508532735950e8f3452561", + "component_budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 19, + "serialized_chars": 35204, + "estimated_input_tokens": 8801, + "estimated_eval_tokens": 17858 + }, + "budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 19, + "serialized_chars": 35204, + "estimated_input_tokens": 8801, + "estimated_eval_tokens": 17858 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Mostly unrelated PRs spanning new model additions, docs, and small refactors. The only strong duplicate pair is the two `fixed_cross_entropy` changes in `loss_utils.py`, which target the same issue and same code path.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": "`pull_request:43251` is the clearest representative of the duplicate loss fix: it directly targets issue #43240, has the more explicit description, and includes the same `loss_utils.py` code path as the paired PR.", + "best_issue_reason": null, + "best_pr_reason": "`pull_request:43251` is the best overall PR to represent the only true duplicate cluster here because it is the more complete/explicit version of the shared `fixed_cross_entropy` fix and is tied to the referenced issue.", + "soft_edge_verdicts": [ + { + "left": "pull_request:39895", + "right": "pull_request:43424", + "accept": false, + "reason": "Both are unrelated feature/test PRs; one adds VideoPrism, the other adds an ExecuTorch dynamic-shape test. No shared bug or mergeable code-path overlap." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43823", + "accept": false, + "reason": "Different tokenizer utility fix vs adding a new model package; not the same underlying change." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43424", + "accept": false, + "reason": "A tokenizer helper addition and an ExecuTorch export test are unrelated changes." + }, + { + "left": "pull_request:42668", + "right": "pull_request:43823", + "accept": false, + "reason": "Both touch processor/model auto-registration, but they are for different models and different problems, so not duplicates." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43823", + "accept": false, + "reason": "Loss-function kwargs fix versus adding MobileLLM; completely different code paths." + }, + { + "left": "pull_request:43251", + "right": "pull_request:44827", + "accept": false, + "reason": "`fixed_cross_entropy` kwargs support and Mistral4 test fixes are unrelated." + }, + { + "left": "pull_request:43424", + "right": "pull_request:44827", + "accept": false, + "reason": "ExecuTorch dynamic export testing and Mistral4 test/model fixes are not the same underlying bug." + }, + { + "left": "pull_request:43424", + "right": "pull_request:43823", + "accept": false, + "reason": "Dynamic-shape export testing is unrelated to adding MobileLLM." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45655", + "accept": false, + "reason": "A new model addition and a Python typing/order fix in `modeling_utils.py` are unrelated." + }, + { + "left": "pull_request:43823", + "right": "pull_request:43995", + "accept": false, + "reason": "New model addition vs Falcon refactor; different models and different issues." + }, + { + "left": "pull_request:43995", + "right": "pull_request:44827", + "accept": false, + "reason": "Falcon output-interface refactor and Mistral4 test fixes do not appear to fix the same concrete bug." + }, + { + "left": "pull_request:43995", + "right": "pull_request:45213", + "accept": false, + "reason": "Falcon refactor and model-creation skill work are unrelated." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45170", + "accept": false, + "reason": "Mistral4 test fixes and `layrnorm` normalization renaming are different changes, even though both touch model code." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45795", + "accept": false, + "reason": "Mistral4 test fixes and docs for audio/video processors are unrelated." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45655", + "accept": false, + "reason": "Mistral4 test/model work and config-resolution ordering in `modeling_utils.py` are unrelated." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45213", + "accept": false, + "reason": "Mistral4 fixes and the model-creation skill PR are unrelated." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45213", + "accept": false, + "reason": "Adding MobileLLM and adding a model-creation skill are not the same underlying change." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45795", + "accept": false, + "reason": "MobileLLM model addition vs documentation for audio/video processors are unrelated." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43254", + "accept": true, + "reason": "Both PRs modify `src/transformers/loss/loss_utils.py` to add the same missing `cross_entropy` kwargs (`weight` and `label_smoothing`) for the same issue #43240, so they are the same underlying fix." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet, and the soft-edge verdicts stay conservative. The one accepted pair, `pull_request:43251` vs `pull_request:43254`, is well supported by the shared `loss_utils.py` path and common issue target #43240, and the other pairwise rejections do not overclaim evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 2, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-40546-2", + "nodes": [ + "pull_request:40546", + "pull_request:42781" + ], + "soft_pairs": [ + "pull_request:40546|pull_request:42781" + ], + "prepared_review_unit_hash": "407c3cf1d884cf4cac249250539d4964706301de66dca1d4ce64f498f5f2b364", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 7224, + "estimated_input_tokens": 1806, + "estimated_eval_tokens": 3868 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 7224, + "estimated_input_tokens": 1806, + "estimated_eval_tokens": 3868 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two VibeVoice PRs overlap on shared model scaffolding, but they are distinct changes: one adds the base VibeVoice integration, while the other adds VibeVoice Realtime and the acoustic tokenizer stack.", + "confidence": 0.9, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #40546 is the broader, earlier VibeVoice integration and has substantial review activity; it is the better representative PR for this cluster.", + "best_issue_reason": null, + "best_pr_reason": "PR #40546 is the best single PR to anchor the cluster because it implements the core VibeVoice model support, whereas #42781 is a separate realtime follow-on.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40546", + "right": "pull_request:42781", + "accept": false, + "reason": "They share VibeVoice infrastructure, but #40546 is the base implementation and #42781 adds realtime/acoustic-tokenizer functionality plus extra generation changes. These are related feature expansions, not the same concrete code 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": 3, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-40755-2", + "nodes": [ + "pull_request:40755", + "pull_request:41224" + ], + "soft_pairs": [ + "pull_request:40755|pull_request:41224" + ], + "prepared_review_unit_hash": "20e4a8b28727b317d69e461293750cfb4b3aba73356bf591e2e9cc530f0b2d6c", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4674, + "estimated_input_tokens": 1169, + "estimated_eval_tokens": 2594 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4674, + "estimated_input_tokens": 1169, + "estimated_eval_tokens": 2594 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two pull requests are not duplicates: one adds TimesFM forecasting with covariates, while the other adds DINOv3 image-classification support. They touch different models, different code paths, and different docs/tests.", + "confidence": 0.99, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": "No canonical PR in this cluster; if forced to pick a representative item, the DINOv3 classification PR is more self-contained, but it is still unrelated to the TimesFM PR.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40755", + "right": "pull_request:41224", + "accept": false, + "reason": "Different features in different model families (TimesFM covariate forecasting vs DINOv3 image classification); they do not describe 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": "pull_request", + "component_index": 4, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-41356-2", + "nodes": [ + "pull_request:41356", + "pull_request:44339" + ], + "soft_pairs": [ + "pull_request:41356|pull_request:44339" + ], + "prepared_review_unit_hash": "aead1308c167b0bae6ff11bf9358340baa5e76f816618383418b505a10a9cd01", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6050, + "estimated_input_tokens": 1513, + "estimated_eval_tokens": 3282 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6050, + "estimated_input_tokens": 1513, + "estimated_eval_tokens": 3282 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two DEIMv2 pull requests target the same model family, but they are not the same change: PR 41356 is an early/basic model + image processor add, while PR 44339 is a much broader follow-up that adds loss code, auto-mappings, conversion tooling, modular files, and more integration work.