diff --git a/analysis/current/analysis-report-hybrid.json b/analysis/current/analysis-report-hybrid.json index d1caa7af96222bdaed07501e3d0d0ba320bb3380..969a1c1f434ecc76802eaaf500a4cc57c5d641f9 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": "20260424T120023Z", - "generated_at": "2026-04-24T12:06:30Z", + "snapshot_id": "20260424T180025Z", + "generated_at": "2026-04-24T18:16:17Z", "evidence_quality": "full", "llm_enrichment": true, "meta_bugs": [ @@ -1150,152 +1150,74 @@ ] }, { - "cluster_id": "cluster-43656-4", - "summary": "Cluster of 1 issues and 3 PRs centered on issue #43824.", + "cluster_id": "cluster-43240-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #43240.", "status": "open", - "confidence": 0.8, - "canonical_issue_number": 43824, - "canonical_pr_number": 43656, + "confidence": 0.75, + "canonical_issue_number": 43240, + "canonical_pr_number": 43251, "issue_numbers": [ - 43824 + 43240 ], "pr_numbers": [ - 43656, - 43836, - 43842 + 43251, + 43254 ], "evidence_types": [ "closing_reference", - "shared_issue_target", - "soft_similarity" + "shared_issue_target" ], "pr_comparisons": [ { - "left_pr_number": 43656, - "right_pr_number": 43836, - "code_similarity": 0.36, - "size_similarity": 0.176, + "left_pr_number": 43251, + "right_pr_number": 43254, + "code_similarity": 0.794, + "size_similarity": 0.64, "file_overlap": 1.0, - "area_overlap": 0.051, - "patch_similarity": 0.048, + "area_overlap": 0.667, + "patch_similarity": 0.882, "shared_filenames": [ - "src/transformers/cli/serve.py" + "src/transformers/loss/loss_utils.py" ], "shared_file_areas": [ { - "filename": "src/transformers/cli/serve.py", + "filename": "src/transformers/loss/loss_utils.py", "left_ranges": [ - [ - 11, - 18 - ], [ 30, - 36 - ], - [ - 315, - 323 - ], - [ - 665, - 671 - ], - [ - 931, - 937 - ], - [ - 1843, - 1849 - ], - [ - 1868, - 1874 + 50 ] ], "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 + 43 ] ] } ] - }, + } + ] + }, + { + "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, @@ -1347,56 +1269,6 @@ } ] }, - { - "cluster_id": "cluster-43240-3", - "summary": "Cluster of 1 issues and 2 PRs centered on issue #43240.", - "status": "open", - "confidence": 0.75, - "canonical_issue_number": 43240, - "canonical_pr_number": 43251, - "issue_numbers": [ - 43240 - ], - "pr_numbers": [ - 43251, - 43254 - ], - "evidence_types": [ - "closing_reference", - "shared_issue_target" - ], - "pr_comparisons": [ - { - "left_pr_number": 43251, - "right_pr_number": 43254, - "code_similarity": 0.794, - "size_similarity": 0.64, - "file_overlap": 1.0, - "area_overlap": 0.667, - "patch_similarity": 0.882, - "shared_filenames": [ - "src/transformers/loss/loss_utils.py" - ], - "shared_file_areas": [ - { - "filename": "src/transformers/loss/loss_utils.py", - "left_ranges": [ - [ - 30, - 50 - ] - ], - "right_ranges": [ - [ - 30, - 43 - ] - ] - } - ] - } - ] - }, { "cluster_id": "cluster-45081-3", "summary": "Cluster of 1 issues and 2 PRs centered on issue #45081.", @@ -1513,6 +1385,281 @@ ] } ] + }, + { + "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": [], @@ -1535,16 +1682,6 @@ "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, @@ -1554,6 +1691,15 @@ "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, @@ -1571,6 +1717,15 @@ "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, diff --git a/analysis/current/analysis-report-hybrid.llm-reviews.json b/analysis/current/analysis-report-hybrid.llm-reviews.json index cb334334f297bfdd246fa4f36596c20b0d3cd982..6802f4c9e6de7c7b9b8cccf0a7744bad60375c5e 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": "20260424T120023Z", - "generated_at": "2026-04-24T12:06:30Z", + "snapshot_id": "20260424T180025Z", + "generated_at": "2026-04-24T18:16:17Z", "model": "gpt-5.4-mini?service_tier=flex", "reviews": [ { @@ -13,8 +13,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-13244-3", "nodes": [ @@ -26,12 +26,12 @@ "issue:13244|issue:16618", "issue:15980|issue:16618" ], - "prepared_review_unit_hash": "da0c79f7af891e93c31bf6a6e896830cf852361d7a2af0a950286b08c971c008", + "prepared_review_unit_hash": "3bd1aa1e5016ec9382b72cbe7c74a64e990c7c4e0b250800fedbd71ab44829a9", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 2477, + "serialized_chars": 2479, "estimated_input_tokens": 620, "estimated_eval_tokens": 1496 }, @@ -39,7 +39,7 @@ "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 2477, + "serialized_chars": 2479, "estimated_input_tokens": 620, "estimated_eval_tokens": 1496 }, @@ -48,24 +48,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The cluster is mostly loose similarity around model/tokenization loading problems, but the issues describe different bugs. #16618 is the broadest, most central candidate; the other two are not true duplicates of it.", - "confidence": 0.91, - "canonical_issue_reason": "#16618 is the most general issue in the set and best matches the cluster\u2019s shared theme of model loading failures.", + "summary": "These issues do not appear to be duplicates of one another: one is about TAPAS tokenization, one about auth-related private model downloads, and one about a model-loading failure for bert-base-uncased. The only somewhat related pair is the last two, but they describe different failure modes and should not be merged.", + "confidence": 0.9, + "canonical_issue_reason": "Issue 16618 is the most generally framed model-loading report, so it is the best single representative of the cluster if one must be chosen.", "canonical_pr_reason": null, - "best_issue_reason": "#16618 is the best representative because it is the broadest user-facing model loading failure; #15980 is specifically an auth/error-message issue, and #13244 is about tokenization mismatch.", + "best_issue_reason": "Issue 16618 is the strongest standalone issue for triage because it is broad, clearly user-facing, and has the most discussion activity among the set.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:13244", "right": "issue:16618", "accept": false, - "reason": "Tokenization mismatch with Tapas vs TensorFlow is a different problem from failing to load bert-base-uncased; only weak topical similarity." + "reason": "Different topics and code paths: TAPAS tokenization vs generic model loading for bert-base-uncased." }, { "left": "issue:15980", "right": "issue:16618", "accept": false, - "reason": "#15980 is about an incorrect error message when downloading a private model without login, not the same underlying loading failure as #16618." + "reason": "Both involve model loading, but one is specifically an unauthenticated private-model download error while the other is a generic inability to load bert-base-uncased; not the same underlying bug." } ] }, @@ -84,10 +84,10 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:24643", "issue:30277", @@ -188,8 +188,8 @@ "issue:41762|issue:43596", "issue:43901|issue:44512", "issue:39290|issue:41720", - "issue:43866|issue:44863", "issue:43039|issue:44560", + "issue:43866|issue:44863", "issue:43854|issue:43866", "issue:43425|issue:45070", "issue:41093|issue:43638", @@ -203,346 +203,370 @@ "issue:41093|issue:41762", "issue:43296|issue:43366" ], - "prepared_review_unit_hash": "3986cd28083623e9ff89dc85221155a45bdd5d11c72859847eceef3b117d0463", + "prepared_review_unit_hash": "b09f576435fcf2d9c74b2cdf4b8a4c6a872d3e820b00fad10d5df17d08c66eec", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 63, - "serialized_chars": 46485, - "estimated_input_tokens": 11622, - "estimated_eval_tokens": 23500 + "serialized_chars": 46475, + "estimated_input_tokens": 11619, + "estimated_eval_tokens": 23494 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly false-positive similarity links across unrelated model/configuration issues. The only clear duplicate pair is the two DeepSpeed ZeRO-3/Bert loading errors; most other pairs share generic error wording but not the same concrete bug.", - "confidence": 0.78, - "canonical_issue_reason": "issue:43596 is the clearest representative of the one strong duplicate pair: it states the concrete ZeRO-3/BertModel index-out-of-bounds failure cleanly and is better phrased than the near-identical follow-up.", + "summary": "Most items are unrelated, with one clear duplicate cluster around DeepSpeed ZeRO-3 / index-out-of-bounds loading failures for BERT/Gemma-style models. A smaller docs-only similarity cluster exists, but the evidence is weaker and broader than the ZeRO-3 bug cluster.", + "confidence": 0.72, + "canonical_issue_reason": "issue:44805 is the best representative of the ZeRO-3 loading failure cluster because its title is the most general form of the shared index-out-of-bounds/mask-shape error and it maps cleanly to the other Bert/ZeRO-3 variants.", "canonical_pr_reason": null, - "best_issue_reason": "Best global anchor for the cluster: it is the most concrete and reusable issue among the near-duplicates, and it maps to a specific loading path rather than a broad or generic symptom.", + "best_issue_reason": "issue:44805 is the strongest canonical issue candidate among the provided items; it is the broadest and most reusable description of the shared underlying bug.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44322", "right": "issue:45464", "accept": false, - "reason": "Same model family, but different failures and code paths: config attribute missing vs streaming chat/completions error." + "reason": "Different Qwen3.5 failures and different code paths; same model family only, not the same bug." }, { "left": "issue:43716", "right": "issue:45237", "accept": false, - "reason": "Both involve Qwen/GPT-style model loading, but one is an autocast dtype mismatch and the other is an AMD GPU runtime failure." + "reason": "Different failure modes: dtype mismatch vs AMD GPU execution failure." }, { "left": "issue:43828", "right": "issue:45237", "accept": false, - "reason": "Different concrete problems: autocast dtype mismatch vs model failing only on AMD GPUs." + "reason": "Autocast dtype mismatch is unrelated to AMD GPU support issues." }, { "left": "issue:45237", "right": "issue:45507", "accept": false, - "reason": "Different models and different failure modes; too broad to be the same bug." + "reason": "Different problem areas; one is GPU backend support, the other is an invalid method call in a model implementation." }, { "left": "issue:44292", "right": "issue:45237", "accept": false, - "reason": "Both are Qwen-related, but one is an NVFP4 runtime error and the other is an AMD GPU compatibility issue." + "reason": "Different model/runtime failures with no clear shared code-path." }, { "left": "issue:30277", "right": "issue:35545", "accept": false, - "reason": "Different subsystems and symptoms: DeepSpeed collective mismatch vs ONNX export failure." + "reason": "DeepSpeed collective mismatch and ONNX export error are unrelated." }, { "left": "issue:35545", "right": "issue:42915", "accept": false, - "reason": "Different model/export paths and unrelated errors." + "reason": "Different model/export paths and different symptoms." }, { "left": "issue:35545", "right": "issue:41720", "accept": false, - "reason": "Both are model inference issues, but the concrete failures are unrelated." + "reason": "ONNX export error and auto device-mapping cuda assert are not the same bug." }, { "left": "issue:44509", "right": "issue:44512", "accept": false, - "reason": "Both are docs cleanups for v5 removals, but they target different removed references and are not the same bug/change." + "reason": "Both are docs regressions in v5, but they reference different removed features and do not clearly share one concrete change." }, { "left": "issue:35545", "right": "issue:36010", "accept": false, - "reason": "ONNX export error vs import failure for GenerationMixin; unrelated." + "reason": "ONNX export and GenerationMixin import breakage are unrelated." }, { "left": "issue:43638", "right": "issue:44805", - "accept": false, - "reason": "Both mention index errors, but the model/load contexts differ and the shared text is too generic to confirm the same code path." + "accept": true, + "reason": "Same ZeRO-3 index-0-out-of-bounds failure pattern on Bert-family loading." }, { "left": "issue:43596", "right": "issue:44805", - "accept": false, - "reason": "Same generic index error shape, but not enough evidence that the Bert ZeRO-3 bug and the mask-shape bug are the same root cause." + "accept": true, + "reason": "Same underlying ZeRO-3 loading/index-out-of-bounds bug, just on a different Bert variant." }, { "left": "issue:44805", "right": "issue:45161", "accept": false, - "reason": "Generic index/mask errors, but different model families and different failing paths." - }, - { - "left": "issue:44805", - "right": "issue:44918", - "accept": false, - "reason": "Mask-shape error vs Qwen3.5 embedding unpacking failure; not the same bug." + "reason": "One is a ZeRO-3 loading bug; the other is a GPT-OSS tensor-parallel issue." }, { "left": "issue:44661", "right": "issue:44805", "accept": false, - "reason": "Tokenizer-mapping code path issue vs generic mask/index error; unrelated." + "reason": "Tokenizer mapping generation bug is unrelated to ZeRO-3 loading errors." }, { "left": "issue:34634", "right": "issue:35545", "accept": false, - "reason": "BarkProcessor voice preset bug is unrelated to ModernBERT ONNX export." + "reason": "BarkProcessor preset handling and ONNX export are unrelated." }, { "left": "issue:30277", "right": "issue:43638", "accept": false, - "reason": "Both are DeepSpeed-related, but one is a collective mismatch and the other is a zero-sized index error." + "reason": "Both are DeepSpeed-related, but the symptoms and code paths differ materially." }, { "left": "issue:43596", "right": "issue:43638", "accept": true, - "reason": "Near-identical ZeRO-3/Bert loading failures with the same index-out-of-bounds symptom; clearly the same underlying bug." + "reason": "Near-identical ZeRO-3 index-out-of-bounds failures on BertModel loading." }, { "left": "issue:43975", "right": "issue:44457", "accept": false, - "reason": "Tokenizer/detokenization bug vs LoRA save/load mismatch; different failures." + "reason": "Different model-specific inference/detokenization bugs." }, { "left": "issue:43039", "right": "issue:45161", "accept": false, - "reason": "Liger Kernel cross_entropy call issue vs GPT-OSS tensor parallel problem; unrelated." + "reason": "Liger Kernel cross-entropy call and GPT-OSS tensor-parallel failure are different issues." }, { "left": "issue:44292", "right": "issue:44457", "accept": false, - "reason": "Different model/runtime domains and different symptoms." + "reason": "Different model/runtime problems with no shared bug." }, { "left": "issue:34928", "right": "issue:44805", "accept": false, - "reason": "Activation checkpointing/FSDP tensor recompute mismatch is not the same as the mask-shape index error." + "reason": "Activation checkpointing/FSDP mismatch is unrelated to ZeRO-3 index-out-of-bounds loading." }, { "left": "issue:24643", "right": "issue:30277", "accept": false, - "reason": "Different DeepSpeed errors and different failure modes." + "reason": "Different DeepSpeed errors and different failure conditions." }, { "left": "issue:43975", "right": "issue:45237", "accept": false, - "reason": "Detokenization bug vs AMD GPU runtime failure; unrelated." + "reason": "Different model families and different runtime failures." }, { "left": "issue:43638", "right": "issue:45161", "accept": false, - "reason": "ZeRO-3/Bert loading bug vs GPT-OSS TP issue; different code paths." + "reason": "Bert ZeRO-3 loading error is unrelated to GPT-OSS tensor parallelism." }, { "left": "issue:34928", "right": "issue:36331", "accept": false, - "reason": "Activation checkpointing/FSDP mismatch vs custom trainer signature change; unrelated." + "reason": "Activation checkpointing/FSDP tensor mismatch is unrelated to the custom trainer loss signature issue." }, { "left": "issue:43596", "right": "issue:45161", "accept": false, - "reason": "Different model families and different failure modes." + "reason": "Different model and different failure path." }, { "left": "issue:43716", "right": "issue:45507", "accept": false, - "reason": "Image preprocessor dtype mismatch vs invalid method call in GraniteMoE; unrelated." + "reason": "Dtype mismatch and invalid method invocation are unrelated." }, { "left": "issue:39290", "right": "issue:45081", "accept": false, - "reason": "Different config/tokenizer issues and different model families." + "reason": "Different model/configuration issues with no shared concrete bug." }, { "left": "issue:43828", "right": "issue:45161", "accept": false, - "reason": "Autocast dtype mismatch vs TP-only GPT-OSS failure; unrelated." + "reason": "Autocast dtype mismatch is unrelated to GPT-OSS TP failure." + }, + { + "left": "issue:43425", + "right": "issue:44292", + "accept": false, + "reason": "Torch version incompatibility and NVFP4 model execution error are unrelated." + }, + { + "left": "issue:44918", + "right": "issue:45161", + "accept": false, + "reason": "TRL embedding unpacking and GPT-OSS tensor-parallel failures are unrelated." }, { "left": "issue:34928", "right": "issue:41720", "accept": false, - "reason": "Different distributed-training failures with different symptoms." + "reason": "FSDP checkpointing error and Qwen3 auto-device-map cuda assert are different bugs." }, { "left": "issue:43827", "right": "issue:44512", "accept": false, - "reason": "Both are v5 docs cleanups, but they reference different removed items and are not the same documentation bug." + "reason": "Both are v5 docs regressions, but they concern different removed items and are not clearly one change." }, { "left": "issue:43716", "right": "issue:44560", "accept": false, - "reason": "Different model-specific dtype/processing problems." + "reason": "Different model-specific dtype/video pipeline failures." }, { "left": "issue:43716", "right": "issue:44918", "accept": false, - "reason": "Different families and failures: dtype mismatch vs embedding unpacking." + "reason": "Different model/input handling failures." }, { "left": "issue:43039", "right": "issue:43828", "accept": false, - "reason": "Different issues in different model/runtime paths." + "reason": "Different model/runtime paths; one is kernel selection, the other is autocast mismatch." }, { "left": "issue:30277", "right": "issue:36331", "accept": false, - "reason": "DeepSpeed collective mismatch vs trainer keyword argument incompatibility." + "reason": "DeepSpeed collective mismatch and trainer signature mismatch are unrelated." }, { "left": "issue:43039", "right": "issue:44805", "accept": false, - "reason": "Liger Kernel cross_entropy being called is unrelated to a mask-shape index error." + "reason": "Liger Kernel cross-entropy call does not match ZeRO-3 loading failures." }, { "left": "issue:34928", "right": "issue:36010", "accept": false, - "reason": "FSDP checkpointing mismatch vs import error; unrelated." + "reason": "Checkpointing/FSDP issue and GenerationMixin import breakage are unrelated." }, { "left": "issue:41762", - "right": "issue:43596", - "accept": false, - "reason": "Same broad ZeRO-3 loading area, but different models and not enough evidence of one root cause." + "right": "issue:43638", + "accept": true, + "reason": "Same ZeRO-3 index-out-of-bounds loading bug, presented on different model names." }, { "left": "issue:43901", "right": "issue:44512", "accept": false, - "reason": "Different docs removals and different sections of the docs." + "reason": "Different stale-doc references and no clear single underlying change." }, { "left": "issue:39290", "right": "issue:41720", "accept": false, - "reason": "Sliding-window config issue vs CUDA assert during auto device mapping; unrelated." + "reason": "Different Qwen/Gemma runtime issues with distinct failure signatures." }, { "left": "issue:43866", "right": "issue:44863", "accept": false, - "reason": "Checkpoint corruption vs checkpoint loading implementation bug; different problems." - }, - { - "left": "issue:43039", - "right": "issue:44560", - "accept": false, - "reason": "Liger Kernel cross_entropy issue vs Qwen3-vl video StopIteration; unrelated." + "reason": "Checkpoint corruption and NemotronH loading failure are not the same bug." }, { "left": "issue:43854", "right": "issue:43866", "accept": false, - "reason": "Unit test loading failure vs corrupted checkpoint report; not the same bug." + "reason": "Unit-test load failure and checkpoint corruption are different problems." }, { "left": "issue:43425", "right": "issue:45070", "accept": false, - "reason": "Torch version incompatibility vs pydantic config-field regression; unrelated." + "reason": "Torch incompatibility and pydantic field breakage are unrelated." }, { "left": "issue:41093", "right": "issue:43638", "accept": false, - "reason": "Both are index errors, but the titles point to different concrete failures and the evidence is too generic." + "reason": "Mask-shape mismatch and ZeRO-3 index-out-of-bounds are different failure modes." }, { "left": "issue:39290", "right": "issue:43531", "accept": false, - "reason": "Both mention sliding-window, but one is a Gemma3/vLLM config attribute issue and the other is a Qwen3-MoE sliding_window issue." + "reason": "Different Qwen/Gemma config issues, not the same bug." }, { "left": "issue:43404", "right": "issue:43866", "accept": false, - "reason": "Weight tying bug in Mistral3 is unrelated to Ovis2 checkpoint corruption." + "reason": "lm_head tying bug and checkpoint corruption are unrelated." }, { "left": "issue:45362", "right": "issue:45464", "accept": false, - "reason": "Both are Qwen3.5-related, but the failures are different: chat crash vs streaming inference API failure." + "reason": "Same model family, but different symptoms and execution paths; not the same concrete bug." }, { "left": "issue:43792", "right": "issue:45070", "accept": false, - "reason": "Whisper runtime failure vs pydantic model field regression; unrelated." + "reason": "Whisper runtime failure and pydantic field regression are unrelated." }, { "left": "issue:43541", "right": "issue:43828", "accept": false, - "reason": "Different runtime contexts and different concrete errors." + "reason": "Grouped_mm tracing failure and autocast dtype mismatch are different bugs." + }, + { + "left": "issue:36010", + "right": "issue:39290", + "accept": false, + "reason": "GenerationMixin import error and Gemma3/vLLM config issue are unrelated." + }, + { + "left": "issue:44841", + "right": "issue:45084", + "accept": false, + "reason": "Processor failure and template compilation error are unrelated." + }, + { + "left": "issue:41093", + "right": "issue:41762", + "accept": false, + "reason": "Both are shape/index problems, but the reported failure modes and likely code paths differ." + }, + { + "left": "issue:43296", + "right": "issue:43366", + "accept": false, + "reason": "Different model support/load issues with no shared concrete change." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative overall. The only accepted soft pair, issue:43596 vs issue:43638, is plausibly the same ZeRO-3/Bert index-out-of-bounds bug from the titles alone, while the other rejections avoid overclaiming on generic similarity. No obvious evidence inflation." + "feedback": "The summary stays within the packet evidence and the soft-edge calls are conservative. The ZeRO-3/BERT/Gemma cluster is the clearest duplicate set, and the docs-only cluster is appropriately treated as weaker." }, "evaluator_used": true, "retried": false, @@ -558,10 +582,10 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:36331", "issue:39186", @@ -623,8 +647,8 @@ "issue:44661|issue:45464", "issue:39290|issue:43742", "issue:43054|issue:43994", - "issue:41093|issue:43596", "issue:43541|issue:44589", + "issue:41093|issue:43596", "issue:42915|issue:43541", "issue:40990|issue:44960", "issue:39186|issue:44918", @@ -648,14 +672,14 @@ "issue:36331|issue:41762", "issue:44560|issue:45507" ], - "prepared_review_unit_hash": "82e2aaff1fa24be3b719b5791e429ca7eb2d0a088206404f1f3d72cd73f95b39", + "prepared_review_unit_hash": "2af7e5185179a934c9888ce3cec0fd72d917bd15ea784d833f44aeacd9f4115b", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, @@ -670,222 +694,216 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is mostly heterogeneous issue reports; the only clear duplicate subcluster is the v5 non-persistent buffer corruption regression.", - "confidence": 0.77, - "canonical_issue_reason": "issue:43950 is the clearest representative of the shared \"non-persistent buffers get junked in v5\" regression, with issue:43644 and issue:44534 reading as the same underlying bug.", + "summary": "This set is mostly unrelated issue reports; the only clear duplicates are the non-persistent buffer regression reports in Transformers 5.x. The rest differ by model, failure mode, or subsystem and should stay separate.", + "confidence": 0.84, + "canonical_issue_reason": "issue:43950 is the strongest canonical issue for the duplicate buffer regression because it states the exact regression (`from_pretrained()` corrupting `register_buffer(persistent=False)`) and is the most specific root-cause description.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43950 is the best global representative because it states the bug precisely, identifies the v5 regression, and matches the strongest duplicate evidence in the cluster.", + "best_issue_reason": "issue:43950 best represents the duplicate cluster because it precisely names the v5 non-persistent-buffer bug, making it the most useful anchor for triage and linking related reports.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43572", "right": "issue:45070", "accept": false, - "reason": "Both are v5 config-related regressions, but one is missing pad_token_idx and the other is a pydantic PretrainedConfig field break; different bugs." + "reason": "Both are v5/config-related regressions, but one is about `StableLmConfig.pad_token_idx` and the other is a pydantic `PretrainedConfig` field issue; different bugs." }, { "left": "issue:44387", "right": "issue:45005", "accept": false, - "reason": "Int4 quantization OOM and tied-weights/translation-model issues are unrelated failure modes." + "reason": "One reports int4 quantization memory/OOM behavior, the other tied-weights problems in translation models; different failure modes." }, { "left": "issue:43541", "right": "issue:45161", "accept": false, - "reason": "Different models and code paths: Mixtral torch-dynamo grouped_mm tracing vs GPT-OSS MoE tensor-parallel failure." + "reason": "Both involve MoE/generation paths, but one is a torch-dynamo `grouped_mm` tracing error and the other is a tensor-parallel support issue for GPT-OSS; not the same bug." }, { "left": "issue:43828", "right": "issue:45464", "accept": false, - "reason": "Autocast dtype mismatch on Phi MoE is not the same as Qwen3.5 streaming chat/completions failure." + "reason": "Autocast dtype mismatch in Phi-tiny-MoE is unrelated to a streaming chat/completions failure on Qwen3.5-0.8B." }, { "left": "issue:44291", "right": "issue:45070", "accept": false, - "reason": "Unexpected _is_hf_initialized argument during init_empty_weights is a different loading path from the pydantic PretrainedConfig field regression." + "reason": "`init_empty_weights` unexpectedly passing `_is_hf_initialized` is a different initialization bug than the pydantic config-field regression." }, { "left": "issue:43366", "right": "issue:45464", "accept": false, - "reason": "GGUF gpt-oss support request and Qwen3.5 streaming inference failure are different issues." + "reason": "GGUF support for gpt-oss and a streaming API failure are unrelated." }, { "left": "issue:43531", "right": "issue:45070", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior is unrelated to the PretrainedConfig/pydantic regression." + "reason": "A Qwen3-MoE `sliding_window` issue is not the same as the generic `PretrainedConfig` field regression." }, { "left": "issue:44661", "right": "issue:45464", "accept": false, - "reason": "Tokenizer mapping/add-new-model-like failure is not the same as a Qwen3.5 streaming API bug." + "reason": "Tokenizer-mapping failure in `add-new-model-like` is unrelated to a Qwen3.5 streaming inference bug." }, { "left": "issue:39290", "right": "issue:43742", "accept": false, - "reason": "Both are load-time attribute/key errors, but they affect different models and different missing attributes." + "reason": "Both are load-time errors, but one is a missing `sliding_window_pattern` attribute for Gemma3/vLLM and the other is a key error loading MobileLLM." }, { "left": "issue:43054", "right": "issue:43994", "accept": false, - "reason": "Same model family, but one is an embedding-quality complaint and the other is a nonsensical-results/pipeline behavior report; not the same concrete bug." + "reason": "Both mention SigLIP2, but one is about worse text embeddings while the other is about nonsensical outputs in AutoModel/pipeline; too different without stronger evidence." }, { - "left": "issue:41093", - "right": "issue:43596", + "left": "issue:43541", + "right": "issue:44589", "accept": false, - "reason": "Both involve indexing errors, but the shapes, trigger conditions, and model/loading paths differ." + "reason": "Torch-dynamo grouped_mm tracing and missing Float8 storage are distinct runtime errors." }, { - "left": "issue:43541", - "right": "issue:44589", + "left": "issue:41093", + "right": "issue:43596", "accept": false, - "reason": "Mixtral tracing failures and missing Float8 storage are unrelated." + "reason": "Both are indexing/shape errors, but one is a mask-length mismatch and the other is a DeepSpeed ZeRO-3 zero-size tensor index error." }, { "left": "issue:42915", "right": "issue:43541", "accept": false, - "reason": "FineGrainedFP8Config on Qwen3-MoE and Mixtral grouped_mm tracing are different bugs." + "reason": "FineGrainedFP8Config failure for Qwen3-MoE is not the same as a Mixtral grouped_mm tracing error." }, { "left": "issue:40990", "right": "issue:44960", "accept": false, - "reason": "High perplexity on gpt-oss-20b and a GLM5 issue do not describe the same underlying problem." + "reason": "High perplexity on GPT-OSS and a GLM5 issue are unrelated model-specific reports." }, { "left": "issue:39186", "right": "issue:44918", "accept": false, - "reason": "FSDP 2-D weight error and TRL SFT embedding unpacking failure are different code paths." + "reason": "An FSDP weight-shape runtime error is unrelated to TRL SFT input-embedding unpacking on Qwen3.5." }, { "left": "issue:43404", "right": "issue:45005", "accept": false, - "reason": "Both mention tied weights, but the models and failure modes differ: Mistral3 lm_head tying vs translation-model v5 weight handling." + "reason": "Both involve tied weights, but one is a Mistral3 image-text model bug and the other is a broader v5 translation-model tied-weights regression; not enough to merge as the same bug." }, { "left": "issue:43645", "right": "issue:45399", "accept": false, - "reason": "Notebook custom model initialization and flash-attn2 fallback blocking are unrelated." + "reason": "Custom-model initialization in notebooks and flash-attn2 fallback gating are different issues." }, { "left": "issue:44530", "right": "issue:45005", "accept": false, - "reason": "PagedAttentionCache linear_attention crash and tied-weights translation regressions are different bugs." + "reason": "PagedAttentionCache group-type errors on Qwen3.5 models are unrelated to tied-weight handling." }, { "left": "issue:44863", "right": "issue:45005", "accept": false, - "reason": "NemotronH checkpoint loading failure is not the same as tied-weights handling on translation models." + "reason": "NemotronH checkpoint loading is a model-compatibility problem, not the tied-weights regression." }, { "left": "issue:43873", "right": "issue:45005", "accept": false, - "reason": "Offloading with quantization and tied-weights translation regressions are separate issues." + "reason": "Quantization/offloading behavior is unrelated to tied weights." }, { "left": "issue:44360", "right": "issue:44512", "accept": false, - "reason": "DSA indexer ReLU discussion and docs mentioning a removed command are unrelated." - }, - { - "left": "issue:42915", - "right": "issue:45399", - "accept": false, - "reason": "FP8 config failure on Qwen3-MoE and flash-attn2 fallback blocking are different problems." + "reason": "A DSA indexer activation request and a docs typo are unrelated." }, { "left": "issue:44918", "right": "issue:45507", "accept": false, - "reason": "Qwen3.5 SFT embedding unpacking and GraniteMoEHybrid invalid method calls are unrelated." + "reason": "TRL SFT embedding unpacking and a GraniteMoEHybrid invalid-method call are different code paths." }, { "left": "issue:44492", "right": "issue:44512", "accept": false, - "reason": "Cache strategy typo and outdated docs command are not the same bug." + "reason": "Cache-strategy typo and removed-run-command docs are unrelated documentation issues." }, { "left": "issue:43975", "right": "issue:44292", "accept": false, - "reason": "DeepSeek detokenization regression and Qwen-3-8B-NVFP4 runtime failure affect different models and behaviors." + "reason": "Detokenization in v5 and a Qwen-3-8B-NVFP4 runtime error are different model/runtime problems." }, { "left": "issue:43950", "right": "issue:44534", "accept": true, - "reason": "Both describe the same v5 regression where non-persistent buffers are loaded/fill with junk." + "reason": "These describe the same v5 regression: non-persistent buffers being populated incorrectly during loading." }, { "left": "issue:43644", "right": "issue:43950", "accept": true, - "reason": "These are the same non-persistent buffer corruption regression, just phrased with different specificity." + "reason": "Both report the same non-persistent-buffer corruption regression in Transformers 5.x." }, { "left": "issue:44292", "right": "issue:45507", "accept": false, - "reason": "Qwen NVFP4 runtime error and GraniteMoEHybrid invalid-method failure are unrelated." + "reason": "Qwen-3-8B-NVFP4 runtime failure is unrelated to GraniteMoEHybrid invalid-method calls." }, { "left": "issue:43828", "right": "issue:44928", "accept": false, - "reason": "Both are training/runtime numerical issues, but autocast dtype mismatch is not the same as 3D position_ids causing SDPA fallback and NaNs." + "reason": "Autocast dtype mismatch and Qwen3.5 RLHF NaN explosion are different failures, even though both involve MoE/precision concerns." }, { "left": "issue:39692", "right": "issue:43054", "accept": false, - "reason": "SigLIP2 docs example errors and SigLIP2 embedding quality regression are different issues." + "reason": "A broken SigLIP2 docs example is not the same as a separate report that SigLIP2 embeddings are worse than SigLIP." }, { "left": "issue:41553", "right": "issue:43883", "accept": false, - "reason": "Bad AutoTokenizer error message for Voxtral and missing all_tied_weights_keys on MolmoForCausalLM are unrelated." + "reason": "Bad AutoTokenizer error messaging for Voxtral is unrelated to missing `all_tied_weights_keys` on MolmoForCausalLM." }, { "left": "issue:43866", "right": "issue:44403", "accept": false, - "reason": "Ovis2 checkpoint corruption and generic transformer-loading noise are not the same bug." + "reason": "A corrupted Ovis2 checkpoint and loading noise are not the same bug." }, { "left": "issue:36331", "right": "issue:41762", "accept": false, - "reason": "CustomTrainer compute_loss kwarg breakage and Gemma3 ZeRO-3 loading index error are unrelated." + "reason": "A custom trainer signature mismatch is unrelated to a Gemma3 DeepSpeed ZeRO-3 indexing error." }, { "left": "issue:44560", "right": "issue:45507", "accept": false, - "reason": "Qwen3-vl-embedding StopIteration during video handling and GraniteMoEHybrid invalid method are different failures." + "reason": "Qwen3-vl video StopIteration and GraniteMoEHybrid invalid-method are unrelated." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet: issue:43950 is a clear representative for the v5 non-persistent-buffer corruption cluster, and the two accept verdicts on issue:43644/issue:43950 and issue:43950/issue:44534 are conservative and well supported by the titles. The remaining soft-edge rejections also read as appropriately cautious given the evidence available." + "feedback": "The summary is grounded in the packet and stays conservative. The two accepted soft-edge pairs are well supported by near-identical issue titles and descriptions about the same non-persistent-buffer regression in Transformers 5.x, and the other rejections avoid overclaiming duplicate status." }, "evaluator_used": true, "retried": false, @@ -901,10 +919,10 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:38175", "issue:41553", @@ -963,8 +981,8 @@ "issue:43054|issue:43493", "issue:43881|issue:43883", "issue:44403|issue:44451", - "issue:42947|issue:43856", "issue:43975|issue:45520", + "issue:42947|issue:43856", "issue:43643|issue:45020", "issue:44403|issue:44488", "issue:43782|issue:44960", @@ -993,244 +1011,256 @@ "issue:42915|issue:43872", "issue:43257|issue:45305" ], - "prepared_review_unit_hash": "da1432dedfb93c739e6a754a8014fa3fbe00a1baa5990493319848cd3b7f2578", + "prepared_review_unit_hash": "d758c0340a6177fa2fdb80123af951978fefa5db6e53f3406086f833a67499e2", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 36, - "serialized_chars": 38594, - "estimated_input_tokens": 9649, - "estimated_eval_tokens": 19554 + "serialized_chars": 38600, + "estimated_input_tokens": 9650, + "estimated_eval_tokens": 19556 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly a collection of unrelated Transformer v5-era regressions, with a few real duplicate pockets around stale pipeline docs and ZeRO/init_empty_weights loading failures. I kept the SigLIP2 and Whisper links conservative because the packet only shows family/title similarity, not a shared concrete defect.", - "confidence": 0.56, - "canonical_issue_reason": "issue:45020 is still the best umbrella issue here: it is open, broad, and captures the recent remote_code/loading regression theme that overlaps with several other reports without forcing weaker pairs into a duplicate bucket.", + "summary": "Mostly a mix of unrelated reports with several tight duplicate clusters. The SigLIP2 group should be described more conservatively: 43493 is the best anchor for the HF-vs-JAX discrepancy, but 38175 looks only loosely related from the available evidence rather than a confirmed duplicate of 43054.", + "confidence": 0.63, + "canonical_issue_reason": "43493 is the strongest single anchor because it names the concrete SigLIP2 HF-vs-JAX implementation discrepancy; it is the cleanest root-cause-style report in the subgroup.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45020 is the strongest cluster anchor overall because it is the broadest and most central regression report in the set, while the other likely duplicates are narrower subcases or weaker title-only matches.", + "best_issue_reason": "43493 is the best overall issue representative because it captures a specific implementation mismatch rather than just a downstream symptom, and it is the clearest anchor for the SigLIP2 cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:41553", "right": "issue:43881", "accept": false, - "reason": "Different models and failure surfaces: a bad tokenizer-loading error message vs a GLM-4v load failure." + "reason": "Different models and different failures; both are loading issues but not the same bug." }, { "left": "issue:43872", "right": "issue:44589", "accept": false, - "reason": "Both are loading incompatibilities, but the concrete causes differ (`_is_hf_initialized` vs Float8 storage lookup)." + "reason": "Both involve compatibility/loading problems, but the `_is_hf_initialized` kwarg bug is distinct from the Float8 storage error." }, { "left": "issue:38175", "right": "issue:43054", "accept": false, - "reason": "Only loose SigLIP2 family similarity; the titles do not establish the same underlying bug." + "reason": "They are both SigLIP2-related quality reports, but the packet only supports broad thematic similarity, not a confirmed shared underlying implementation bug." }, { "left": "issue:42947", "right": "issue:44387", "accept": false, - "reason": "Both involve memory, but one is gradient checkpointing under PEFT and the other is int4 OOM/reserved-memory growth." + "reason": "Different problems: LoRA gradient checkpointing vs int4 quantization memory/OOM." }, { "left": "issue:43054", "right": "issue:43493", "accept": true, - "reason": "Both are SigLIP2 regression reports about degraded/incorrect outputs, so they plausibly share the same implementation mismatch." + "reason": "Same SigLIP2 discrepancy family; 43493 states the root HF-vs-JAX mismatch behind the degraded outputs." }, { "left": "issue:43881", "right": "issue:43883", "accept": false, - "reason": "Unrelated issues: GLM-4v loading vs a Molmo tied-weights attribute error." + "reason": "Different model families and different failure modes." }, { "left": "issue:44403", "right": "issue:44451", "accept": false, - "reason": "One is load-time logging noise, the other is an actual model-load failure for ScandiBERT." + "reason": "Generic loading noise/warnings vs a specific model load failure." }, { - "left": "issue:42947", - "right": "issue:43856", + "left": "issue:43975", + "right": "issue:45520", "accept": false, - "reason": "Different training-memory problems with different symptoms and likely different fixes." + "reason": "Unrelated subsystems: tokenizer detokenization vs flash-attn import/key errors." }, { - "left": "issue:43975", - "right": "issue:45520", + "left": "issue:42947", + "right": "issue:43856", "accept": false, - "reason": "Detokenization regression and a flash-attn import KeyError are different code paths." + "reason": "Both mention memory, but the training/checkpointing contexts and root causes differ." }, { "left": "issue:43643", "right": "issue:45020", "accept": false, - "reason": "Related in theme, but `trust_remote_code` missing fields is not clearly the same concrete regression as the broader remote_code breakage." + "reason": "Both are remote_code-related, but one is a specific AutoConfig symptom and the other is a broad umbrella report; not enough to confirm the same bug." }, { "left": "issue:44403", "right": "issue:44488", "accept": false, - "reason": "Generic loading noise vs a specific inability to load a different model." + "reason": "These are separate model-loading reports, not the same defect." }, { "left": "issue:43782", "right": "issue:44960", "accept": false, - "reason": "Different model families and different failure modes; no shared concrete bug is evident." + "reason": "Different model families and incompatible error types." }, { "left": "issue:42491", "right": "issue:44368", "accept": false, - "reason": "Checkpoint compatibility across versions vs a LoRA tie-word-embeddings warning; related wording, not the same bug." + "reason": "LoRA hf4.x/hf5.x compatibility breakage is unrelated to a tie_word_embeddings warning." }, { "left": "issue:41762", "right": "issue:42915", "accept": false, - "reason": "Different ZeRO-3/FP8 failures with different models and code paths." + "reason": "Different models and different DeepSpeed/config problems." }, { "left": "issue:43975", "right": "issue:44451", "accept": false, - "reason": "Tokenizer detokenization regression is unrelated to a model-loading failure." + "reason": "Different issues: detokenization regression vs a model load failure." }, { "left": "issue:45020", "right": "issue:45356", "accept": false, - "reason": "Both are recent regressions, but remote_code loading and Kimi tokenizer codec/fix_mistral_regex behavior are not the same defect." + "reason": "Both mention remote_code/tokenizer regressions, but the Kimi tokenizer codec bug is a different concrete problem." }, { "left": "issue:44661", "right": "issue:45020", "accept": false, - "reason": "Tokenizer registration bug vs remote_code loading regression; similar surface area, different problem." + "reason": "Tokenizer-mapping template generation bug is not the same as remote_code loading regressions." }, { "left": "issue:43054", "right": "issue:43278", "accept": false, - "reason": "Same SigLIP2 family, but the available evidence only shows a dtype change, not the same underlying bug." + "reason": "SigLIP2 embedding quality vs a dtype change during evaluate; not the same bug." }, { "left": "issue:43824", "right": "issue:43872", "accept": false, - "reason": "Import error for a model class vs bitsandbytes/init_empty_weights incompatibility; different failures." + "reason": "Importing a missing VL class is unrelated to the bitsandbytes `_is_hf_initialized` incompatibility." }, { "left": "issue:44991", "right": "issue:45399", "accept": false, - "reason": "Tokenizer loading failure and flash-attn fallback gating are separate issues." + "reason": "Tokenizer loading failure and flash-attn fallback logic are different code paths." }, { "left": "issue:43827", "right": "issue:44509", "accept": true, - "reason": "Both are stale v5 docs issues still referencing removed pipeline tasks." + "reason": "Same docs cleanup: both still reference pipeline tasks removed in v5." }, { "left": "issue:43792", "right": "issue:44220", "accept": false, - "reason": "Whisper/audio-front-end similarity is plausible, but the titles do not clearly show the same runtime defect." + "reason": "The Whisper report is too generic to confirm it is the same fbank helper bug." }, { "left": "issue:45081", "right": "issue:45399", "accept": false, - "reason": "Tokenizer regex crash and flash-attn fallback blocking are different bugs." + "reason": "Tokenizer regex patch crash and flash-attn fallback gating are unrelated." }, { "left": "issue:43404", "right": "issue:43950", "accept": false, - "reason": "Weight-tying in Mistral3 and non-persistent buffer corruption are unrelated code paths." + "reason": "Weight-tying in Mistral3 and non-persistent buffer corruption are distinct issues." }, { "left": "issue:43257", "right": "issue:43866", "accept": false, - "reason": "Qwen3 MoE weight conversion and an Ovis2 checkpoint corruption report are distinct issues." + "reason": "Qwen3 MoE deepspeed conversion bug vs an Ovis2 checkpoint corruption report." }, { "left": "issue:42915", "right": "issue:45020", "accept": false, - "reason": "FP8/DeepSpeed training failure is not the same as the broad remote_code loading regression." + "reason": "Qwen3 MoE FP8 training/memory issue is unrelated to remote_code loading regressions." }, { "left": "issue:43742", "right": "issue:45399", "accept": false, - "reason": "MobileLLM key error and flash-attn fallback gating are unrelated." + "reason": "Different models and different failure mechanisms." }, { "left": "issue:41553", - "right": "issue:44488", - "accept": false, - "reason": "Different models and different load failures; only generic loading trouble is shared." - }, - { - "left": "issue:42915", - "right": "issue:43872", + "right": "issue:44991", "accept": false, - "reason": "FP8 config failure and `_is_hf_initialized`/Int8Params incompatibility are separate incompatibilities." + "reason": "Different model families and different tokenizer-loading errors." }, { - "left": "issue:43257", - "right": "issue:45305", + "left": "issue:43742", + "right": "issue:45020", "accept": false, - "reason": "Both mention Qwen3 MoE, but one is missing weight conversion and the other is gradient averaging under GAS." + "reason": "A specific model key error is not the same as the broader remote_code regression." }, { "left": "issue:43940", "right": "issue:45313", "accept": true, - "reason": "Both are Qwen3/Qwen3.5 ZeRO-3 weight-loading failures that report missing weights in the same general code path." + "reason": "Same DeepSpeed ZeRO-3 weight-loading failure class on Qwen3-family models." }, { "left": "issue:43872", "right": "issue:44291", "accept": true, - "reason": "Same `_is_hf_initialized` / `init_empty_weights` incompatibility family, just surfaced through different entry points." + "reason": "Exact same `_is_hf_initialized` / init_empty_weights incompatibility." }, { "left": "issue:43854", "right": "issue:44863", "accept": false, - "reason": "Different model families and different load failures; no shared concrete bug is evident." + "reason": "Different model families and different checkpoint-loading failures." }, { "left": "issue:44928", "right": "issue:45588", "accept": false, - "reason": "Gradient explosion/SDPA fallback and a flash_attention crash on `s_aux=None` are different problems." + "reason": "RLHF gradient explosion from position_ids/SDPA fallback is unrelated to flash_attention s_aux handling." + }, + { + "left": "issue:41553", + "right": "issue:44488", + "accept": false, + "reason": "Separate model-loading failures, not the same bug." + }, + { + "left": "issue:42915", + "right": "issue:43872", + "accept": false, + "reason": "Qwen3 MoE FP8 training memory issue is unrelated to the bitsandbytes `_is_hf_initialized` crash." + }, + { + "left": "issue:43257", + "right": "issue:45305", + "accept": false, + "reason": "Different Qwen3 training/load bugs with different symptoms and code paths." } ] }, "evaluator_result": { "accept": false, - "feedback": "The anchor choice is mostly grounded, but several soft-edge accepts are too assertive for the packet. In particular, the SigLIP2 pairs (38175\u201343054 and 43054\u201343278) are only loosely related by model/family/title and do not establish a shared bug from the available evidence. The Whisper pair (43792\u201344220) is also plausible but not clearly the same defect from titles alone. The more conservative loading-regression pairs (43872\u201344291, 43940\u201345313, 43827\u201344509) are fine, but the summary and a few accepted verdicts overstate certainty beyond the packet." + "feedback": "Mostly grounded, but one soft-edge verdict is too strong for the evidence available. The SigLIP2 pair (issue:38175 \u2194 issue:43054) is only supported by broad title similarity; from the packet alone it is safer to call them related symptoms, not the same underlying implementation mismatch. Because the cluster summary also presents SigLIP2 as a clear duplicate subgroup, the overall writeup is a bit overconfident and should be made more conservative." }, "evaluator_used": true, "retried": true, @@ -1246,10 +1276,10 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:24643", "issue:30064", @@ -1306,8 +1336,8 @@ "issue:44479|issue:44560", "issue:44530|issue:44863", "issue:43366|issue:43828", - "issue:44155|issue:45584", "issue:24643|issue:30064", + "issue:44155|issue:45584", "issue:43366|issue:43531", "issue:43550|issue:44910", "issue:43645|issue:43646", @@ -1331,220 +1361,220 @@ "issue:42491|issue:43720", "issue:44960|issue:44977" ], - "prepared_review_unit_hash": "7e9461d13590345fc39f1d8f42c8b127386bdaae573625e40bc1b4230b6c9707", + "prepared_review_unit_hash": "4a0772e4c38cbdc509a62209740a10779b54923e621469b01c702cc07f6bfb33", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 30, - "serialized_chars": 36154, - "estimated_input_tokens": 9039, - "estimated_eval_tokens": 18334 + "serialized_chars": 36151, + "estimated_input_tokens": 9038, + "estimated_eval_tokens": 18332 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous: a grab-bag of unrelated Transformers bug reports across different models/features. Only a few soft pairs look like true duplicates; the rest should stay separate.", - "confidence": 0.89, - "canonical_issue_reason": "No single canonical issue; this is a heterogeneous bundle of unrelated bugs. Only a few pairs are clear duplicates.", + "summary": "This cluster is a loose collection of mostly unrelated Transformers issue reports, with a few clear duplicate subclusters: non-persistent buffer corruption, custom model initialization failures, Qwen video-regression reports, and repeated mask-shape IndexErrors. No PRs are present.", + "confidence": 0.83, + "canonical_issue_reason": "issue:44534 is the cleanest representative of the strongest duplicate subcluster: it is the broader, clearer restatement of the non-persistent-buffer regression and subsumes issue:43644.", "canonical_pr_reason": null, - "best_issue_reason": "As a whole, none of these issues is a strong global representative because they span different models, regressions, and code paths.", + "best_issue_reason": "issue:44534 is the best global issue representative because it is the most general and clearly phrased duplicate target among the issues in this cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:36331", "right": "issue:41093", "accept": false, - "reason": "Different failures: trainer API kwarg mismatch vs mask/tensor shape IndexError." + "reason": "Different failures: custom trainer API mismatch vs tensor mask-shape IndexError." }, { "left": "issue:41093", "right": "issue:44805", "accept": true, - "reason": "Same IndexError class with the same mask/tensor shape mismatch pattern." + "reason": "Same generic mask/tensor shape-mismatch error; titles indicate the same underlying IndexError regression." }, { "left": "issue:43872", "right": "issue:45538", "accept": false, - "reason": "Unrelated bugs: bitsandbytes constructor incompatibility vs tokenizer max-length handling." + "reason": "Unrelated bugs: bitsandbytes constructor incompatibility vs tokenizer max-length constant." }, { "left": "issue:44479", "right": "issue:44560", - "accept": false, - "reason": "Both touch Qwen VL/video paths, but the concrete failures and affected surfaces differ." + "accept": true, + "reason": "Both report the same Qwen video-input regression in the 5.3.0 timeframe; same affected code path is likely." }, { "left": "issue:44530", "right": "issue:44863", "accept": false, - "reason": "Different models and different failure modes; not the same bug." + "reason": "Different model/path failures: PagedAttentionCache linear_attention crash vs NemotronH checkpoint loading." }, { "left": "issue:43366", "right": "issue:43828", "accept": false, - "reason": "GGUF gpt-oss support is unrelated to Phi-tiny-MoE autocast dtype mismatch." + "reason": "Different areas and symptoms: GGUF/gpt-oss support vs autocast dtype mismatch in Phi-tiny-MoE." }, { - "left": "issue:44155", - "right": "issue:45584", + "left": "issue:24643", + "right": "issue:30064", "accept": false, - "reason": "AudioFlamingo3 batched-track leakage vs Whisper empty-transcription failure are unrelated." + "reason": "Completely different bugs: DeepSpeed training weight shape error vs void segmentation-map processing." }, { - "left": "issue:24643", - "right": "issue:30064", + "left": "issue:44155", + "right": "issue:45584", "accept": false, - "reason": "DeepSpeed weight-shape training error vs image processor void-segmentation bug are unrelated." + "reason": "Different audio/ASR issues with no shared code path evident." }, { "left": "issue:43366", "right": "issue:43531", "accept": false, - "reason": "Different model families and different issues; no shared concrete code path." + "reason": "Different features/models: gpt-oss GGUF support vs Qwen3-MoE sliding_window handling." }, { "left": "issue:43550", "right": "issue:44910", "accept": false, - "reason": "torch.compile/SDPA on Bamba is unrelated to Qwen3.5 flash-attention position_ids crash." + "reason": "Different attention/compile failures in different models and code paths." }, { "left": "issue:43645", "right": "issue:43646", "accept": true, - "reason": "Both report the same Transformers v5 custom-model initialization regression; one is just a more specific reproduction." + "reason": "Very close duplicate wording around custom model initialization breaking in Transformers 5.0." }, { "left": "issue:43950", "right": "issue:45325", "accept": false, - "reason": "Non-persistent-buffer corruption and Qwen2.5-VL rope-index scaling are different regressions." + "reason": "Different regressions: non-persistent buffer corruption vs Qwen2.5-VL rope/position-id scaling." }, { "left": "issue:44560", "right": "issue:44918", "accept": false, - "reason": "Both mention Qwen3.5/VL embeddings, but one is video StopIteration and the other is TRL SFT unpacking failure." + "reason": "Both are Qwen video/embedding related, but the concrete failures and code paths differ (video StopIteration vs TRL SFT unpacking)." }, { "left": "issue:43366", "right": "issue:44589", "accept": false, - "reason": "Unrelated: gpt-oss GGUF support vs missing Float8 storage type." + "reason": "Unrelated: GGUF architecture support vs float8 storage lookup failure." }, { "left": "issue:43824", "right": "issue:43957", "accept": false, - "reason": "ImportError for a specific class vs meta-device loading regression are distinct issues." + "reason": "Different load/import regressions with different mechanisms and affected models." }, { "left": "issue:42915", "right": "issue:43957", "accept": false, - "reason": "Qwen3Moe FP8 config failure is unrelated to meta-device loading problems." + "reason": "Different bugs: FineGrainedFP8Config failure vs meta-device loading failure." }, { "left": "issue:42617", "right": "issue:43366", "accept": false, - "reason": "3d_parallel.py runtime failure is not the same as gpt-oss GGUF support." + "reason": "Different subjects: 3D parallel script failure vs GGUF gpt-oss support." }, { "left": "issue:38175", "right": "issue:43994", - "accept": true, - "reason": "Same SigLIP2 base model and same broken inference behavior; one report uses a different surface (AutoModel/pipeline) but appears to be the same underlying bug." + "accept": false, + "reason": "Same model family, but the reports are too symptom-level and not clearly the same underlying bug." }, { "left": "issue:43646", "right": "issue:43950", "accept": false, - "reason": "Custom model init regression and non-persistent-buffer corruption are separate v5 issues." + "reason": "Different custom-model regression vs silent non-persistent-buffer corruption." }, { "left": "issue:44560", "right": "issue:44805", "accept": false, - "reason": "Different Qwen-related failures; one is video StopIteration, the other is a mask/tensor IndexError." + "reason": "Different code paths and symptoms: Qwen video StopIteration vs mask/tensor shape mismatch." }, { "left": "issue:36010", "right": "issue:42915", "accept": false, - "reason": "GenerationMixin import error and Qwen3Moe FP8 failure are unrelated." + "reason": "Different failures: missing GenerationMixin import vs Qwen3-MoE FP8 config issue." }, { "left": "issue:43638", "right": "issue:44661", "accept": false, - "reason": "Zero3/Bert loading failure is unrelated to tokenizer-mapping/model registration bug." + "reason": "Different bugs: DeepSpeed Zero-3/Bert index error vs add-new-model-like tokenizer mapping issue." }, { "left": "issue:44877", "right": "issue:45030", "accept": false, - "reason": "Both are config-validation complaints, but they affect different models and likely different checks." + "reason": "Both are config-validation related, but the affected models and failure modes differ." }, { "left": "issue:43596", "right": "issue:44661", "accept": false, - "reason": "Zero3/Bert index error is unrelated to add-new-model-like tokenizer-mapping handling." + "reason": "Different code paths: Zero-3 Bert init error vs tokenizer-mapping registration failure." }, { "left": "issue:43317", "right": "issue:44756", "accept": false, - "reason": "Device-map dequantized loading/offload issue is unrelated to mmap OOM on Strix Halo." + "reason": "Different problems: dequantized-model offload loading vs mmap OOM on Strix Halo." }, { "left": "issue:43644", "right": "issue:44534", "accept": true, - "reason": "These are the same non-persistent-buffer regression in Transformers v5, just phrased differently." + "reason": "Direct duplicates: same non-persistent-buffer regression, with 44534 being the broader rephrasing." }, { "left": "issue:45313", "right": "issue:45357", "accept": false, - "reason": "Both are Qwen3.5 regressions, but one is ZeRO-3 weight loading and the other is save_pretrained key serialization." + "reason": "Different Qwen3.5 load/save regressions affecting different components." }, { "left": "issue:38175", "right": "issue:39692", "accept": false, - "reason": "SigLIP2 zero-probability inference bug is not the same as the documentation example's model/processor mismatch and quantization failures." + "reason": "SigLIP2 is the only shared context, but 39692 is a broader documentation-example issue with additional quantization/model-processor problems." }, { "left": "issue:42491", "right": "issue:43720", "accept": false, - "reason": "Qwen3_moe LoRA compatibility on hf5.x is unrelated to BitNet packed-weight loading." + "reason": "Unrelated loading/compatibility problems in different quantization/accelerate paths." }, { "left": "issue:44960", "right": "issue:44977", "accept": false, - "reason": "Different models and different generation issues; no shared bug." + "reason": "Different model families and failures: GLM5 vs Qwen3.5 flash-attention generation." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet: the cluster is indeed mostly heterogeneous, and the accepted soft pairs are narrowly framed and conservative based on the titles. I don't see an overstatement of evidence in the verdicts." + "feedback": "The summary is grounded in the packet: it correctly reflects that the set is mostly a collection of issue reports, and the named duplicate subclusters are supported by the issue titles. The no-PR statement is also consistent with the packet. The soft-edge acceptances are generally conservative, with the strongest evidence on the non-persistent-buffer and mask-shape pairs. " }, "evaluator_used": true, "retried": false, @@ -1560,10 +1590,10 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:36010", "issue:39404", @@ -1619,15 +1649,15 @@ "issue:43854|issue:43931", "issue:43856|issue:43873", "issue:42491|issue:45276", - "issue:43257|issue:43854", "issue:41720|issue:42915", + "issue:43257|issue:43854", "issue:39692|issue:43994", - "issue:43856|issue:44387", "issue:44488|issue:44991", + "issue:43856|issue:44387", "issue:45362|issue:45406", - "issue:44661|issue:44683", "issue:43644|issue:43645", "issue:42915|issue:44756", + "issue:44661|issue:44683", "issue:42491|issue:43931", "issue:44910|issue:45588", "issue:43404|issue:43454", @@ -1639,289 +1669,282 @@ "issue:41720|issue:44155", "issue:43873|issue:44387", "issue:39692|issue:44960", - "issue:44387|issue:44756", "issue:43425|issue:43957", + "issue:44387|issue:44756", "issue:43854|issue:45216", "issue:44292|issue:44912", "issue:42947|issue:43381", "issue:44291|issue:44756", - "issue:45276|issue:45292", "issue:44743|issue:44960", + "issue:45276|issue:45292", "issue:43381|issue:44928", "issue:43957|issue:44756", "issue:44164|issue:44756", "issue:43646|issue:43708", - "issue:45292|issue:45335", - "issue:44402|issue:44451" + "issue:45292|issue:45335" ], - "prepared_review_unit_hash": "9e30b58949dc052130488af35c04a0d0971161cca664edccb7b3023eefa64a04", + "prepared_review_unit_hash": "f11c5d19c87a85f9fe938011bbc90b84a995dde28423c1230b7841abea208c04", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 47, "item_count": 47, - "soft_pair_count": 39, - "serialized_chars": 38694, - "estimated_input_tokens": 9674, - "estimated_eval_tokens": 19604 + "soft_pair_count": 38, + "serialized_chars": 38399, + "estimated_input_tokens": 9600, + "estimated_eval_tokens": 19456 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is heterogeneous, but two small duplicate families stand out: tokenizer/model-loading failures for specific BERT-like models, and resize_token_embeddings not propagating to downstream embeddings. Most other pairs are distinct bugs in different code paths.", - "confidence": 0.63, - "canonical_issue_reason": "issue:45292 is the most general, model-agnostic report of the resize_token_embeddings propagation bug, and it can serve as the umbrella issue for the accepted resize-related duplicates.", + "summary": "There is one clear duplicate cluster around `resize_token_embeddings` not propagating to output/decoder embeddings (issues 45276, 45292, 45335). The rest of the soft pairs are mostly thematically similar but appear to be different bugs/models and should stay separate.", + "confidence": 0.89, + "canonical_issue_reason": "issue:45292 is the broadest, model-agnostic report of the shared `resize_token_embeddings` bug and best covers the narrower Gemma4/T5Gemma variants.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45292 is open, broadly phrased, and describes the core API regression without model-specific noise, making it the best representative issue among the candidates.", + "best_issue_reason": "issue:45292 is the best cluster anchor: open, general, and directly describes the common failure mode that the other two issues narrow to specific model components.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44451", "right": "issue:44488", - "accept": true, - "reason": "Both report the same current-version model-loading regression for BERT-style models; a single tokenizer/load fix could plausibly cover both." + "accept": false, + "reason": "Same general area (model loading) but different models and no clear shared code-path bug; likely related, not duplicate." }, { "left": "issue:43708", "right": "issue:44075", "accept": false, - "reason": "Trainer resume/max_steps logic is unrelated to optimizer argument handling." + "reason": "Different trainer/optimizer problems; the titles do not describe the same underlying defect." }, { "left": "issue:43854", "right": "issue:43931", "accept": false, - "reason": "Different model-loading failures with different symptoms and likely different code paths." + "reason": "Both are model-loading failures, but for different models and distinct symptoms (unit-test load vs weight-shape mismatch)." }, { "left": "issue:43856", "right": "issue:43873", "accept": false, - "reason": "MoE training memory usage is not the same bug as quantized offloading behavior." + "reason": "Both involve memory/quantization, but one is Qwen3 MoE training memory use and the other is offloading under quantization; not the same bug." }, { "left": "issue:42491", "right": "issue:45276", "accept": false, - "reason": "LoRA checkpoint compatibility is unrelated to resize_token_embeddings propagation." - }, - { - "left": "issue:43257", - "right": "issue:43854", - "accept": false, - "reason": "Accelerate/deepspeed weight conversion is unrelated to a GLM unit-test load failure." + "reason": "Different models and different failures; one is a LoRA compatibility issue, the other is resize-token-embedding propagation." }, { "left": "issue:41720", "right": "issue:42915", "accept": false, - "reason": "CUDA assert on auto device mapping is not the same as FineGrainedFP8Config failure." + "reason": "Both mention Qwen3 MoE, but one is a device-mapping crash and the other is a conversion/loading issue under accelerate+deepspeed." }, { - "left": "issue:39692", - "right": "issue:43994", + "left": "issue:43257", + "right": "issue:43854", "accept": false, - "reason": "SigLIP2 doc example errors are different from incorrect inference results on a separate model instance." + "reason": "Unrelated model families and failure modes; no shared concrete bug." }, { - "left": "issue:43856", - "right": "issue:44387", + "left": "issue:39692", + "right": "issue:43994", "accept": false, - "reason": "Training memory inefficiency and int4 quantization OOM are different regressions." + "reason": "Both are SigLIP2-related, but one is a docs/example issue and the other is a model/pipeline behavior report; not enough evidence of one underlying bug." }, { "left": "issue:44488", "right": "issue:44991", - "accept": true, - "reason": "Both are tokenizer/model-loading failures for specific text models in the same version range and look like the same underlying loader regression." + "accept": false, + "reason": "Both are tokenizer-loading regressions, but they concern different models and likely different configs/root causes." }, { - "left": "issue:45362", - "right": "issue:45406", + "left": "issue:43856", + "right": "issue:44387", "accept": false, - "reason": "Chat-generation crash and serve/processor AttributeError are different failures in different entry points." + "reason": "Both are memory-related, but one is training-memory inefficiency and the other is int4 reserved-memory OOM; not the same change." }, { - "left": "issue:44661", - "right": "issue:44683", + "left": "issue:45362", + "right": "issue:45406", "accept": false, - "reason": "Tokenizer mapping registration and compiled flex_attention are unrelated subsystems." + "reason": "Different model classes and different processor/runtime failures; not a duplicate." }, { "left": "issue:43644", "right": "issue:43645", "accept": false, - "reason": "Non-persistent buffer initialization and Jupyter custom-model initialization are different Transformers 5 issues." + "reason": "Both are Transformers 5.0 regressions, but one is junk non-persistent buffers and the other is custom model init in notebooks; separate bugs." }, { "left": "issue:42915", "right": "issue:44756", "accept": false, - "reason": "Qwen3 MoE FP8 failure is unrelated to mmap/OOM on Strix Halo." + "reason": "Unrelated issues: Qwen3 MoE conversion vs Strix Halo mmap/OOM." + }, + { + "left": "issue:44661", + "right": "issue:44683", + "accept": false, + "reason": "Completely different areas: tokenizer mapping helper vs compiled flex attention on new torch." }, { "left": "issue:42491", "right": "issue:43931", "accept": false, - "reason": "LoRA checkpoint compatibility is unrelated to a weight-shape mismatch on model load." + "reason": "Different Qwen3/VL problems with no shared underlying code path." }, { "left": "issue:44910", "right": "issue:45588", "accept": false, - "reason": "Both involve flash_attention, but they describe different crashing conditions and code paths." + "reason": "Both touch flash attention, but one is a Qwen3.5 packed-sequence interpretation bug and the other is an AttributeError on sink-less models; not the same defect." }, { "left": "issue:43404", "right": "issue:43454", "accept": false, - "reason": "Both are weight-tying bugs, but on different model classes and not the same concrete failure." + "reason": "Both are lm_head weight-tying complaints, but they target different model implementations and symptoms; too broad to merge." }, { "left": "issue:42491", "right": "issue:43856", "accept": false, - "reason": "LoRA checkpoint portability is unrelated to MoE training memory usage." + "reason": "Different Qwen3 MoE issues: LoRA compatibility vs training memory usage." }, { "left": "issue:45276", "right": "issue:45335", "accept": true, - "reason": "Both say resize_token_embeddings fails to update downstream embeddings in model-specific variants; one fix could plausibly address both." + "reason": "Same underlying `resize_token_embeddings` propagation bug; both report the embeddings not updating in different model wrappers." }, { "left": "issue:36010", "right": "issue:39404", "accept": false, - "reason": "Importing GenerationMixin and Whisper return_language pipeline behavior are unrelated." + "reason": "No shared code path: import error for GenerationMixin vs Whisper pipeline `return_language` regression." }, { "left": "issue:44164", "right": "issue:44291", "accept": false, - "reason": "extra_state save/load handling is different from init_empty_weights argument handling." + "reason": "Both involve save/load behavior, but one is `extra_state` handling and the other is `init_empty_weights`/`_is_hf_initialized`; different bugs." }, { "left": "issue:44402", "right": "issue:44488", "accept": false, - "reason": "Tokenizer vocab-size mismatch and model-loading failure are related only broadly, not clearly the same bug." + "reason": "Tokenizer vocab mismatch vs model loading failure for a different model; not the same issue." }, { "left": "issue:41720", "right": "issue:44155", "accept": false, - "reason": "Qwen3 auto device mapping failure and AudioFlamingo3 batch leakage are unrelated." + "reason": "Distinct subsystems and symptoms: Qwen3 device mapping crash vs AudioFlamingo3 batched inference leakage." }, { "left": "issue:43873", "right": "issue:44387", "accept": false, - "reason": "Quantized offloading behavior and int4 reserved-memory OOM are different issues." + "reason": "Related to memory pressure, but one is quantization offloading and the other is int4 CUDA reserved memory/OOM; not duplicate enough." }, { "left": "issue:39692", "right": "issue:44960", "accept": false, - "reason": "SigLIP2 documentation problems are unrelated to GLM5." + "reason": "Different models and problem types; one is SigLIP2 docs/model mismatch, the other is GLM5." }, { - "left": "issue:44387", - "right": "issue:44756", + "left": "issue:43425", + "right": "issue:43957", "accept": false, - "reason": "int4 quantization OOM and Strix Halo mmap OOM are different memory problems." + "reason": "Both are version-compatibility regressions, but one is torch 2.10 and the other is `torch.device(\"meta\")` model loading; separate causes." }, { - "left": "issue:43425", - "right": "issue:43957", + "left": "issue:44387", + "right": "issue:44756", "accept": false, - "reason": "Torch version incompatibility and meta-device loading breakage are different regressions." + "reason": "Both mention memory, but one is quantization OOM and the other is Strix Halo mmap behavior; unrelated." }, { "left": "issue:43854", "right": "issue:45216", "accept": false, - "reason": "Unit-test loading of a specific model is unrelated to save_pretrained checkpoint correctness for Qwen3.5." + "reason": "Different models and different failures: GLM-4.7-Flash test loading vs Qwen3.5 checkpoint saving." }, { "left": "issue:44292", "right": "issue:44912", "accept": false, - "reason": "NVFP4 runtime failure and MXFP4 fallback behavior are different quantization bugs." + "reason": "Both are quantization-related, but on different models and with different failure modes; not the same change." }, { "left": "issue:42947", "right": "issue:43381", "accept": false, - "reason": "Gradient checkpointing under PEFT LoRA and eval-mode checkpointing are different problems." + "reason": "Both involve gradient checkpointing, but one is PEFT/LoRA effectiveness and the other is eval-mode usage; different bugs." }, { "left": "issue:44291", "right": "issue:44756", "accept": false, - "reason": "init_empty_weights argument mismatch is unrelated to mmap/OOM behavior." - }, - { - "left": "issue:45276", - "right": "issue:45292", - "accept": false, - "reason": "They are closely related, but 45276 is Gemma4-specific and 45292 is the broader output_embeddings report; keep the broader issue as the canonical one rather than duplicating." + "reason": "No meaningful overlap beyond being regressions; `_is_hf_initialized` loading error is unrelated to mmap/OOM." }, { "left": "issue:44743", "right": "issue:44960", "accept": false, - "reason": "Recurrent-state reset in modular_qwen3_5 and GLM5 are unrelated model implementations." + "reason": "Different model implementations and different runtime behavior bugs." + }, + { + "left": "issue:45276", + "right": "issue:45292", + "accept": true, + "reason": "Same `resize_token_embeddings` bug; 45292 is the general report and 45276 is a Gemma4-specific instance." }, { "left": "issue:43381", "right": "issue:44928", "accept": false, - "reason": "Eval-mode gradient checkpointing and Qwen3.5 SDPA/BF16 instability are different bugs." + "reason": "Both concern checkpointing/sequence handling, but one is eval-mode checkpointing and the other is Qwen3.5 3D position_ids/SDPA behavior." }, { "left": "issue:43957", "right": "issue:44756", "accept": false, - "reason": "Meta-device loading breakage is unrelated to mmap OOM on Strix Halo." + "reason": "Different loading path problems with no shared underlying defect." }, { "left": "issue:44164", "right": "issue:44756", "accept": false, - "reason": "extra_state serialization and mmap OOM are unrelated." + "reason": "Save/from_pretrained extra_state handling is unrelated to mmap/OOM on Strix Halo." }, { "left": "issue:43646", "right": "issue:43708", "accept": false, - "reason": "Custom model initialization and checkpoint-resume step counting are unrelated." + "reason": "Different initialization/resume bugs; no shared code-path evidence." }, { "left": "issue:45292", "right": "issue:45335", "accept": true, - "reason": "Both describe resize_token_embeddings failing to update model output/decoder embeddings; a single fix in the resizing path could plausibly cover both." - }, - { - "left": "issue:44402", - "right": "issue:44451", - "accept": false, - "reason": "Pad/unk vocab mismatch and a load failure for a different model are not clearly the same underlying bug." + "reason": "Same `resize_token_embeddings` propagation issue; 45335 is a t5gemma-specific manifestation." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary stays within the evidence in the packet and is appropriately cautious. The accepted soft-edge pairs are all title-level similar and the rejection reasons are conservative; the canonical issue choice is also grounded by the generic wording of 45292. No pair is overstated as definitely the same bug." + "feedback": "The cluster summary is well grounded in the packet. The resize_token_embeddings group (45276, 45292, 45335) is supported by the titles and the chosen anchor/canonical issue is conservative. The other soft-pair rejections also stay on the cautious side and do not overclaim duplication from thematic similarity alone." }, "evaluator_used": true, "retried": false, @@ -1937,10 +1960,10 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:32090", "issue:36032", @@ -1970,6 +1993,8 @@ "issue:44079", "issue:44164", "issue:44265", + "issue:44402", + "issue:44451", "issue:44479", "issue:44488", "issue:44509", @@ -1979,7 +2004,6 @@ "issue:44683", "issue:44756", "issue:44805", - "issue:44811", "issue:44863", "issue:44877", "issue:44898", @@ -1988,11 +2012,11 @@ "issue:44991", "issue:45081", "issue:45084", - "issue:45161", - "issue:45584" + "issue:45161" ], "soft_pairs": [ "issue:44479|issue:44877", + "issue:44402|issue:44451", "issue:43645|issue:44164", "issue:43257|issue:44863", "issue:43425|issue:43828", @@ -2011,38 +2035,37 @@ "issue:43994|issue:44079", "issue:44671|issue:44991", "issue:43856|issue:44756", - "issue:39404|issue:44671", - "issue:43596|issue:44683", "issue:43425|issue:44918", + "issue:39404|issue:44671", "issue:40990|issue:42947", + "issue:43596|issue:44683", "issue:44589|issue:45084", "issue:36032|issue:43452", - "issue:32090|issue:39404", "issue:43582|issue:43632", "issue:44991|issue:45081", + "issue:32090|issue:39404", "issue:43957|issue:44164", "issue:40990|issue:43421", + "issue:43883|issue:44488", "issue:44164|issue:44479", "issue:44488|issue:45081", - "issue:43883|issue:44488", "issue:43425|issue:45161", - "issue:43611|issue:43644", - "issue:44811|issue:45584" + "issue:43611|issue:43644" ], - "prepared_review_unit_hash": "8795b1a249cfbbe0dc6c0015d8f74d2054d024ea70211b6067eeabe32d6c43f0", + "prepared_review_unit_hash": "6c8a8cbe78b171370d188bf37d57edaee6e99a2441cc440a6490ebe9ec7989a3", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 36, - "serialized_chars": 38485, + "serialized_chars": 38488, "estimated_input_tokens": 9622, "estimated_eval_tokens": 19500 }, @@ -2051,228 +2074,228 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is a loose set of Transformers/v5 regression issues, mostly distinct model-loading or runtime bugs rather than true duplicates. The strongest representative issue is the broad custom-model loading regression in issue 43611, but none of the soft-edge pairs look safe to merge as duplicates.", - "confidence": 0.63, - "canonical_issue_reason": "issue:43611 is the broadest and most central report: Transformers 5.0 breaking model loading for custom classes via `base_model_prefix`, which aligns with several nearby v5 loading-regression reports.", + "summary": "This cluster is mostly a loose collection of Transformers v5 regressions, especially model/tokenizer loading problems, but the soft pairs are not the same concrete bugs. No soft merges are warranted.", + "confidence": 0.72, + "canonical_issue_reason": "issue:43611 is the broadest and most representative loading-regression report in the set: it describes a v5 break affecting model loading via `base_model_prefix`, which aligns with the overall theme of the cluster better than the narrower model-specific issues.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43611 best represents the cluster because it describes a core v5 loading regression with broad impact, whereas the other issues are more specific model- or feature-level failures.", + "best_issue_reason": "issue:43611 is the best single issue to anchor this cluster because it is general, user-facing, and closest to the common failure mode across the nearby reports (loading regressions after v5).", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44479", "right": "issue:44877", "accept": false, - "reason": "Both are model-related regressions, but one is a video-input bug for Qwen VL variants and the other is a Granite Speech config-loading issue; different code paths." + "reason": "Both are v5 regressions, but one is a video-input pipeline issue and the other is strict config handling; different code paths and failure modes." + }, + { + "left": "issue:44402", + "right": "issue:44451", + "accept": false, + "reason": "One is tokenizer vocab boundary metadata, the other is a model-load failure for a specific checkpoint; not the same bug." }, { "left": "issue:43645", "right": "issue:44164", "accept": false, - "reason": "Custom model initialization in notebooks is unrelated to save/from_pretrained handling of `extra_state`; these are distinct failure modes." + "reason": "Custom model initialization in notebooks and `extra_state` save/load handling are unrelated." }, { "left": "issue:43257", "right": "issue:44863", "accept": false, - "reason": "Qwen3 MoE loading with accelerate/deepspeed and NemotronH checkpoint loading are different model families and different loader bugs." + "reason": "Both are loading failures, but for different model families and different mechanisms (`accelerate+deepspeed` conversion vs NemotronH checkpoint compatibility)." }, { "left": "issue:43425", "right": "issue:43828", "accept": false, - "reason": "Torch 2.10 incompatibility is a version-compatibility issue, while the other is an autocast dtype mismatch on a specific model." + "reason": "Torch version incompatibility and autocast dtype mismatch are distinct problems." }, { "left": "issue:43828", "right": "issue:43957", "accept": false, - "reason": "One is an autocast dtype mismatch; the other is a meta-device loading breakage. Related theme, not same bug." + "reason": "Autocast dtype mismatch is not the same as meta-device loading breakage." }, { "left": "issue:44589", "right": "issue:44756", "accept": false, - "reason": "Float8 storage lookup failure and Strix Halo mmap OOM are unrelated runtime problems." + "reason": "Float8 storage lookup error and Apple Silicon mmap OOM are unrelated." }, { "left": "issue:43906", "right": "issue:44530", "accept": false, - "reason": "An isolated reproduction of an older issue is not the same as a PagedAttentionCache crash on Qwen3.5; different symptoms and paths." + "reason": "An isolated reproduction of an old issue is not the same as the Qwen3.5 PagedAttentionCache crash." }, { "left": "issue:43931", "right": "issue:44863", "accept": false, - "reason": "Qwen3-VL weight-shape mismatch and NemotronH checkpoint-loading failure affect different models and loaders." + "reason": "Different models and different failure signatures: Qwen3-VL shape mismatch vs NemotronH checkpoint loading." }, { "left": "issue:43611", "right": "issue:43645", "accept": false, - "reason": "Both are v5 regressions around model loading, but one is base_model_prefix handling and the other is notebook-defined custom model initialization; not the same defect." + "reason": "Both involve model loading, but one is a `base_model_prefix` regression and the other is notebook-defined custom model initialization; not one concrete bug." }, { "left": "issue:39404", "right": "issue:44912", "accept": false, - "reason": "Whisper return_language pipeline behavior is unrelated to GPT-OSS MXFP4 quantization fallback." + "reason": "Whisper `return_language` pipeline regression and GPT-OSS MXFP4 quantization fallback are unrelated." }, { "left": "issue:43425", "right": "issue:43716", "accept": false, - "reason": "Torch 2.10 incompatibility is distinct from a Mistral image preprocessor/model dtype mismatch." + "reason": "General torch compatibility and Mistral image dtype mismatch are different bugs." }, { "left": "issue:44530", "right": "issue:45084", "accept": false, - "reason": "PagedAttentionCache linear_attention crash and compile-time non-template-node error are unrelated." + "reason": "`PagedAttentionCache` group-type crash and template compilation failure are separate code paths." }, { "left": "issue:43901", "right": "issue:44509", "accept": false, - "reason": "Both are docs issues, but they document different removed/deprecated pipeline behaviors." + "reason": "Both are docs issues, but they cover different pipeline/task deprecations and are not duplicates." }, { "left": "issue:43299", "right": "issue:43931", "accept": false, - "reason": "Both involve Qwen3-VL, but one is a MoE loading regression and the other is a checkpoint shape mismatch; too different to duplicate." + "reason": "Both mention Qwen3-VL-related loading, but one is a general MoE loading breakage and the other is a checkpoint shape mismatch; too different to merge." }, { "left": "issue:44265", "right": "issue:44898", "accept": false, - "reason": "torch.export failures with torch_compilable_check are unrelated to Perceiver non-default-resolution loading." + "reason": "Torch export with `torch_compilable_check` and Perceiver interpolation failure are unrelated." }, { "left": "issue:44479", "right": "issue:44805", "accept": false, - "reason": "Video-input regression and mask-shape IndexError are different execution paths and error classes." + "reason": "Video-input regression and mask shape mismatch are not the same underlying bug." }, { "left": "issue:43994", "right": "issue:44079", "accept": false, - "reason": "Siglip2 producing bad outputs is unrelated to `ModelOutput` key assignment when values were previously None." + "reason": "Nonsensical model outputs and `ModelOutput` key assignment with `None` are unrelated." }, { "left": "issue:44671", "right": "issue:44991", "accept": false, - "reason": "CamemBERT prediction correctness and tokenizer loading for EMBEDDIA/est-roberta are separate problems." + "reason": "CamemBERT masked-LM prediction errors and tokenizer loading failure are different issues." }, { "left": "issue:43856", "right": "issue:44756", "accept": false, - "reason": "Memory inefficiency in Qwen3 MoE training is not the same as disabling mmap to avoid OOM on Strix Halo." + "reason": "Training memory inefficiency and Strix Halo mmap OOM are separate performance/memory problems." }, { - "left": "issue:39404", - "right": "issue:44671", + "left": "issue:43425", + "right": "issue:44918", "accept": false, - "reason": "Whisper pipeline language return and CamemBERT masked-LM predictions are unrelated model-specific issues." + "reason": "Torch version compatibility and Qwen3.5 embedding unpacking are different failure modes." }, { - "left": "issue:43596", - "right": "issue:44683", + "left": "issue:39404", + "right": "issue:44671", "accept": false, - "reason": "Deepspeed ZeRO3 initialization index error and compiled flex_attention failure on newer torch versions are different bugs." + "reason": "Whisper pipeline behavior and CamemBERT MLM outputs are unrelated." }, { - "left": "issue:43425", - "right": "issue:44918", + "left": "issue:40990", + "right": "issue:42947", "accept": false, - "reason": "Torch 2.10 incompatibility is unrelated to Qwen3.5 embedding unpacking with TRL SFT trainer." + "reason": "High perplexity on a model and gradient checkpointing not taking effect are distinct issues." }, { - "left": "issue:40990", - "right": "issue:42947", + "left": "issue:43596", + "right": "issue:44683", "accept": false, - "reason": "High perplexity on gpt-oss and ineffective gradient checkpointing with LoRA are not the same underlying issue." + "reason": "DeepSpeed zero3 init index error and compiled flex_attention failure on newer torch versions are unrelated." }, { "left": "issue:44589", "right": "issue:45084", "accept": false, - "reason": "Float8 storage resolution failure and compiler rejection of non-template nodes are unrelated." + "reason": "Missing Float8 storage and template-node compilation errors are different bugs." }, { "left": "issue:36032", "right": "issue:43452", "accept": false, - "reason": "T5 tokenizer special-token method conflicts and gguf_file loading failures are distinct tokenizer/model-loading bugs." - }, - { - "left": "issue:32090", - "right": "issue:39404", - "accept": false, - "reason": "Trainer GPU broadcast TypeError and Whisper return_language pipeline regression are unrelated." + "reason": "Tokenizer special-token method conflict and `gguf_file` loading breakage are not the same problem." }, { "left": "issue:43582", "right": "issue:43632", "accept": false, - "reason": "Apple Silicon allocator warmup TypeError is not the same as the `_is_hf_initialized` flag breakage." + "reason": "Apple Silicon warmup TypeError and `_is_hf_initialized` flag breakage are different runtime issues." }, { "left": "issue:44991", "right": "issue:45081", "accept": false, - "reason": "Tokenizer load failure for EMBEDDIA/est-roberta and Mistral regex-patch backend_tokenizer crash are different tokenizer code paths." + "reason": "Tokenizer loading failure and `_patch_mistral_regex` backend-tokenizer crash are related to tokenizers, but they are different concrete failures." + }, + { + "left": "issue:32090", + "right": "issue:39404", + "accept": false, + "reason": "Trainer GPU broadcast `NoneType` error and Whisper `return_language` regression are unrelated." }, { "left": "issue:43957", "right": "issue:44164", "accept": false, - "reason": "Meta-device loading failures and save/from_pretrained extra_state handling are separate mechanisms." + "reason": "Meta-device loading and `extra_state` save/load are separate mechanisms." }, { "left": "issue:40990", "right": "issue:43421", "accept": false, - "reason": "GPT-OSS perplexity regression and runtime special-token post-processor update bug are unrelated." + "reason": "Perplexity regression and runtime special-token post-processor update are unrelated." + }, + { + "left": "issue:43883", + "right": "issue:44488", + "accept": false, + "reason": "Missing `all_tied_weights_keys` and inability to load a specific BERT checkpoint are different issues." }, { "left": "issue:44164", "right": "issue:44479", "accept": false, - "reason": "extra_state save/load handling is unrelated to the Qwen VL video-input regression." + "reason": "`extra_state` serialization and video-input regression are unrelated." }, { "left": "issue:44488", "right": "issue:45081", "accept": false, - "reason": "Loading `cjvt/sleng-bert` and patching Mistral regex are different tokenizer-loading failures." - }, - { - "left": "issue:43883", - "right": "issue:44488", - "accept": false, - "reason": "Missing `all_tied_weights_keys` on MolmoForCausalLM is unrelated to the sleng-bert tokenizer load problem." + "reason": "Both involve loading/tokenizer behavior, but one is a model-loading failure and the other is a tokenizer regex patch crash; not the same bug." }, { "left": "issue:43425", "right": "issue:45161", "accept": false, - "reason": "Torch 2.10 incompatibility and GPT-OSS MoE tensor-parallel failure are distinct issues." + "reason": "Torch compatibility and GPT-OSS tensor-parallel loading are different problems." }, { "left": "issue:43611", "right": "issue:43644", "accept": false, - "reason": "Both are Transformers 5 regressions, but one is custom model loading via `base_model_prefix` and the other is non-persistent buffer initialization; related but not duplicate." - }, - { - "left": "issue:44811", - "right": "issue:45584", - "accept": false, - "reason": "Ignoring `skip_special_tokens` in batch_decode and failing on empty transcription after align_special_tokens are close Whisper-processing reports, but they target different symptoms and likely different code paths." + "reason": "Both are v5 model-loading regressions, but they target different failures: `base_model_prefix` loading vs non-persistent buffer initialization." } ] }, @@ -2294,7 +2317,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:34567", "issue:36032", @@ -2313,7 +2336,6 @@ "issue:43540", "issue:43541", "issue:43582", - "issue:43632", "issue:43643", "issue:43644", "issue:43645", @@ -2334,21 +2356,23 @@ "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:45507", + "issue:45584" ], "soft_pairs": [ + "issue:44811|issue:45584", "issue:44206|issue:44220", - "issue:42947|issue:44756", "issue:44488|issue:44987", + "issue:42947|issue:44756", "issue:43716|issue:45084", "issue:34567|issue:40444", "issue:43883|issue:44991", @@ -2357,264 +2381,256 @@ "issue:43452|issue:43482", "issue:44451|issue:44987", "issue:43317|issue:43482", - "issue:43541|issue:45084", "issue:36032|issue:42915", - "issue:44849|issue:45325", + "issue:43541|issue:45084", "issue:39404|issue:43825", + "issue:44849|issue:45325", "issue:42915|issue:44530", "issue:43404|issue:44466", "issue:43262|issue:43377", "issue:36032|issue:43645", "issue:44987|issue:44991", - "issue:45084|issue:45507", "issue:43646|issue:44534", + "issue:45084|issue:45507", "issue:43994|issue:44610", - "issue:45216|issue:45357", "issue:43645|issue:44534", + "issue:45216|issue:45357", "issue:43322|issue:43540", - "issue:44403|issue:45081", "issue:43377|issue:43819", + "issue:44403|issue:45081", "issue:44451|issue:45081", "issue:41553|issue:43582", - "issue:44220|issue:44683", - "issue:43632|issue:44756", - "issue:43404|issue:45127" + "issue:44220|issue:44683" ], - "prepared_review_unit_hash": "d4d63c46d6f509e737748b75d47e5520920fef43203898f0c80cab1df0409e8d", + "prepared_review_unit_hash": "f862802ba83fc25a8eb496eedd17212f4cf94f26fb57cef28ecbbfbc2e1ae789", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 33, - "serialized_chars": 37546, - "estimated_input_tokens": 9387, - "estimated_eval_tokens": 19030 + "soft_pair_count": 32, + "serialized_chars": 37202, + "estimated_input_tokens": 9301, + "estimated_eval_tokens": 18858 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly a heterogeneous set of Transformers issues. The supported duplicate pairs are the audio fbank extraction reports (44206\u219444220) and the Qwen3.5 save_pretrained serialization regression (45216\u219445357). The non-persistent-buffer/custom-init items do not rise to the same duplicate level.", - "confidence": 0.91, - "canonical_issue_reason": "Issue 45216 is the clearest canonical anchor among the supported duplicates: 45357 points to the same Qwen3.5 save_pretrained serialization path and regression shape.", + "summary": "Mostly a heterogeneous cluster of unrelated Transformers regressions; only a couple of pairs look like true duplicates, centered on GGUF loading and Qwen3.5 save_pretrained serialization.", + "confidence": 0.67, + "canonical_issue_reason": "Issue 45216 is the cleanest anchor: it states the Qwen3.5 save_pretrained regression directly, and 45357 reads like a follow-up/variant of the same checkpoint-serialization bug.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45216 is the strongest issue representative overall because it is a precise, regression-framed bug with a direct same-path duplicate in 45357.", + "best_issue_reason": "45216 is the best representative issue because it is concrete, specific to the underlying regression, and has the clearest near-duplicate in 45357.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44206", - "right": "issue:44220", - "accept": true, - "reason": "Same audio feature-extraction failure around `_torch_extract_fbank_features` / fbank handling." + "left": "issue:44811", + "right": "issue:45584", + "accept": false, + "reason": "Both are Whisper-related, but one is about batch_decode skip_special_tokens handling and the other about empty-transcription generation after align_special_tokens; different failure modes." }, { - "left": "issue:42947", - "right": "issue:44756", + "left": "issue:44206", + "right": "issue:44220", "accept": false, - "reason": "Different problems: LoRA/gradient checkpointing vs Apple/Strix Halo mmap OOM." + "reason": "Both touch audio feature extraction, but the titles point to different bugs: an unsupported center argument vs a separate _torch_extract_fbank_features() issue." }, { "left": "issue:44488", "right": "issue:44987", "accept": false, - "reason": "Both are load failures, but for different models and likely different regressions." + "reason": "Both are model-loading failures, but they affect different models and describe different regressions; too broad to be the same bug." + }, + { + "left": "issue:42947", + "right": "issue:44756", + "accept": false, + "reason": "Different areas entirely: LoRA/gradient checkpointing behavior vs Apple Silicon mmap/OOM handling." }, { "left": "issue:43716", "right": "issue:45084", "accept": false, - "reason": "Unrelated: image preprocessor dtype mismatch vs template compilation error." + "reason": "Mistral image dtype mismatch is unrelated to a template compilation TypeError." }, { "left": "issue:34567", "right": "issue:40444", "accept": false, - "reason": "Trainer token-count tracking bug is unrelated to Qwen2.5-VL iterable dataset failure." + "reason": "TrainerState token counting and Qwen2.5-VL multi-image IterableDataset failures are unrelated." }, { "left": "issue:43883", "right": "issue:44991", "accept": false, - "reason": "Different tokenizer/model loading issues; no clear shared code-path bug." + "reason": "Different model/tokenizer-loading regressions with different root symptoms; not the same concrete bug." }, { "left": "issue:43644", "right": "issue:43646", "accept": false, - "reason": "Close in wording, but one is junk non-persistent buffers and the other is custom model init breakage." + "reason": "Both are v5 regression reports, but one is about non-persistent buffers and the other about custom model initialization; too generic to merge." }, { "left": "issue:43643", "right": "issue:44530", "accept": false, - "reason": "Config round-tripping issue is unrelated to PagedAttentionCache / linear_attention crash." + "reason": "AutoConfig trust_remote_code field loss is unrelated to Qwen3.5 PagedAttentionCache crashes." }, { "left": "issue:43452", "right": "issue:43482", - "accept": false, - "reason": "Both involve GGUF loading, but one is a generic API break and the other is a Qwen2.5-specific failure; not enough evidence they are the same bug." + "accept": true, + "reason": "Both point to the same GGUF/from_pretrained loading regression in the v5 loader path; one is the generic API break, the other a specific Qwen2.5-GGUF manifestation." }, { "left": "issue:44451", "right": "issue:44987", "accept": false, - "reason": "Different model-specific loading failures; same broad theme is too weak." + "reason": "Both are loading failures, but they are for different repositories/models and do not indicate the same code-path bug." }, { "left": "issue:43317", "right": "issue:43482", "accept": false, - "reason": "Dequantized offload load failure is unrelated to GGUF loading regression." - }, - { - "left": "issue:43541", - "right": "issue:45084", - "accept": false, - "reason": "Torch dynamo tracing error is unrelated to template compilation error." + "reason": "Device-map offload/dequantized-model loading is a different failure mode from GGUF loading in v5." }, { "left": "issue:36032", "right": "issue:42915", "accept": false, - "reason": "Tokenizer method conflict vs FineGrainedFP8Config failure are unrelated." + "reason": "T5 tokenizer special-token method conflict and Qwen3Moe FineGrainedFP8Config failure are unrelated." }, { - "left": "issue:44849", - "right": "issue:45325", + "left": "issue:43541", + "right": "issue:45084", "accept": false, - "reason": "Different Qwen variants and different bugs: hidden states vs rope/position id scaling." + "reason": "Torch Dynamo grouped_mm tracing failure is unrelated to the template-node compilation error." }, { "left": "issue:39404", "right": "issue:43825", "accept": false, - "reason": "One is a Whisper pipeline regression; the other is only a bad error message for translation support." + "reason": "Both involve pipeline behavior, but one is a Whisper return_language regression and the other is an error-message/docs issue about translation support." + }, + { + "left": "issue:44849", + "right": "issue:45325", + "accept": false, + "reason": "Different Qwen model families and different bugs: hidden-states output vs rope index scaling." }, { "left": "issue:42915", "right": "issue:44530", "accept": false, - "reason": "Different Qwen3Moe/Qwen3.5 failures with different code paths and symptoms." + "reason": "Qwen3Moe FP8 configuration failure and Qwen3.5 PagedAttentionCache linear_attention crash are different issues." }, { "left": "issue:43404", "right": "issue:44466", "accept": false, - "reason": "Both mention tied weights, but one is a missing tie in Mistral3 loading and the other is device-dependent save_pretrained serialization." + "reason": "Both concern tied weights, but one is an untied lm_head bug in Mistral3ForConditionalGeneration and the other is a device-dependent save_pretrained serialization issue." }, { "left": "issue:43262", "right": "issue:43377", "accept": false, - "reason": "Audio chat-template sampling-rate default is unrelated to MIMI batch padding-mask mismatch." + "reason": "Audio chat-template sampling-rate defaults and MIMI padding-mask batching differences are separate bugs." }, { "left": "issue:36032", "right": "issue:43645", "accept": false, - "reason": "Tokenizer constructor conflict and custom model init in notebooks are different issues." + "reason": "Tokenizer method conflict and custom model initialization in notebooks are not the same bug." }, { "left": "issue:44987", "right": "issue:44991", "accept": false, - "reason": "Different model/tokenizer load failures; same version range is not enough to merge." + "reason": "Both are tokenizer/model loading regressions, but they affect different models and likely different loader paths." }, { - "left": "issue:45084", - "right": "issue:45507", + "left": "issue:43646", + "right": "issue:44534", "accept": false, - "reason": "Template compilation error is unrelated to GraniteMoE invalid method calls." + "reason": "Custom model initialization and non-persistent buffer junk are related by theme, but the titles describe different concrete regressions." }, { - "left": "issue:43646", - "right": "issue:44534", + "left": "issue:45084", + "right": "issue:45507", "accept": false, - "reason": "General custom model initialization breakage is not the same as non-persistent buffer corruption." + "reason": "Template compilation failure and GraniteMoEHybrid invalid-method calls are unrelated." }, { "left": "issue:43994", "right": "issue:44610", "accept": false, - "reason": "Siglip2 bad outputs and OmDet-Turbo size mismatch are unrelated multimodal bugs." - }, - { - "left": "issue:45216", - "right": "issue:45357", - "accept": true, - "reason": "Same Qwen3.5 save_pretrained regression: incorrect checkpoint serialization / visual encoder keys in the same code path." + "reason": "Both involve model/processor mismatch, but they are for different models and different preprocessing expectations." }, { "left": "issue:43645", "right": "issue:44534", "accept": false, - "reason": "Jupyter custom-model init regression is not the same bug as junk non-persistent buffers." + "reason": "Custom notebook model initialization and v5 non-persistent buffer junk are not the same concrete bug." + }, + { + "left": "issue:45216", + "right": "issue:45357", + "accept": true, + "reason": "Same Qwen3.5 save_pretrained regression: both report incorrect checkpoint serialization, with 45357 narrowing it to visual encoder keys." }, { "left": "issue:43322", "right": "issue:43540", "accept": false, - "reason": "Segmentation fault on Llava Next loading is unrelated to Qwen3OmniMoe video-processing ValueError." + "reason": "Llava Next loading segfault and Qwen3OmniMoe video-input ValueError are different model-specific failures." }, { - "left": "issue:44403", - "right": "issue:45081", + "left": "issue:43377", + "right": "issue:43819", "accept": false, - "reason": "Loading-noise UX issue is unrelated to the Mistral regex patch crash." + "reason": "MIMI batch-vs-single padding-mask discrepancy is unrelated to DAC.from_latents missing STE behavior." }, { - "left": "issue:43377", - "right": "issue:43819", + "left": "issue:44403", + "right": "issue:45081", "accept": false, - "reason": "MIMI padding-mask batching bug is unrelated to DAC from_latents/STE mismatch." + "reason": "Generic loading noise and a Mistral regex patch AttributeError are different issues." }, { "left": "issue:44451", "right": "issue:45081", "accept": false, - "reason": "Different failures: ScandiBERT load regression vs Mistral regex patch crash." + "reason": "Different model-loading failures with no shared concrete bug path." }, { "left": "issue:41553", "right": "issue:43582", "accept": false, - "reason": "Bad AutoTokenizer error for Voxtral is unrelated to Apple Silicon allocator TypeError." + "reason": "Bad AutoTokenizer error message for Voxtral and Apple Silicon caching_allocator_warmup TypeError are unrelated." }, { "left": "issue:44220", "right": "issue:44683", "accept": false, - "reason": "Audio fbank extraction bug is unrelated to compiled flex_attention on torch>=2.9." - }, - { - "left": "issue:43632", - "right": "issue:44756", - "accept": false, - "reason": "_is_hf_initialized flag regression is unrelated to mmap OOM on Strix Halo." - }, - { - "left": "issue:43404", - "right": "issue:45127", - "accept": false, - "reason": "Tied lm_head weights bug and LoRA merge collapse with extended vocab are different code paths." + "reason": "Audio fbank feature extraction and compiled flex_attention on torch>=2.9 are unrelated." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The output is mostly conservative, but the summary overstates the evidence by presenting \u201cnon-persistent buffers during v5 init\u201d as a tight duplicate pair. In the packet, the related soft-edge verdicts for 43644\u219443646 and 43646\u219444534 were both rejected, so that cluster is not actually supported at the same level as the accepted audio and Qwen3.5 save_pretrained pairs. The summary should stay closer to the supported pairs only." + "accept": true, + "feedback": "The cluster summary is grounded in the packet and stays conservative. The two accepted pairs are well supported by their titles alone: 43452/43482 both point to the same GGUF/v5 loading regression, and 45216/45357 both describe the same Qwen3.5 save_pretrained serialization bug. The remaining pairwise rejections avoid overclaiming and generally distinguish different models or failure modes appropriately." }, "evaluator_used": true, - "retried": true, + "retried": false, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -2630,7 +2646,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:33666", "issue:35707", @@ -2642,11 +2658,10 @@ "issue:42915", "issue:43296", "issue:43317", - "issue:43377", + "issue:43404", "issue:43421", "issue:43425", "issue:43482", - "issue:43525", "issue:43531", "issue:43611", "issue:43632", @@ -2665,286 +2680,269 @@ "issue:44589", "issue:44610", "issue:44683", + "issue:44756", "issue:44811", "issue:44829", "issue:44877", "issue:44987", "issue:44991", "issue:45020", - "issue:45072", "issue:45081", "issue:45084", + "issue:45127", "issue:45325", "issue:45357", "issue:45479", - "issue:45491", "issue:45538", "issue:45542" ], "soft_pairs": [ + "issue:43632|issue:44756", "issue:44265|issue:44610", + "issue:43404|issue:45127", "issue:42915|issue:45084", "issue:44987|issue:45081", - "issue:44479|issue:45325", "issue:43296|issue:43531", + "issue:44479|issue:45325", "issue:44062|issue:44987", - "issue:42175|issue:45542", "issue:42915|issue:44291", + "issue:40990|issue:44811", + "issue:42175|issue:45542", "issue:43317|issue:43856", "issue:43611|issue:44534", - "issue:40990|issue:44811", "issue:36032|issue:43742", "issue:40444|issue:45325", "issue:43632|issue:44534", - "issue:43818|issue:45357", "issue:43421|issue:44568", - "issue:43531|issue:44877", + "issue:43818|issue:45357", "issue:42915|issue:44589", - "issue:44683|issue:45020", - "issue:43482|issue:45538", + "issue:43531|issue:44877", "issue:36032|issue:41720", + "issue:44683|issue:45020", "issue:43425|issue:44403", + "issue:43482|issue:45538", "issue:44829|issue:45479", "issue:33666|issue:40444", "issue:44403|issue:44991", "issue:43792|issue:44589", - "issue:43377|issue:45491", "issue:44079|issue:44534", - "issue:35707|issue:40444", - "issue:43482|issue:43525", - "issue:44291|issue:44589", - "issue:44079|issue:45072" + "issue:35707|issue:40444" ], - "prepared_review_unit_hash": "f402fff550fa03442a65ade2005174df85262d9ad224225cecf570217870578f", + "prepared_review_unit_hash": "d7ffc5c6c082c02c1c6e3fd7228f2baa7b9c0bb8dfe5b48c0d0dbe0f87802dba", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 32, - "serialized_chars": 37370, - "estimated_input_tokens": 9343, - "estimated_eval_tokens": 18942 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36158, + "estimated_input_tokens": 9040, + "estimated_eval_tokens": 18336 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly a grab bag of unrelated Transformers issues across models, tokenizers, loading, and training. One soft duplicate candidate stands out around Qwen VL temporal-position / rope-index handling in v5.3.0, but the rest are not close duplicates.", - "confidence": 0.43, - "canonical_issue_reason": "issue:45020 is the broadest open tracker here: it captures a general recent-transformers regression affecting model loading/remote_code, which makes it the safest representative for this mixed set of issue reports.", + "summary": "This set is highly heterogeneous: the suggested pairs share at most broad subsystem vocabulary (tokenizers, Qwen, v5, FP8, etc.) but not the same concrete bug or code path. I don\u2019t see a true duplicate cluster here, so no canonical issue/PR stands out.", + "confidence": 0.96, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:45020 is the best global anchor because it is broad, open, and closer to a cluster-level regression theme than the many narrow model-specific reports.