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44339 is the more complete and representative DEIMv2 implementation; PR 41356 looks like an earlier partial version of the same model bring-up.", + "best_issue_reason": null, + "best_pr_reason": "PR 44339 is the strongest single artifact for the cluster because it subsumes the basic model work and includes the broader integration needed for a full Transformers addition.", + "soft_edge_verdicts": [ + { + "left": "pull_request:41356", + "right": "pull_request:44339", + "accept": false, + "reason": "Same model area, but not the same concrete change: 44339 expands the implementation substantially and adds new code paths beyond the basic PR 41356. They look like related iterations, not mergeable duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 5, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-41797-3", + "nodes": [ + "pull_request:41797", + "pull_request:45186", + "pull_request:45630" + ], + "soft_pairs": [ + "pull_request:41797|pull_request:45186", + "pull_request:45186|pull_request:45630" + ], + "prepared_review_unit_hash": "e1a19f8c3b8362708496e15bc6c804d492d42ab8069491a8c1d2e2e8dbc273af", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 10429, + "estimated_input_tokens": 2608, + "estimated_eval_tokens": 5472 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 10429, + "estimated_input_tokens": 2608, + "estimated_eval_tokens": 5472 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are three separate pull requests adding different models (DeepSeek OCR, Isaac, and Kimi2-6). They share only common integration scaffolding and docs/auto-registration updates, not the same underlying bug or change.", + "confidence": 0.99, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: the items implement distinct model additions for different architectures, so they are not duplicates of one another.", + "best_issue_reason": null, + "best_pr_reason": "If a representative PR is needed, 45630 is the most comprehensive of the three (broadest model integration surface and highest review activity), but it is not a duplicate/canonical merge target for the others.", + "soft_edge_verdicts": [ + { + "left": "pull_request:41797", + "right": "pull_request:45186", + "accept": false, + "reason": "DeepSeek OCR and Isaac are different model additions; shared auto-registration/docs files are generic scaffolding, not evidence of the same change or bug fix." + }, + { + "left": "pull_request:45186", + "right": "pull_request:45630", + "accept": false, + "reason": "Isaac and Kimi2-6 target different models and code paths; overlap is limited to standard model-adding boilerplate, so they should not be merged as duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 6, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-42975-2", + "nodes": [ + "pull_request:42975", + "pull_request:42976" + ], + "soft_pairs": [ + "pull_request:42975|pull_request:42976" + ], + "prepared_review_unit_hash": "9657b54097d3755e2baba74dc3162ee1d9e5761a6ab1869684ff68e46a3b69d6", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5935, + "estimated_input_tokens": 1484, + "estimated_eval_tokens": 3224 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5935, + "estimated_input_tokens": 1484, + "estimated_eval_tokens": 3224 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both items are workflow-maintenance PRs that upgrade GitHub Actions, but they update different actions and different code paths: one is for Node 24 compatibility in checkout/cache/upload-artifact, the other is for docker/build-push-action and related workflow pin bumps. They are similar in theme, not the same underlying change.", + "confidence": 0.92, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 42975 is the better representative of this cluster because it has the broader, clearer objective (Node 24 compatibility across many workflows) and the larger, more coherent action-version bump set.", + "best_issue_reason": null, + "best_pr_reason": "PR 42975 is the strongest PR to represent the group overall: it targets a specific compatibility problem and spans multiple workflows, whereas PR 42976 is a separate dependency/version refresh for docker build workflows.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42975", + "right": "pull_request:42976", + "accept": false, + "reason": "Reject: they are both GitHub Actions upgrade PRs, but they change different actions and solve different maintenance tasks; no shared concrete bug/change to merge into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 7, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-42978-7", + "nodes": [ + "pull_request:42978", + "pull_request:43448", + "pull_request:43451", + "pull_request:43973", + "pull_request:44601", + "pull_request:45490", + "pull_request:45838" + ], + "soft_pairs": [ + "pull_request:42978|pull_request:43448", + "pull_request:42978|pull_request:43451", + "pull_request:42978|pull_request:45490", + "pull_request:43448|pull_request:43451", + "pull_request:43448|pull_request:45490", + "pull_request:43451|pull_request:45490", + "pull_request:43973|pull_request:45838", + "pull_request:44601|pull_request:45838", + "pull_request:45490|pull_request:45838" + ], + "prepared_review_unit_hash": "e85946c296e917a66db1d032dd235a4b647d49ecdbdcf8c6c117a4bd4a8c0864", + "component_budget": { + "node_count": 7, + "item_count": 7, + "soft_pair_count": 9, + "serialized_chars": 23513, + "estimated_input_tokens": 5879, + "estimated_eval_tokens": 12014 + }, + "budget": { + "node_count": 7, + "item_count": 7, + "soft_pair_count": 9, + "serialized_chars": 23513, + "estimated_input_tokens": 5879, + "estimated_eval_tokens": 12014 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "All proposed soft edges look like false positives: the PRs are separate model additions or unrelated infrastructure changes, with only generic docs/registry overlap. None appear to fix the same concrete bug or implement the same mergeable change.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single PR is a true duplicate target here; if one representative PR must be picked, 43451 is the most substantial and review-heavy model-addition PR, but it remains distinct from the others.", + "best_issue_reason": null, + "best_pr_reason": "43451 is the strongest standalone representative of the model-addition subgroup, but the set does not contain a mergeable duplicate cluster.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42978", + "right": "pull_request:43448", + "accept": false, + "reason": "ViT NEPA and Molmo are different model additions; the overlap is only in shared registration/docs scaffolding." + }, + { + "left": "pull_request:42978", + "right": "pull_request:43451", + "accept": false, + "reason": "ViT NEPA vs Molmo2 are unrelated model families, not the same underlying change." + }, + { + "left": "pull_request:42978", + "right": "pull_request:45490", + "accept": false, + "reason": "ViT NEPA and CTSM are distinct model implementations; shared toctree/auto wiring is boilerplate." + }, + { + "left": "pull_request:43448", + "right": "pull_request:43451", + "accept": false, + "reason": "Molmo and Molmo2 are separate model families/generations, so this is not a duplicate fix or mergeable single PR." + }, + { + "left": "pull_request:43448", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo and CTSM address different models and code paths; overlap is limited to generic model-addition plumbing." + }, + { + "left": "pull_request:43451", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo2 and CTSM are unrelated model additions, not the same concrete change." + }, + { + "left": "pull_request:43973", + "right": "pull_request:45838", + "accept": false, + "reason": "Lfm2 audio support and PP-OCRv6 text recognition are different modalities and model stacks; only docs/index files overlap." + }, + { + "left": "pull_request:44601", + "right": "pull_request:45838", + "accept": false, + "reason": "Native pipeline-parallel loading support is infrastructure work, while PP-OCRv6 is a model support PR; they do not fix the same code-path problem." + }, + { + "left": "pull_request:45490", + "right": "pull_request:45838", + "accept": false, + "reason": "CTSM model support and PP-OCRv6 text recognition are different model additions, not duplicate changes." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 8, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43291-3", + "nodes": [ + "pull_request:43291", + "pull_request:43665", + "pull_request:44815" + ], + "soft_pairs": [ + "pull_request:43291|pull_request:43665", + "pull_request:43291|pull_request:44815", + "pull_request:43665|pull_request:44815" + ], + "prepared_review_unit_hash": "9c6844e510f4a45023fa4fcee17143709c927e23bdc70db874ff94e864c47cd2", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 7092, + "estimated_input_tokens": 1773, + "estimated_eval_tokens": 3802 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 7092, + "estimated_input_tokens": 1773, + "estimated_eval_tokens": 3802 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These pull requests are not the same change set: one is a Whisper tokenizer/test fix, one is unrelated CLIP/ViT test edits, and one is a broader FP8/dequantization fix across several files. No duplicate cluster emerges here.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44815 is the most substantive and coherent change: it fixes a concrete dequantization/loading path and includes targeted code updates plus tests. The others are either narrowly scoped to Whisper or appear to be test-only edits.", + "best_issue_reason": null, + "best_pr_reason": "PR 44815 is the best representative of the group because it contains a real cross-file implementation fix, whereas PR 43291 is narrow and PR 43665 looks like unrelated or placeholder test changes rather than a true bug fix.