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43632", + "right": "issue:44756", + "accept": false, + "reason": "Different problems: HF init flag regression vs Strix Halo mmap/OOM handling." + }, { "left": "issue:44265", "right": "issue:44610", "accept": false, - "reason": "Different failures: torch.export/torch_compilable_check versus OmDet-Turbo processor image-size mismatch." + "reason": "torch.export/torch_compilable_check is unrelated to OmDet-Turbo input-size mismatch." + }, + { + "left": "issue:43404", + "right": "issue:45127", + "accept": false, + "reason": "Both mention weight tying, but one is missing tie in Mistral3 and the other is LoRA merge collapse; different bugs." }, { "left": "issue:42915", "right": "issue:45084", "accept": false, - "reason": "Unrelated bugs: Qwen3Moe FP8 config failure versus a template-node compilation error." + "reason": "Qwen3Moe FP8 config failure and template-node compilation error are unrelated failure modes." }, { "left": "issue:44987", "right": "issue:45081", "accept": false, - "reason": "Both are loading regressions, but one is broad remote_code breakage and the other is a specific Mistral tokenizer regex/backend_tokenizer crash." - }, - { - "left": "issue:44479", - "right": "issue:45325", - "accept": true, - "reason": "Both point to the same Qwen VL temporal-position / rope-index regression in transformers 5.3.0, with 45325 looking like a specific manifestation of the broader 44479 bug." + "reason": "Different models and code paths: physical-intelligence/fast loading vs Mistral regex patch tokenizer crash." }, { "left": "issue:43296", "right": "issue:43531", "accept": false, - "reason": "Different Qwen models and different symptoms: PaddleOCR-VL load failure versus Qwen3-MoE sliding-window behavior." + "reason": "PaddleOCR-VL load failure and Qwen3-MoE sliding_window bug are unrelated." }, { - "left": "issue:44062", - "right": "issue:44987", + "left": "issue:44479", + "right": "issue:45325", "accept": false, - "reason": "Tokenizer AddedToken argument conflict is unrelated to remote_code loading failures." + "reason": "Both are Qwen VL regressions, but one is a broad video-input regression and the other is a specific still-image RoPE scaling bug." }, { - "left": "issue:42175", - "right": "issue:45542", + "left": "issue:44062", + "right": "issue:44987", "accept": false, - "reason": "Both mention TF packaging, but one is missing TensorFlow in the torch extra and the other is a backend-selection error from tensorboard-only installs." + "reason": "AddedToken special-argument conflict is a tokenizer API bug, not the same as the physical-intelligence/fast loading failure." }, { "left": "issue:42915", "right": "issue:44291", "accept": false, - "reason": "Same broad loading area, but different concrete problems: FP8 config handling versus init_empty_weights/_is_hf_initialized." + "reason": "Both involve loading in v5, but FP8 config failure and _is_hf_initialized/init_empty_weights TypeError are distinct issues." + }, + { + "left": "issue:40990", + "right": "issue:44811", + "accept": false, + "reason": "Perplexity evaluation issue is unrelated to Whisper batch_decode skip_special_tokens behavior." + }, + { + "left": "issue:42175", + "right": "issue:45542", + "accept": false, + "reason": "Both concern TensorFlow packaging, but one is missing tf backend in torch extra and the other is a tensorboard-only backend error." }, { "left": "issue:43317", "right": "issue:43856", "accept": false, - "reason": "Device-map/offload loading failure and Qwen3 MoE training memory usage are not the same bug." + "reason": "GPU/CPU offload loading failure and Qwen3 MoE memory inefficiency are different problems." }, { "left": "issue:43611", "right": "issue:44534", "accept": false, - "reason": "Both are Transformers v5 regressions, but the underlying issues differ: base_model_prefix loading versus non-persistent buffer initialization." - }, - { - "left": "issue:40990", - "right": "issue:44811", - "accept": false, - "reason": "Completely different domains: perplexity evaluation versus Whisper batch_decode special-token handling." + "reason": "Both are v5 regressions, but base_model_prefix loading and non-persistent buffer corruption are separate code paths." }, { "left": "issue:36032", "right": "issue:43742", "accept": false, - "reason": "Different tokenizer/model loading failures with different error paths and model families." + "reason": "Tokenizer special-token conflict and MobileLLM-125M key error are unrelated load failures." }, { "left": "issue:40444", "right": "issue:45325", "accept": false, - "reason": "Both involve Qwen VL image/video handling, but one is multi-image finetuning and the other is a temporal-position scaling regression." + "reason": "Different Qwen2.5-VL bugs: multi-image iterable finetuning vs RoPE temporal-position scaling." }, { "left": "issue:43632", "right": "issue:44534", "accept": false, - "reason": "Related to Transformers v5 initialization, but the specific flag breakage and buffer corruption are distinct bugs." - }, - { - "left": "issue:43818", - "right": "issue:45357", - "accept": false, - "reason": "Video-LLaVA model architecture corruption and Qwen3.5 save_pretrained key regression are unrelated." + "reason": "HF initialization flag regression is not the same as junk-filled non-persistent buffers." }, { "left": "issue:43421", "right": "issue:44568", "accept": false, - "reason": "Both concern special tokens, but one is runtime post-processor refresh and the other is a tokenizer-specific add_special_tokens regression." + "reason": "Special-token runtime update bug and mdeberta-v3 BOS/EOS insertion bug are related only superficially." }, { - "left": "issue:43531", - "right": "issue:44877", + "left": "issue:43818", + "right": "issue:45357", "accept": false, - "reason": "Qwen3-MoE sliding-window behavior and granite_speech config strictness are unrelated." + "reason": "Video-LLaVA weight/temporal-attention issue is unrelated to Qwen3.5 save_pretrained key mismatch." }, { "left": "issue:42915", "right": "issue:44589", "accept": false, - "reason": "Qwen3Moe FP8 config failure is unrelated to missing Float8 storage registration." + "reason": "FP8 config failure and missing Float8 storage type are different FP8-related bugs, not the same defect." }, { - "left": "issue:44683", - "right": "issue:45020", + "left": "issue:43531", + "right": "issue:44877", "accept": false, - "reason": "Compiled flex_attention on torch>=2.9 is a distinct lower-level attention/torch compatibility issue from remote_code loading regressions." + "reason": "Qwen3-MoE sliding_window bug and granite_speech strict-config loading are unrelated." }, { - "left": "issue:43482", - "right": "issue:45538", + "left": "issue:36032", + "right": "issue:41720", "accept": false, - "reason": "GGUF loading under v5 and CLIPTokenizer model_max_length are unrelated tokenizer/model issues." + "reason": "Tokenizer load conflict and Qwen3 auto device-map cuda assert are unrelated." }, { - "left": "issue:36032", - "right": "issue:41720", + "left": "issue:44683", + "right": "issue:45020", "accept": false, - "reason": "T5 tokenizer init error and Qwen3 auto device-map cudaErrorAssert are different failures." + "reason": "Compiled flex_attention on torch>=2.9 and remote_code loading regressions are different areas." }, { "left": "issue:43425", "right": "issue:44403", "accept": false, - "reason": "Torch version compatibility and noisy transformer loading logs are unrelated." + "reason": "Torch version incompatibility is not the same as noisy transformer loading." + }, + { + "left": "issue:43482", + "right": "issue:45538", + "accept": false, + "reason": "Qwen2.5-GGUF/v5 loading failure and CLIPTokenizer max_length bug are unrelated." }, { "left": "issue:44829", "right": "issue:45479", "accept": false, - "reason": "Both are sequence-classification training problems, but one is flash_attention_3-specific and the other is the num_labels=1 loss edge case." + "reason": "Both involve bad training behavior, but flash_attention_3 degeneration and single-label/num_labels=1 zero-loss are distinct causes." }, { "left": "issue:33666", "right": "issue:40444", "accept": false, - "reason": "Different Qwen VL training scenarios; multi-GPU training is not the same as multi-image iterable dataset failure." + "reason": "Same broad family (Qwen VL training), but multi-GPU training and multi-image iterable finetuning are not the same bug." }, { "left": "issue:44403", "right": "issue:44991", "accept": false, - "reason": "Logging noise on load is not the same as tokenizer load failure for EMBEDDIA/est-roberta." + "reason": "Unnecessary load noise and tokenizer load failure for est-roberta are different issues." }, { "left": "issue:43792", "right": "issue:44589", "accept": false, - "reason": "Whisper runtime failure and Float8 storage lookup error are unrelated." - }, - { - "left": "issue:43377", - "right": "issue:45491", - "accept": false, - "reason": "Both involve batch-vs-single discrepancies, but one is MIMI padding-mask support and the other is Gemma3 sliding-window/all-padding NaNs; too different to merge." + "reason": "Whisper runtime failure and missing Float8 storage object are unrelated." }, { "left": "issue:44079", - "right": "issue:45072", + "right": "issue:44534", "accept": false, - "reason": "ModelOutput key assignment and dtype mismatches are unrelated." + "reason": "ModelOutput key assignment and non-persistent buffer corruption are different internal bugs." }, { "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:43482", - "right": "issue:43525", - "accept": false, - "reason": "GGUF loading failure and missing pad_token_id on Llama4Config are different issues." - }, - { - "left": "issue:44291", - "right": "issue:44589", - "accept": false, - "reason": "Unexpected _is_hf_initialized argument in init_empty_weights is unrelated to missing Float8 storage." - }, - { - "left": "issue:44079", - "right": "issue:45072", - "accept": false, - "reason": "ModelOutput key bookkeeping and bfloat16 dtype mismatches are not the same bug." + "reason": "Progressive generation with inputs_embeds/past_key_values is unrelated to Qwen2.5-VL multi-image dataset finetuning." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "Grounded in the packet and appropriately conservative overall. The canonical anchor choice of issue:45020 is defensible from its broad open title, and the one accepted soft pair (44479/45325) is a plausible Qwen VL regression link without overstating certainty. The other pair verdicts read as cautious and not overclaimed from the available evidence." - }, - "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 }, @@ -2959,7 +2957,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:34634", "issue:35707", @@ -2971,11 +2969,12 @@ "issue:43262", "issue:43296", "issue:43317", + "issue:43377", "issue:43454", "issue:43482", + "issue:43525", "issue:43526", "issue:43531", - "issue:43606", "issue:43611", "issue:43632", "issue:43644", @@ -2984,7 +2983,6 @@ "issue:43746", "issue:43749", "issue:43792", - "issue:43819", "issue:43828", "issue:43873", "issue:43881", @@ -2992,34 +2990,38 @@ "issue:43957", "issue:43994", "issue:44079", - "issue:44186", "issue:44265", "issue:44291", "issue:44387", "issue:44466", "issue:44488", + "issue:44589", "issue:44617", "issue:44683", - "issue:44877", "issue:44898", "issue:44991", "issue:45072", "issue:45081", "issue:45325", "issue:45381", + "issue:45491", "issue:45563", "issue:45584" ], "soft_pairs": [ + "issue:43377|issue:45491", + "issue:43482|issue:43525", + "issue:44291|issue:44589", "issue:43749|issue:44079", + "issue:44079|issue:45072", "issue:43644|issue:44079", "issue:43632|issue:45072", "issue:40444|issue:45381", "issue:44265|issue:45072", "issue:43881|issue:44488", "issue:45325|issue:45381", - "issue:43611|issue:43646", "issue:43531|issue:44291", + "issue:43611|issue:43646", "issue:41720|issue:45081", "issue:42175|issue:43296", "issue:43454|issue:44466", @@ -3035,214 +3037,210 @@ "issue:43881|issue:44991", "issue:43317|issue:43873", "issue:40990|issue:45584", - "issue:34634|issue:35707", - "issue:43606|issue:44265", - "issue:44291|issue:44877", - "issue:44186|issue:44265", - "issue:43606|issue:43819" + "issue:34634|issue:35707" ], - "prepared_review_unit_hash": "4f3b8297c0e986ac55926a14c236151abc731d22ecffebb8b128b3ac679a7ec5", + "prepared_review_unit_hash": "c22d20c078767bf7e4f2a00609c0508fbdd893e92cef0217ed7a6050c50b69b5", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 29, - "serialized_chars": 36332, - "estimated_input_tokens": 9083, - "estimated_eval_tokens": 18422 + "serialized_chars": 36393, + "estimated_input_tokens": 9099, + "estimated_eval_tokens": 18454 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly noisy: many issues touch Transformers v5/model-loading regressions, but the specific failure modes differ. No pull requests are present. The best canonical representative is the broad v5 initialization regression report.", - "confidence": 0.67, - "canonical_issue_reason": "issue:43632 is the broadest and most root-cause-like report in the v5 init/load regression subgroup, making it the best representative issue for this noisy cluster.", + "summary": "This cluster is mostly a loose thematic group of transformer-regression reports, not a set of true duplicates. The strongest center is around Transformers v5 loading/initialization regressions, but the paired items usually hit different code paths or model families.", + "confidence": 0.74, + "canonical_issue_reason": "Issue 43632 is the best representative because it captures a broad, core v5 initialization regression that can plausibly underlie several nearby loading bugs, while still being concrete and well-scoped.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43632 is the strongest global representative because it describes a central Transformers v5 initialization breakage that plausibly underlies several nearby load/init complaints.", + "best_issue_reason": "Issue 43632 is the best issue to keep as the cluster anchor: it is broad enough to represent the v5 loading/init breakage theme, but specific enough to remain actionable.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43377", + "right": "issue:45491", + "accept": false, + "reason": "Both mention sequence/batching behavior, but one is MIMI encoder padding-mask inconsistency and the other is Gemma3 sliding-window NaNs; different models and different failure mechanisms." + }, + { + "left": "issue:43482", + "right": "issue:43525", + "accept": false, + "reason": "Both are Transformers v5 load regressions, but one is GGUF loading and the other is a missing pad_token_id attribute on Llama4Config; distinct bugs." + }, + { + "left": "issue:44291", + "right": "issue:44589", + "accept": false, + "reason": "Both involve v5/init-loading breakage, but one is an unexpected _is_hf_initialized argument with init_empty_weights and the other is a missing Float8 storage type; not the same code path." + }, { "left": "issue:43749", "right": "issue:44079", "accept": false, - "reason": "FSDP CPU RAM efficient loading vs ModelOutput key assignment are unrelated bugs in different code paths." + "reason": "FSDP CPU RAM efficient loading and ModelOutput key assignment are unrelated behaviors; only a broad v5 context overlaps." + }, + { + "left": "issue:44079", + "right": "issue:45072", + "accept": false, + "reason": "ModelOutput key handling and CI dtype mismatches in SwitchTransformers/TimmWrapperModel are different bugs with different symptoms." }, { "left": "issue:43644", "right": "issue:44079", "accept": false, - "reason": "Non-persistent buffer initialization and ModelOutput field assignment do not describe the same failure." + "reason": "Non-persistent buffer serialization corruption is a separate state-dict/load issue from ModelOutput key assignment." }, { "left": "issue:43632", "right": "issue:45072", "accept": false, - "reason": "A broken _is_hf_initialized init path is not the same bug as bfloat16 dtype mismatches in inference." + "reason": "The _is_hf_initialized regression and bfloat16 dtype mismatches are different failures; they may both surface in v5 but not the same underlying bug." }, { "left": "issue:40444", "right": "issue:45381", "accept": false, - "reason": "Multi-image iterable finetuning failure and Qwen2.5-VL video position-id bug are different multimodal issues." + "reason": "One is multi-image iterable dataset finetuning for Qwen2.5-VL, the other is video vision_position_ids in Qwen2.5-VL; related model family but different input modality bug." }, { "left": "issue:44265", "right": "issue:45072", "accept": false, - "reason": "torch.export/exportability checks are unrelated to dtype mismatch failures during inference." + "reason": "torch.export.export with torch_compilable_check and inference dtype mismatches are unrelated issues." }, { "left": "issue:43881", "right": "issue:44488", "accept": false, - "reason": "glm-4v-9b load failure and sleng-bert tokenizer loading failure are different model-specific problems." + "reason": "GLM-4V load failure and cjvt/sleng-bert tokenizer/model load failure are unrelated model-specific loading problems." }, { "left": "issue:45325", "right": "issue:45381", "accept": false, - "reason": "Both concern Qwen2.5-VL position ids, but one is still-image scaling and the other is video input ordering; not the same concrete bug." + "reason": "Both are Qwen2.5-VL position-id bugs, but one is still-image temporal scaling and the other is video input vision_position_ids; related but distinct paths." }, { - "left": "issue:43611", - "right": "issue:43646", + "left": "issue:43531", + "right": "issue:44291", "accept": false, - "reason": "base_model_prefix loading regression and custom model initialization breakage are adjacent v5 symptoms, but not clearly one identical bug." + "reason": "Sliding_window behavior in Qwen3-MoE and init_empty_weights/_is_hf_initialized are different regression classes." }, { - "left": "issue:43531", - "right": "issue:44291", + "left": "issue:43611", + "right": "issue:43646", "accept": false, - "reason": "sliding_window behavior in Qwen3-MoE is a different code path from init_empty_weights/_is_hf_initialized loading errors." + "reason": "Base_model_prefix loading and custom model initialization are both v5 load/init regressions, but they are different concrete breakages." }, { "left": "issue:41720", "right": "issue:45081", "accept": false, - "reason": "device-map cudaErrorAssert on Qwen3 and Mistral tokenizer regex patch crash are unrelated." + "reason": "Qwen3 auto device mapping cudaErrorAssert and Mistral tokenizer regex patch crash are unrelated." }, { "left": "issue:42175", "right": "issue:43296", "accept": false, - "reason": "TensorFlow backend packaging and PaddleOCR-VL loading are unrelated." + "reason": "TensorFlow backend packaging and PaddleOCR-VL model loading are different issues with no shared failure path." }, { "left": "issue:43454", "right": "issue:44466", "accept": false, - "reason": "AyaVision weight-tying failure and lm_head serialization inconsistency are related to weights but not the same bug." + "reason": "AyaVision lm_head weight tying and inconsistent lm_head.weight serialization are both weight-tying related, but one is a missing tie and the other is device-dependent serialization behavior." }, { "left": "issue:43994", "right": "issue:44898", "accept": false, - "reason": "SigLIP2 nonsensical outputs and Perceiver non-default resolution failure are different vision-model issues." + "reason": "SigLIP2 nonsensical pipeline output and Perceiver non-default resolution failure are different model-specific inference issues." }, { "left": "issue:44387", "right": "issue:44617", "accept": false, - "reason": "int4 CUDA memory growth and Sam3Video OOM are different memory-pressure issues with different triggers." + "reason": "Int4 quantization memory regression and Sam3Video OOM are both memory-related, but the causes and affected code paths differ." }, { "left": "issue:43828", "right": "issue:44683", "accept": false, - "reason": "autocast dtype mismatch in Phi-tiny-MoE is unrelated to compiled flex_attention failing on torch>=2.9." + "reason": "torch.autocast dtype mismatch in Phi-tiny-MoE is unrelated to compiled flex_attention failures on torch >= 2.9." }, { "left": "issue:42915", "right": "issue:43482", "accept": false, - "reason": "Qwen3Moe FP8 config failure and Qwen2.5-GGUF loading under v5 are different model/config issues." + "reason": "Qwen3Moe FP8 config failure and Qwen2.5-GGUF loading failure are different model/loading paths." }, { "left": "issue:43526", "right": "issue:43883", "accept": false, - "reason": "BeitImageProcessorFast label reduction and Molmo missing all_tied_weights_keys are unrelated." + "reason": "BeitImageProcessorFast label reduction and Molmo all_tied_weights_keys are unrelated issues." }, { "left": "issue:43792", "right": "issue:43957", "accept": false, - "reason": "Whisper runtime failure and meta-device loading regressions are different failure modes." + "reason": "Whisper large-v2 runtime failure and meta-device loading regressions on transformers 5 are separate problems." }, { "left": "issue:43701", "right": "issue:45325", "accept": false, - "reason": "resume_from_checkpoint key mismatch is unrelated to Qwen2.5-VL rope index scaling." + "reason": "Checkpoint key mismatch during resume and Qwen2.5-VL rope-index scaling are unrelated bugs." }, { "left": "issue:43262", "right": "issue:43746", "accept": false, - "reason": "Audio chat-template sampling-rate defaulting and GraniteSpeech PEFT checkpoint loading are different audio/model-loading bugs." + "reason": "Audio chat-template sample-rate defaulting and GraniteSpeech PEFT local checkpoint loading are different audio/model-loading issues." }, { "left": "issue:43632", "right": "issue:45563", "accept": false, - "reason": "_is_hf_initialized regression and paged generate warning behavior are unrelated." + "reason": "_is_hf_initialized regression and stale paged generate warning are not the same bug." }, { "left": "issue:43881", "right": "issue:44991", "accept": false, - "reason": "glm-4v-9b loading failure and tokenizer loading for EMBEDDIA/est-roberta are different model/tokenizer issues." + "reason": "GLM-4V loading failure and tokenizer loading failure for EMBEDDIA/est-roberta are distinct model/tokenizer regressions." }, { "left": "issue:43317", "right": "issue:43873", "accept": false, - "reason": "device_map auto dequantized-model offload failure and quantization offloading behavior are only broadly related, not the same concrete bug." + "reason": "gpu+cpu offload failing for dequantized models and offloading with quantization not working are related only at a high level; the concrete failure modes differ." }, { "left": "issue:40990", "right": "issue:45584", "accept": false, - "reason": "high perplexity on gpt-oss-20b and Whisper empty-transcription generation failure are unrelated." + "reason": "High perplexity on gpt-oss-20b and Whisper empty transcription failure are unrelated generation/evaluation issues." }, { "left": "issue:34634", "right": "issue:35707", "accept": false, - "reason": "BarkProcessor voice preset and progressive generation with inputs_embeds/past_key_values are unrelated." - }, - { - "left": "issue:43606", - "right": "issue:44265", - "accept": false, - "reason": "CPU offload device mismatch for Bark-small is unrelated to torch.export exportability failures." - }, - { - "left": "issue:44291", - "right": "issue:44877", - "accept": false, - "reason": "init_empty_weights unexpected argument and strict config blocking granite_speech config are different loading regressions." - }, - { - "left": "issue:44186", - "right": "issue:44265", - "accept": false, - "reason": "LayoutLMv2 tokenizer padding/truncation crashes and torch.export failures are different subsystems." - }, - { - "left": "issue:43606", - "right": "issue:43819", - "accept": false, - "reason": "CPU offload device mismatch and DAC.from_latents/forward mismatch are unrelated." + "reason": "BarkProcessor voice_preset and progressive generation with inputs_embeds/past_key_values are completely unrelated." } ] }, @@ -3261,10 +3259,10 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:35707", "issue:36331", @@ -3281,18 +3279,19 @@ "issue:43404", "issue:43454", "issue:43526", - "issue:43531", "issue:43550", - "issue:43572", "issue:43577", "issue:43606", "issue:43708", "issue:43720", "issue:43749", "issue:43792", + "issue:43819", "issue:43873", "issue:43881", "issue:44186", + "issue:44265", + "issue:44291", "issue:44292", "issue:44423", "issue:44466", @@ -3310,24 +3309,27 @@ "issue:44977", "issue:44991", "issue:45072", - "issue:45161", "issue:45325", "issue:45357", "issue:45406" ], "soft_pairs": [ - "issue:43377|issue:44898", + "issue:43606|issue:44265", + "issue:44291|issue:44877", + "issue:44186|issue:44265", + "issue:43606|issue:43819", "issue:44610|issue:45325", + "issue:43377|issue:44898", "issue:35707|issue:41720", - "issue:43377|issue:44610", - "issue:43454|issue:45072", "issue:43454|issue:43550", + "issue:43454|issue:45072", + "issue:43377|issue:44610", "issue:44466|issue:45357", - "issue:43749|issue:44534", "issue:39692|issue:40444", + "issue:43749|issue:44534", "issue:43296|issue:44991", - "issue:43792|issue:44683", "issue:43296|issue:44877", + "issue:43792|issue:44683", "issue:41720|issue:43322", "issue:43454|issue:43720", "issue:43404|issue:45357", @@ -3338,272 +3340,282 @@ "issue:43577|issue:43708", "issue:43873|issue:44756", "issue:42617|issue:42915", - "issue:43550|issue:43720", - "issue:44479|issue:44918", "issue:44610|issue:44898", "issue:44877|issue:44991", + "issue:43550|issue:43720", + "issue:44479|issue:44918", "issue:44186|issue:44610", "issue:36331|issue:42915", + "issue:36331|issue:42617", "issue:43316|issue:44913", "issue:44671|issue:44743", - "issue:36331|issue:42617", "issue:42915|issue:43317", "issue:43550|issue:43606", - "issue:44292|issue:44479", - "issue:43531|issue:43572", "issue:41720|issue:42617", - "issue:41720|issue:45161" + "issue:44292|issue:44479" ], - "prepared_review_unit_hash": "adebc7116b52ecbbc7e9c1adb056cb7b31bd52468cf6b05d32884debdc32dadf", + "prepared_review_unit_hash": "af40a5c109f29ff6676b5131695b1388f8c0cea334d0bbd463cecab90012a688", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 37, - "serialized_chars": 38693, - "estimated_input_tokens": 9674, - "estimated_eval_tokens": 19604 + "soft_pair_count": 39, + "serialized_chars": 39466, + "estimated_input_tokens": 9867, + "estimated_eval_tokens": 19990 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is highly heterogeneous: the items span unrelated bugs in generation, loading/offloading, configs, tokenizers, and multimodal serving. None of the soft pairs look like the same concrete underlying bug or change, so I reject all duplicate edges.", - "confidence": 0.98, - "canonical_issue_reason": null, + "summary": "This set is highly heterogeneous: the titles point to many different bugs across loading, multimodal, tokenizer, and training paths. I do not see any soft pair that is clearly the same underlying issue, so I would keep them separate.", + "confidence": 0.16, + "canonical_issue_reason": "issue:43749 is the broadest, most infrastructure-level report here: a concrete loading regression with cross-references, making it the best representative issue in this otherwise mixed set.", "canonical_pr_reason": null, - "best_issue_reason": "No single issue is a safe global representative; the cluster is too mixed and the soft pairs are not true duplicates.", + "best_issue_reason": "issue:43749 is the strongest single issue to anchor on because it describes a clear, central failure mode in model loading rather than a narrow model-specific symptom.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43377", - "right": "issue:44898", + "left": "issue:43606", + "right": "issue:44265", + "accept": false, + "reason": "Different failures: CPU offload device mismatch vs torch.export failing on torch_compilable_check." + }, + { + "left": "issue:44291", + "right": "issue:44877", "accept": false, - "reason": "Different models and failure modes: MIMI batched-vs-single padding-mask bug vs Perceiver image-size/interpolation issue." + "reason": "Unexpected init argument vs strict config loading; different code paths and fixes." + }, + { + "left": "issue:44186", + "right": "issue:44265", + "accept": false, + "reason": "Tokenizer crash on NER/padding vs export failure in compiled-check models." + }, + { + "left": "issue:43606", + "right": "issue:43819", + "accept": false, + "reason": "Offload device mismatch is unrelated to DAC.from_latents missing STE behavior." }, { "left": "issue:44610", "right": "issue:45325", "accept": false, - "reason": "Processor/model resolution mismatch vs Qwen2.5-VL rope-index temporal scaling; unrelated code paths." + "reason": "Processor/model image-size mismatch vs Qwen2.5-VL temporal position scaling bug." + }, + { + "left": "issue:43377", + "right": "issue:44898", + "accept": false, + "reason": "Batched-vs-single padding mask bug vs Perceiver non-default resolution failure." }, { "left": "issue:35707", "right": "issue:41720", "accept": false, - "reason": "Generation with inputs_embeds/past_key_values is unrelated to Qwen3 auto device-map cudaErrorAssert." + "reason": "Generation with inputs_embeds/past_key_values is unrelated to Qwen3 auto device map cudaErrorAssert." }, { - "left": "issue:43377", - "right": "issue:44610", + "left": "issue:43454", + "right": "issue:43550", "accept": false, - "reason": "Batched encoder output mismatch vs OmDet image processor size mismatch; not the same bug." + "reason": "lm_head weight tying bug vs Bamba torch.compile/SDPA failure." }, { "left": "issue:43454", "right": "issue:45072", "accept": false, - "reason": "lm_head tying/serialization bug vs dtype mismatch in wrapper models; different root causes." + "reason": "Weight-tying serialization issue vs dtype mismatch in SwitchTransformers/TimmWrapperModel." }, { - "left": "issue:43454", - "right": "issue:43550", + "left": "issue:43377", + "right": "issue:44610", "accept": false, - "reason": "Weight-tying issue and torch.compile+SDPA failure are separate problems." + "reason": "Different multimodal issues: MIMI padding masks vs OmDet-Turbo processor resolution mismatch." }, { "left": "issue:44466", "right": "issue:45357", "accept": false, - "reason": "Both involve serialization, but one is device-dependent lm_head.weight behavior and the other is incorrect visual-encoder keys in Qwen3.5." + "reason": "Device-dependent lm_head serialization vs Qwen3.5 visual encoder key saving regression." }, { - "left": "issue:43749", - "right": "issue:44534", + "left": "issue:39692", + "right": "issue:40444", "accept": false, - "reason": "FSDP RAM-efficient loading breakage is not the same as non-persistent buffers being filled with junk." + "reason": "SigLIP2 doc example errors are unrelated to Qwen2.5-VL IterableDataset finetuning failure." }, { - "left": "issue:39692", - "right": "issue:40444", + "left": "issue:43749", + "right": "issue:44534", "accept": false, - "reason": "Documentation example errors and finetuning failures with iterable datasets are different issues." + "reason": "FSDP CPU-efficient loading broken is different from v5 non-persistent buffer junk filling." }, { "left": "issue:43296", "right": "issue:44991", "accept": false, - "reason": "Different models and failures: vLLM/PaddleOCR load error vs tokenizer loading regression in transformers v5." + "reason": "PaddleOCR-VL loading in vLLM differs from tokenizer loading failure for est-roberta." }, { - "left": "issue:43792", - "right": "issue:44683", + "left": "issue:43296", + "right": "issue:44877", "accept": false, - "reason": "Whisper runtime failure and torch>=2.9 flex_attention compile failure are unrelated." + "reason": "PaddleOCR-VL/vLLM loading issue is not the same as granite_speech strict-config rejection." }, { - "left": "issue:43296", - "right": "issue:44877", + "left": "issue:43792", + "right": "issue:44683", "accept": false, - "reason": "vLLM model-load failure vs strict config loading for granite_speech; different subsystems." + "reason": "Whisper model load failure is unrelated to compiled flex_attention on torch >= 2.9." }, { "left": "issue:41720", "right": "issue:43322", "accept": false, - "reason": "Qwen3 device-map CUDA assert vs Llava Next segfault on load are different bugs." + "reason": "Qwen3 auto device-map assert differs from Llava Next segmentation fault on load." }, { "left": "issue:43454", "right": "issue:43720", "accept": false, - "reason": "lm_head weight tying bug vs packed-weight unpacking during accelerate loading; not the same problem." + "reason": "Different loading/serialization bugs: lm_head tying vs unpacking packed weights during accelerate load." }, { "left": "issue:43404", "right": "issue:45357", "accept": false, - "reason": "Both touch serialization/weights, but Mistral3 lm_head tying is distinct from Qwen3.5 visual-encoder key saving." + "reason": "Mistral3 lm_head tying bug is different from Qwen3.5 visual encoder key regression." }, { "left": "issue:41720", "right": "issue:44977", "accept": false, - "reason": "CUDA assert under auto device mapping vs flash-attention generation regression; different failure modes." + "reason": "cudaErrorAssert on A800 is not the same as Qwen3.5 flash-attention generation regression." }, { "left": "issue:44423", "right": "issue:45406", "accept": false, - "reason": "Both are serve crashes, but the root causes differ: multimodal continuous batching vs Gemma4Processor missing _tokenizer." + "reason": "Continuous-batching multimodal crash vs Gemma4Processor missing _tokenizer; different processors and failures." }, { "left": "issue:43526", "right": "issue:43881", "accept": false, - "reason": "BeitImageProcessorFast reduce_labels bug is unrelated to glm-4v-9b load failure." + "reason": "BeitImageProcessorFast label reduction bug is unrelated to glm-4v-9b loading failure." }, { "left": "issue:44186", "right": "issue:45072", "accept": false, - "reason": "Tokenizer batching/padding crash vs bfloat16 dtype mismatch in wrapper models; unrelated." + "reason": "LayoutLMv2 tokenizer crash differs from dtype mismatch in SwitchTransformers/TimmWrapperModel." }, { "left": "issue:43577", "right": "issue:43708", "accept": false, - "reason": "Blip2 dtype propagation bug and resume_from_checkpoint max_steps miscalculation are separate issues." + "reason": "Blip2 dtype not propagated is unrelated to Trainer resume/max_steps recalculation." }, { "left": "issue:43873", "right": "issue:44756", "accept": false, - "reason": "Both mention offloading/memory, but quantization offload behavior is not the same as mmap/OOM on Strix Halo." + "reason": "Quantization/offloading behavior issue vs mmap OOM on Strix Halo; not the same bug." }, { "left": "issue:42617", "right": "issue:42915", "accept": false, - "reason": "3d_parallel.py execution failure and Qwen3Moe FineGrainedFP8Config failure do not share a concrete code-path bug." + "reason": "3d_parallel.py failure and Qwen3Moe FineGrainedFP8Config failure are different runtime issues." }, { - "left": "issue:43550", - "right": "issue:43720", + "left": "issue:44610", + "right": "issue:44898", "accept": false, - "reason": "torch.compile with SDPA and accelerate loading of packed BitNet weights are unrelated." + "reason": "OmDet-Turbo processor output size mismatch is not the same as Perceiver interpolation failure." }, { - "left": "issue:44479", - "right": "issue:44918", + "left": "issue:44877", + "right": "issue:44991", "accept": false, - "reason": "Video-input regression in Qwen VL models vs TRL SFT input-embedding unpacking issue; different bugs." + "reason": "Strict config loading for granite_speech is unrelated to tokenizer loading for est-roberta." }, { - "left": "issue:44610", - "right": "issue:44898", + "left": "issue:43550", + "right": "issue:43720", "accept": false, - "reason": "OmDet processor resolution mismatch vs Perceiver interpolation failure; different models and fixes." + "reason": "torch.compile SDPA failure and packed-weight unpacking during load are different code paths." }, { - "left": "issue:44877", - "right": "issue:44991", + "left": "issue:44479", + "right": "issue:44918", "accept": false, - "reason": "Granite speech strict config loading and est-roberta tokenizer loading are unrelated." + "reason": "Video-input regression in v5.3.0 is distinct from input-embedding unpacking in trl SFT trainer." }, { "left": "issue:44186", "right": "issue:44610", "accept": false, - "reason": "Tokenizer batch/padding crash vs OmDet image processor size mismatch; not duplicates." + "reason": "Tokenizer crash on NER inputs differs from OmDet-Turbo processor/model resolution mismatch." }, { "left": "issue:36331", "right": "issue:42915", "accept": false, - "reason": "Trainer compute_loss signature regression is unrelated to Qwen3Moe FP8 config failure." + "reason": "Trainer custom compute_loss signature error is unrelated to Qwen3Moe FP8 loading." + }, + { + "left": "issue:36331", + "right": "issue:42617", + "accept": false, + "reason": "Unexpected Trainer keyword arg and 3d_parallel.py failure are different training/runtime problems." }, { "left": "issue:43316", "right": "issue:44913", "accept": false, - "reason": "Both are config API issues, but Gemma3TextConfig discrepancy is not the same as GPTNeoX rotary_pct reload bug." + "reason": "Gemma3TextConfig API discrepancy is unrelated to GPTNeoX rotary_pct reload behavior." }, { "left": "issue:44671", "right": "issue:44743", "accept": false, - "reason": "CamemBERT masked-LM prediction bug and Qwen3.5 recurrent-state reset bug are unrelated." - }, - { - "left": "issue:36331", - "right": "issue:42617", - "accept": false, - "reason": "CustomTrainer kwarg regression and 3d_parallel execution failure are different problems." + "reason": "CamemBERT MLM prediction regression and Qwen3.5 recurrent-state reset are different model bugs." }, { "left": "issue:42915", "right": "issue:43317", "accept": false, - "reason": "Qwen3Moe FP8 load failure and dequantized model offload failure are not the same bug." + "reason": "Qwen3Moe FineGrainedFP8Config failure is not the same as dequantized model offload loading failure." }, { "left": "issue:43550", "right": "issue:43606", "accept": false, - "reason": "Bamba torch.compile/SDPA crash and bark-small CPU offload device mismatch are distinct issues." - }, - { - "left": "issue:44292", - "right": "issue:44479", - "accept": false, - "reason": "Qwen-3-8B-NVFP4 runtime issue differs from the Qwen VL video-input regression." - }, - { - "left": "issue:43531", - "right": "issue:43572", - "accept": false, - "reason": "Qwen3-MoE sliding-window cache issue is unrelated to StableLm pad_token_idx config regression." + "reason": "Bamba SDPA compile bug and Bark CPU offload mismatch are unrelated." }, { "left": "issue:41720", "right": "issue:42617", "accept": false, - "reason": "Qwen3 device-map CUDA assert is unrelated to 3d_parallel.py failure." + "reason": "Qwen3 device-map assert differs from 3d_parallel.py execution failure." }, { - "left": "issue:41720", - "right": "issue:45161", + "left": "issue:44292", + "right": "issue:44479", "accept": false, - "reason": "Qwen3 auto device-map assert and GPT-OSS MoE tensor-parallel problem are different code paths." + "reason": "Qwen-3-8B-NVFP4 running error is not the same as Qwen v5.3.0 video-input regression." } ] }, @@ -3622,10 +3634,10 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:30064", "issue:33357", @@ -3642,8 +3654,10 @@ "issue:43381", "issue:43388", "issue:43421", + "issue:43531", "issue:43540", "issue:43550", + "issue:43572", "issue:43606", "issue:43653", "issue:43720", @@ -3653,7 +3667,6 @@ "issue:43873", "issue:43927", "issue:44062", - "issue:44077", "issue:44186", "issue:44361", "issue:44368", @@ -3665,11 +3678,10 @@ "issue:44625", "issue:44843", "issue:44898", - "issue:44918", - "issue:44936", "issue:44991", "issue:45059", "issue:45072", + "issue:45161", "issue:45357", "issue:45381", "issue:45406", @@ -3677,13 +3689,15 @@ "issue:45479" ], "soft_pairs": [ + "issue:43531|issue:43572", + "issue:41720|issue:45161", "issue:43540|issue:43782", "issue:43388|issue:45059", "issue:44186|issue:44361", - "issue:42915|issue:43322", "issue:41720|issue:43873", - "issue:45406|issue:45464", + "issue:42915|issue:43322", "issue:36010|issue:42617", + "issue:45406|issue:45464", "issue:44514|issue:44545", "issue:36331|issue:41720", "issue:33357|issue:35707", @@ -3698,233 +3712,231 @@ "issue:43606|issue:43653", "issue:43782|issue:45381", "issue:34567|issue:35707", + "issue:34634|issue:41720", "issue:44898|issue:45072", "issue:42886|issue:44843", - "issue:34634|issue:41720", - "issue:43381|issue:43844", - "issue:44451|issue:44991", "issue:43421|issue:43653", + "issue:44451|issue:44991", "issue:44062|issue:44451", - "issue:44077|issue:44625", - "issue:44918|issue:44936" + "issue:43381|issue:43844" ], - "prepared_review_unit_hash": "09c926973e7e676f722f847d06d8781d3c1ac9b011369cccc019ceb0a66d9864", + "prepared_review_unit_hash": "3e9eeddf8eb4d697a4ed643f0ba42b83f879698a66e2594a3f67e1fc118f1fc9", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 36797, - "estimated_input_tokens": 9200, - "estimated_eval_tokens": 18656 + "serialized_chars": 36765, + "estimated_input_tokens": 9192, + "estimated_eval_tokens": 18640 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly a heterogeneous cluster of unrelated issues across tokenizers, processors, generation, training, and loading paths. The strongest duplicate-like pairs are the Qwen2_5_VL `apply_chat_template` batched `padding=False` crash and the offline tokenizer-load regression around `HF_HUB_OFFLINE`/cache behavior; the rest look like broad subsystem similarity rather than the same bug.", - "confidence": 0.86, - "canonical_issue_reason": "issue:44545 is the clearest canonical issue for the exact duplicate pair with 44514: the titles match very closely and both describe the same batched `apply_chat_template` crash when `padding=False`.", + "summary": "Most pairs are unrelated superficial similarities. Two soft duplicate candidates stand out: the Qwen2_5_VLProcessor batched padding=False crash, and the HF_HUB_OFFLINE tokenizer-loading regression.", + "confidence": 0.78, + "canonical_issue_reason": "Issue 44514 is the best canonical issue: it has the fuller repro for the `Qwen2_5_VLProcessor.apply_chat_template` crash with `padding=False`, and 44545 appears to be the same bug with less detail.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44545 is the strongest single representative in this mixed set because it anchors the clearest duplicate pair and has the most explicit, narrowly described failure mode among the accepted matches.", + "best_issue_reason": "44514 is the strongest issue to anchor this cluster because it is a precise, reproducible report and the clearest representative of an actual duplicate pair.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43531", + "right": "issue:43572", + "accept": false, + "reason": "Different models and failure modes: Qwen3-MoE sliding-window behavior vs StableLmConfig pad token metadata." + }, + { + "left": "issue:41720", + "right": "issue:45161", + "accept": false, + "reason": "Both involve model execution, but the reported problems are different: A800 cudaErrorAssert vs GPT-OSS MoE tensor-parallel behavior." + }, { "left": "issue:43540", "right": "issue:43782", "accept": false, - "reason": "Different model families and failure modes: Qwen3OmniMoe video processing vs Qwen3VL load-time weight-only error." + "reason": "Different code paths: video input processing in Qwen3OmniMoe vs Qwen3VL `from_pretrained(weight_only=True)` loading error." }, { "left": "issue:43388", "right": "issue:45059", "accept": false, - "reason": "Different code paths and symptoms: `gather_for_metrics` label handling vs SAM3 text/bbox behavior." + "reason": "Unrelated bugs in evaluation metric gathering vs SAM3 text/bounding-box prompting behavior." }, { "left": "issue:44186", "right": "issue:44361", "accept": false, - "reason": "Both are tokenizer bugs, but on different tokenizers and different failures; not the same underlying issue." - }, - { - "left": "issue:42915", - "right": "issue:43322", - "accept": false, - "reason": "One is Qwen3Moe FP8 config handling, the other is Llava Next segfault on load; unrelated." + "reason": "Both are tokenizer/task failures, but they affect different tokenizer families and different underlying errors." }, { "left": "issue:41720", "right": "issue:43873", "accept": false, - "reason": "Different runtime problems: auto device mapping CUDA assert vs offloading/quantization behavior." + "reason": "Different issues: device-map assertion on Qwen3 vs offloading/quantization behavior." }, { - "left": "issue:45406", - "right": "issue:45464", + "left": "issue:42915", + "right": "issue:43322", "accept": false, - "reason": "Different components and bugs: Gemma4Processor missing `_tokenizer` vs Qwen3.5 streaming inference failure." + "reason": "Different failures in different model stacks: FineGrainedFP8 on Qwen3Moe vs Llava Next load-time segfault." }, { "left": "issue:36010", "right": "issue:42617", "accept": false, - "reason": "Unrelated problems: GenerationMixin import error vs `3d_parallel.py` execution failure." + "reason": "No shared underlying bug; import-path regression is unrelated to running `3d_parallel.py`." + }, + { + "left": "issue:45406", + "right": "issue:45464", + "accept": false, + "reason": "Different surfaces and symptoms: transformers-serve processor init crash vs chat/completions streaming failure." }, { "left": "issue:44514", "right": "issue:44545", "accept": true, - "reason": "Near-exact duplicate titles and matching symptom: both report the same batched `apply_chat_template` crash with `padding=False`." + "reason": "Same exact `Qwen2_5_VLProcessor.apply_chat_template` crash on batched input with `padding=False`; 44545 is a duplicate report." }, { "left": "issue:36331", "right": "issue:41720", "accept": false, - "reason": "CustomTrainer API mismatch vs Qwen3 device-mapping CUDA assert; different stack layers." + "reason": "Different bugs: custom trainer signature mismatch vs model device-mapping assertion." }, { "left": "issue:33357", "right": "issue:35707", "accept": false, - "reason": "MacOS CLIP bus error and progressive generation with embeddings/past-key-values are unrelated." + "reason": "No common code path; MacOS bus error in CLIP loading is unrelated to progressive generation with `inputs_embeds` and `past_key_values`." }, { "left": "issue:41720", "right": "issue:43746", "accept": false, - "reason": "Device-mapping CUDA assert is unrelated to PEFT/local-checkpoint loading for GraniteSpeech." + "reason": "Different problems: Qwen3 device-map failure vs PEFT-adapter checkpoint loading for GraniteSpeech." }, { "left": "issue:43606", "right": "issue:43720", "accept": false, - "reason": "Both involve loading/offload mechanics, but the titles point to different concrete failures and models." + "reason": "Both touch loading/offload, but one is a CPU-offload device mismatch and the other is BitNet packed-weight unpacking during accelerate loading." }, { "left": "issue:30064", "right": "issue:34634", "accept": false, - "reason": "Image segmentation map handling vs Bark voice preset parsing are unrelated processor bugs." + "reason": "Unrelated processor bugs: segmentation-map handling vs Bark voice preset parsing." }, { "left": "issue:44492", "right": "issue:44509", "accept": false, - "reason": "A cache-strategy typo fix is unrelated to docs still mentioning removed pipeline tasks." + "reason": "A documentation typo is not the same as stale pipeline-task docs in v5; different scope and fix." }, { "left": "issue:43550", "right": "issue:43653", "accept": false, - "reason": "Bamba torch.compile/SDPA failure and BigBirdTokenizer special-token registration are different subsystems." + "reason": "Different tokenizer/model issues: torch.compile + SDPA vs mask-token registration and empty decode output." }, { "left": "issue:44368", "right": "issue:45357", "accept": false, - "reason": "A tie_word_embeddings warning and incorrect visual encoder keys on save/load are different issues." + "reason": "Different regressions affecting different parts of model config/save behavior." }, { "left": "issue:44625", "right": "issue:45479", "accept": false, - "reason": "Different classification bugs: config propagation in Qwen3.5 vs degenerate zero-loss behavior across sequence classifiers." + "reason": "Related to classification config, but not the same bug: one is `num_labels` propagation in Qwen3.5, the other is degenerate zero loss for single-label classification across models." }, { "left": "issue:43421", "right": "issue:43927", "accept": false, - "reason": "Runtime special-token/post-processor sync vs DiaConfig save/load token ID loss are different code paths." + "reason": "Different tokenizer-state bugs: runtime post-processor updates vs saved config losing custom token IDs." }, { "left": "issue:43606", "right": "issue:43653", "accept": false, - "reason": "CPU offload device mismatch is unrelated to BigBirdTokenizer mask-token registration." + "reason": "Different bugs in different models: device mismatch during offload vs tokenizer special-token registration." }, { "left": "issue:43782", "right": "issue:45381", "accept": false, - "reason": "Different models and failures: Qwen3VL weight-only load error vs Qwen2.5-VL video position IDs bug." + "reason": "Different Qwen vision-language failures: `weight_only=True` load error vs incorrect video `vision_position_ids`." }, { "left": "issue:34567", "right": "issue:35707", "accept": false, - "reason": "TrainerState bookkeeping issue vs generation-with-embeds/past-key-values bug; not the same bug." + "reason": "No shared underlying issue; trainer token counting is unrelated to generation with cached past key values." + }, + { + "left": "issue:34634", + "right": "issue:41720", + "accept": false, + "reason": "Bark processor voice preset handling is unrelated to Qwen3 device-mapping crashes." }, { "left": "issue:44898", "right": "issue:45072", "accept": false, - "reason": "Perceiver image resizing failure and bfloat16 dtype mismatches are unrelated." + "reason": "Different models and failure modes: Perceiver image resolution handling vs dtype mismatches in inference." }, { "left": "issue:42886", "right": "issue:44843", "accept": true, - "reason": "Both titles describe the same offline tokenizer-loading regression: `HF_HUB_OFFLINE=1` / cache failure in `AutoTokenizer.from_pretrained`." - }, - { - "left": "issue:34634", - "right": "issue:41720", - "accept": false, - "reason": "BarkProcessor voice preset handling and Qwen3 device-mapping CUDA assert are unrelated." + "reason": "Both describe tokenizer loading breaking in HF_HUB_OFFLINE mode due to an unconditional hub metadata call in the tokenizer-loading path." }, { - "left": "issue:43381", - "right": "issue:43844", + "left": "issue:43421", + "right": "issue:43653", "accept": false, - "reason": "Gradient checkpointing eval-mode restriction vs gradient growth under ZeRO-3 are different training issues." + "reason": "Different tokenizer bugs: post-processor not refreshed at runtime vs mask token not registered as special." }, { "left": "issue:44451", "right": "issue:44991", "accept": false, - "reason": "Both are tokenizer load failures on newer versions, but for different models and without evidence of the same code path." - }, - { - "left": "issue:43421", - "right": "issue:43653", - "accept": false, - "reason": "Special-token post-processor updates and BigBird mask-token registration are unrelated." + "reason": "Both are tokenizer load failures after newer versions, but they hit different models and the root cause is not established as the same." }, { "left": "issue:44062", "right": "issue:44451", "accept": false, - "reason": "AddedToken argument collision vs model-specific tokenizer load failure are unrelated." - }, - { - "left": "issue:44077", - "right": "issue:44625", - "accept": false, - "reason": "Patchtsmixer `post_init` policy and Qwen3.5 `num_labels` propagation are unrelated." + "reason": "The AddedToken keyword-argument error is a specific tokenizer construction bug, while ScandiBERT loading failure is a separate model-specific report." }, { - "left": "issue:44918", - "right": "issue:44936", + "left": "issue:43381", + "right": "issue:43844", "accept": false, - "reason": "TRL SFT embedding unpacking issue and trainer evaluate-after-train failure are different workflows." + "reason": "Unrelated training/gradient issues: eval-mode gradient checkpointing vs ZeRO-3 gradient explosion." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The clustering is mostly conservative, but two statements overreach the packet: (1) the canonical reason for issue:44545 claims the pair has the \"same crash signature,\" which is not supported by the packet metadata/title alone; and (2) the 42886/44843 rationale asserts a specific shared implementation path (`model_info()` in `_patch_mistral_regex`) that is not evidenced in the packet. Please downgrade these to title/metadata-grounded similarity unless the underlying issue bodies are available." + "accept": true, + "feedback": "The cluster summary is grounded in the packet, and the two accepted soft edges are conservative enough: 44514/44545 are near-identical reports of the same Qwen2_5_VLProcessor padding=False crash, and 42886/44843 both point to the same HF_HUB_OFFLINE tokenizer-loading regression. The rejected pairs are also framed cautiously and do not overclaim duplicates." }, "evaluator_used": true, - "retried": true, + "retried": false, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -3940,7 +3952,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:30064", "issue:36010", @@ -3955,14 +3967,12 @@ "issue:43577", "issue:43596", "issue:43618", - "issue:43643", "issue:43653", "issue:43697", "issue:43716", "issue:43720", "issue:43746", "issue:43756", - "issue:43782", "issue:43818", "issue:43819", "issue:43873", @@ -3970,18 +3980,20 @@ "issue:43994", "issue:44008", "issue:44062", + "issue:44077", "issue:44186", "issue:44220", "issue:44488", "issue:44589", "issue:44610", + "issue:44625", "issue:44661", "issue:44671", "issue:44811", "issue:44843", - "issue:44877", "issue:44898", - "issue:44977", + "issue:44918", + "issue:44936", "issue:44987", "issue:45042", "issue:45072", @@ -3992,6 +4004,8 @@ "issue:45479" ], "soft_pairs": [ + "issue:44918|issue:44936", + "issue:44077|issue:44625", "issue:44987|issue:45042", "issue:43531|issue:44589", "issue:43994|issue:44671", @@ -4005,8 +4019,8 @@ "issue:39692|issue:43873", "issue:43618|issue:43697", "issue:43540|issue:44008", - "issue:40444|issue:43746", "issue:43746|issue:43873", + "issue:40444|issue:43746", "issue:44220|issue:44661", "issue:43716|issue:44008", "issue:43335|issue:43756", @@ -4015,229 +4029,227 @@ "issue:44843|issue:45081", "issue:43421|issue:44811", "issue:30064|issue:36010", - "issue:43577|issue:43818", "issue:44062|issue:44488", "issue:44186|issue:44898", "issue:43540|issue:45381", "issue:43550|issue:45072", - "issue:43550|issue:43927", - "issue:43643|issue:44877", - "issue:43782|issue:44977" + "issue:43577|issue:43818", + "issue:43550|issue:43927" ], - "prepared_review_unit_hash": "8726974a8fc1839c71ea1470e09c2ebe0c49f52a12f9c364477eafaccf537dae", + "prepared_review_unit_hash": "68eda53b31bae9b20c6a5ed8e508c5f6db13830f46cc2ced5cff3abba4766f85", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 31, - "serialized_chars": 37437, - "estimated_input_tokens": 9360, - "estimated_eval_tokens": 18976 + "serialized_chars": 37390, + "estimated_input_tokens": 9348, + "estimated_eval_tokens": 18952 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is not a single duplicate cluster; it is a mixed collection of unrelated bugs and regressions. The soft edges mostly reflect superficial keyword overlap (tokenizers, vision, loading, dtype, etc.) rather than the same concrete code-path failure.", - "confidence": 0.93, - "canonical_issue_reason": "No clear canonical issue: the items span many unrelated subsystems and model-specific failures, so there is no single representative bug in this cluster.", + "summary": "This set is not a duplicate cluster: the items span many unrelated bugs across tokenizers, vision/video processors, quantization, training, and model config. All soft edges should be rejected.", + "confidence": 0.97, + "canonical_issue_reason": "No canonical issue: the collection is heterogeneous and does not center on one underlying bug or change.", "canonical_pr_reason": null, - "best_issue_reason": "No global best issue: none of these issues can credibly stand in for the rest because the underlying problems differ too much.", + "best_issue_reason": "issue:43873 is the closest loose representative because it is open and has the most active discussion/inbound references, but it is still not a duplicate target for the rest of the set.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44918", + "right": "issue:44936", + "accept": false, + "reason": "Different failures: Qwen3.5 embedding unpacking in TRL SFT vs trainer.evaluate() after train()." + }, + { + "left": "issue:44077", + "right": "issue:44625", + "accept": false, + "reason": "Unrelated: patchtsmixer post_init policy vs Qwen3.5 num_labels propagation." + }, { "left": "issue:44987", "right": "issue:45042", "accept": false, - "reason": "Unrelated failures: offline hub/model loading vs PIL image processor requiring torchvision." + "reason": "Different subsystems: loading a physical-intelligence model vs PIL image processors wrongly requiring torchvision." }, { "left": "issue:43531", "right": "issue:44589", "accept": false, - "reason": "Different bugs in different paths: Qwen3-MoE sliding-window behavior vs Float8 storage lookup." + "reason": "Different bugs: Qwen3-MoE sliding_window vs Float8 storage lookup failure." }, { "left": "issue:43994", "right": "issue:44671", "accept": false, - "reason": "Different models and symptoms: SigLIP2 pipeline/model mismatch vs CamemBERT masked-LM prediction regression." + "reason": "Different models and symptoms: SigLIP2 inference issues vs CamemBERT masked LM regression." }, { "left": "issue:39692", "right": "issue:44610", "accept": false, - "reason": "Doc/example errors for SigLIP2 are not the same bug as OmDet-Turbo processor size mismatch." + "reason": "Doc/example mistakes for SigLIP2 are unrelated to OmDet-Turbo processor size mismatch." }, { "left": "issue:43421", "right": "issue:44186", "accept": false, - "reason": "Tokenizer post-processor update at runtime is unrelated to LayoutLMv2 NER/padding crashes." + "reason": "Both are tokenizer-related, but they are distinct code paths and failures." }, { "left": "issue:45081", "right": "issue:45356", "accept": false, - "reason": "Both mention fix_mistral_regex, but one is an AttributeError crash and the other is a codec/warning regression; not the same underlying bug." + "reason": "Both touch mistral regex handling, but one is a crash and the other is a tokenizer regression/codec warning; not the same concrete bug." }, { "left": "issue:43525", "right": "issue:43531", "accept": false, - "reason": "Llama4 pad_token_id missing vs Qwen3-MoE sliding_window issue are unrelated model/config bugs." + "reason": "Llama4 pad_token_id attribute error is unrelated to Qwen3-MoE sliding_window behavior." }, { "left": "issue:43596", "right": "issue:44220", "accept": false, - "reason": "DeepSpeed zero3/BertModel init failure is unrelated to _torch_extract_fbank_features()." + "reason": "Deepspeed zero3/BertModel initialization error is unrelated to fbank feature extraction." }, { "left": "issue:45183", "right": "issue:45479", "accept": false, - "reason": "Input validation error messaging is not the same bug as degenerate zero-loss sequence classification." + "reason": "Input validation error messaging is unrelated to the zero-loss sequence-classification bug." }, { "left": "issue:43746", "right": "issue:45381", "accept": false, - "reason": "PEFT/local-checkpoint loading for GraniteSpeech is unrelated to Qwen2.5-VL video position IDs." + "reason": "GraniteSpeech PEFT checkpoint loading is unrelated to Qwen2.5-VL video position ids." }, { "left": "issue:39692", "right": "issue:43873", "accept": false, - "reason": "SigLIP2 doc/example issues do not match offloading problems with quantization." + "reason": "SigLIP2 documentation/example errors are unrelated to quantization offloading behavior." }, { "left": "issue:43618", "right": "issue:43697", "accept": false, - "reason": "Missing CLIPOutput attentions and RTDetr output differences are different regressions." + "reason": "CLIPOutput attentions regression is unrelated to RTDetrV2 output differences." }, { "left": "issue:43540", "right": "issue:44008", "accept": false, - "reason": "Qwen3OmniMoe video-input processing and Gemma3n audio_mel_mask collision are unrelated." + "reason": "Qwen3OmniMoe video processing failure is unrelated to Gemma3n audio mask name collision." }, { - "left": "issue:40444", - "right": "issue:43746", + "left": "issue:43746", + "right": "issue:43873", "accept": false, - "reason": "IterableDataset multi-image finetuning failure is unrelated to PEFT adapter loading from local checkpoints." + "reason": "PEFT adapter loading and quantized offloading are separate bugs." }, { - "left": "issue:43746", - "right": "issue:43873", + "left": "issue:40444", + "right": "issue:43746", "accept": false, - "reason": "Local checkpoint/adapters loading and quantization offloading are separate problems." + "reason": "Qwen2.5-VL iterable dataset multi-image training failure is unrelated to GraniteSpeech local checkpoint loading." }, { "left": "issue:44220", "right": "issue:44661", "accept": false, - "reason": "Fbank feature extraction bug is unrelated to add-new-model-like failing in TOKENIZER_MAPPING_NAMES." + "reason": "Audio feature extraction bug is unrelated to add-new-model-like failing in tokenizer mapping." }, { "left": "issue:43716", "right": "issue:44008", "accept": false, - "reason": "Image preprocessor dtype mismatch is unrelated to the Gemma3n variable-name collision." + "reason": "Mistral image preprocessor dtype mismatch is unrelated to Gemma3n variable collision." }, { "left": "issue:43335", "right": "issue:43756", "accept": false, - "reason": "SwitchTransformers sparse-layer config bug and Smollm3 RoPE-layer mismatch are different issues." + "reason": "SwitchTransformers sparse-layer config bug is unrelated to Smollm3 RoPE layer dropping." }, { "left": "issue:43720", "right": "issue:43819", "accept": false, - "reason": "BitNet packed-weight loading and DAC from_latents/STE mismatch do not share the same code path." + "reason": "BitNet loading/unpacking issue is unrelated to DAC forward/from_latents mismatch." }, { "left": "issue:43653", "right": "issue:43720", "accept": false, - "reason": "Tokenizer special-token registration issue is unrelated to BitNet accelerate loading." + "reason": "BigBirdTokenizer special-token decode bug is unrelated to BitNet accelerate-loading bug." }, { "left": "issue:44843", "right": "issue:45081", "accept": false, - "reason": "Offline model_info() patching problem and Mistral regex crash are different failures, even if both touch tokenizer loading." + "reason": "Both involve mistral-regex code, but one breaks offline model_info calls while the other crashes on a missing backend_tokenizer attribute." }, { "left": "issue:43421", "right": "issue:44811", "accept": false, - "reason": "Runtime special-token/post-processor updates are unrelated to Whisper batch_decode skip_special_tokens behavior." + "reason": "Runtime special-token post-processing and Whisper batch_decode skip_special_tokens are different behaviors." }, { "left": "issue:30064", "right": "issue:36010", "accept": false, - "reason": "Void segmentation map processing and GenerationMixin import failure are entirely unrelated." - }, - { - "left": "issue:43577", - "right": "issue:43818", - "accept": false, - "reason": "BLIP2 dtype handling and Video-LLaVA temporal-attention/weight-sharing issues are different bugs." + "reason": "Void segmentation map processing is unrelated to GenerationMixin import failure." }, { "left": "issue:44062", "right": "issue:44488", "accept": false, - "reason": "AddedToken constructor argument collision is unrelated to the sleng-bert loading failure." + "reason": "AddedToken special-argument TypeError is not the same bug as loading cjvt/sleng-bert." }, { "left": "issue:44186", "right": "issue:44898", "accept": false, - "reason": "LayoutLMv2 tokenizer crashes and Perceiver interpolation failures are different model-specific problems." + "reason": "LayoutLMv2 tokenizer crashes are unrelated to Perceiver image classification at non-default resolution." }, { "left": "issue:43540", "right": "issue:45381", "accept": false, - "reason": "Both involve video inputs, but Qwen3OmniMoe processing and Qwen2.5-VL vision_position_ids are distinct bugs." + "reason": "Both mention video inputs, but they are different model families and different failure modes." }, { "left": "issue:43550", "right": "issue:45072", "accept": false, - "reason": "torch.compile/SDPA failure in Bamba is unrelated to dtype mismatches in SwitchTransformers/TimmWrapperModel." - }, - { - "left": "issue:43550", - "right": "issue:43927", - "accept": false, - "reason": "Bamba compile/SDPA bug and DiaConfig token-id persistence bug are unrelated." + "reason": "torch.compile/SDPA failure in Bamba is unrelated to bf16 dtype mismatches in SwitchTransformers/TimmWrapperModel." }, { - "left": "issue:43643", - "right": "issue:44877", + "left": "issue:43577", + "right": "issue:43818", "accept": false, - "reason": "trust_remote_code missing fields and strict granite_speech config loading are different config-handling issues." + "reason": "Blip2 dtype handling is unrelated to Video-LLaVA temporal-attention/weight-sharing problems." }, { - "left": "issue:43782", - "right": "issue:44977", + "left": "issue:43550", + "right": "issue:43927", "accept": false, - "reason": "Qwen3VL weight_only loading error is unrelated to Qwen3.5 flash-attention generation failure." + "reason": "Bamba torch.compile SDPA regression is unrelated to DiaConfig custom token ID loss." } ] }, @@ -4256,10 +4268,10 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:30064", "issue:34634", @@ -4268,7 +4280,6 @@ "issue:41720", "issue:42175", "issue:43262", - "issue:43526", "issue:43531", "issue:43550", "issue:43577", @@ -4278,7 +4289,6 @@ "issue:43644", "issue:43650", "issue:43653", - "issue:43697", "issue:43720", "issue:43749", "issue:43782", @@ -4301,7 +4311,9 @@ "issue:44805", "issue:44821", "issue:44857", + "issue:44877", "issue:44936", + "issue:44977", "issue:44991", "issue:45020", "issue:45072", @@ -4311,238 +4323,245 @@ "issue:45406" ], "soft_pairs": [ + "issue:43643|issue:44877", "issue:43577|issue:43582", + "issue:43782|issue:44977", "issue:43531|issue:43643", "issue:44448|issue:44671", "issue:43644|issue:43749", - "issue:44561|issue:45020", "issue:43653|issue:43819", + "issue:44561|issue:45020", "issue:43825|issue:43994", "issue:43550|issue:43819", - "issue:43650|issue:43906", "issue:43825|issue:43827", "issue:44186|issue:44442", "issue:44821|issue:45084", + "issue:43650|issue:43906", "issue:41720|issue:44991", "issue:44805|issue:44936", - "issue:44485|issue:44509", - "issue:43606|issue:45072", "issue:30064|issue:36331", + "issue:43606|issue:45072", + "issue:44485|issue:44509", "issue:42175|issue:45081", "issue:43782|issue:45325", "issue:44610|issue:45072", - "issue:44060|issue:44368", "issue:34634|issue:36010", + "issue:44060|issue:44368", "issue:45081|issue:45406", "issue:43720|issue:45072", "issue:43262|issue:43819", "issue:43653|issue:44671", - "issue:43749|issue:44291", "issue:43582|issue:44857", - "issue:43526|issue:43697" + "issue:43749|issue:44291" ], - "prepared_review_unit_hash": "a2cd2883ebe85c6b67fc7d3b2117aff834e89eead81e200cf6541517b1adea11", + "prepared_review_unit_hash": "b36fa89192bc3b82a60d484e384712abcbc234fbcf89edf0b1a4a0e2dd7cc3ec", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 29, - "serialized_chars": 36605, - "estimated_input_tokens": 9152, - "estimated_eval_tokens": 18560 + "soft_pair_count": 30, + "serialized_chars": 36840, + "estimated_input_tokens": 9210, + "estimated_eval_tokens": 18676 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is largely heterogeneous: most pairs share only broad topic words (loading, tokenizers, processors, v5 regressions) but not the same concrete bug or change. I would reject all soft edges; there is no clear duplicate subset here.", - "confidence": 0.91, - "canonical_issue_reason": "No single canonical issue fits this cluster well; the issues span unrelated regressions across processors, model loading, training, and docs.", + "summary": "Mostly a heterogeneous set of unrelated transformer issues with only a few loose theme overlaps (v5 regressions, remote_code, tokenizer/processor loading). No PRs are present. I would not merge any of the soft pairs as duplicates.", + "confidence": 0.95, + "canonical_issue_reason": "No single canonical duplicate stands out; the cluster is too heterogeneous. If an umbrella is needed, 45020 is the broadest remote_code-regression report.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45020 is the broadest umbrella-style report in the set (remote_code regressions) and the most plausible representative, but it still does not match the other issues closely enough to serve as a true duplicate canonical.", + "best_issue_reason": "45020 is the closest thing to an umbrella issue because it captures the broad 'recent versions break remote_code' theme seen in a few nearby reports, though it still does not unify the cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43643", + "right": "issue:44877", + "accept": false, + "reason": "Both involve config/model loading, but one is missing fields with trust_remote_code and the other is strict config rejection for granite_speech; different bugs." + }, { "left": "issue:43577", "right": "issue:43582", "accept": false, - "reason": "Different failures in different subsystems: BLIP2 dtype loading vs Apple Silicon allocator warmup." + "reason": "BLIP2 dtype propagation and Apple Silicon allocator warmup TypeError are unrelated code paths." + }, + { + "left": "issue:43782", + "right": "issue:44977", + "accept": false, + "reason": "Different models and failures: Qwen3VL weight_only loading error vs Qwen3.5 flash-attention generation issue." }, { "left": "issue:43531", "right": "issue:43643", "accept": false, - "reason": "Qwen3-MoE sliding-window behavior and trust_remote_code config fields are unrelated bugs." + "reason": "Sliding-window behavior in Qwen3-MoE is unrelated to trust_remote_code config field loss." }, { "left": "issue:44448", "right": "issue:44671", "accept": false, - "reason": "Both are v5 output regressions, but they affect different models and code paths." + "reason": "Both are v5 regressions, but Pegasus generation output changes and CamemBERT masked LM predictions are distinct model/code paths." }, { "left": "issue:43644", "right": "issue:43749", "accept": false, - "reason": "Distinct loading issues: non-persistent buffer junk vs FSDP CPU RAM efficient loading." + "reason": "Non-persistent buffer junk and FSDP RAM-efficient loading are separate loading/initialization problems." }, { - "left": "issue:44561", - "right": "issue:45020", + "left": "issue:43653", + "right": "issue:43819", "accept": false, - "reason": "Related theme of remote_code breakage, but one is a specific v5 helper removal while the other is a broader meta-report." + "reason": "BigBirdTokenizer special-token registration and DAC from_latents/STE mismatch are unrelated." }, { - "left": "issue:43653", - "right": "issue:43819", + "left": "issue:44561", + "right": "issue:45020", "accept": false, - "reason": "Tokenizer special-token registration and DAC latent/STE mismatch are unrelated." + "reason": "45020 is a broad umbrella for remote_code breakage, while 44561 is a specific is_torch_fx_available removal regression; not the same concrete bug." }, { "left": "issue:43825", "right": "issue:43994", "accept": false, - "reason": "Pipeline error messaging and SigLIP2 output quality are different problems." + "reason": "Pipeline error-message text and SigLIP nonsensical outputs are unrelated." }, { "left": "issue:43550", "right": "issue:43819", "accept": false, - "reason": "Bamba torch.compile/SDPA issue is unrelated to DAC forward/from_latents behavior." - }, - { - "left": "issue:43650", - "right": "issue:43906", - "accept": false, - "reason": "Placeholder/nonsense issue and an isolated reproduction of another bug are not duplicates." + "reason": "torch.compile + SDPA failure in Bamba is unrelated to DAC latent decoding mismatch." }, { "left": "issue:43825", "right": "issue:43827", "accept": false, - "reason": "Both concern removed pipeline tasks, but one is a runtime error message and the other is docs drift." + "reason": "One is a runtime error message, the other is stale docs; related topic but not the same bug." }, { "left": "issue:44186", "right": "issue:44442", "accept": false, - "reason": "Different tokenizer/model loading failures with different models and inputs." + "reason": "LayoutLMv2 NER padding/truncation crash and FastSpeech2Conformer tokenizer loading are different tokenizer issues." }, { "left": "issue:44821", "right": "issue:45084", "accept": false, - "reason": "AutoImageProcessor-from-URL and template-node compilation errors are unrelated." + "reason": "AutoImageProcessor URL loading and template compilation errors are unrelated." + }, + { + "left": "issue:43650", + "right": "issue:43906", + "accept": false, + "reason": "Too little concrete overlap; one is a vague 'ADD THE DATA' issue and the other is a reproduction of a different linked report." }, { "left": "issue:41720", "right": "issue:44991", "accept": false, - "reason": "Different failures: Qwen3 device-mapping crash vs tokenizer loading for a different model." + "reason": "Qwen3 auto device mapping CUDA assert and est-roberta tokenizer loading are unrelated." }, { "left": "issue:44805", "right": "issue:44936", "accept": false, - "reason": "Generic shape-mismatch IndexError and trainer.evaluate() failure after train are not the same bug." + "reason": "Mask-shape IndexError and trainer.evaluate-after-train failure are distinct issues." }, { - "left": "issue:44485", - "right": "issue:44509", + "left": "issue:30064", + "right": "issue:36331", "accept": false, - "reason": "RoPE implementation discussion and removed-pipeline-task documentation are unrelated." + "reason": "Void segmentation map processing and CustomTrainer compute_loss kwargs are unrelated." }, { "left": "issue:43606", "right": "issue:45072", "accept": false, - "reason": "Different model-specific inference mismatches: CPU offload device mismatch vs bfloat16 dtype mismatch." + "reason": "CPU offload device mismatch in Bark-small and bf16 dtype mismatches in wrappers are different bugs." }, { - "left": "issue:30064", - "right": "issue:36331", + "left": "issue:44485", + "right": "issue:44509", "accept": false, - "reason": "Image processor segmentation-map failure and CustomTrainer loss-signature breakage are unrelated." + "reason": "GLM-5 RoPE discussion and docs still mentioning removed pipeline tasks are unrelated." }, { "left": "issue:42175", "right": "issue:45081", "accept": false, - "reason": "Tensorflow packaging/backends and Mistral regex patching are different issues." + "reason": "TensorFlow backend installation and Mistral regex patch crash are unrelated." }, { "left": "issue:43782", "right": "issue:45325", "accept": false, - "reason": "Both are Qwen VL issues, but they affect different models and different mechanisms." + "reason": "Different Qwen model families and different bugs: weight_only loading vs still-image RoPE scaling." }, { "left": "issue:44610", "right": "issue:45072", "accept": false, - "reason": "OmDet image-size mismatch and dtype mismatches in other models are unrelated." + "reason": "Processor image-size mismatch and bf16 dtype mismatch are not the same code-path problem." }, { - "left": "issue:44060", - "right": "issue:44368", + "left": "issue:34634", + "right": "issue:36010", "accept": false, - "reason": "One is a tied-weights bug; the other is a user-facing warning about config, not the same defect." + "reason": "BarkProcessor voice_preset and GenerationMixin import failure are unrelated." }, { - "left": "issue:34634", - "right": "issue:36010", + "left": "issue:44060", + "right": "issue:44368", "accept": false, - "reason": "BarkProcessor voice preset and GenerationMixin import errors are unrelated." + "reason": "Both mention tied-weights warnings, but they involve different Qwen variants and different triggering conditions; not clearly the same concrete bug." }, { "left": "issue:45081", "right": "issue:45406", "accept": false, - "reason": "Both are attribute errors in processor/tokenizer code, but they hit different processors and fields." + "reason": "Both are processor/tokenizer attribute errors, but on different processors and different missing attributes; not mergeable as one fix." }, { "left": "issue:43720", "right": "issue:45072", "accept": false, - "reason": "BitNet packed-weight loading and bfloat16 dtype mismatches are different problems." + "reason": "Packed-weight unpacking in BitNet and dtype mismatches in other models are unrelated." }, { "left": "issue:43262", "right": "issue:43819", "accept": false, - "reason": "Audio sampling-rate defaulting and DAC latent reconstruction are unrelated." + "reason": "Audio chat-template sampling-rate defaulting and DAC latent mismatch are unrelated." }, { "left": "issue:43653", "right": "issue:44671", "accept": false, - "reason": "BigBird special-token registration and CamemBERT masked-LM output regressions are different bugs." - }, - { - "left": "issue:43749", - "right": "issue:44291", - "accept": false, - "reason": "Both involve loading, but FSDP RAM-efficient loading and init_empty_weights argument handling are distinct code paths." + "reason": "BigBirdTokenizer special-token registration and CamemBERT masked LM output regression are different model/tokenizer bugs." }, { "left": "issue:43582", "right": "issue:44857", "accept": false, - "reason": "Apple Silicon warmup TypeError and CUDA AMP image-loss crash are unrelated." + "reason": "Apple Silicon caching_allocator_warmup TypeError and LwDetrImageLoss AMP crash are unrelated." }, { - "left": "issue:43526", - "right": "issue:43697", + "left": "issue:43749", + "right": "issue:44291", "accept": false, - "reason": "BeitImageProcessorFast label reduction and RTDetrV2 output differences are not the same underlying issue." + "reason": "Both concern loading, but FSDP CPU RAM efficient loading and init_empty_weights with unexpected _is_hf_initialized are distinct failures." } ] }, @@ -4561,10 +4580,10 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:34567", "issue:34634", @@ -4576,7 +4595,6 @@ "issue:43257", "issue:43262", "issue:43329", - "issue:43450", "issue:43452", "issue:43454", "issue:43526", @@ -4608,6 +4626,7 @@ "issue:44977", "issue:44991", "issue:45042", + "issue:45072", "issue:45084", "issue:45356", "issue:45357", @@ -4616,6 +4635,7 @@ "issue:45600" ], "soft_pairs": [ + "issue:43526|issue:43697", "issue:43526|issue:44554", "issue:43329|issue:45600", "issue:45084|issue:45538", @@ -4626,243 +4646,258 @@ "issue:43638|issue:44936", "issue:43452|issue:44991", "issue:43257|issue:43329", - "issue:43854|issue:44977", "issue:43746|issue:44811", + "issue:43854|issue:44977", "issue:38175|issue:44610", "issue:44589|issue:45042", "issue:43257|issue:43696", "issue:39692|issue:44912", "issue:44568|issue:45356", "issue:43819|issue:43927", - "issue:43720|issue:44610", - "issue:43550|issue:44912", "issue:36010|issue:43645", + "issue:43720|issue:44610", "issue:43262|issue:44811", + "issue:43550|issue:44912", "issue:43749|issue:44756", - "issue:43329|issue:44479", "issue:43531|issue:45042", + "issue:43329|issue:44479", "issue:43257|issue:43931", "issue:43257|issue:43756", "issue:36010|issue:36331", - "issue:43697|issue:45357", "issue:34567|issue:40990", - "issue:43329|issue:43450" + "issue:43697|issue:45357", + "issue:43577|issue:45072" ], - "prepared_review_unit_hash": "022972e5321558d0ac00828515e031847a5a522e0e1917e22504a2517febed05", + "prepared_review_unit_hash": "ef7779cfb1cd1971437635f94a1811ef8055961ae7b6f7c8bb412c2ebf9f55eb", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 31, - "serialized_chars": 37223, - "estimated_input_tokens": 9306, - "estimated_eval_tokens": 18868 + "soft_pair_count": 32, + "serialized_chars": 37525, + "estimated_input_tokens": 9382, + "estimated_eval_tokens": 19020 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Most pairs are clearly unrelated regressions across different models/components. The only strong duplicate-like match is the Qwen video-input regression: the undefined-helper bug in `_get_num_multimodal_tokens` aligns with the broader v5.3.0 video-input failure report.", - "confidence": 0.82, - "canonical_issue_reason": "issue:43329 is the most concrete root-cause report for the Qwen video regression; it pinpoints the broken video branch in `_get_num_multimodal_tokens` with undefined helpers.", + "summary": "This cluster is a broad grab-bag of mostly unrelated closed issues across training, tokenizers, multimodal processing, loading, and model-specific regressions. I only see one plausible duplicate-style soft edge: the two video-regression reports around Qwen/VLM multimodal token counting. Everything else looks like distinct bugs.", + "confidence": 0.79, + "canonical_issue_reason": "No single canonical issue stands out because the cluster is heterogeneous; only issue:43329 has a clear duplicate-like counterpart in the soft pairs.