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43291", + "right": "pull_request:43665", + "accept": false, + "reason": "Different targets and different problems: Whisper tokenization/decode logic versus CLIP/ViT test files. They do not appear to fix the same underlying bug or code path." + }, + { + "left": "pull_request:43291", + "right": "pull_request:44815", + "accept": false, + "reason": "Whisper decode behavior and FP8/dequantization/loading are unrelated subsystems with no shared concrete bug path." + }, + { + "left": "pull_request:43665", + "right": "pull_request:44815", + "accept": false, + "reason": "Despite superficial similarity in being test-heavy, these PRs address different areas and do not look mergeable as one fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 9, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43488-2", + "nodes": [ + "pull_request:43488", + "pull_request:43532" + ], + "soft_pairs": [ + "pull_request:43488|pull_request:43532" + ], + "prepared_review_unit_hash": "c35da48f9d38520ae515b82be57154402d304ad1e0f1ca1aeabc18ae4fb77730", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4563, + "estimated_input_tokens": 1141, + "estimated_eval_tokens": 2538 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4563, + "estimated_input_tokens": 1141, + "estimated_eval_tokens": 2538 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two PRs are not duplicates: one is a setup/version/dependency/test tweak, while the other rewires CI workflows and related testing/notification code. Their overlap is superficial (shared test file) and they do not fix the same code-path problem.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "pull_request:43488", + "right": "pull_request:43532", + "accept": false, + "reason": "Different underlying changes and goals: #43488 touches setup.py, dependency tables, and a ViT test; #43532 changes GitHub workflow files plus testing/notification utilities. Shared filename alone is not enough to treat them as the same PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 10, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43612-2", + "nodes": [ + "pull_request:43612", + "pull_request:43613" + ], + "soft_pairs": [ + "pull_request:43612|pull_request:43613" + ], + "prepared_review_unit_hash": "15a9b572ed595151d57c0fd90e08e3c2275fe61335d049bd6142a4d5872729be", + "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": "The two PRs are closely related in infrastructure and documentation, but they implement different features: promptable concept segmentation vs promptable visual segmentation. They share scaffolding files, but the underlying models, tests, and task docs are distinct, so this is not a duplicate pair.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 43613 is the better representative only in the sense that it is the broader, more model-backed feature, but it is not a duplicate of 43612 because it targets a different segmentation task and code path.", + "best_issue_reason": null, + "best_pr_reason": "PR 43613 is the stronger anchor for the cluster because it covers the more general visual-segmentation feature with more backend/model integrations, but it should not be merged with 43612 as a duplicate.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43612", + "right": "pull_request:43613", + "accept": false, + "reason": "Shared docs/pipeline plumbing is not enough: one adds promptable concept segmentation and the other adds promptable visual segmentation, with different task docs, model integrations, and test files. They are separate features, not the same underlying change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 11, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43651-2", + "nodes": [ + "pull_request:43651", + "pull_request:43663" + ], + "soft_pairs": [ + "pull_request:43651|pull_request:43663" + ], + "prepared_review_unit_hash": "23639f2037b88fcb98692c71b0bbf9ee15deef849357ce991a3238d96807ff49", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4292, + "estimated_input_tokens": 1073, + "estimated_eval_tokens": 2402 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4292, + "estimated_input_tokens": 1073, + "estimated_eval_tokens": 2402 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are two separate Trainer extensibility PRs in the same file, but they address different code paths: one changes gradient-accumulation loss scaling, the other makes signature-column filtering overrideable. Related area, not the same underlying change.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "No true canonical duplicate exists here; the PRs solve different Trainer behaviors rather than one shared bug or feature.", + "best_issue_reason": null, + "best_pr_reason": "PR #43651 is the more central representative of the cluster only in the sense that it adds a broader trainer hook, but it should not be treated as a duplicate of #43663.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43651", + "right": "pull_request:43663", + "accept": false, + "reason": "Both touch trainer.py, but one is about gradient-accumulation loss scaling and the other about column/signature filtering. Different behavior, different fix, not 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": 12, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43656-3", + "nodes": [ + "pull_request:43656", + "pull_request:43836", + "pull_request:43842" + ], + "soft_pairs": [ + "pull_request:43656|pull_request:43842", + "pull_request:43836|pull_request:43842" + ], + "prepared_review_unit_hash": "f78b626bcd2b1c5055d7d1b12ef7bc1b15019d7aebbcc9186db646cba1d4f189", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 5993, + "estimated_input_tokens": 1499, + "estimated_eval_tokens": 3254 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 5993, + "estimated_input_tokens": 1499, + "estimated_eval_tokens": 3254 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "All three PRs are in the same `src/transformers/cli/serve.py` area and appear to address the same import-time `TypeAdapter` annotation problem in the CLI. The most focused representative is the minimal, explicit pydantic-related fix.", + "confidence": 0.74, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 43842 is the clearest and most targeted fix: it explicitly addresses the `TypeAdapter` NameError when pydantic is absent, keeps the change minimal, and directly annotates the problematic code path.", + "best_issue_reason": null, + "best_pr_reason": "PR 43842 is the best overall representative because it is the most precise and least invasive fix for the concrete `TypeAdapter` NameError in `serve.py`.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43656", + "right": "pull_request:43842", + "accept": true, + "reason": "Both PRs fix the same underlying `TypeAdapter` annotation/import-time NameError in `src/transformers/cli/serve.py`; the changes are different implementations of the same bug fix and could plausibly be folded into one PR." + }, + { + "left": "pull_request:43836", + "right": "pull_request:43842", + "accept": true, + "reason": "Both PRs target the same `TypeAdapter` NameError in the CLI serve module. Even though 43836 is broader, its stated workaround and the pydantic-specific fix in 43842 are aimed at the same concrete code-path problem." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet, and the chosen representative PR is reasonably supported as the most targeted fix. Both soft-edge accepts are conservative enough here: the PRs share the same file and same TypeAdapter-related bug theme, and their fixes are compatible enough to plausibly live in one PR." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 13, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43779-2", + "nodes": [ + "pull_request:43779", + "pull_request:43816" + ], + "soft_pairs": [ + "pull_request:43779|pull_request:43816" + ], + "prepared_review_unit_hash": "e7c674adcc031aa8883109a5dfc678b4407fb20b10764302092e384d031ba83a", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4362, + "estimated_input_tokens": 1091, + "estimated_eval_tokens": 2438 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4362, + "estimated_input_tokens": 1091, + "estimated_eval_tokens": 2438 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both pull requests appear to implement the same SwanLab integration change: adding run id/resume support in `integration_utils.py` for issue #43698, with one variant also expanding the docs. They are strong duplicate PR candidates.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #43816 is the cleaner representative: it carries the same SwanLab id/resume support plus the accompanying documentation updates, making it the more complete version of the shared change.", + "best_issue_reason": null, + "best_pr_reason": "PR #43816 is the best global representative because it appears to include the full feature change and docs for SwanLab run id/resume support, while #43779 is the narrower implementation-focused variant.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43779", + "right": "pull_request:43816", + "accept": true, + "reason": "Same underlying SwanLab callback enhancement for id/resume support in the same file and same issue target; the doc differences do not change the core code-path change, so these are duplicate PRs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: both PRs target issue #43698, touch the same file, and the previews indicate the same SwanLab id/resume support with #43816 adding docs. The duplicate/mergeable verdict is conservative enough given the shared target and overlapping code change." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 14, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 2, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43996-28", + "nodes": [ + "pull_request:43996", + "pull_request:43997", + "pull_request:44007", + "pull_request:44010", + "pull_request:44013", + "pull_request:44017", + "pull_request:44018", + "pull_request:44019", + "pull_request:44044", + "pull_request:44056", + "pull_request:44059", + "pull_request:44066", + "pull_request:44068", + "pull_request:44071", + "pull_request:44072", + "pull_request:44073", + "pull_request:44074", + "pull_request:44076", + "pull_request:44085", + "pull_request:44086", + "pull_request:44098", + "pull_request:44101", + "pull_request:44116", + "pull_request:44129", + "pull_request:44154", + "pull_request:44161", + "pull_request:44722" + ], + "soft_pairs": [ + "pull_request:43996|pull_request:44085", + "pull_request:43996|pull_request:44044", + "pull_request:44066|pull_request:44085", + "pull_request:44007|pull_request:44072", + "pull_request:44072|pull_request:44722", + "pull_request:44066|pull_request:44072", + "pull_request:44013|pull_request:44044", + "pull_request:44066|pull_request:44086", + "pull_request: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:44059|pull_request:44722", + "pull_request:44098|pull_request:44101", + "pull_request:44018|pull_request:44071", + "pull_request:44017|pull_request:44161", + "pull_request:44017|pull_request:44722", + "pull_request:44017|pull_request:44073", + "pull_request:44068|pull_request:44071", + "pull_request:44071|pull_request:44086", + "pull_request:43997|pull_request:44073", + "pull_request:44017|pull_request:44071", + "pull_request:44073|pull_request:44101", + "pull_request:44059|pull_request:44071", + "pull_request:44073|pull_request:44161", + "pull_request:44056|pull_request:44101", + "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:43997|pull_request:44129", + "pull_request:44071|pull_request:44129", + "pull_request:44010|pull_request:44018", + "pull_request:43996|pull_request:44161", + "pull_request:43996|pull_request:44017", + "pull_request:44010|pull_request:44044", + "pull_request:44044|pull_request:44074", + "pull_request:44066|pull_request:44722", + "pull_request:44085|pull_request:44722", + "pull_request:44085|pull_request:44129", + "pull_request:43996|pull_request:44007", + "pull_request:43996|pull_request:44129", + "pull_request:44044|pull_request:44129", + "pull_request:44044|pull_request:44154" + ], + "prepared_review_unit_hash": "0c9ad5a7d44b1769765c7f0e2eb368375662a59eb4087d189ea12b01d40382ea", + "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 batch of model-specific output-tracing refactors. Only a few pairs are true near-duplicates within the same concrete code path (notably GPT-Neo and GPT-J/CodeGen); the rest are the same umbrella theme but different models and should stay separate.", + "confidence": 0.87, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44066 is the clearest canonical representative: it directly targets the GPT-J/CodeGen output-tracing migration, has an explicit #43979 link, and its diff matches the concrete standardized-decorator refactor pattern most cleanly.", + "best_issue_reason": null, + "best_pr_reason": "PR 44066 is the best global representative of the cluster\u2019s duplicate set because it is focused, explicitly linked to the umbrella issue, and closest to the repeated GPT-J/CodeGen refactor change path.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43996", + "right": "pull_request:44085", + "accept": false, + "reason": "Different model families (CVT/FNet vs GPT-J); same umbrella tracing pattern, but not the same concrete code change." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44044", + "accept": false, + "reason": "Different models and code paths; both are output-tracing refactors, but not duplicates of the same change." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44085", + "accept": true, + "reason": "Both are GPT-J output-tracing refactors in the same file and same code path; they look like the same underlying change." + }, + { + "left": "pull_request:44007", + "right": "pull_request:44072", + "accept": false, + "reason": "RegNet/ResNet vs EfficientNet are different model implementations; shared decorator migration theme is too broad to merge." + }, + { + "left": "pull_request:44072", + "right": "pull_request:44722", + "accept": false, + "reason": "EfficientNet and GPT-J/CodeGen are unrelated code paths; only the refactor style matches." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44072", + "accept": false, + "reason": "GPT-J/CodeGen and EfficientNet are different models and different concrete fixes." + }, + { + "left": "pull_request:44013", + "right": "pull_request:44044", + "accept": false, + "reason": "MobileNetV2 vs DeBERTa_v2 are unrelated implementations; same tracing theme is not enough for duplication." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J/CodeGen and MGP-STR are different model paths; not the same bug/change." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-J/CodeGen and MPT are separate code paths; both use the new tracing API but are not duplicates." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44068", + "accept": true, + "reason": "Both are GPT-Neo output-tracing refactors on the same model/file, with the same standardized decorator migration." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44068", + "accept": false, + "reason": "GPT-J/CodeGen vs GPT-Neo are different models and different code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44066", + "accept": false, + "reason": "GPT-Neo and GPT-J/CodeGen are distinct model implementations; shared issue target does not make them duplicates." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44722", + "accept": false, + "reason": "ResNet and GPT-J/CodeGen are unrelated model families and fixes." + }, + { + "left": "pull_request:44086", + "right": "pull_request:44722", + "accept": false, + "reason": "MGP-STR and GPT-J/CodeGen touch different code paths; same refactor pattern only." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44085", + "accept": false, + "reason": "ResNet vs GPT-J are different models; not the same underlying change." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44019", + "accept": false, + "reason": "GPT-Neo and ResNet are unrelated model implementations." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44071", + "accept": false, + "reason": "ResNet vs MPT are different code paths and different concrete output-handling changes." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo and Flaubert are different models; same tracing migration pattern only." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT-Neo vs GPT-J/CodeGen are different model families and fixes." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo and Flaubert are separate model code paths." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44722", + "accept": false, + "reason": "MPT and GPT-J/CodeGen are different model implementations." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo and MGP-STR are unrelated model paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44085", + "accept": false, + "reason": "GPT-Neo and GPT-J are different models; not a duplicate change." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo vs MGP-STR are different code paths." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44085", + "accept": false, + "reason": "MPT and GPT-J are separate model fixes." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT2 and MGP-STR are different models and different concrete refactors." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J and MGP-STR are unrelated implementations; only the decorator migration theme overlaps." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT2 vs GPT-J/CodeGen are different code paths." + }, + { + "left": "pull_request:44098", + "right": "pull_request:44101", + "accept": false, + "reason": "ViLT and Flaubert/XLM are different model families; too broad to be duplicates." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-Neo and MPT are different models; same standardized-output work but not the same change." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44161", + "accept": false, + "reason": "Segformer and LongT5 are unrelated model implementations." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44017", + "accept": false, + "reason": "RegNet and Segformer are different models and different concrete fixes." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44056", + "accept": false, + "reason": "RegNet and MPNet are separate code paths; same tracing infrastructure change only." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44076", + "accept": false, + "reason": "MPT and ImageGPT are different model files and different output-tracing changes." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44073", + "accept": false, + "reason": "Segformer and VisualBert are unrelated model implementations." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44101", + "accept": false, + "reason": "VisualBert and Flaubert/XLM are different model families." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT2 and MPT are different code paths and not the same fix." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44101", + "accept": false, + "reason": "MPNet and Flaubert/XLM are distinct model implementations." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44018", + "accept": false, + "reason": "RegNet and GPT-Neo are unrelated concrete changes." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44161", + "accept": false, + "reason": "RegNet and LongT5 are different models and fixes." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44129", + "accept": false, + "reason": "MPT and SpeechT5 are different code paths; same tracing pattern only." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44071", + "accept": false, + "reason": "SqueezeBert and MPT are unrelated model implementations." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44073", + "accept": false, + "reason": "SqueezeBert and VisualBert are different model paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44129", + "accept": false, + "reason": "GPT-Neo and SpeechT5 are separate model code paths." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44161", + "accept": false, + "reason": "CVT/FNet and LongT5 are different models; same umbrella refactor is not enough." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44017", + "accept": false, + "reason": "CVT/FNet and Segformer are different model implementations." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44044", + "accept": false, + "reason": "SqueezeBert and DeBERTa_v2 are unrelated code paths." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44074", + "accept": false, + "reason": "DeBERTa_v2 and TextNet are different models and fixes." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44722", + "accept": true, + "reason": "Both center on the same GPT-J/CodeGen output-tracing refactor; the later PR looks like the same change family." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44722", + "accept": true, + "reason": "Both touch GPT-J output tracing in the same file and are the same underlying refactor, despite 44722 also carrying the CodeGen companion change." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44129", + "accept": false, + "reason": "GPT-J and SpeechT5 are different models and different fixes." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44007", + "accept": false, + "reason": "CVT/FNet and RegNet/ResNet are different model families; no shared concrete bug." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44129", + "accept": false, + "reason": "CVT/FNet and SpeechT5 are unrelated model code paths." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44129", + "accept": false, + "reason": "DeBERTa_v2 and SpeechT5 are different model implementations." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44154", + "accept": false, + "reason": "DeBERTa_v2 and Vits are different models; only the tracing refactor theme overlaps." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and the soft-edge verdicts are mostly conservative. The accepted pairs are all same-model/same-file refactor variants that plausibly merge into a single bugfix PR, while the rejected pairs correctly stay away from cross-model overreach. No clear evidence of overstating duplicate status." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 14, + "component_count": 26, + "review_unit_index": 2, + "review_unit_count": 2, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43996-28", + "nodes": [ + "pull_request:43997", + "pull_request:44010", + "pull_request:44024", + "pull_request:44056", + "pull_request:44073", + "pull_request:44074", + "pull_request:44076", + "pull_request:44129" + ], + "soft_pairs": [ + "pull_request:44024|pull_request:44076", + "pull_request:44073|pull_request:44074", + "pull_request:44056|pull_request:44073", + "pull_request:44056|pull_request:44074", + "pull_request:43997|pull_request:44010", + "pull_request:44010|pull_request:44129" + ], + "prepared_review_unit_hash": "d503011584788ee1b2a5bef08291a8550059ddd93010f4af300af5db0559ed27", + "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": "All items are the same broad modernization pattern\u2014model-specific migration to standardized output capture\u2014but they target different architectures and code paths, so none of the soft pairs are true duplicates.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44129 is the best representative because it is the only one tied to an explicit issue and shows the standardized output-capture refactor most clearly, but it is still specific to SpeechT5 rather than a shared bugfix.", + "best_issue_reason": null, + "best_pr_reason": "PR 44129 is the strongest single PR to anchor the cluster: explicit issue linkage, clear refactor intent, and a self-contained model-specific implementation.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44024", + "right": "pull_request:44076", + "accept": false, + "reason": "Different models (FocalNet vs ImageGPT) and different forward paths; same refactor style, not the same underlying change." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44074", + "accept": false, + "reason": "Different models (VisualBert vs TextNet); they share output-tracing cleanup, but the affected code and behavior are unrelated." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44073", + "accept": false, + "reason": "MPNet and VisualBert are separate model implementations with distinct output-capture wiring; not mergeable as one PR." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44074", + "accept": false, + "reason": "MPNet vs TextNet touches different model internals and output-return conventions; same theme, not same bug/change." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44010", + "accept": false, + "reason": "RegNet and SqueezeBert are unrelated model code paths; both standardize outputs, but they do not fix the same concrete problem." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44129", + "accept": false, + "reason": "SqueezeBert and SpeechT5 are different models with different output-tracing implementations; the overlap is only in refactoring approach." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 15, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43998-13", + "nodes": [ + "pull_request:43998", + "pull_request:43999", + "pull_request:44000", + "pull_request:44001", + "pull_request:44002", + "pull_request:44003", + "pull_request:44004", + "pull_request:44025", + "pull_request:44026", + "pull_request:44027", + "pull_request:44028", + "pull_request:44029", + "pull_request:44030" + ], + "soft_pairs": [ + "pull_request:43998|pull_request:44002", + "pull_request:43998|pull_request:44000", + "pull_request:43998|pull_request:44001", + "pull_request:43998|pull_request:44003", + "pull_request:43998|pull_request:44029", + "pull_request:43999|pull_request:44001", + "pull_request:43999|pull_request:44002", + "pull_request:43999|pull_request:44025", + "pull_request:43999|pull_request:44026", + "pull_request:43999|pull_request:44027", + "pull_request:44000|pull_request:44001", + "pull_request:44000|pull_request:44002", + "pull_request:44000|pull_request:44003", + "pull_request:44000|pull_request:44025", + "pull_request:44001|pull_request:44002", + "pull_request:44001|pull_request:44003", + "pull_request:44001|pull_request:44025", + "pull_request:44002|pull_request:44029", + "pull_request:44002|pull_request:44003", + "pull_request:44003|pull_request:44028", + "pull_request:44003|pull_request:44004", + "pull_request:43998|pull_request:44004", + "pull_request:44001|pull_request:44004", + "pull_request:44002|pull_request:44004", + "pull_request:44000|pull_request:44004", + "pull_request:44025|pull_request:44026", + "pull_request:44025|pull_request:44027", + "pull_request:44025|pull_request:44028", + "pull_request:44025|pull_request:44029", + "pull_request:44025|pull_request:44030", + "pull_request:44026|pull_request:44029", + "pull_request:44026|pull_request:44027", + "pull_request:44026|pull_request:44028", + "pull_request:44026|pull_request:44030", + "pull_request:44027|pull_request:44028", + "pull_request:44027|pull_request:44029", + "pull_request:44027|pull_request:44030", + "pull_request:44028|pull_request:44029", + "pull_request:44028|pull_request:44030", + "pull_request:44029|pull_request:44030" + ], + "prepared_review_unit_hash": "7d7011b1878eeec12309620fd4e6e9a88736902d5d528f889aec869820f3c09b", + "component_budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 40, + "serialized_chars": 40178, + "estimated_input_tokens": 10045, + "estimated_eval_tokens": 20346 + }, + "budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 40, + "serialized_chars": 40178, + "estimated_input_tokens": 10045, + "estimated_eval_tokens": 20346 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs share a common refactor theme (output tracing / can_return_tuple) but target different models and code paths, so they are not duplicates of the same change.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "pull_request:43998", + "right": "pull_request:44002", + "accept": false, + "reason": "Different model families (`timm_backbone` vs `upernet`); same refactor theme, not the same concrete fix." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44000", + "accept": false, + "reason": "Unrelated model implementations; no shared code path or bug beyond generic output-tracing refactoring." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44001", + "accept": false, + "reason": "Different models (`timm_backbone` vs `univnet`); separate forward/output handling changes." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44003", + "accept": false, + "reason": "`timm_backbone` and `mamba/falcon_mamba` are distinct subsystems with separate refactors." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44029", + "accept": false, + "reason": "Different architectures and files; not the same underlying change." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44001", + "accept": false, + "reason": "Different model code paths (`mobilenet_v1` vs `univnet`), only broadly similar tracing refactor." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44002", + "accept": false, + "reason": "Separate models and forward signatures; not one mergeable duplicate change." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44025", + "accept": false, + "reason": "`mobilenet_v1` is unrelated to `depth_anything` / `prompt_depth_anything`; no shared concrete bug." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44026", + "accept": false, + "reason": "Different encoder-decoder model families; same theme but not same fix." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44027", + "accept": false, + "reason": "`mobilenet_v1` and `speech_encoder_decoder` touch different implementations and behaviors." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44001", + "accept": false, + "reason": "Different models (`vision_text_dual_encoder` vs `univnet`); no shared code path." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44002", + "accept": false, + "reason": "Separate model families and APIs; same refactor motif only." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44003", + "accept": false, + "reason": "Different subsystems (`vision_text_dual_encoder` vs `mamba`); not mergeable as one fix." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44025", + "accept": false, + "reason": "Distinct model code paths; similar output-tracing cleanup is not enough for duplication." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44002", + "accept": false, + "reason": "`univnet` and `upernet` are unrelated model implementations." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44003", + "accept": false, + "reason": "Different architectures and files; no same underlying bug/change." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44025", + "accept": false, + "reason": "`univnet` does not overlap with `depth_anything` code paths." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44029", + "accept": false, + "reason": "`upernet` and `rwkv` are unrelated; same refactor pattern only." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44003", + "accept": false, + "reason": "Different model families with separate forward/output behavior." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44028", + "accept": false, + "reason": "`mamba` and `superpoint` are unrelated; no common concrete fix." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44004", + "accept": false, + "reason": "Different code paths (`mamba` vs `codegen`); not the same PR-worthy change." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44004", + "accept": false, + "reason": "`timm_backbone` and `codegen` are unrelated implementations." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44004", + "accept": false, + "reason": "Separate model classes and forward semantics; no duplicate bug." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44004", + "accept": false, + "reason": "Different subsystems (`upernet` vs `codegen`); only generic tracing refactor overlap." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44004", + "accept": false, + "reason": "Distinct models and output formats; not the same underlying change." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44026", + "accept": false, + "reason": "`depth_anything` and `vision_encoder_decoder` are different model families." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44027", + "accept": false, + "reason": "Different models and APIs; same broad cleanup theme, not one fix." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44028", + "accept": false, + "reason": "`depth_anything` and `superpoint` do not share a concrete code path." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44029", + "accept": false, + "reason": "Different model families (`depth_anything` vs `rwkv`); not duplicates." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44030", + "accept": false, + "reason": "`depth_anything` and `dpr` are unrelated changes despite similar refactoring." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44029", + "accept": false, + "reason": "`vision_encoder_decoder` and `rwkv` are unrelated code paths." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44027", + "accept": false, + "reason": "Different encoder-decoder stacks; not the same concrete bug/change." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44028", + "accept": false, + "reason": "`vision_encoder_decoder` and `superpoint` are unrelated models." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44030", + "accept": false, + "reason": "Different model families and output handling; no shared fix." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44028", + "accept": false, + "reason": "`speech_encoder_decoder` and `superpoint` are unrelated implementations." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44029", + "accept": false, + "reason": "Different model subsystems; same refactor pattern only." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44030", + "accept": false, + "reason": "`speech_encoder_decoder` and `dpr` are not the same underlying change." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44029", + "accept": false, + "reason": "`superpoint` and `rwkv` have no shared code path." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44030", + "accept": false, + "reason": "Different models and behaviors; not mergeable as one PR." + }, + { + "left": "pull_request:44029", + "right": "pull_request:44030", + "accept": false, + "reason": "`rwkv` and `dpr` are unrelated model implementations; only the output-tracing cleanup overlaps." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 16, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-44662-3", + "nodes": [ + "pull_request:44662", + "pull_request:45075", + "pull_request:45401" + ], + "soft_pairs": [ + "pull_request:44662|pull_request:45401", + "pull_request:44662|pull_request:45075", + "pull_request:45075|pull_request:45401" + ], + "prepared_review_unit_hash": "d7c4c19dbbeb6e3f5509886139a59b38000defb7f62c93c8d79c48f2cc0a7e5a", + "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": "These are three distinct model-addition PRs for different architectures and tasks (PenguinVL, DeepSeek-OCR-2, and Voxtral TTS). They share only common Transformers integration scaffolding, so they are not duplicates.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single PR is a valid canonical duplicate representative: each PR introduces a different model family with its own config, modeling, processor, and tests.", + "best_issue_reason": null, + "best_pr_reason": "None of these PRs should be treated as the cluster\u2019s best duplicate representative, because they do not fix the same underlying bug or implement the same change.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44662", + "right": "pull_request:45401", + "accept": false, + "reason": "PenguinVL (vision-language) and Voxtral TTS (text-to-speech) are unrelated model implementations; shared auto-registration and docs files are just boilerplate." + }, + { + "left": "pull_request:44662", + "right": "pull_request:45075", + "accept": false, + "reason": "PenguinVL and DeepSeek-OCR-2 are different models with different codepaths and files; overlap is only in generic model-registration/docs plumbing." + }, + { + "left": "pull_request:45075", + "right": "pull_request:45401", + "accept": false, + "reason": "DeepSeek-OCR-2 (OCR/vision) and Voxtral TTS (speech generation) are different concrete features, not the same bug or mergeable change set." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 17, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-44979-2", + "nodes": [ + "pull_request:44979", + "pull_request:45363" + ], + "soft_pairs": [ + "pull_request:44979|pull_request:45363" + ], + "prepared_review_unit_hash": "becd15cd66a1f1137551d1eba27cb4d209d94fba44c7920633e12a5ad0f59a2a", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4407, + "estimated_input_tokens": 1102, + "estimated_eval_tokens": 2460 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4407, + "estimated_input_tokens": 1102, + "estimated_eval_tokens": 2460 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are related in the broad theme of module/kernel fusion, but they are not the same change: one introduces a generic module fusion API, while the other wires up n-to-1 kernel fusion through KernelConfig and integration points.", + "confidence": 0.87, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #44979 is the better canonical representative because it introduces the foundational, general-purpose Module Fusion API and includes dedicated tests. It is broader and more self-contained than the draft PR #45363, which appears to be a downstream, specific integration of that idea.", + "best_issue_reason": null, + "best_pr_reason": "PR #44979 is the strongest cluster anchor: it is non-draft, API-level, and appears to define the core abstraction that the other PR builds upon. PR #45363 is narrower and likely depends on the concepts introduced here.