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43329 best represents the duplicate cluster because it identifies the specific failing code path rather than only the downstream regression symptoms.", + "best_issue_reason": "issue:43329 is the strongest representative because it describes a concrete, reproducible multimodal video-path bug and is the only item that plausibly matches another report in the cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43526", + "right": "issue:43697", + "accept": false, + "reason": "Different subsystems and failure modes: Beit image label reduction vs RTDetrV2 output drift." + }, { "left": "issue:43526", "right": "issue:44554", "accept": false, - "reason": "Unrelated: BeitImageProcessorFast label reduction vs an MPS attention correctness issue." + "reason": "Unrelated bugs: image processor label handling vs an attention correctness issue on MPS." }, { "left": "issue:43329", "right": "issue:45600", "accept": false, - "reason": "Different areas: Qwen multimodal video token counting vs auto_mappings referencing removed configs." + "reason": "Different code paths: multimodal video token counting vs auto-mapping references to removed configs." }, { "left": "issue:45084", "right": "issue:45538", "accept": false, - "reason": "Unrelated failures: template-node compilation error vs CLIPTokenizer max_length behavior." + "reason": "No overlap in underlying bug: compilation error vs tokenizer max_length default behavior." }, { "left": "issue:43653", "right": "issue:44912", "accept": false, - "reason": "Different bugs: BigBird special-token registration vs gpt-oss quantization loading/fallback." + "reason": "Tokenizer special-token registration is unrelated to MXFP4 quantization loading." }, { "left": "issue:43454", "right": "issue:43577", "accept": false, - "reason": "Different code paths: AyaVision weight tying vs BLIP2 dtype loading." + "reason": "Different model families and issues: lm_head tying vs dtype propagation in BLIP2." }, { "left": "issue:44568", "right": "issue:45488", "accept": false, - "reason": "Both tokenizer-related, but different concrete bugs and models; no shared code-path shown." + "reason": "Both are tokenizer regressions, but they affect different models and different mechanisms." }, { "left": "issue:34634", "right": "issue:36331", "accept": false, - "reason": "BarkProcessor voice_preset issue is unrelated to CustomTrainer.compute_loss kwargs handling." + "reason": "BarkProcessor voice_preset failure is unrelated to CustomTrainer compute_loss keyword handling." }, { "left": "issue:43638", "right": "issue:44936", "accept": false, - "reason": "Both are training-related, but the failures differ: Zero3/non-pretrained Bert IndexError vs evaluate-after-train behavior." + "reason": "Different trainer failures: ZeRO-3/non-pretrained BERT indexing vs evaluate-after-train behavior." }, { "left": "issue:43452", "right": "issue:44991", "accept": false, - "reason": "Unrelated loading regressions: gguf_file handling vs a tokenizer load failure for EMBEDDIA/est-roberta." + "reason": "Both involve loading/tokenizers, but one is gguf_file + auto classes and the other is a specific tokenizer regression; not the same bug." }, { "left": "issue:43257", "right": "issue:43329", "accept": false, - "reason": "Different subsystems: Qwen3 MoE accelerate/deepspeed weight conversion vs Qwen video token counting." + "reason": "Qwen3 MOE weight conversion/load issue is unrelated to multimodal video token counting." }, { - "left": "issue:43854", - "right": "issue:44977", + "left": "issue:43746", + "right": "issue:44811", "accept": false, - "reason": "Different models and failure modes: GLM-4.7 test loading vs Qwen3.5 flash-attention generation." + "reason": "PEFT checkpoint loading for GraniteSpeech is unrelated to Whisper batch_decode special-token handling." }, { - "left": "issue:43746", - "right": "issue:44811", + "left": "issue:43854", + "right": "issue:44977", "accept": false, - "reason": "Unrelated: GraniteSpeech PEFT checkpoint loading vs Whisper batch_decode skip_special_tokens." + "reason": "Different model-specific inference/load problems: GLM-4.7-Flash loading vs Qwen3.5 flash-attention generation." }, { "left": "issue:38175", "right": "issue:44610", "accept": false, - "reason": "Different bugs: SigLIP2 zero probabilities vs OmDet-Turbo processor/model image-size mismatch." + "reason": "SigLIP2 zero probabilities and OmDet-Turbo input-size mismatch are distinct vision bugs." }, { "left": "issue:44589", "right": "issue:45042", "accept": false, - "reason": "Unrelated: Float8 storage lookup error vs PIL backend torchvision dependency regression." + "reason": "Float8 storage lookup error is unrelated to PIL backend requiring torchvision." }, { "left": "issue:43257", "right": "issue:43696", "accept": false, - "reason": "Different problems: MoE weight conversion/loading vs CUDA OOM." + "reason": "Qwen3 MOE conversion/loading differs from a CUDA OOM on GPT-oss-20b." }, { "left": "issue:39692", "right": "issue:44912", "accept": false, - "reason": "Docs example/model mismatch and quantization failure are not the same as gpt-oss MXFP4 loading behavior." + "reason": "Documentation example errors are unrelated to MXFP4 quantization loading." }, { "left": "issue:44568", "right": "issue:45356", "accept": false, - "reason": "Both tokenizer regressions, but they affect different models and token handling logic." + "reason": "Both are tokenizer-related, but they concern different tokenizers and different regression mechanisms." }, { "left": "issue:43819", "right": "issue:43927", "accept": false, - "reason": "Different issues: DAC STE/from_latents mismatch vs DiaConfig save/load losing custom token IDs." + "reason": "DAC forward/from_latents mismatch is unrelated to DiaConfig save/load token ID loss." + }, + { + "left": "issue:36010", + "right": "issue:43645", + "accept": false, + "reason": "GenerationMixin import failure and Jupyter custom-model init issues are distinct API breakages." }, { "left": "issue:43720", "right": "issue:44610", "accept": false, - "reason": "Packed-weight unpacking during accelerate loading is unrelated to OmDet-Turbo processor shape output." + "reason": "BitNet packed-weight loading is unrelated to OmDet-Turbo processor size mismatch." + }, + { + "left": "issue:43262", + "right": "issue:44811", + "accept": false, + "reason": "Audio chat-template sampling-rate default is unrelated to Whisper batch_decode skipping special tokens." }, { "left": "issue:43550", "right": "issue:44912", "accept": false, - "reason": "Different code paths: torch.compile+SDPA on Bamba vs quantization fallback on gpt-oss." + "reason": "torch.compile/SDPA failure is unrelated to MXFP4 quantization fallback." }, { - "left": "issue:36010", - "right": "issue:43645", + "left": "issue:43749", + "right": "issue:44756", "accept": false, - "reason": "The notebook/custom-model regression is too broad; the GenerationMixin import error is a distinct symptom without clear same root cause." + "reason": "FSDP CPU RAM-efficient loading and Strix Halo mmap/OOM are separate memory-loading issues." }, { - "left": "issue:43262", - "right": "issue:44811", + "left": "issue:43531", + "right": "issue:45042", "accept": false, - "reason": "Audio chat-template sampling-rate default is unrelated to Whisper batch_decode skip_special_tokens." + "reason": "Qwen3-MoE sliding_window behavior is unrelated to PIL backend torchvision requirements." }, { - "left": "issue:43749", - "right": "issue:44756", - "accept": false, - "reason": "FSDP CPU RAM efficient loading and Strix Halo mmap OOM are separate loading/memory issues." + "left": "issue:43329", + "right": "issue:44479", + "accept": true, + "reason": "These both point to the same video-input/multimodal regression path in Qwen/VLM processing, with 43329 naming the broken video branch directly." }, { "left": "issue:43257", "right": "issue:43931", "accept": false, - "reason": "Different loading failures: MoE conversion with accelerate/deepspeed vs Qwen3-VL weight-shape mismatch." + "reason": "Qwen3 MOE loading/weight conversion is unrelated to Qwen3-VL shape mismatch." }, { "left": "issue:43257", "right": "issue:43756", "accept": false, - "reason": "Unrelated model-specific issues: MoE conversion vs Smollm3 RoPE-layer mismatch." + "reason": "Different model families and bugs: MOE loading vs Smollm3 RoPE-layer configuration." }, { - "left": "issue:43697", - "right": "issue:45357", + "left": "issue:36010", + "right": "issue:36331", "accept": false, - "reason": "Different regressions: RTDetrV2 output differences vs Qwen3.5 save_pretrained key mapping." + "reason": "Importing GenerationMixin and CustomTrainer.compute_loss keyword mismatch are unrelated failures." }, { "left": "issue:34567", "right": "issue:40990", "accept": false, - "reason": "TrainerState token counter not updating is unrelated to GPT-oss perplexity." - }, - { - "left": "issue:43329", - "right": "issue:43450", - "accept": false, - "reason": "Both involve video processing, but one is a broken multimodal-token helper in the video branch while the other is batched processor shape output; not the same concrete bug." + "reason": "Trainer input-token counter bug is unrelated to GPT-oss perplexity behavior." }, { - "left": "issue:43653", - "right": "issue:44912", + "left": "issue:43697", + "right": "issue:45357", "accept": false, - "reason": "Tokenizer special-token registration bug is unrelated to gpt-oss quantization behavior." + "reason": "RTDetrV2 output drift and Qwen3.5 visual-encoder save_pretrained regression are separate model-specific bugs." }, { - "left": "issue:43531", - "right": "issue:45042", + "left": "issue:43577", + "right": "issue:45072", "accept": false, - "reason": "Qwen3-MoE sliding-window bug is unrelated to PIL backend requiring torchvision." + "reason": "BLIP2 dtype propagation and SwitchTransformers/TimmWrapperModel bfloat16 mismatches are different loading/inference bugs." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: it stays conservative about the cluster being heterogeneous, and it only endorses one soft pair that is plausibly the same multimodal video-path regression. No soft-edge verdict overstates the evidence." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -4877,7 +4912,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:28282", "issue:33357", @@ -4889,10 +4924,12 @@ "issue:42175", "issue:42915", "issue:43317", + "issue:43329", + "issue:43450", "issue:43452", + "issue:43493", "issue:43526", "issue:43540", - "issue:43577", "issue:43582", "issue:43643", "issue:43646", @@ -4903,13 +4940,12 @@ "issue:43824", "issue:43906", "issue:43927", + "issue:43994", "issue:44062", "issue:44291", "issue:44479", - "issue:44484", "issue:44488", "issue:44560", - "issue:44704", "issue:44737", "issue:44821", "issue:44898", @@ -4918,7 +4954,6 @@ "issue:44987", "issue:44991", "issue:45042", - "issue:45072", "issue:45137", "issue:45325", "issue:45375", @@ -4929,227 +4964,222 @@ "issue:45588" ], "soft_pairs": [ - "issue:43577|issue:45072", - "issue:42175|issue:44938", + "issue:43329|issue:43450", + "issue:43452|issue:43582", "issue:41720|issue:43540", "issue:44479|issue:45381", - "issue:43452|issue:43582", + "issue:42175|issue:44938", "issue:44987|issue:45538", "issue:43317|issue:45538", - "issue:43906|issue:45381", "issue:43927|issue:44912", "issue:43540|issue:44560", "issue:44291|issue:45042", + "issue:33357|issue:34567", + "issue:43906|issue:45381", "issue:43540|issue:44479", "issue:42915|issue:45538", - "issue:33357|issue:34567", "issue:42915|issue:43742", "issue:42175|issue:43824", "issue:44737|issue:45588", "issue:43526|issue:45479", - "issue:42175|issue:44488", "issue:42915|issue:44821", + "issue:42175|issue:44488", "issue:44062|issue:44991", "issue:45137|issue:45405", "issue:38175|issue:44898", "issue:43582|issue:43782", "issue:43646|issue:43749", - "issue:43643|issue:45375", "issue:28282|issue:34689", "issue:36010|issue:42175", + "issue:43643|issue:45375", "issue:43756|issue:45325", - "issue:44484|issue:44704" + "issue:43742|issue:44291", + "issue:43493|issue:43994" ], - "prepared_review_unit_hash": "4bbaf97b258892c65b134cd9790c05c7a6e21e72576fe352b6e72ce3354640a6", + "prepared_review_unit_hash": "0df656a80f63ba86672f02b6dfe8e0bfbe247e97fcac64ac5c0af9ed87387132", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 30, - "serialized_chars": 36755, - "estimated_input_tokens": 9189, - "estimated_eval_tokens": 18634 + "soft_pair_count": 31, + "serialized_chars": 37106, + "estimated_input_tokens": 9277, + "estimated_eval_tokens": 18810 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly unrelated issues across different models, environments, and failure modes. The only strong duplicate-like pair is the Qwen2.5-VL video input regression cluster.", - "confidence": 0.89, - "canonical_issue_reason": "issue:44479 is the broadest and most representative bug report in the only clear duplicate cluster, covering the v5.3.0 video-input regression and the Qwen2.5-VL symptom specifically called out by the narrower report.", + "summary": "The packet is mostly heterogeneous, but there are two solid duplicate subclusters: the Qwen video-input regression and the SigLIP2 discrepancy reports. The tokenizer pair `issue:44062` / `issue:44991` is not strong enough to merge on the evidence shown and is rejected conservatively.", + "confidence": 0.64, + "canonical_issue_reason": "Issue 44479 is the broadest, most explicit representative of the Qwen video-input regression subcluster, covering multiple affected Qwen VL variants and serving as the best anchor among the candidate issues.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44479 is the clearest canonical issue overall because it is concrete, versioned, and captures the shared code-path regression behind the related Qwen video-input reports.", + "best_issue_reason": "Issue 44479 is the strongest global issue candidate because it is the most central and broadly scoped duplicate target in the packet; the other items are either narrower repros or unrelated bugs.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43577", - "right": "issue:45072", + "left": "issue:43329", + "right": "issue:43450", "accept": false, - "reason": "Both are dtype-related, but they affect different models and different loading/inference paths; not the same concrete bug." + "reason": "Both are video-related, but one is an undefined-variable bug in multimodal token counting and the other is a batched-shape bug in video processors." }, { - "left": "issue:42175", - "right": "issue:44938", + "left": "issue:43452", + "right": "issue:43582", "accept": false, - "reason": "One is a missing TensorFlow backend dependency, the other is a Python 3.14 load failure; different causes and fixes." + "reason": "Completely different areas: gguf/tokenizer loading vs Apple Silicon allocator warmup." }, { "left": "issue:41720", "right": "issue:43540", "accept": false, - "reason": "Both are Qwen/video-related, but one is a CUDA assert during device mapping and the other is a video-input ValueError in a different model path." + "reason": "Different failure modes and code paths: auto device-mapping CUDA assert vs Qwen3OmniMoe video-input validation." }, { "left": "issue:44479", "right": "issue:45381", "accept": true, - "reason": "Both report the same Qwen2.5-VL video-input / position-id regression in v5.3.0; 45381 is a narrower symptom of the broader bug." + "reason": "Same underlying Qwen VL video-position-id regression; 45381 is a narrower repro of the broader 44479 video-input breakage." }, { - "left": "issue:43452", - "right": "issue:43582", + "left": "issue:42175", + "right": "issue:44938", "accept": false, - "reason": "Tokenizer/model gguf loading failure and AppleSilicon allocator TypeError are unrelated bugs." + "reason": "Unrelated packaging/backend issue vs Python 3.14 load failure." }, { "left": "issue:44987", "right": "issue:45538", "accept": false, - "reason": "Different topics: model loading for a specific repo versus an oversized CLIP tokenizer max length default." + "reason": "Tokenizer/model loading failure and CLIP max-length constant issue are different bugs." }, { "left": "issue:43317", "right": "issue:45538", "accept": false, - "reason": "GPU/CPU offload with dequantized models is unrelated to the CLIPTokenizer max_length issue." - }, - { - "left": "issue:43906", - "right": "issue:45381", - "accept": false, - "reason": "A reproduction of a prior issue is not the same as the Qwen2.5-VL video position-id regression." + "reason": "Unrelated device-map/offload bug vs tokenizer configuration bug." }, { "left": "issue:43927", "right": "issue:44912", "accept": false, - "reason": "Custom token IDs lost on save/load is unrelated to MXFP4 quantization fallback during model loading." + "reason": "Different code paths: config save/load losing token IDs vs quantization fallback to bf16." }, { "left": "issue:43540", "right": "issue:44560", "accept": false, - "reason": "Both mention Qwen video inputs, but the model families and concrete failures differ (ValueError vs StopIteration)." + "reason": "Both concern Qwen video inputs, but the model variants and concrete errors differ too much to treat as the same bug." }, { "left": "issue:44291", "right": "issue:45042", "accept": false, - "reason": "init_empty_weights constructor argument handling and PIL backend torchvision dependency are different code paths." + "reason": "Unrelated issues: init_empty_weights argument handling vs PIL backend torchvision dependency." }, { - "left": "issue:43540", - "right": "issue:44479", + "left": "issue:33357", + "right": "issue:34567", "accept": false, - "reason": "Related model area, but different Qwen variants and different failure behavior; not clearly one underlying bug." + "reason": "MacOS bus error on CLIP vs TrainerState token-count tracking are unrelated." }, { - "left": "issue:42915", - "right": "issue:45538", + "left": "issue:43906", + "right": "issue:45381", "accept": false, - "reason": "FineGrainedFP8Config loading failure is unrelated to tokenizer max_length behavior." + "reason": "No clear evidence these are the same bug; one is an isolated reproduction of a different issue." }, { - "left": "issue:33357", - "right": "issue:34567", + "left": "issue:43540", + "right": "issue:44479", + "accept": false, + "reason": "Related theme, but not the same concrete bug: different Qwen video code paths and different symptoms." + }, + { + "left": "issue:42915", + "right": "issue:45538", "accept": false, - "reason": "MacOS bus error in CLIP loading and TrainerState token counting are unrelated issues." + "reason": "FP8 config failure and CLIP tokenizer max-length bug are unrelated." }, { "left": "issue:42915", "right": "issue:43742", "accept": false, - "reason": "Different model-loading failures with no shared concrete code-path problem." + "reason": "Different problems: FineGrainedFP8Config loading vs MobileLLM key error." }, { "left": "issue:42175", "right": "issue:43824", "accept": false, - "reason": "TensorFlow backend packaging and missing Qwen2.5-VL export are unrelated." + "reason": "Packaging/backend installation issue vs missing Qwen class import." }, { "left": "issue:44737", "right": "issue:45588", "accept": false, - "reason": "XLNet CPU placement bug and flash_attention sink-less crash affect different modules and mechanisms." + "reason": "XLNet CPU allocation bug and flash-attention null-aux crash are unrelated." }, { "left": "issue:43526", "right": "issue:45479", "accept": false, - "reason": "BEiT image processor label reduction and sequence-classification zero-loss are unrelated behaviors." + "reason": "Different model families and failure modes: BEiT label reduction vs degenerate zero loss in sequence classification." }, { - "left": "issue:42175", - "right": "issue:44488", + "left": "issue:42915", + "right": "issue:44821", "accept": false, - "reason": "Missing TensorFlow backend and a model load failure for a specific repo are not the same bug." + "reason": "FP8 config bug and AutoImageProcessor URL loading are unrelated." }, { - "left": "issue:42915", - "right": "issue:44821", + "left": "issue:42175", + "right": "issue:44488", "accept": false, - "reason": "Quantization/config loading failure is unrelated to AutoImageProcessor URL loading." + "reason": "Backend installation issue vs model/tokenizer loading failure." }, { "left": "issue:44062", "right": "issue:44991", "accept": false, - "reason": "AddedToken constructor error and tokenizer loading failure for a specific model are different issues." + "reason": "One side is a specific AddedToken TypeError and the other is a generic tokenizer-loading failure; the available evidence does not show the same underlying regression." }, { "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 PEFT version pin issue are unrelated." }, { "left": "issue:38175", "right": "issue:44898", "accept": false, - "reason": "Unexpected zero probabilities in one vision model and Perceiver resize failure are different model-specific bugs." + "reason": "Different model/feature areas: SigLIP2 output anomaly vs Perceiver positional-encoding interpolation." }, { "left": "issue:43582", "right": "issue:43782", "accept": false, - "reason": "AppleSilicon allocator warmup TypeError and Qwen3VL weight_only loading error are unrelated." + "reason": "Apple Silicon TypeError and Qwen3VL weight_only loading error are different bugs." }, { "left": "issue:43646", "right": "issue:43749", "accept": false, - "reason": "Custom model initialization breakage in v5.0 and FSDP CPU RAM-efficient loading are distinct problems." - }, - { - "left": "issue:43643", - "right": "issue:45375", - "accept": false, - "reason": "Missing fields with trust_remote_code and a dropped Qwen3_5MoeVisionConfig field are not clearly the same bug." + "reason": "General custom model init breakage vs FSDP CPU RAM efficient loading are not the same concrete failure." }, { "left": "issue:28282", "right": "issue:34689", "accept": false, - "reason": "ImportError for missing PyTorch and model loading breakage for Llama 3.2 Vision have different root causes." + "reason": "Missing PyTorch import and Llama 3.2 Vision loading regression are unrelated." }, { "left": "issue:36010", @@ -5157,26 +5187,38 @@ "accept": false, "reason": "GenerationMixin import failure and TensorFlow backend packaging are unrelated." }, + { + "left": "issue:43643", + "right": "issue:45375", + "accept": false, + "reason": "Both involve config fields, but the titles indicate different mechanisms and no clear same-bug evidence." + }, { "left": "issue:43756", "right": "issue:45325", "accept": false, - "reason": "Smollm3 RoPE-layer selection and Qwen2.5-VL temporal position scaling are different model-specific bugs." + "reason": "RoPE-layer omission and temporal position-id scaling are different bugs." }, { - "left": "issue:44484", - "right": "issue:44704", + "left": "issue:43742", + "right": "issue:44291", "accept": false, - "reason": "save_pretrained shard-size behavior and cached_file kwarg forwarding are unrelated." + "reason": "MobileLLM key error and init_empty_weights argument mismatch are unrelated." + }, + { + "left": "issue:43493", + "right": "issue:43994", + "accept": true, + "reason": "Same SigLIP2 model family and same underlying incorrect-output discrepancy; 43994 is a user-facing repro of the HF-vs-JAX mismatch." } ] }, "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative overall. The only accepted soft-edge pair is well-supported by the titles: issue:44479 broadly covers the v5.3.0 video-input regression, and issue:45381 is a narrower qwen2.5-vl symptom. The other pair verdicts are phrased cautiously and do not overclaim shared root causes." + "accept": false, + "feedback": "The cluster summary is mostly grounded, but one soft-edge accept is too strong for the packet: `issue:44062` / `issue:44991` only shows a specific AddedToken TypeError on one side and a generic tokenizer-loading failure on the other, so calling them the same underlying regression goes beyond the evidence available here. The Qwen video and SigLIP2 overlaps are plausible, but that pair makes the verdict non-conservative." }, "evaluator_used": true, - "retried": false, + "retried": true, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -5189,20 +5231,18 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:28282", "issue:29127", "issue:34567", "issue:36331", - "issue:41720", "issue:41762", "issue:43295", "issue:43452", - "issue:43493", "issue:43531", "issue:43577", "issue:43643", @@ -5213,17 +5253,19 @@ "issue:43742", "issue:43749", "issue:43819", - "issue:43906", - "issue:43994", "issue:44062", "issue:44291", + "issue:44464", "issue:44466", + "issue:44484", "issue:44488", "issue:44514", "issue:44561", "issue:44568", "issue:44589", "issue:44625", + "issue:44704", + "issue:44743", "issue:44792", "issue:44811", "issue:44821", @@ -5244,237 +5286,230 @@ "issue:45600" ], "soft_pairs": [ - "issue:43493|issue:43994", - "issue:43742|issue:44291", "issue:28282|issue:29127", - "issue:44062|issue:45081", + "issue:44484|issue:44704", "issue:34567|issue:36331", - "issue:43452|issue:44488", + "issue:44062|issue:45081", "issue:44291|issue:44821", - "issue:44514|issue:45290", + "issue:43452|issue:44488", "issue:44792|issue:44964", - "issue:43688|issue:43749", + "issue:44514|issue:45290", "issue:45405|issue:45600", + "issue:43688|issue:43749", "issue:43643|issue:44561", "issue:44514|issue:45381", - "issue:43697|issue:45216", "issue:43452|issue:43577", + "issue:43697|issue:45216", "issue:43742|issue:44589", "issue:45042|issue:45081", "issue:43531|issue:44821", "issue:43688|issue:45440", "issue:43452|issue:44843", - "issue:43653|issue:44568", "issue:44625|issue:44877", + "issue:43653|issue:44568", "issue:43720|issue:44898", - "issue:43295|issue:45356", - "issue:41762|issue:44936", "issue:43819|issue:44811", + "issue:41762|issue:44936", + "issue:43295|issue:45356", "issue:44466|issue:45005", - "issue:41720|issue:43906" + "issue:44464|issue:44743" ], - "prepared_review_unit_hash": "b4773358d07fdb69285f742df08050e499ec0879cff3cd9460929bd51bc8995b", + "prepared_review_unit_hash": "1900b5e6f3f8b4004d3f6d8d01e5d6234391e7e6efaff901060e88c7b1c4381a", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 28, - "serialized_chars": 36495, - "estimated_input_tokens": 9124, - "estimated_eval_tokens": 18504 + "soft_pair_count": 27, + "serialized_chars": 36193, + "estimated_input_tokens": 9049, + "estimated_eval_tokens": 18354 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is heterogeneous: most items are unrelated regressions or feature bugs across tokenizers, trainer, model loading, and multimodal processors. Only a couple of soft pairs look like true duplicates or near-duplicates.", - "confidence": 0.79, - "canonical_issue_reason": "No single canonical issue fits the cluster well; it spans several distinct bug families rather than one underlying defect.", + "summary": "Most pairs are unrelated bug reports touching different code paths. The only plausible duplicate is the v5 tied-weights serialization/saving regression pair.", + "confidence": 0.62, + "canonical_issue_reason": "issue:45005 is the broader, more canonical description of the v5 tied-weights save/serialization regression; issue:44466 reads like a specific manifestation depending on model device.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43452 is the clearest representative of a concrete, user-facing loading regression with broad API impact, but it is not a true umbrella for the whole set.", + "best_issue_reason": "issue:45005 is the best global issue candidate because it captures the underlying tied-weights problem more generally and is easier to map to related symptoms.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:43493", - "right": "issue:43994", - "accept": true, - "reason": "Both describe the same SigLIP2 model correctness problem: HF outputs disagree with the reference implementation and produce nonsensical results through AutoModel/pipeline." - }, - { - "left": "issue:43742", - "right": "issue:44291", - "accept": false, - "reason": "Both are loading failures, but the concrete bugs differ: a key error in MobileLLM loading vs an init_empty_weights/_is_hf_initialized argument mismatch." - }, { "left": "issue:28282", "right": "issue:29127", "accept": false, - "reason": "Completely different problems: missing PyTorch import vs a LayoutLMv3 validation/error-message issue." + "reason": "Different failures: missing PyTorch dependency vs clearer LayoutLMv3 error messaging." }, { - "left": "issue:44062", - "right": "issue:45081", + "left": "issue:44484", + "right": "issue:44704", "accept": false, - "reason": "Both touch tokenizer loading, but the failure modes and code paths differ: AddedToken special-arg duplication vs _patch_mistral_regex assuming backend_tokenizer exists." + "reason": "One is about max shard size defaults; the other is AutoProcessor failing to forward kwargs to cached_file." }, { "left": "issue:34567", "right": "issue:36331", "accept": false, - "reason": "Trainer-related, but not the same bug: num_input_tokens_seen not updating vs CustomTrainer.compute_loss signature breaking on num_items_in_batch." + "reason": "TrainerState token counting and CustomTrainer.compute_loss keyword incompatibility are separate trainer issues." }, { - "left": "issue:43452", - "right": "issue:44488", + "left": "issue:44062", + "right": "issue:45081", "accept": false, - "reason": "Both involve model/tokenizer loading, but there is no clear evidence they stem from the same concrete regression or code path." + "reason": "AddedToken special-argument duplication is unrelated to the Mistral regex backend_tokenizer crash." }, { "left": "issue:44291", "right": "issue:44821", "accept": false, - "reason": "Unrelated loading paths: init_empty_weights argument handling vs AutoImageProcessor URL loading." + "reason": "init_empty_weights/_is_hf_initialized and loading AutoImageProcessor from URL are different loading failures." }, { - "left": "issue:44514", - "right": "issue:45290", + "left": "issue:43452", + "right": "issue:44488", "accept": false, - "reason": "Both are chat-template crashes, but the triggers are different and likely independent: batched padding=False vs tool-call assistant messages with no content." + "reason": "Both are model loading problems, but the affected APIs and failure modes are not the same." }, { "left": "issue:44792", "right": "issue:44964", "accept": false, - "reason": "Different multimodal models and symptoms; one is a failing Janus test, the other is a Phi-4 multimodal loading regression." + "reason": "A failed Janus image-generation test is not the same bug as failing to load Phi-4 multimodal." }, { - "left": "issue:43688", - "right": "issue:43749", + "left": "issue:44514", + "right": "issue:45290", "accept": false, - "reason": "Distinct bugs in different subsystems: auxiliary loss normalization vs FSDP CPU RAM efficient loading." + "reason": "Both involve apply_chat_template, but one is batched padding behavior and the other is tool-call assistant message handling." }, { "left": "issue:45405", "right": "issue:45600", "accept": false, - "reason": "Not the same issue: an unreleased dependency version bump vs stale auto-mapping references breaking CI." + "reason": "Unreleased PEFT minimum version and removed Sam3LiteText config references are unrelated CI/versioning issues." + }, + { + "left": "issue:43688", + "right": "issue:43749", + "accept": false, + "reason": "Auxiliary-loss normalization in MoE models is unrelated to broken FSDP CPU RAM-efficient loading." }, { "left": "issue:43643", "right": "issue:44561", "accept": false, - "reason": "Both mention trust_remote_code, but the regressions differ: missing config fields vs removal of is_torch_fx_available." + "reason": "Missing fields from trust_remote_code AutoConfig and removal of is_torch_fx_available are different regressions." }, { "left": "issue:44514", "right": "issue:45381", "accept": false, - "reason": "Different Qwen2.5-VL regressions affecting different parts of processor/chat-template handling." + "reason": "Different Qwen2.5-VL bugs: chat templating on batches vs wrong video vision_position_ids." }, { - "left": "issue:43697", - "right": "issue:45216", + "left": "issue:43452", + "right": "issue:43577", "accept": false, - "reason": "Different model families and failure modes: RTDetrV2 output drift vs Qwen3.5 save_pretrained checkpoint corruption." + "reason": "gguf_file loading breakage is unrelated to BLIP2 dtype propagation staying float32." }, { - "left": "issue:43452", - "right": "issue:43577", + "left": "issue:43697", + "right": "issue:45216", "accept": false, - "reason": "Both are loading/model issues, but one is GGUF/from_pretrained breakage and the other is a dtype propagation bug in Blip2." + "reason": "RTDetrV2 output divergence and Qwen3.5 save_pretrained checkpoint correctness are different problems." }, { "left": "issue:43742", "right": "issue:44589", "accept": false, - "reason": "Both are load-time errors, but one is a key error in model loading and the other is a missing Float8 storage type." + "reason": "MobileLLM key error and missing Float8 storage type are separate loading/storage issues." }, { "left": "issue:45042", "right": "issue:45081", "accept": false, - "reason": "Different regressions in unrelated tokenizer/image-processing code paths." + "reason": "PIL/torchvision dependency regression is not the same as the Mistral regex tokenizer crash." }, { "left": "issue:43531", "right": "issue:44821", "accept": false, - "reason": "Different subsystems and symptoms: Qwen3-MoE sliding_window behavior vs AutoImageProcessor URL loading." + "reason": "Qwen3-MoE sliding_window behavior and AutoImageProcessor URL loading are unrelated." }, { "left": "issue:43688", "right": "issue:45440", "accept": false, - "reason": "Different model families and bugs: auxiliary loss normalization vs DeepSeekV3 implementation divergence." + "reason": "Both are MoE-related, but auxiliary-loss normalization and DeepSeekV3 implementation divergence are different bugs." }, { "left": "issue:43452", "right": "issue:44843", "accept": false, - "reason": "One is GGUF/from_pretrained loading breakage; the other is an offline-mode failure in _patch_mistral_regex." + "reason": "gguf_file loading failure is unrelated to model_info being called in offline mode." }, { - "left": "issue:43653", - "right": "issue:44568", + "left": "issue:44625", + "right": "issue:44877", "accept": false, - "reason": "Both concern special tokens, but the concrete issues differ by tokenizer and behavior." + "reason": "num_labels propagation and strict granite_speech config loading are separate config issues." }, { - "left": "issue:44625", - "right": "issue:44877", + "left": "issue:43653", + "right": "issue:44568", "accept": false, - "reason": "Unrelated config issues: num_labels propagation vs strict config blocking granite_speech loading." + "reason": "BigBird mask-token special registration and mdeberta BOS/EOS insertion are different tokenizer bugs." }, { "left": "issue:43720", "right": "issue:44898", "accept": false, - "reason": "Different model/code paths: BitNet packed-weight loading vs Perceiver interpolation on non-default resolution." + "reason": "BitNet packed-weight loading and Perceiver non-default resolution handling are unrelated." }, { - "left": "issue:43295", - "right": "issue:45356", + "left": "issue:43819", + "right": "issue:44811", "accept": false, - "reason": "Different regressions: processor.tokenizer/image routing breakage vs Kimi-K2.5 codec and warning behavior." + "reason": "DAC latent reconstruction mismatch and Whisper batch_decode skip_special_tokens behavior are different code paths." }, { "left": "issue:41762", "right": "issue:44936", "accept": false, - "reason": "Different trainer/loading failures: ZeRO-3 model load index error vs evaluate-after-train failure." + "reason": "Gemma3 ZeRO-3 load failure and trainer.evaluate after train are not the same issue." }, { - "left": "issue:43819", - "right": "issue:44811", + "left": "issue:43295", + "right": "issue:45356", "accept": false, - "reason": "Different functionality entirely: DAC latent reconstruction vs Whisper batch_decode special-token handling." + "reason": "Custom processor/tokenizer regression and Kimi-K2.5 codec/fix_mistral_regex regression are different tokenizer issues." }, { "left": "issue:44466", "right": "issue:45005", "accept": true, - "reason": "Both point to the same tied-weights serialization regression in v5, with device-dependent lm_head.weight behavior and translation models as manifestations of the same bug." + "reason": "Both describe the same v5 tied-weights/save_pretrained serialization regression; 45005 is the broader translation-model manifestation and 44466 is a device-dependent symptom." }, { - "left": "issue:41720", - "right": "issue:43906", + "left": "issue:44464", + "right": "issue:44743", "accept": false, - "reason": "Different Qwen3-related problems: auto device mapping cudaErrorAssert vs a reproduction of another issue." + "reason": "Chunked generation with compiled forward and Qwen3.5 recurrent state reset are distinct generation/runtime bugs." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is well grounded in the packet and stays conservative about the soft edges. The two accepted pairs are plausibly the same underlying bug family, and the rejected pairs avoid overstating similarity. No mergeability problems are apparent." + "feedback": "The summary is well grounded in the packet and stays mostly conservative. The soft-edge verdicts generally separate clearly different issue titles/code paths, and the lone accepted pair is a plausible duplicate based on the shared tied-weights/v5 serialization theme. No obvious overstatement beyond the evidence in the titles." }, "evaluator_used": true, "retried": false, @@ -5490,10 +5525,10 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:24643", "issue:28282", @@ -5502,11 +5537,13 @@ "issue:32090", "issue:33357", "issue:33666", + "issue:34567", "issue:35141", "issue:38175", "issue:41720", "issue:43122", "issue:43262", + "issue:43278", "issue:43295", "issue:43329", "issue:43452", @@ -5517,6 +5554,7 @@ "issue:43577", "issue:43643", "issue:43653", + "issue:43688", "issue:43697", "issue:43720", "issue:43742", @@ -5530,31 +5568,28 @@ "issue:44554", "issue:44610", "issue:44625", - "issue:44743", "issue:44843", "issue:44849", "issue:44936", "issue:44977", "issue:44991", "issue:45084", - "issue:45200", - "issue:45229", "issue:45325", "issue:45356", "issue:45357", "issue:45588" ], "soft_pairs": [ - "issue:44464|issue:44743", - "issue:43525|issue:43643", + "issue:41720|issue:43906", "issue:24643|issue:29127", + "issue:43525|issue:43643", "issue:43577|issue:43697", - "issue:44361|issue:44442", "issue:38175|issue:43295", + "issue:44361|issue:44442", "issue:44843|issue:44991", "issue:43653|issue:44361", - "issue:43122|issue:43906", "issue:44479|issue:44936", + "issue:43122|issue:43906", "issue:44977|issue:45356", "issue:28282|issue:32090", "issue:28282|issue:33357", @@ -5562,235 +5597,249 @@ "issue:43577|issue:45588", "issue:30064|issue:33666", "issue:43577|issue:44554", - "issue:43653|issue:43927", "issue:44464|issue:44977", - "issue:43329|issue:45325", + "issue:43653|issue:43927", "issue:43531|issue:43742", - "issue:43550|issue:44361", + "issue:43329|issue:45325", "issue:44479|issue:44625", - "issue:43504|issue:43720", + "issue:43550|issue:44361", + "issue:41720|issue:44464", "issue:43452|issue:44451", + "issue:43504|issue:43720", "issue:43504|issue:43550", - "issue:41720|issue:44464", "issue:44849|issue:45357", "issue:43262|issue:45084", - "issue:45200|issue:45229", - "issue:43504|issue:44610" + "issue:32090|issue:34567", + "issue:32090|issue:33666", + "issue:43504|issue:44610", + "issue:43278|issue:43688" ], - "prepared_review_unit_hash": "31db77567e6a1728bedf20843efe71cdea887bdd0d5de5ec4197675a925babf4", + "prepared_review_unit_hash": "c7aadc8dc6bb4a8d4f8e3ad1b7007cb8775c8bdd11fefbdfe90ec8604c976f36", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 31, - "serialized_chars": 37234, - "estimated_input_tokens": 9309, - "estimated_eval_tokens": 18874 + "soft_pair_count": 33, + "serialized_chars": 37812, + "estimated_input_tokens": 9453, + "estimated_eval_tokens": 19162 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is heterogeneous: the items span unrelated tokenizer, processor, generation, training, and model-loading bugs/regressions. None of the soft pairs look like the same underlying defect, so there is no strong duplicate canonical here.", - "confidence": 0.83, - "canonical_issue_reason": "No clear canonical issue: the set is too diverse to collapse onto one underlying bug or fix target.", + "summary": "This cluster is a heterogeneous mix of unrelated Transformers issues: model loading, tokenizers, multimodal processors, training/TrainerState, dtype drift, and a few Qwen/BLIP/BEiT-specific regressions. The soft edges are mostly superficial text similarity, not true duplicates.", + "confidence": 0.96, + "canonical_issue_reason": "Issue 43504 is the closest thing to a hub because it is a concrete model-loading failure and sits near several other load-time regressions by wording, but the cluster is still too mixed to have a real duplicate canonical issue.", "canonical_pr_reason": null, - "best_issue_reason": "No single issue is a good global representative; the cluster is too heterogeneous for a meaningful best duplicate target.", + "best_issue_reason": "Issue 43504 is the least bad representative of the cluster\u2019s broad loading-regression theme, but it is not a safe global canonical because the linked issues span different models and code paths.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44464", - "right": "issue:44743", + "left": "issue:41720", + "right": "issue:43906", "accept": false, - "reason": "Different generation regressions: compiled-forward inconsistency vs recurrent state reset with cache." + "reason": "Different bugs: Qwen3 auto device mapping CUDA assert vs an isolated reproduction of another issue." }, { - "left": "issue:43525", - "right": "issue:43643", + "left": "issue:24643", + "right": "issue:29127", "accept": false, - "reason": "Different config-loading problems: missing pad_token_id vs missing fields from trust_remote_code AutoConfig." + "reason": "Unrelated symptoms and code paths: DeepSpeed weight shape error vs LayoutLMv3 box validation/message clarity." }, { - "left": "issue:24643", - "right": "issue:29127", + "left": "issue:43525", + "right": "issue:43643", "accept": false, - "reason": "Different failures: DeepSpeed training runtime error vs LayoutLMv3 box-information validation/error messaging." + "reason": "Both are config-related, but one is a missing pad_token_id on Llama4 and the other is trust_remote_code dropping fields; not the same bug." }, { "left": "issue:43577", "right": "issue:43697", "accept": false, - "reason": "Different bugs: BLIP2 dtype handling vs RTDetrV2 output divergence in v5." + "reason": "Different models and failures: BLIP2 dtype preservation vs RTDetrV2 output drift." }, { - "left": "issue:44361", - "right": "issue:44442", + "left": "issue:38175", + "right": "issue:43295", "accept": false, - "reason": "Different tokenizer loading failures for different models and code paths." + "reason": "SigLIP2 zero-probability issue and processor.tokenizer/images regression are different problems." }, { - "left": "issue:38175", - "right": "issue:43295", + "left": "issue:44361", + "right": "issue:44442", "accept": false, - "reason": "Different symptoms: siglip2 zero probabilities vs processor.tokenizer/custom image-passing regression." + "reason": "Different tokenizer failures: MLukeTokenizer task error vs FastSpeech2ConformerTokenizer load failure." }, { "left": "issue:44843", "right": "issue:44991", "accept": false, - "reason": "Both affect tokenizer loading, but one is an offline model_info call and the other is a model-specific tokenizer load failure." + "reason": "Offline model_info() call in tokenizer patch vs EMBEDDIA/est-roberta loading regression; different causes." }, { "left": "issue:43653", "right": "issue:44361", "accept": false, - "reason": "BigBird special-token decode issue is unrelated to MLukeTokenizer task-time AttributeError." + "reason": "BigBird special-token decode bug is not the same as MLukeTokenizer task AttributeError." }, { - "left": "issue:43122", - "right": "issue:43906", + "left": "issue:44479", + "right": "issue:44936", "accept": false, - "reason": "Insufficient evidence they share the same root cause; one is a tokenizer regression, the other is a reproduction of a different issue." + "reason": "Qwen video-input regression vs trainer.evaluate() failing after train(); unrelated." }, { - "left": "issue:44479", - "right": "issue:44936", + "left": "issue:43122", + "right": "issue:43906", "accept": false, - "reason": "Different areas: Qwen VL video regression vs trainer.evaluate() failure after train()." + "reason": "Version-to-version tokenization change is not the same as the isolated reproduction of another bug." }, { "left": "issue:44977", "right": "issue:45356", "accept": false, - "reason": "Different problems: Qwen3.5 flash-attention generation bug vs Kimi-K2.5 tokenizer codec regression." + "reason": "Different surfaces: flash-attention generation failure in Qwen3.5 vs tokenizer codec handling regression in Kimi-K2.5." }, { "left": "issue:28282", "right": "issue:32090", "accept": false, - "reason": "Completely different: missing PyTorch import vs NoneType broadcast in Trainer." + "reason": "Missing PyTorch import error vs NoneType passed to _gpu_broadcast_one; unrelated." }, { "left": "issue:28282", "right": "issue:33357", "accept": false, - "reason": "Different failures: missing PyTorch import vs MacOS bus error with community CLIP." + "reason": "Environment import failure vs MacOS bus error in CLIP model loading; not the same issue." }, { "left": "issue:28282", "right": "issue:35141", "accept": false, - "reason": "Different issues: import error vs embedding reinitialization after resize." + "reason": "No shared bug path: PyTorch missing import vs embedding reinitialization after resize." }, { "left": "issue:43577", "right": "issue:45588", "accept": false, - "reason": "Different code paths: BLIP2 dtype loading vs flash_attention crash on s_aux=None." + "reason": "BLIP2 dtype mismatch and flash_attention.py crashing on s_aux=None are different code paths." }, { "left": "issue:30064", "right": "issue:33666", "accept": false, - "reason": "Unrelated: void segmentation-map processing vs Qwen2-VL multi-GPU training." + "reason": "Void segmentation-map processing and Qwen2-VL multi-GPU training are unrelated." }, { "left": "issue:43577", "right": "issue:44554", "accept": false, - "reason": "Different defects: BLIP2 dtype issue vs MPS attention correctness bug." - }, - { - "left": "issue:43653", - "right": "issue:43927", - "accept": false, - "reason": "Different bugs: special-token decode output vs DiaConfig losing custom token IDs on save/load." + "reason": "BLIP2 dtype bug is not the same as the MPS attention correctness issue." }, { "left": "issue:44464", "right": "issue:44977", "accept": false, - "reason": "Different generation bugs with different mechanisms and model families." + "reason": "Chunked generation compiled-forward inconsistency vs Qwen3.5 flash-attention generation failure; different bugs." }, { - "left": "issue:43329", - "right": "issue:45325", + "left": "issue:43653", + "right": "issue:43927", "accept": false, - "reason": "Different video/VLM regressions: undefined helpers in token counting vs rope-index scaling bug." + "reason": "BigBird mask-token registration issue and DiaConfig custom-token-ID loss are different tokenizer/config bugs." }, { "left": "issue:43531", "right": "issue:43742", "accept": false, - "reason": "Different areas: Qwen3-MoE sliding-window issue vs MobileLLM loading key error." + "reason": "Qwen3-MoE sliding_window bug vs MobileLLM loading key error; unrelated." }, { - "left": "issue:43550", - "right": "issue:44361", + "left": "issue:43329", + "right": "issue:45325", "accept": false, - "reason": "Different defects: Bamba torch.compile/SDPA bug vs MLukeTokenizer AttributeError." + "reason": "Both touch multimodal/video logic, but one is undefined helpers in token counting and the other is rope-index scaling for still images." }, { "left": "issue:44479", "right": "issue:44625", "accept": false, - "reason": "Different Qwen3.5 issues: video input regression vs num_labels propagation." + "reason": "Video-input regression vs num_labels propagation bug; different model parts." }, { - "left": "issue:43504", - "right": "issue:43720", + "left": "issue:43550", + "right": "issue:44361", + "accept": false, + "reason": "torch.compile/SDPA failure in Bamba is unrelated to MLukeTokenizer AttributeError." + }, + { + "left": "issue:41720", + "right": "issue:44464", "accept": false, - "reason": "Different loading bugs: legacy field in Beit vs packed-weight unpacking in BitNet." + "reason": "CUDA assert in Qwen3 auto device mapping and chunked generation inconsistency are separate failures." }, { "left": "issue:43452", "right": "issue:44451", "accept": false, - "reason": "Related to model loading, but not clearly the same root cause; insufficient evidence to merge." + "reason": "gguf_file breaks tokenizer/model loading APIs, but ScandiBERT load failure is a different model-specific issue." }, { "left": "issue:43504", - "right": "issue:43550", + "right": "issue:43720", "accept": false, - "reason": "Unrelated bugs in different models and execution paths." + "reason": "BEiT legacy-field load bug and BitNet packed-weight unpacking bug are both loading-related but not the same code path." }, { - "left": "issue:41720", - "right": "issue:44464", + "left": "issue:43504", + "right": "issue:43550", "accept": false, - "reason": "Different failure modes: auto device mapping cudaErrorAssert vs compiled-forward chunked generation." + "reason": "BEiT pretrained-load legacy field issue vs Bamba torch.compile SDPA bug; unrelated." }, { "left": "issue:44849", "right": "issue:45357", "accept": false, - "reason": "Different Qwen3.5 regressions: hidden-states behavior vs save_pretrained visual key corruption." + "reason": "Qwen3.5 output_hidden_states bug and save_pretrained visual-key regression are different regressions." }, { "left": "issue:43262", "right": "issue:45084", "accept": false, - "reason": "Different issues: chat-template audio sample-rate default vs compile error on non-template nodes." + "reason": "Audio processor sampling-rate default bug vs chat template compilation error; different subsystems." }, { - "left": "issue:45200", - "right": "issue:45229", + "left": "issue:32090", + "right": "issue:34567", + "accept": false, + "reason": "NoneType broadcast error in trainer vs TrainerState num_input_tokens_seen not updating; unrelated." + }, + { + "left": "issue:32090", + "right": "issue:33666", "accept": false, - "reason": "Different Gemma 4 problems: text-only mm_token_type_ids default vs multi-GPU inference OOM." + "reason": "Trainer broadcast failure and Qwen2-VL multi-GPU training issue are not the same bug." }, { "left": "issue:43504", "right": "issue:44610", "accept": false, - "reason": "Different bugs: Beit legacy field load failure vs OmDet-Turbo processor/model input-size mismatch." + "reason": "BEiT legacy-field loading issue vs OmDet-Turbo processor/model input-size mismatch; different failures." + }, + { + "left": "issue:43278", + "right": "issue:43688", + "accept": false, + "reason": "Embedding dtype drift during eval vs auxiliary-loss normalization bug; unrelated." } ] }, @@ -5807,17 +5856,15 @@ "component_count": 13, "review_unit_index": 18, "review_unit_count": 43, - "status": "reviewed", + "status": "error", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ - "issue:32090", "issue:33357", "issue:33666", - "issue:34567", "issue:36010", "issue:36331", "issue:39692", @@ -5858,275 +5905,68 @@ "issue:44913", "issue:44964", "issue:44977", + "issue:45200", + "issue:45229", "issue:45290", "issue:45405", "issue:45520", "issue:45584" ], "soft_pairs": [ - "issue:32090|issue:34567", - "issue:32090|issue:33666", - "issue:43278|issue:43688", "issue:43334|issue:43572", "issue:43756|issue:44913", "issue:43540|issue:43716", "issue:43525|issue:43572", "issue:43493|issue:43825", "issue:43742|issue:44821", - "issue:43720|issue:43927", + "issue:45200|issue:45229", "issue:33666|issue:36010", - "issue:43606|issue:43927", "issue:43688|issue:43873", + "issue:43720|issue:43927", + "issue:43606|issue:43927", "issue:43257|issue:43299", "issue:43278|issue:43844", "issue:43540|issue:44977", - "issue:43720|issue:44361", "issue:44488|issue:44843", + "issue:43720|issue:44361", "issue:39692|issue:43493", "issue:44964|issue:45405", "issue:43493|issue:43844", - "issue:43756|issue:44060", "issue:33666|issue:36331", + "issue:43756|issue:44060", "issue:44589|issue:45520", - "issue:44521|issue:45290", "issue:44625|issue:45584", - "issue:44423|issue:44734", + "issue:44521|issue:45290", "issue:43646|issue:44466", + "issue:44423|issue:44734", "issue:43824|issue:44589", "issue:43688|issue:43746", - "issue:33357|issue:33666", "issue:39692|issue:43295", + "issue:33357|issue:33666", "issue:43572|issue:44291" ], - "prepared_review_unit_hash": "bce2088b80eab07a2eec3247d951b3e1cd3df91801de0a36afad777b7d1f100e", + "prepared_review_unit_hash": "e265358a354d294653517b540cb753ff3377f748df229c2bcc92d3579e5bc800", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 33, - "serialized_chars": 37805, - "estimated_input_tokens": 9452, - "estimated_eval_tokens": 19160 + "soft_pair_count": 31, + "serialized_chars": 37175, + "estimated_input_tokens": 9294, + "estimated_eval_tokens": 18844 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, - "analyst_result": { - "summary": "The soft pairs are mostly false positives across unrelated bugs (training, config, multimodal serving, loading, docs). No pair appears to be the same underlying defect or a shared fixable code path.", - "confidence": 0.94, - "canonical_issue_reason": null, - "canonical_pr_reason": null, - "best_issue_reason": null, - "best_pr_reason": null, - "soft_edge_verdicts": [ - { - "left": "issue:32090", - "right": "issue:34567", - "accept": false, - "reason": "Different trainer failures: GPU broadcast TypeError vs TrainerState token counter not updating." - }, - { - "left": "issue:32090", - "right": "issue:33666", - "accept": false, - "reason": "Unrelated training contexts: `_gpu_broadcast_one` NoneType error vs Qwen2-VL multi-GPU training request." - }, - { - "left": "issue:43278", - "right": "issue:43688", - "accept": false, - "reason": "Different models and symptoms: BF16/FP32 eval dtype drift vs auxiliary-loss normalization error." - }, - { - "left": "issue:43334", - "right": "issue:43572", - "accept": false, - "reason": "Both mention missing config fields, but on different models and attributes (`pad_token_id` vs `pad_token_idx`)." - }, - { - "left": "issue:43756", - "right": "issue:44913", - "accept": false, - "reason": "Both involve rotary settings, but one is Smollm3 RoPE layer selection and the other is GPTNeoX config reload persistence." - }, - { - "left": "issue:43540", - "right": "issue:43716", - "accept": false, - "reason": "Different multimodal preprocessing bugs: Qwen3OmniMoe video processing vs Mistral-3 image dtype mismatch." - }, - { - "left": "issue:43525", - "right": "issue:43572", - "accept": false, - "reason": "Same broad theme of missing config IDs, but distinct models, fields, and failure modes." - }, - { - "left": "issue:43493", - "right": "issue:43825", - "accept": false, - "reason": "SigLIP2 implementation mismatch is unrelated to a pipeline translation-task error message regression." - }, - { - "left": "issue:43742", - "right": "issue:44821", - "accept": false, - "reason": "Different loading paths: MobileLLM key error vs AutoImageProcessor URL loading failure." - }, - { - "left": "issue:43720", - "right": "issue:43927", - "accept": false, - "reason": "Packed-weight unpacking during accelerate load is unrelated to config token IDs lost on save/load." - }, - { - "left": "issue:33666", - "right": "issue:36010", - "accept": false, - "reason": "Qwen2-VL multi-GPU training request is unrelated to a GenerationMixin import failure." - }, - { - "left": "issue:43606", - "right": "issue:43927", - "accept": false, - "reason": "CPU offload device mismatch is unrelated to DiaConfig serialization losing custom token IDs." - }, - { - "left": "issue:43688", - "right": "issue:43873", - "accept": false, - "reason": "Auxiliary-loss normalization and quantization offloading are different problems with different code paths." - }, - { - "left": "issue:43257", - "right": "issue:43299", - "accept": false, - "reason": "Both are Qwen3/MoE loading issues, but one is accelerate+deepspeed weight conversion and the other is a transformers dev regression in model loading." - }, - { - "left": "issue:43278", - "right": "issue:43844", - "accept": false, - "reason": "Unrelated training bugs: embedding dtype changes during eval vs abnormal gradient growth under ZeRO-3." - }, - { - "left": "issue:43540", - "right": "issue:44977", - "accept": false, - "reason": "Both involve Qwen3.5/Qwen3OmniMoe, but one is video-input validation and the other is flash-attention generation behavior." - }, - { - "left": "issue:43720", - "right": "issue:44361", - "accept": false, - "reason": "Packed-weight loading bug is not the same as MLukeTokenizer task AttributeError." - }, - { - "left": "issue:44488", - "right": "issue:44843", - "accept": false, - "reason": "Model load failure for sleng-bert is unrelated to the offline-mode Mistral regex patch issue." - }, - { - "left": "issue:39692", - "right": "issue:43493", - "accept": false, - "reason": "Documentation example errors are not the same as a SigLIP2 implementation discrepancy." - }, - { - "left": "issue:44964", - "right": "issue:45405", - "accept": false, - "reason": "Phi-4 multimodal load failure is unrelated to the PEFT minimum-version bump being unreleased." - }, - { - "left": "issue:43493", - "right": "issue:43844", - "accept": false, - "reason": "Different subsystems and symptoms: SigLIP2 model parity vs ZeRO-3 gradient growth." - }, - { - "left": "issue:43756", - "right": "issue:44060", - "accept": false, - "reason": "Both are model-specific loading/config issues, but they concern different architectures and different bugs." - }, - { - "left": "issue:33666", - "right": "issue:36331", - "accept": false, - "reason": "Qwen2-VL multi-GPU training is unrelated to a custom compute_loss signature breakage." - }, - { - "left": "issue:44589", - "right": "issue:45520", - "accept": false, - "reason": "Float8 storage lookup failure is unrelated to a flash_attn import-utils KeyError on Python 3.13." - }, - { - "left": "issue:44521", - "right": "issue:45290", - "accept": false, - "reason": "Both touch apply_chat_template, but one is zeroed assistant masks for multimodal inputs and the other is a crash on tool-call messages with no content." - }, - { - "left": "issue:44625", - "right": "issue:45584", - "accept": false, - "reason": "Qwen3.5 num_labels propagation and Whisper empty-transcription generation are unrelated bugs." - }, - { - "left": "issue:44423", - "right": "issue:44734", - "accept": false, - "reason": "Two different server crashes: multimodal `str`-to-`.to()` failure vs KV-cache continuation tensor indexing." - }, - { - "left": "issue:43646", - "right": "issue:44466", - "accept": false, - "reason": "Custom model initialization breakage is not the same as inconsistent lm_head.weight serialization by device." - }, - { - "left": "issue:43824", - "right": "issue:44589", - "accept": false, - "reason": "Importing a Qwen2.5-VL class is unrelated to missing Float8 storage support." - }, - { - "left": "issue:43688", - "right": "issue:43746", - "accept": false, - "reason": "Aux-loss normalization and PEFT local-checkpoint loading are different failures in different code paths." - }, - { - "left": "issue:33357", - "right": "issue:33666", - "accept": false, - "reason": "MacOS bus error with CLIP is unrelated to Qwen2-VL multi-GPU training." - }, - { - "left": "issue:39692", - "right": "issue:43295", - "accept": false, - "reason": "Doc-example mistakes are not the same as a regression in processor/tokenizer access and image passing." - }, - { - "left": "issue:43572", - "right": "issue:44291", - "accept": false, - "reason": "Missing pad_token_idx in StableLmConfig is unrelated to `_is_hf_initialized` being passed during init_empty_weights." - } - ] - }, + "analyst_result": null, "evaluator_result": null, "evaluator_used": false, "retried": false, @@ -6142,10 +5982,10 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:15354", "issue:29942", @@ -6197,11 +6037,11 @@ "issue:45584" ], "soft_pairs": [ - "issue:43504|issue:43606", "issue:43994|issue:44493", + "issue:43504|issue:43606", + "issue:44464|issue:45584", "issue:43504|issue:43653", "issue:43927|issue:44361", - "issue:44464|issue:45584", "issue:43575|issue:45405", "issue:43278|issue:43701", "issue:44792|issue:45405", @@ -6213,32 +6053,32 @@ "issue:45084|issue:45520", "issue:43232|issue:44849", "issue:43844|issue:44964", - "issue:43582|issue:44977", "issue:39401|issue:44568", + "issue:43582|issue:44977", "issue:45072|issue:45198", "issue:44315|issue:44849", "issue:37428|issue:43957", "issue:44554|issue:45356", "issue:43334|issue:43525", + "issue:43295|issue:44610", "issue:45200|issue:45325", "issue:44466|issue:45127", - "issue:43295|issue:44610", "issue:44898|issue:45412" ], - "prepared_review_unit_hash": "6a59b39f5c0a7599aa18619a3ee6052e9a8a487d0f8d5825111379c1bea34563", + "prepared_review_unit_hash": "4ceb043023b5768f38f363880e5d1d6f174d9929acc5d68404d323b678a6fce8", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 27, - "serialized_chars": 35998, + "serialized_chars": 35999, "estimated_input_tokens": 9000, "estimated_eval_tokens": 18256 }, @@ -6247,174 +6087,174 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is heterogeneous: the issues span unrelated model-specific bugs, tokenizer regressions, generation edge cases, and CI/device failures. I do not see a true duplicate core, so there is no strong canonical anchor.", - "confidence": 0.96, - "canonical_issue_reason": "No single canonical issue stands out because the items are largely unrelated; if forced, issue 43504 is the cleanest self-contained bug report, but it does not represent the rest of the cluster.", + "summary": "This cluster is heterogeneous: the items span unrelated bugs in tokenizers, generation, model loading, dtype/device behavior, CI, and versioning. The soft links are mostly superficial keyword overlap, so none of the candidate pairs look like true duplicates.", + "confidence": 0.93, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Issue 43504 is the most concrete and reproducible standalone bug report in the set, with a clear loading failure and a plausible fix path, but it is only a representative issue, not a duplicate hub.", + "best_issue_reason": "No single issue is a safe global representative; the cluster mixes unrelated failure modes across different models and subsystems, so there is no clear canonical issue to anchor on.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43994", + "right": "issue:44493", + "accept": false, + "reason": "Different bugs: SigLIP2 bad outputs vs a position-id warning affecting many models; not the same failing code path." + }, { "left": "issue:43504", "right": "issue:43606", "accept": false, - "reason": "Different failures: BEiT model preset loading vs. Bark CPU offload device mismatch. Same broad area, not the same bug." + "reason": "Legacy-field model loading bug vs CPU offload device mismatch; unrelated symptoms and fixes." }, { - "left": "issue:43994", - "right": "issue:44493", + "left": "issue:44464", + "right": "issue:45584", "accept": false, - "reason": "One is SigLIP2 inference behaving nonsensically; the other is a position-id key warning across many models. No shared concrete code path." + "reason": "Compiled-forward chunked generation issue vs empty-transcription token alignment bug; distinct generation paths." }, { "left": "issue:43504", "right": "issue:43653", "accept": false, - "reason": "BEiT legacy-field loading bug and BigBirdTokenizer mask-token registration are unrelated subsystems." + "reason": "Pretrained model preset loading vs BigBirdTokenizer special-token decode behavior; different subsystems." }, { "left": "issue:43927", "right": "issue:44361", "accept": false, - "reason": "Both are tokenizer/config failures, but for different models and symptoms; not the same underlying defect." - }, - { - "left": "issue:44464", - "right": "issue:45584", - "accept": false, - "reason": "Chunked generation with compiled forward is unrelated to Whisper empty-transcription generation after token alignment." + "reason": "Save/load custom token IDs causing IndexError vs tokenizer AttributeError on tasks; not the same bug." }, { "left": "issue:43575", "right": "issue:45405", "accept": false, - "reason": "Qwen2 TP OOM and a PEFT version-pin regression are entirely different issues." + "reason": "TP-related OOM vs a release/version-constant problem; no shared underlying change." }, { "left": "issue:43278", "right": "issue:43701", "accept": false, - "reason": "BF16/FP32 dtype drift in eval is not the same as a resume-from-checkpoint key mismatch." + "reason": "BF16-to-FP32 eval dtype drift vs resume checkpoint key mismatch; unrelated failure modes." }, { "left": "issue:44792", "right": "issue:45405", "accept": false, - "reason": "Janus test failure and an unmet PEFT version requirement do not share the same bug." + "reason": "Janus image-generation test failure vs PEFT minimum-version bump; no common code path." }, { "left": "issue:29942", "right": "issue:30333", "accept": false, - "reason": "Flash Attention 2 test failures and MLflow job-reporting issues are unrelated." + "reason": "Flash Attention 2 test failures vs MLFlow reporting after failed training; unrelated concerns." }, { "left": "issue:43606", "right": "issue:44112", "accept": false, - "reason": "Both mention CI/device handling, but one is a real CPU offload mismatch and the other is a stale test override issue." + "reason": "Both mention devices, but one is a real CPU-offload mismatch and the other is a stale CI test; not the same bug." }, { "left": "issue:15354", "right": "issue:38175", "accept": false, - "reason": "torch.jit.script GeneratorExp export problem and SigLIP2 zero-probability outputs are different model behaviors." + "reason": "TorchScript GeneratorExp limitation vs zero probabilities in SigLIP2; completely different issues." }, { "left": "issue:44554", "right": "issue:45446", "accept": false, - "reason": "MPS attention correctness and a PyTorch version check for AuxRequest import are unrelated." + "reason": "MPS attention correctness on mismatched heads vs flex_attention import version check; different code paths." }, { "left": "issue:43540", "right": "issue:45200", "accept": false, - "reason": "Video-input processing in Qwen3OmniMoe is not the same as Gemma 4 mm_token_type_ids defaults for text-only fine-tuning." + "reason": "Qwen3OmniMoe video-input processing vs Gemma 4 mm_token_type_ids handling; both multimodal, but not the same defect." }, { "left": "issue:45084", "right": "issue:45520", "accept": false, - "reason": "Compilation/template-node error and a Python 3.13 flash_attn import KeyError are different failure modes." + "reason": "Compiler template-node error vs flash_attn import failure on Python 3.13; unrelated." }, { "left": "issue:43232", "right": "issue:44849", "accept": false, - "reason": "Generation kwargs update after sync_gpus and Qwen3.5 hidden-state output behavior are separate generation issues." + "reason": "Generation kwargs update after sync_gpus vs Qwen3.5 hidden-states bug; same broad area, different bug." }, { "left": "issue:43844", "right": "issue:44964", "accept": false, - "reason": "ZeRO-3 gradient inflation and Phi-4 multimodal loading on latest transformers are unrelated." + "reason": "ZeRO-3 gradient inflation vs Phi-4 multimodal loading failure; no shared underlying problem." }, { - "left": "issue:43582", - "right": "issue:44977", + "left": "issue:39401", + "right": "issue:44568", "accept": false, - "reason": "Apple Silicon caching allocator TypeError and Qwen3.5 flash-attention generation bugs do not match." + "reason": "Qwen3 offset_mapping regression vs mdeberta special-token insertion; both tokenizer bugs, but distinct." }, { - "left": "issue:39401", - "right": "issue:44568", + "left": "issue:43582", + "right": "issue:44977", "accept": false, - "reason": "Qwen3 tokenizer offset mappings and mdeberta special-token addition are different tokenizer regressions." + "reason": "Apple Silicon allocator TypeError vs Qwen3.5 flash-attention generation bug; unrelated." }, { "left": "issue:45072", "right": "issue:45198", "accept": false, - "reason": "Dtype mismatch in inference and Wav2Vec2 save/tokenization failure are different code paths." + "reason": "bfloat16 dtype mismatches in inference vs Wav2Vec2 save/tokenization failure; different subsystems." }, { "left": "issue:44315", "right": "issue:44849", "accept": false, - "reason": "Liger Kernel model_init application issue and Qwen3.5 hidden-state bug are unrelated." + "reason": "Liger Kernel not applied with model_init vs Qwen3.5 hidden-states issue; not the same fix." }, { "left": "issue:37428", "right": "issue:43957", "accept": false, - "reason": "Flash-attention import failure and meta-device model loading regressions are not the same bug." + "reason": "Flash-support import failure vs meta-device model loading breakage; separate problems." }, { "left": "issue:44554", "right": "issue:45356", "accept": false, - "reason": "MPS attention correctness issue and Kimi-K2.5 tokenizer codec regression are distinct." + "reason": "MPS attention correctness vs Kimi-K2.5 tokenizer codec regression; unrelated." }, { "left": "issue:43334", "right": "issue:43525", "accept": false, - "reason": "Both are pad_token_id attribute errors, but they affect different model configs and likely different fixes." + "reason": "Both mention missing pad_token_id, but they affect different model/config classes and load paths." + }, + { + "left": "issue:43295", + "right": "issue:44610", + "accept": false, + "reason": "Processor.tokenizer regression vs OmDet-Turbo input-size mismatch; different processor/model contracts." }, { "left": "issue:45200", "right": "issue:45325", "accept": false, - "reason": "Gemma 4 mm_token_type_ids defaults and Qwen2.5-VL rope-index scaling are unrelated multimodal bugs." + "reason": "Gemma 4 token-type handling vs Qwen2.5-VL rope-index scaling; distinct multimodal bugs." }, { "left": "issue:44466", "right": "issue:45127", "accept": false, - "reason": "Tied-weight serialization inconsistency and LoRA-merge model collapse are both weight-related, but not the same concrete defect." - }, - { - "left": "issue:43295", - "right": "issue:44610", - "accept": false, - "reason": "Processor/tokenizer API regression and OmDet-Turbo size mismatch are separate model-processing issues." + "reason": "lm_head.weight serialization inconsistency vs LoRA merge collapse with extended vocab; related theme but different concrete failures." }, { "left": "issue:44898", "right": "issue:45412", "accept": false, - "reason": "Perceiver interpolation failure and RT-DETR memory release behavior are unrelated." + "reason": "Perceiver resize/interpolate failure vs RT-DETR memory leak on deletion; no common underlying issue." } ] }, @@ -6436,7 +6276,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:37428", "issue:38175", @@ -6471,6 +6311,7 @@ "issue:44561", "issue:44568", "issue:44589", + "issue:44779", "issue:44792", "issue:44849", "issue:44936", @@ -6488,243 +6329,244 @@ ], "soft_pairs": [ "issue:43493|issue:43701", - "issue:44792|issue:45563", "issue:43873|issue:44464", + "issue:44792|issue:45563", "issue:44514|issue:44521", - "issue:43388|issue:43526", "issue:37428|issue:43824", - "issue:43844|issue:44936", + "issue:43388|issue:43526", "issue:43572|issue:44987", + "issue:43844|issue:44936", "issue:43572|issue:44589", "issue:43824|issue:43975", "issue:43295|issue:43450", + "issue:43295|issue:43873", "issue:44360|issue:44561", "issue:38175|issue:45412", "issue:44442|issue:45198", - "issue:43295|issue:43873", - "issue:44206|issue:45584", - "issue:43122|issue:44849", - "issue:43278|issue:43856", "issue:43295|issue:43994", + "issue:43122|issue:44849", + "issue:44206|issue:45584", "issue:42915|issue:43824", + "issue:43278|issue:43856", "issue:38175|issue:43493", "issue:43827|issue:43901", "issue:44568|issue:44991", "issue:43653|issue:44112", - "issue:45290|issue:45381", "issue:43450|issue:43493", + "issue:45290|issue:45381", "issue:45127|issue:45245", "issue:43819|issue:45083", - "issue:44462|issue:44561" + "issue:44462|issue:44561", + "issue:44561|issue:44779" ], - "prepared_review_unit_hash": "d02f685d3e77dda93403d7df2e0dc0693a0f2e455ceb506245088290fb3d2ab1", + "prepared_review_unit_hash": "2e2c5cadd241920eda5e9d6ea375f9ab1e604685fa0abc24204edfc0d42d2627", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 29, - "serialized_chars": 35783, - "estimated_input_tokens": 8946, - "estimated_eval_tokens": 18148 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36650, + "estimated_input_tokens": 9163, + "estimated_eval_tokens": 18582 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous and the vast majority of proposed soft matches are false positives. The only clear duplicate-like pair is the two SigLIP2 model-bad-output reports, which appear to describe the same underlying implementation issue.", - "confidence": 0.62, - "canonical_issue_reason": "issue:43994 is the best representative because it states the broader end-user symptom for the SigLIP2 problem and covers both AutoModel and pipeline behavior, subsuming the more specific zero-probabilities report.", + "summary": "This set is mostly a grab bag of unrelated Transformers regressions/docs issues. The closest overlap is around multimodal chat-template handling, but none of the soft pairs are strong enough to treat as duplicates.", + "confidence": 0.66, + "canonical_issue_reason": "issue:44521 is the most active, well-referenced open issue and the best umbrella candidate among the multimodal/chat-template regressions here, though the overall cluster is heterogeneous.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43994 is the strongest canonical candidate among the issues because it is the clearest, broadest description of the only truly overlapping bug in the set.", + "best_issue_reason": "If a single issue must anchor the set, issue:44521 is the strongest choice because it has the most ongoing discussion and inbound references while describing a concrete, user-facing bug.