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44979", + "right": "pull_request:45363", + "accept": false, + "reason": "Reject: these are adjacent but not the same underlying change. #44979 adds a general Module Fusion API, while #45363 implements n-to-1 kernel fusion via KernelConfig and touches different integration code paths. They would not plausibly be merged as one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 18, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45086-2", + "nodes": [ + "pull_request:45086", + "pull_request:45317" + ], + "soft_pairs": [ + "pull_request:45086|pull_request:45317" + ], + "prepared_review_unit_hash": "be859ebf09058f3220d163e3a3fbd86a4e273be06c3dbc71a6e525b7382000ef", + "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 PRs target the same Mistral regex patch bug in the same code path (`_patch_mistral_regex`) and share the same issue target. PR #45317 looks like the more complete fix because it includes test coverage in addition to the code change.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45317 is the stronger canonical PR: it fixes the same AttributeError, has the same file-level change, and adds tests, making it the more complete representation of the fix.", + "best_issue_reason": null, + "best_pr_reason": "PR #45317 is the best representative of the cluster because it most fully addresses the bug and includes validation via tests.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45086", + "right": "pull_request:45317", + "accept": true, + "reason": "Same underlying bug and same fix location (`tokenization_utils_tokenizers.py` / `_patch_mistral_regex`), with the later PR extending the earlier one by adding tests; they are effectively duplicate fixes for the same issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 19, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45115-2", + "nodes": [ + "pull_request:45115", + "pull_request:45569" + ], + "soft_pairs": [ + "pull_request:45115|pull_request:45569" + ], + "prepared_review_unit_hash": "fb109d5fdbf4367650716ec1e9f95fecf68ba89c72481e79ba63480beb923890", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6065, + "estimated_input_tokens": 1517, + "estimated_eval_tokens": 3290 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6065, + "estimated_input_tokens": 1517, + "estimated_eval_tokens": 3290 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs touch NemotronH internals, but they address different changes: #45115 is a conversion-mapping/refactor PR, while #45569 is a broader model-splitting and docs/modeling update. They are related but not duplicates.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "#45569 is the broader, more complete NemotronH change set: it introduces the dense/sparse model split, updates auto/modeling wiring, docs, and tests. It looks like the main implementation PR rather than a narrow supporting refactor.", + "best_issue_reason": null, + "best_pr_reason": "#45569 is the best representative of the cluster because it covers the actual user-facing/model-architecture rework, whereas #45115 is limited to conversion key renaming and compatibility mapping.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45115", + "right": "pull_request:45569", + "accept": false, + "reason": "They share NemotronH files, but the concrete changes differ: #45115 only adds checkpoint conversion renames and compatibility mappings, while #45569 splits/rewires NemotronH into dense and sparse models with docs and tests. Not the same fix and not plausibly one merged PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 20, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45332-2", + "nodes": [ + "pull_request:45332", + "pull_request:45333" + ], + "soft_pairs": [ + "pull_request:45332|pull_request:45333" + ], + "prepared_review_unit_hash": "e1d0c9e5c5f8cf6e5d16091ea97e4aa0a6fd0934135be9a61f71f80c5293c217", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5397, + "estimated_input_tokens": 1350, + "estimated_eval_tokens": 2956 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5397, + "estimated_input_tokens": 1350, + "estimated_eval_tokens": 2956 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two open PRs in the same heterogeneous-config feature area, but one is a broader end-to-end heterogeneous model support change and the other is a narrower config-only change. They are related, not duplicates.", + "confidence": 0.81, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45332 is the broader umbrella change: it includes per-layer config handling plus modeling/cache/masking updates and tests, so it subsumes the narrower config-only work in #45333.", + "best_issue_reason": null, + "best_pr_reason": "PR #45332 is the best standalone candidate because it covers the full heterogeneous model support path, not just configuration plumbing.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45332", + "right": "pull_request:45333", + "accept": false, + "reason": "Related feature work, but not the same underlying change: #45333 is config support only, while #45332 adds broader modeling/cache behavior. They would not naturally be merged as one duplicate PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 21, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45415-2", + "nodes": [ + "pull_request:45415", + "pull_request:45425" + ], + "soft_pairs": [ + "pull_request:45415|pull_request:45425" + ], + "prepared_review_unit_hash": "c835e998a8664a515e60034ae4c0d0905862aa8ec1cae81792b4a78cd470c5d2", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5514, + "estimated_input_tokens": 1379, + "estimated_eval_tokens": 3014 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5514, + "estimated_input_tokens": 1379, + "estimated_eval_tokens": 3014 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two open PRs are both typing-related, but they address different changes: PR 45415 is a broad mypy/type-checking sweep across many `src/transformers/*.py` files and config, while PR 45425 adds shared typing protocols/helpers in `_typing.py` and updates a smaller set of typing-related call sites. The overlap in a few files is not enough to treat them as the same change.", + "confidence": 0.92, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45415 is the best canonical representative because it is the broader umbrella change: a large type-checking pass across many modules plus config adjustments, rather than a narrower helper/type-annotation refinement.", + "best_issue_reason": null, + "best_pr_reason": "PR 45415 is the strongest standalone representative of the cluster since it covers the widest scope and is the most likely target for deduping related typing-sweep work.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45415", + "right": "pull_request:45425", + "accept": false, + "reason": "Reject: both are typing-focused, but they are not the same underlying bug/change. 45415 is a broad repository-wide type-checking sweep, while 45425 introduces shared typing protocols and aliases in `_typing.py` and updates a smaller set of consumers. Shared filenames alone do not make them 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": 22, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45487-4", + "nodes": [ + "pull_request:45487", + "pull_request:45817", + "pull_request:45836", + "pull_request:45843" + ], + "soft_pairs": [ + "pull_request:45487|pull_request:45843", + "pull_request:45487|pull_request:45836", + "pull_request:45817|pull_request:45843", + "pull_request:45836|pull_request:45843" + ], + "prepared_review_unit_hash": "ec86b5cee032337369eb62048a6d238280b2fd5487cbf832f9ad34491bd1305e", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 4, + "serialized_chars": 10389, + "estimated_input_tokens": 2598, + "estimated_eval_tokens": 5452 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 4, + "serialized_chars": 10389, + "estimated_input_tokens": 2598, + "estimated_eval_tokens": 5452 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are mostly separate PRs that happen to share a broad \"model parallel\" theme; one is just test skipping. They do not appear to fix the same concrete bug or code path.", + "confidence": 0.9, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45487 is the most representative cluster anchor because it is an explicit model-parallel fix with concrete code changes across multiple model implementations, not just a test adjustment.", + "best_issue_reason": null, + "best_pr_reason": "PR #45487 is the clearest canonical representative for the cluster's theme and has the broadest directly relevant fix among the candidates.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45487", + "right": "pull_request:45843", + "accept": false, + "reason": "Both concern model-parallel behavior, but they fix different models and different code paths (AltCLIP/ChineseCLIP vs Deimv2). Same broad subsystem, not the same underlying bug." + }, + { + "left": "pull_request:45487", + "right": "pull_request:45836", + "accept": false, + "reason": "#45836 only skips failing tests for MiniCPM-V/Qwen3.5; it does not fix the model-parallel bug in #45487." + }, + { + "left": "pull_request:45817", + "right": "pull_request:45843", + "accept": false, + "reason": "Both are model-parallel fixes, but one is Gemma4-specific and the other is Deimv2-specific. They are different concrete fixes and should not be merged as duplicates." + }, + { + "left": "pull_request:45836", + "right": "pull_request:45843", + "accept": false, + "reason": "#45836 is a test-skip PR, while #45843 changes Deimv2 model code. They are unrelated fixes." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 23, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45548-2", + "nodes": [ + "pull_request:45548", + "pull_request:45662" + ], + "soft_pairs": [ + "pull_request:45548|pull_request:45662" + ], + "prepared_review_unit_hash": "57d7464d7b01b6b4c52c9279faaac3f86236cdeef567bce811039bb382a0d884", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4505, + "estimated_input_tokens": 1127, + "estimated_eval_tokens": 2510 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4505, + "estimated_input_tokens": 1127, + "estimated_eval_tokens": 2510 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two PRs both touch expert-parallel loading, but they fix different failure modes: one is about preserving/recognizing distributed_config for EP + DeepSpeed ZeRO-3 loading, while the other is about preventing FSDP2 rank-0 broadcast from overwriting experts during sharded loading.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": "PR 45662 is the more concrete and self-contained bug fix: it addresses a specific incorrect parameter assignment path during distributed sharded loading, with targeted code changes across the loading stack.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45548", + "right": "pull_request:45662", + "accept": false, + "reason": "Different underlying bugs and code paths: 45548 focuses on config serialization/EP detection for accelerate+ZeRO-3, while 45662 fixes post-shard parameter wrapping to stop rank-0 broadcast from overwriting experts under FSDP2. They are 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": 24, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45639-2", + "nodes": [ + "pull_request:45639", + "pull_request:45645" + ], + "soft_pairs": [ + "pull_request:45639|pull_request:45645" + ], + "prepared_review_unit_hash": "46b68e240c887eea68e1b9c113d631f2acbe22281dbf5974d0bd2a5c0e502cc0", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4590, + "estimated_input_tokens": 1148, + "estimated_eval_tokens": 2552 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4590, + "estimated_input_tokens": 1148, + "estimated_eval_tokens": 2552 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs address the same xdist-related captured_info collision in testing_utils; 45645 is the broader, more complete fix that also updates CI handling for multiple artifact files.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45645 is the better canonical PR because it includes the core xdist-safe file handling in testing_utils plus the downstream workflow changes needed to read multiple captured_info files in CI.", + "best_issue_reason": null, + "best_pr_reason": "PR 45645 is the best representative of the change set: it covers the same underlying bug as 45639 and adds the necessary artifact/CI plumbing rather than just the library-side fix.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45639", + "right": "pull_request:45645", + "accept": true, + "reason": "Same underlying bug: xdist workers colliding on captured_info output. 45645 appears to subsume 45639\u2019s fix and extends it with related CI handling, so they are plausibly one merged 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": 25, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45683-2", + "nodes": [ + "pull_request:45683", + "pull_request:45734" + ], + "soft_pairs": [ + "pull_request:45683|pull_request:45734" + ], + "prepared_review_unit_hash": "eba4ca0f26b2d3be0c00e316270a9341d31af2208b44dbab31b1d3a8e81e7538", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4469, + "estimated_input_tokens": 1118, + "estimated_eval_tokens": 2492 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4469, + "estimated_input_tokens": 1118, + "estimated_eval_tokens": 2492 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two open PRs touch the same quantization helper, but they fix different bugs: one special-cases audio submodules, the other changes how default skip lists are combined with user-supplied skips. They should not be clustered as duplicates.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "45734 is the better representative PR because it fixes the core skip-module composition logic in `get_modules_to_not_convert`, which is broader and more central than the narrow audio-module special case in 45683.", + "best_issue_reason": null, + "best_pr_reason": "45734 is the strongest standalone PR in the set: it addresses a concrete quantization failure mode in the main code path and its fix is directly about the helper\u2019s behavior rather than a model-specific workaround.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45683", + "right": "pull_request:45734", + "accept": false, + "reason": "Both touch quantization skip logic, but 45683 adds audio-tower/embed_audio exclusions while 45734 changes additive handling of `skip_modules`; these are different underlying bugs and would not naturally merge into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 26, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45737-2", + "nodes": [ + "pull_request:45737", + "pull_request:45738" + ], + "soft_pairs": [ + "pull_request:45737|pull_request:45738" + ], + "prepared_review_unit_hash": "cc2ade73a49ec6a8883a7a24c433988645588bcd049e8aad2bce56b1b24daa1c", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4131, + "estimated_input_tokens": 1033, + "estimated_eval_tokens": 2322 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4131, + "estimated_input_tokens": 1033, + "estimated_eval_tokens": 2322 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs address the same MusicgenMelody cache initialization bug in `forward()`: replacing `EncoderDecoderCache(DynamicCache, DynamicCache)` with a single `DynamicCache`. PR #45737 is the more complete duplicate because it bundles the fix with a regression test, while #45738 is the fix-only variant.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45737 is the best canonical PR because it contains the same code fix as #45738 plus a regression test, making it the most complete representation of the bug fix.", + "best_issue_reason": null, + "best_pr_reason": "PR #45737 is the strongest overall candidate: it fixes the concrete cache bug and adds a targeted regression test, whereas #45738 only changes the implementation.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45737", + "right": "pull_request:45738", + "accept": true, + "reason": "Same underlying code-path bug in `musicgen_melody` cache setup; the diffs match on the core fix and the test-only addition in #45737 could plausibly live in the same PR as #45738." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The assessment is grounded in the packet: both PRs make the same `musicgen_melody` cache initialization change, and #45737 only adds a regression test on top of that fix. The soft-edge accept is conservative enough because the diffs are mergeable into one PR for the same bugfix." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + } + ] +} diff --git a/snapshots/20260510T180022Z/analysis-runs/hybrid-model-20260510t180022z/manifest.json b/snapshots/20260510T180022Z/analysis-runs/hybrid-model-20260510t180022z/manifest.json new file mode 100644 index 0000000000000000000000000000000000000000..34aaf4772380a85367a883f628b1fe3fc627e301 --- /dev/null +++ b/snapshots/20260510T180022Z/analysis-runs/hybrid-model-20260510t180022z/manifest.json @@ -0,0 +1,14 @@ +{ + "analysis_id": "hybrid-model-20260510t180022z", + "artifacts": { + "hybrid": "snapshots/20260510T180022Z/analysis-runs/hybrid-model-20260510t180022z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260510T180022Z/analysis-runs/hybrid-model-20260510t180022z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "model": null, + "published_at": "2026-05-10T18:06:42Z", + "repo": "huggingface/transformers", + "schema_version": 1, + "snapshot_id": "20260510T180022Z", + "variant": "hybrid" +} diff --git a/snapshots/20260510T180022Z/manifest.json b/snapshots/20260510T180022Z/manifest.json index 14e1a98b3296a26a54a9e339afb70b7720c30b5a..5439e7602d6ca510c53f35996a113539eaba52ce 100644 --- a/snapshots/20260510T180022Z/manifest.json +++ b/snapshots/20260510T180022Z/manifest.json @@ -32,6 +32,24 @@ "timeline_events": 37 }, "extracted_at": "2026-05-10T18:00:22Z", + "published_analysis": { + "canonical_analysis_id": "hybrid-model-20260510t180022z", + "runs": { + "hybrid-model-20260510t180022z": { + "analysis_id": "hybrid-model-20260510t180022z", + "artifacts": { + "hybrid": "snapshots/20260510T180022Z/analysis-runs/hybrid-model-20260510t180022z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260510T180022Z/analysis-runs/hybrid-model-20260510t180022z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "manifest_path": "snapshots/20260510T180022Z/analysis-runs/hybrid-model-20260510t180022z/manifest.json", + "model": null, + "published_at": "2026-05-10T18:06:42Z", + "variant": "hybrid" + } + }, + "schema_version": 1 + }, "repo": "huggingface/transformers", "snapshot_id": "20260510T180022Z", "watermark": {