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43493", "right": "issue:43701", "accept": false, - "reason": "Different failures: SigLIP2 output discrepancy vs checkpoint resume key mismatch; no shared code path." - }, - { - "left": "issue:44792", - "right": "issue:45563", - "accept": false, - "reason": "Unrelated test failure in janus vs stale warning on paged generate." + "reason": "Different bugs: SigLIP2 model discrepancy vs checkpoint resume key mismatch." }, { "left": "issue:43873", "right": "issue:44464", "accept": false, - "reason": "Different areas and symptoms: quantized offloading vs chunked generation with compiled forward." + "reason": "Unrelated areas: quantization/offloading vs chunked generation with compiled forward." }, { - "left": "issue:44514", - "right": "issue:44521", + "left": "issue:44792", + "right": "issue:45563", "accept": false, - "reason": "Both involve chat templates, but one is a batched padding crash and the other is incorrect assistant masks; too different to merge as one bug." + "reason": "Different failures: janus image-generation test vs stale generation warning." }, { - "left": "issue:43388", - "right": "issue:43526", + "left": "issue:44514", + "right": "issue:44521", "accept": false, - "reason": "Different label-handling bugs in different components; not the same underlying issue." + "reason": "Same API family, but different concrete defects: batched padding crash vs zero assistant masks in multimodal inputs." }, { "left": "issue:37428", "right": "issue:43824", "accept": false, - "reason": "Both are import errors, but for different symbols and different features/models." + "reason": "Both are ImportErrors, but they involve different missing symbols and different model families." }, { - "left": "issue:43844", - "right": "issue:44936", + "left": "issue:43388", + "right": "issue:43526", "accept": false, - "reason": "Different training/runtime problems: ZeRO-3 gradient inflation vs trainer evaluate failing after train." + "reason": "Both involve labels, but one drops tuple elements in gather_for_metrics and the other collapses labels in a fast image processor." }, { "left": "issue:43572", "right": "issue:44987", "accept": false, - "reason": "Both are version-related model load issues, but they affect different models and likely different fixes." + "reason": "Different problems: missing StableLmConfig field vs model loading failure for a specific checkpoint." + }, + { + "left": "issue:43844", + "right": "issue:44936", + "accept": false, + "reason": "Training instability with ZeRO-3 is unrelated to trainer.evaluate() failing after train()." }, { "left": "issue:43572", "right": "issue:44589", "accept": false, - "reason": "Unrelated config/version regression vs Float8 storage lookup error." + "reason": "No overlap: config field regression vs Float8 storage lookup error." }, { "left": "issue:43824", "right": "issue:43975", "accept": false, - "reason": "Different model-loading import failure vs tokenizer detokenization regression." + "reason": "ImportError for a missing class is not the same as DeepSeek detokenization corruption." }, { "left": "issue:43295", "right": "issue:43450", "accept": false, - "reason": "Different multimodal processor bugs: tokenizer/image handling crash vs batched video shape error." + "reason": "Processor/tokenizer regression and batched video shape bug are different code paths and symptoms." + }, + { + "left": "issue:43295", + "right": "issue:43873", + "accept": false, + "reason": "Custom processor regression is unrelated to quantization/offloading behavior." }, { "left": "issue:44360", "right": "issue:44561", "accept": false, - "reason": "Unrelated: DSA indexer architecture discussion vs trust_remote_code breakage from API removal." + "reason": "DSA indexer ReLU discussion is unrelated to removing is_torch_fx_available." }, { "left": "issue:38175", "right": "issue:45412", "accept": false, - "reason": "SigLIP2 incorrect outputs vs RT-DETR memory leak are unrelated." + "reason": "SigLIP2 zero-probabilities bug is unrelated to RT-DETR memory release." }, { "left": "issue:44442", "right": "issue:45198", "accept": false, - "reason": "Different tokenizer/model families and different failure modes." + "reason": "Different tokenizer/model-loading failures in different architectures." }, { "left": "issue:43295", - "right": "issue:43873", - "accept": false, - "reason": "Different parts of the stack and different symptoms; not the same bug." - }, - { - "left": "issue:44206", - "right": "issue:45584", + "right": "issue:43994", "accept": false, - "reason": "Feature extractor center-arg crash is unrelated to Whisper empty-transcription generation failure." + "reason": "Processor/tokenizer regression and SigLIP2 inference nonsense are not the same bug." }, { "left": "issue:43122", "right": "issue:44849", "accept": false, - "reason": "Different tokenizer regression vs Qwen3.5 hidden-states bug." + "reason": "Tokenization drift across versions is unrelated to Qwen3.5 hidden-state output behavior." }, { - "left": "issue:43278", - "right": "issue:43856", + "left": "issue:44206", + "right": "issue:45584", "accept": false, - "reason": "Embedding dtype drift during evaluate is not the same as Qwen3 MoE memory inefficiency." + "reason": "Feature-extractor center-arg crash and Whisper empty-transcription failure are different issues." }, { - "left": "issue:43295", - "right": "issue:43994", + "left": "issue:42915", + "right": "issue:43824", "accept": false, - "reason": "Same broad multimodal area, but different concrete failures; not enough to treat as one bug." + "reason": "Qwen3Moe FP8 config failure and Qwen2.5-VL import error are unrelated." }, { - "left": "issue:42915", - "right": "issue:43824", + "left": "issue:43278", + "right": "issue:43856", "accept": false, - "reason": "Different models and different failure types: FP8 config failure vs missing export import error." + "reason": "Embedding dtype mismatch and MoE memory usage are different training issues." }, { "left": "issue:38175", "right": "issue:43493", "accept": false, - "reason": "Both mention SigLIP2, but one is an output-probability issue and the other is a discrepancy vs JAX; not clearly the same concrete bug." + "reason": "Same general SigLIP2 area, but one is zero probabilities and the other is HF-vs-JAX discrepancy." }, { "left": "issue:43827", "right": "issue:43901", "accept": false, - "reason": "Both are docs cleanup around pipeline APIs, but they reference different deprecated behaviors and pages; too loose for duplicate triage." + "reason": "Both are docs issues, but they refer to different pages and different deprecated pipeline APIs." }, { "left": "issue:44568", "right": "issue:44991", "accept": false, - "reason": "Different tokenizer/model regressions with different symptoms." + "reason": "Different tokenizer regressions affecting different models and failure modes." }, { "left": "issue:43653", "right": "issue:44112", "accept": false, - "reason": "Unrelated tokenizer special-token bug vs a GraniteSpeech CI test issue." + "reason": "Tokenizer special-token bug and GraniteSpeech CI test flake are unrelated." }, { - "left": "issue:45290", - "right": "issue:45381", + "left": "issue:43450", + "right": "issue:43493", "accept": false, - "reason": "Different multimodal chat-template bug vs video position-id bug." + "reason": "Video batching shape bug and SigLIP2 implementation discrepancy do not share the same code path." }, { - "left": "issue:43450", - "right": "issue:43493", + "left": "issue:45290", + "right": "issue:45381", "accept": false, - "reason": "Different bugs: batched video processor shape vs SigLIP2 model output discrepancy." + "reason": "Assistant-message/tool-call chat-template crash is not the same as Qwen2.5-VL video position-id issue." }, { "left": "issue:45127", "right": "issue:45245", "accept": false, - "reason": "LoRA merge collapse and category-cardinality runtime error are unrelated." + "reason": "LoRA/tied-embedding collapse and category-cardinality RuntimeError are unrelated." }, { "left": "issue:43819", "right": "issue:45083", "accept": false, - "reason": "Different model/helper functions and different failure modes." + "reason": "DAC latent decoding mismatch and qwen3_omni_moe feature-length helper behavior are different bugs." }, { "left": "issue:44462", "right": "issue:44561", "accept": false, - "reason": "Tokenizer repository loading issue vs API removal breaking trust_remote_code models are unrelated." + "reason": "Tokenizer JSON loading and removal of is_torch_fx_available affect different layers of the stack." }, { - "left": "issue:43994", - "right": "issue:38175", - "accept": true, - "reason": "Same model family and same underlying symptom class: SigLIP2 outputs are broken/inconsistent, with one report describing zero probabilities and the other nonsensical outputs." + "left": "issue:44561", + "right": "issue:44779", + "accept": false, + "reason": "Remote-code compatibility break and DeepSeek detokenization regression are different issues." } ] }, @@ -6743,10 +6585,10 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:29127", "issue:29942", @@ -6767,6 +6609,7 @@ "issue:43606", "issue:43611", "issue:43653", + "issue:43720", "issue:43723", "issue:43819", "issue:43825", @@ -6777,7 +6620,6 @@ "issue:44448", "issue:44493", "issue:44554", - "issue:44561", "issue:44568", "issue:44610", "issue:44743", @@ -6799,287 +6641,299 @@ ], "soft_pairs": [ "issue:45200|issue:45588", - "issue:44561|issue:44779", "issue:43450|issue:43575", "issue:44610|issue:44857", "issue:44857|issue:45593", "issue:37428|issue:43425", - "issue:45310|issue:45478", - "issue:44448|issue:44743", - "issue:43819|issue:44112", "issue:43262|issue:43450", + "issue:43819|issue:44112", + "issue:44448|issue:44743", + "issue:45310|issue:45478", "issue:43606|issue:45083", "issue:43278|issue:43825", "issue:29942|issue:32090", "issue:37428|issue:44351", "issue:39692|issue:43526", "issue:43611|issue:43931", - "issue:43335|issue:43550", "issue:43819|issue:44493", + "issue:43335|issue:43550", "issue:45200|issue:45381", "issue:43450|issue:43526", - "issue:44855|issue:45083", "issue:39692|issue:44493", - "issue:44977|issue:45229", - "issue:43335|issue:43653", - "issue:44292|issue:45520", - "issue:44448|issue:44779", + "issue:44855|issue:45083", "issue:29127|issue:32090", + "issue:44448|issue:44779", "issue:38175|issue:44493", + "issue:43335|issue:43653", + "issue:44292|issue:45520", + "issue:44977|issue:45229", "issue:43335|issue:45083", "issue:43335|issue:43504", - "issue:44568|issue:45491", "issue:43550|issue:44112", + "issue:44568|issue:45491", "issue:43335|issue:45072", "issue:43723|issue:44554", "issue:40444|issue:43526", "issue:44448|issue:44977", - "issue:43335|issue:45593" + "issue:43335|issue:45593", + "issue:43720|issue:44112" ], - "prepared_review_unit_hash": "b5bca066223b52bd550838efb99562e7ad6457c0e68fe2898b2f2c38252475f0", + "prepared_review_unit_hash": "7d408e6d01071dc1cada7bdb13614bae5b33d50bcab3099ae5721b76b010fae6", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 37, - "serialized_chars": 38874, - "estimated_input_tokens": 9719, - "estimated_eval_tokens": 19694 + "serialized_chars": 38895, + "estimated_input_tokens": 9724, + "estimated_eval_tokens": 19704 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Only one soft pair is a true duplicate: the two identical Qwen3.5 MoE `from_pretrained` errors. The rest are distinct bugs across different models, processors, or failure modes and should not be merged.", - "confidence": 0.95, - "canonical_issue_reason": "issue:45310 is the earlier instance of the only clear duplicate pair, with the same Qwen3.5 MoE `from_pretrained` error title and likely the fuller original report.", + "summary": "This cluster is mostly a set of unrelated transformer bug reports. The only clear duplicate pair is the repeated Qwen3.5 MoE `from_pretrained` error; the rest are similar only at a broad subsystem level and should stay separate.", + "confidence": 0.98, + "canonical_issue_reason": "issue:45310 is the earlier report with the same title and the same Qwen3.5 MoE `from_pretrained` failure; it is the better canonical target for the duplicate pair with issue:45478.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45310 is the best representative issue because it cleanly captures the duplicated Qwen3.5 MoE loading failure; no PRs are present in this cluster.", + "best_issue_reason": "issue:45310 is the clearest representative issue in the cluster because it is a precise, reproducible bug report and has a direct duplicate.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45200", "right": "issue:45588", "accept": false, - "reason": "Different subsystems and failure modes: Gemma4 text-only fine-tuning token IDs vs flash-attention auxiliary-state crash." - }, - { - "left": "issue:44561", - "right": "issue:44779", - "accept": false, - "reason": "Both are v5 breakages, but one is a removed helper affecting trust_remote_code models and the other is a tokenizer output regression for Deepseek." + "reason": "Both involve model/integration behavior, but one is Gemma 4 multimodal token ids and the other is a flash-attention sink-less crash; different code paths and bugs." }, { "left": "issue:43450", "right": "issue:43575", "accept": false, - "reason": "Batched video processor shape bug is unrelated to Qwen2.5-57B TP loading OOM." + "reason": "Video processor shape handling and Qwen2.5-VL tensor-parallel OOM are unrelated failures." }, { "left": "issue:44610", "right": "issue:44857", "accept": false, - "reason": "Different model components: processor output size mismatch vs loss crash under float16 AMP." + "reason": "Processor input-size mismatch and AMP/CUDA loss crash are different bugs in different components." }, { "left": "issue:44857", "right": "issue:45593", "accept": false, - "reason": "Different detector bugs: AMP/CUDA crash in loss computation vs missing auxiliary losses when denoising is disabled." + "reason": "Both are training-time issues, but one is a float16/CUDA crash and the other is missing auxiliary losses; not the same defect." }, { "left": "issue:37428", "right": "issue:43425", "accept": false, - "reason": "Both mention v5/compatibility, but one is a missing flash-attention import and the other is a Torch 2.10 incompatibility problem." - }, - { - "left": "issue:45310", - "right": "issue:45478", - "accept": true, - "reason": "Exact same Qwen3.5 MoE `from_pretrained` error report; these are clear duplicates." + "reason": "An import error for a missing flash-attention symbol and a Torch 2.10 incompatibility are separate compatibility problems." }, { - "left": "issue:44448", - "right": "issue:44743", + "left": "issue:43262", + "right": "issue:43450", "accept": false, - "reason": "Pegasus output drift across versions is unrelated to Qwen3.5 recurrent-state reset with cache." + "reason": "Audio chat-template sampling rate default and batched video processor shape are unrelated multimodal bugs." }, { "left": "issue:43819", "right": "issue:44112", "accept": false, - "reason": "DAC forward/from_latents mismatch is unrelated to a GraniteSpeech CI device-override test failure." + "reason": "DAC forward/from_latents mismatch and GraniteSpeech stale device-override CI failure are different issues." }, { - "left": "issue:43262", - "right": "issue:43450", + "left": "issue:44448", + "right": "issue:44743", "accept": false, - "reason": "Audio chat-template sampling-rate default issue is unrelated to batched video processor shape handling." + "reason": "Pegasus v4/v5 output differences and Qwen3.5 recurrent-state reset are different model behaviors and code paths." + }, + { + "left": "issue:45310", + "right": "issue:45478", + "accept": true, + "reason": "Exact same Qwen3.5 MoE `from_pretrained` error title and same underlying loading bug; clearly duplicates." }, { "left": "issue:43606", "right": "issue:45083", "accept": false, - "reason": "CPU offload device mismatch for bark-small is unrelated to a qwen3_omni_moe feature-length helper bug." + "reason": "CPU offload device mismatch for bark-small and `_get_feat_extract_output_lengths` behavior in qwen3_omni_moe are unrelated." }, { "left": "issue:43278", "right": "issue:43825", "accept": false, - "reason": "Embedding dtype drift in evaluate is unrelated to a pipeline error message about translation tasks." + "reason": "BF16/FP32 embedding dtype drift and pipeline translation-task messaging are different concerns." }, { "left": "issue:29942", "right": "issue:32090", "accept": false, - "reason": "Flash Attention 2 test failures are not the same bug as a Trainer `_gpu_broadcast_one` NoneType TypeError." + "reason": "Flash Attention 2 test failures and `_gpu_broadcast_one` rejecting NoneType are distinct failures." }, { "left": "issue:37428", "right": "issue:44351", "accept": false, - "reason": "Both are import-related, but they involve different missing symbols and different breakages." + "reason": "Missing `_flash_supports_window_size` and missing `HybridCache` imports are both import errors but for different symbols and fixes." }, { "left": "issue:39692", "right": "issue:43526", "accept": false, - "reason": "SigLIP2 docs example problems are unrelated to BeitImageProcessorFast `reduce_labels` returning only one label." + "reason": "SigLIP2 doc example issues and BeitImageProcessorFast `reduce_labels` behavior are unrelated." }, { "left": "issue:43611", "right": "issue:43931", "accept": false, - "reason": "Model loading failure from `base_model_prefix` removal is distinct from Qwen3-VL weight-shape mismatch." + "reason": "`base_model_prefix` loading breakage and Qwen3-VL weight-shape mismatch are different model-loading problems." }, { - "left": "issue:43335", - "right": "issue:43550", + "left": "issue:43819", + "right": "issue:44493", "accept": false, - "reason": "SwitchTransformers sparse-layer config bug is unrelated to Bamba-9B-v2 torch.compile SDPA failure." + "reason": "DAC latent conversion mismatch and unexpected position-id keys are unrelated bugs." }, { - "left": "issue:43819", - "right": "issue:44493", + "left": "issue:43335", + "right": "issue:43550", "accept": false, - "reason": "DAC latent mismatch and generic position-id key warnings are different issues with no shared code-path." + "reason": "SwitchTransformers sparse-layer config and Bamba torch.compile/SDPA failure are different model-specific problems." }, { "left": "issue:45200", "right": "issue:45381", "accept": false, - "reason": "Both touch multimodal fine-tuning, but one is missing mm token type IDs and the other is wrong vision position IDs." + "reason": "Gemma 4 text-only fine-tuning defaults and Qwen2.5-VL video position ids are different multimodal issues." }, { "left": "issue:43450", "right": "issue:43526", "accept": false, - "reason": "Batched video shape bug is unrelated to BEiT `reduce_labels` behavior." + "reason": "Both touch Beit-related processors, but one is batched video shape handling and the other is image-label reduction; not the same bug." }, { - "left": "issue:44855", - "right": "issue:45083", + "left": "issue:39692", + "right": "issue:44493", "accept": false, - "reason": "Python 3.13 `IndentationError` from torch.jit parsing is unrelated to the qwen3_omni_moe feature-length helper." + "reason": "Documentation example errors and position-id warnings in many models are not the same underlying defect." }, { - "left": "issue:39692", - "right": "issue:44493", + "left": "issue:44855", + "right": "issue:45083", "accept": false, - "reason": "Documentation example errors are not the same as unexpected position-id key warnings in models." + "reason": "Python 3.13 `IndentationError` in DebertaV2 import and qwen3_omni_moe feature-length helper behavior are unrelated." }, { - "left": "issue:44977", - "right": "issue:45229", + "left": "issue:29127", + "right": "issue:32090", "accept": false, - "reason": "Qwen3.5 flash-attention generation bug is unrelated to Gemma4 multi-GPU CUDA OOM." + "reason": "LayoutLMv3 box-clarity error messaging and trainer broadcast NoneType are unrelated failures." }, { - "left": "issue:43335", - "right": "issue:43653", + "left": "issue:44448", + "right": "issue:44779", "accept": false, - "reason": "SwitchTransformers sparse-layer creation bug is unrelated to BigBirdTokenizer special-token registration." + "reason": "Pegasus output differences and DeepSeek tokenizer regressions are separate model/tokenizer issues." }, { - "left": "issue:44292", - "right": "issue:45520", + "left": "issue:38175", + "right": "issue:44493", "accept": false, - "reason": "Qwen-3-8B-NVFP4 runtime error is unrelated to Python 3.13 flash_attn import KeyError." + "reason": "SigLIP2 zero probabilities and position-id key warnings are not the same bug." }, { - "left": "issue:44448", - "right": "issue:44779", + "left": "issue:43335", + "right": "issue:43653", "accept": false, - "reason": "Pegasus output differences and Deepseek tokenizer regressions are different models and failure modes." + "reason": "SwitchTransformers sparse-layer config and BigBirdTokenizer special-token decode issue are unrelated." }, { - "left": "issue:29127", - "right": "issue:32090", + "left": "issue:44292", + "right": "issue:45520", "accept": false, - "reason": "LayoutLMv3 error-message clarity issue is unrelated to Trainer broadcast TypeError." + "reason": "Qwen-3-8B-NVFP4 runtime error and Python 3.13 flash_attn import KeyError are different failures." }, { - "left": "issue:38175", - "right": "issue:44493", + "left": "issue:44977", + "right": "issue:45229", "accept": false, - "reason": "SigLIP2 zero-probabilities bug is unrelated to generic unexpected position-id key warnings." + "reason": "Qwen3.5 flash-attention generation bug and Gemma4 multi-GPU CUDA OOM are unrelated." }, { "left": "issue:43335", "right": "issue:45083", "accept": false, - "reason": "SwitchTransformers sparse-layer bug is unrelated to qwen3_omni_moe length computation." + "reason": "SwitchTransformers config bug and qwen3_omni_moe feature-length helper behavior are unrelated." }, { "left": "issue:43335", "right": "issue:43504", "accept": false, - "reason": "Sparse-layer misconfiguration is unrelated to BEiT semantic-segmentation preset loading with a legacy field." + "reason": "SwitchTransformers sparse-layer creation and Beit semantic-segmentation legacy-field loading are different issues." + }, + { + "left": "issue:43550", + "right": "issue:44112", + "accept": false, + "reason": "Bamba SDPA/torch.compile failure and GraniteSpeech CI device override failure are unrelated." }, { "left": "issue:44568", "right": "issue:45491", "accept": false, - "reason": "Tokenizer special-token regression is unrelated to Gemma3 NaN embeddings from mixed-length sliding-window attention." + "reason": "mDeBERTa special-token addition regression and Gemma3 NaN embeddings are different tokenizer/model problems." + }, + { + "left": "issue:43335", + "right": "issue:45072", + "accept": false, + "reason": "SwitchTransformers config bug and bfloat16 dtype mismatches in inference are not the same underlying issue." }, { "left": "issue:43723", "right": "issue:44554", "accept": false, - "reason": "AutoTokenizer loading issue in v5 is unrelated to an MPS attention correctness bug." + "reason": "AutoTokenizer loading regression and MPS attention correctness issue are unrelated." }, { "left": "issue:40444", "right": "issue:43526", "accept": false, - "reason": "Qwen2.5-VL iterable dataset failure with multiple images is unrelated to BEiT fast processor `reduce_labels` behavior." + "reason": "Qwen2.5-VL iterable dataset multi-image finetuning failure and BeitImageProcessorFast label reduction are different areas." }, { "left": "issue:44448", "right": "issue:44977", "accept": false, - "reason": "Pegasus output drift and Qwen3.5 flash-attention generation failures are different concrete bugs." + "reason": "Pegasus output drift and Qwen3.5 flash-attention generation failure are separate model-specific bugs." }, { "left": "issue:43335", "right": "issue:45593", "accept": false, - "reason": "SwitchTransformers sparse-layer config issue is unrelated to D-FINE auxiliary-loss handling." + "reason": "SwitchTransformers sparse-layer config and D-FINE auxiliary-loss behavior are unrelated training/model issues." + }, + { + "left": "issue:43720", + "right": "issue:44112", + "accept": false, + "reason": "BitNet packed-weight unpacking during accelerate loading and GraniteSpeech CI stale device override are different failures." } ] }, "evaluator_result": { "accept": true, - "feedback": "The cluster summary is well grounded in the packet: the only clearly duplicated pair is issue:45310 / issue:45478, which have the same title and are the only pair the evidence supports as a duplicate. The non-duplicate soft-edge calls are appropriately conservative. One minor improvement: avoid unsupported phrasing like \"likely the fuller original report\" unless the packet provides that evidence." + "feedback": "Accepted. The canonical pair is well grounded by the packet: issue:45310 and issue:45478 have identical titles and clearly match. The remaining soft-edge rejections stay conservative at the title/body-summary level, and the cluster summary does not overstate the evidence." }, "evaluator_used": true, "retried": false, @@ -7098,7 +6952,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:25251", "issue:29942", @@ -7112,17 +6966,16 @@ "issue:43066", "issue:43278", "issue:43329", + "issue:43381", "issue:43412", "issue:43421", "issue:43550", "issue:43606", "issue:43653", "issue:43701", - "issue:43720", "issue:43873", "issue:43976", "issue:43994", - "issue:44112", "issue:44186", "issue:44265", "issue:44448", @@ -7150,27 +7003,26 @@ "issue:45588" ], "soft_pairs": [ - "issue:43720|issue:44112", "issue:45372|issue:45588", "issue:43066|issue:44462", - "issue:43412|issue:45588", "issue:34689|issue:35141", - "issue:45372|issue:45406", "issue:44977|issue:45563", "issue:44857|issue:45072", "issue:43606|issue:44857", + "issue:43412|issue:45588", "issue:43873|issue:45229", + "issue:45372|issue:45406", + "issue:43873|issue:44493", "issue:37428|issue:44987", "issue:43701|issue:45083", - "issue:43873|issue:44493", + "issue:29942|issue:35141", "issue:43976|issue:45440", "issue:45245|issue:45563", - "issue:29942|issue:35141", "issue:43550|issue:45083", "issue:41720|issue:45229", "issue:43278|issue:43329", - "issue:45372|issue:45459", "issue:32090|issue:33357", + "issue:45372|issue:45459", "issue:44451|issue:45520", "issue:44448|issue:44466", "issue:43065|issue:43994", @@ -7180,229 +7032,230 @@ "issue:44857|issue:45588", "issue:44186|issue:45198", "issue:43421|issue:45491", + "issue:43278|issue:43381", "issue:43994|issue:45412", "issue:44265|issue:45198" ], - "prepared_review_unit_hash": "674d0d23f2bb471f391eb3416fbed7963cdd7a8639095ac7463e23e62fbccca9", + "prepared_review_unit_hash": "b3e62fc6f83b2d19584561cf0791db84f72df75daaca74d11c982c2c96df9382", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { - "node_count": 48, - "item_count": 48, + "node_count": 47, + "item_count": 47, "soft_pair_count": 32, - "serialized_chars": 37424, - "estimated_input_tokens": 9356, - "estimated_eval_tokens": 18968 + "serialized_chars": 36797, + "estimated_input_tokens": 9200, + "estimated_eval_tokens": 18656 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These are largely unrelated bug reports across different models, tokenizers, and runtime paths; the soft-similarity links are not strong enough to treat any pair as true duplicates.", - "confidence": 0.98, - "canonical_issue_reason": null, + "summary": "This set looks like a loose collection of Transformers issues with superficial thematic overlap (tokenizers, Gemma/Qwen, flash-attn, offloading, dtype, export), but the soft pairs mostly describe different root causes and should not be deduplicated. No PRs are present. Issue 45372 is the best cluster anchor only because it is the most connected item in the candidate graph, not because it matches the others exactly.", + "confidence": 0.56, + "canonical_issue_reason": "Issue 45372 is the most central node among the soft links, with multiple nearby tokenizer/processor-loading references, so it is the best available anchor for this set.", "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "45372 has the broadest apparent overlap with other candidates in the provided similarity graph; it is the best representative issue, though still not a clear duplicate hub.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:43720", - "right": "issue:44112", - "accept": false, - "reason": "Both mention failures in CI/device handling, but one is accelerate packed-weight unpacking and the other is a stale GraniteSpeech device-override test; different bugs." - }, { "left": "issue:45372", "right": "issue:45588", "accept": false, - "reason": "Gemma 4 processor import/dependency failure vs flash-attention crash on sink-less models; different code paths." + "reason": "Both involve tokenizer/processor-related failures, but one is a missing import for Gemma 4 loading and the other is a flash-attention runtime crash on `s_aux=None`; different code paths." }, { "left": "issue:43066", "right": "issue:44462", "accept": false, - "reason": "Tokenizer decoder-type mismatch and AutoTokenizer ignoring tokenizer.json are related to tokenizers but describe different defects." - }, - { - "left": "issue:43412", - "right": "issue:45588", - "accept": false, - "reason": "ExecuTorch export/training-guard issue is unrelated to an s_aux=None flash-attention crash." + "reason": "Both touch tokenizer loading/serialization, but one is a wrong decoder type in v5 and the other is AutoTokenizer ignoring `tokenizer.json`; not the same bug." }, { "left": "issue:34689", "right": "issue:35141", "accept": false, - "reason": "Llama 3.2 Vision model loading vs embedding reinit after resize; separate model-loading and weight-tie bugs." - }, - { - "left": "issue:45372", - "right": "issue:45406", - "accept": false, - "reason": "Both involve Gemma 4, but one is an import error in processor loading and the other is a missing _tokenizer attribute in serve; not the same bug." + "reason": "Model loading failure for Llama 3.2 Vision is unrelated to the embedding reinitialization bug in `post_init`." }, { "left": "issue:44977", "right": "issue:45563", "accept": false, - "reason": "Qwen3.5 flash-attention generation failure is unrelated to a stale num_return_sequences warning." + "reason": "Flash-attention generation failure and a stale `num_return_sequences` warning are unrelated behavior." }, { "left": "issue:44857", "right": "issue:45072", "accept": false, - "reason": "Different models and failure modes: AMP/CUDA crash in LwDetrImageLoss vs dtype mismatches in SwitchTransformers/TimmWrapperModel." + "reason": "Both are dtype/device-related inference issues, but they affect different models and failure modes." }, { "left": "issue:43606", "right": "issue:44857", "accept": false, - "reason": "CPU offload device mismatch for bark-small is not the same as the LwDetrImageLoss AMP/CUDA crash." + "reason": "CPU offload device mismatch and float16 AMP CUDA crash are separate bugs." + }, + { + "left": "issue:43412", + "right": "issue:45588", + "accept": false, + "reason": "Executorch export / unsupported op failure is unrelated to the flash_attention `s_aux=None` crash." }, { "left": "issue:43873", "right": "issue:45229", "accept": false, - "reason": "General quantization/offloading behavior vs multi-GPU CUDA OOM on Gemma4; not one underlying bug." + "reason": "Both mention offload/memory behavior, but one is quantization offloading and the other is multi-GPU OOM on Gemma4." + }, + { + "left": "issue:45372", + "right": "issue:45406", + "accept": false, + "reason": "Both are Gemma 4 loading/serving issues, but one is a missing `ReasoningEffort` import and the other is a missing `_tokenizer` attribute." + }, + { + "left": "issue:43873", + "right": "issue:44493", + "accept": false, + "reason": "Quantized offloading problems and unexpected position-id keys are different issues." }, { "left": "issue:37428", "right": "issue:44987", "accept": false, - "reason": "Missing flash-support import and a transformers>=5.1.0 model-loading regression are different compatibility issues." + "reason": "Import error for `_flash_supports_window_size` and Qwen3.5 flash-attention generation failure are distinct failures." }, { "left": "issue:43701", "right": "issue:45083", "accept": false, - "reason": "Checkpoint key mismatch and qwen3_omni_moe feature-length helper behavior are unrelated." + "reason": "Checkpoint resume key mismatch is unrelated to the qwen3_omni_moe feature-extraction helper behavior." }, { - "left": "issue:43873", - "right": "issue:44493", + "left": "issue:29942", + "right": "issue:35141", "accept": false, - "reason": "Offloading/quantization issue vs unexpected position-id key behavior; different symptoms and code paths." + "reason": "Flash Attention 2 test failures do not match the embedding reinitialization bug." }, { "left": "issue:43976", "right": "issue:45440", "accept": false, - "reason": "Python version support regression vs DeepseekV3MoE divergence; no common underlying change." + "reason": "Python version incompatibility and DeepSeekV3MoE divergence are unrelated." }, { "left": "issue:45245", "right": "issue:45563", "accept": false, - "reason": "Category-count runtime error and stale generate warning are unrelated." - }, - { - "left": "issue:29942", - "right": "issue:35141", - "accept": false, - "reason": "Flash Attention test failure and embedding reinitialization on resize are distinct bugs." + "reason": "Category-count limit error is unrelated to the stale generation warning." }, { "left": "issue:43550", "right": "issue:45083", "accept": false, - "reason": "torch.compile/SDPA failure in Bamba and qwen3_omni_moe length helper behavior are different issues." + "reason": "torch.compile/SDPA failure and feature-length helper behavior are different code paths." }, { "left": "issue:41720", "right": "issue:45229", "accept": false, - "reason": "Qwen3 auto device mapping cuda assert and Gemma4 multi-GPU OOM are different model/runtime problems." + "reason": "Qwen3 auto device mapping CUDA assert and Gemma4 multi-GPU OOM are different model/runtime problems." }, { "left": "issue:43278", "right": "issue:43329", "accept": false, - "reason": "Training/evaluate dtype drift is unrelated to undefined variables in multimodal token counting." + "reason": "Embedding dtype drift between train/eval is unrelated to the undefined video-branch helper variables." }, { - "left": "issue:45372", - "right": "issue:45459", + "left": "issue:32090", + "right": "issue:33357", "accept": false, - "reason": "Gemma 4 processor import failure and protobuf-error masking in tokenizers are different tokenizer/processor bugs." + "reason": "Trainer `_gpu_broadcast_one` NoneType error and MacOS bus error on CLIP are unrelated." }, { - "left": "issue:32090", - "right": "issue:33357", + "left": "issue:45372", + "right": "issue:45459", "accept": false, - "reason": "Trainer broadcast NoneType error and MacOS CLIP bus error are unrelated failures." + "reason": "Tokenizer import failure and protobuf-related error masking are different tokenizer-loading bugs." }, { "left": "issue:44451", "right": "issue:45520", "accept": false, - "reason": "Model-loading failure for a specific repo and a Python 3.13 flash_attn import KeyError are not the same bug." + "reason": "ScandiBERT load failure and Python 3.13 `flash_attn` import-key error are unrelated." }, { "left": "issue:44448", "right": "issue:44466", "accept": false, - "reason": "Both are v4/v5 behavior regressions, but one is Pegasus output differences and the other is lm_head serialization; different concrete problems." + "reason": "Both involve v4/v5 behavior changes, but one is output divergence and the other is serialization/tied-weight inconsistency; not the same concrete bug." }, { "left": "issue:43065", "right": "issue:43994", "accept": false, - "reason": "Dummy Conv2d in Sam3PixelDecoder and SigLIP2 nonsensical outputs are unrelated." + "reason": "Dummy Conv2d in Sam3PixelDecoder and SigLIP2 nonsensical AutoModel/pipeline outputs are different model issues." }, { "left": "issue:43065", "right": "issue:45412", "accept": false, - "reason": "PixelDecoder implementation detail vs RT-DETR memory leak; different code paths." + "reason": "Dummy layer in Sam3PixelDecoder and RT-DETR memory release issue are unrelated." }, { "left": "issue:25251", "right": "issue:32090", "accept": false, - "reason": "Pipeline top_k nested-list output and Trainer GPU broadcast NoneType are unrelated." + "reason": "Pipeline `top_k` output shape change and `_gpu_broadcast_one` NoneType error are unrelated." }, { "left": "issue:43653", "right": "issue:44743", "accept": false, - "reason": "BigBirdTokenizer special-token registration and qwen3_5 recurrent-state reset are unrelated." + "reason": "BigBirdTokenizer special-token decode bug and Qwen3.5 recurrent-state reset bug are unrelated." }, { "left": "issue:44857", "right": "issue:45588", "accept": false, - "reason": "AMP/CUDA crash in LwDetrImageLoss vs flash-attention s_aux=None crash; different subsystems and failure modes." + "reason": "AMP/CUDA loss crash and flash_attention `s_aux=None` crash are separate inference failures." }, { "left": "issue:44186", "right": "issue:45198", "accept": false, - "reason": "LayoutLMv2Tokenizer crash on NER/padding and Wav2Vec2 save_pretrained/tokenization failures are separate tokenizer bugs." + "reason": "LayoutLMv2 NER/padding crash and Wav2Vec2 save/tokenization failure are different tokenizer bugs." }, { "left": "issue:43421", "right": "issue:45491", "accept": false, - "reason": "Runtime post-processor update behavior and Gemma3 NaN embeddings are unrelated." + "reason": "Runtime special-token post-processor update feature and Gemma3 NaN embeddings are unrelated." + }, + { + "left": "issue:43278", + "right": "issue:43381", + "accept": false, + "reason": "Train/eval embedding dtype mismatch is unrelated to gradient checkpointing in eval mode." }, { "left": "issue:43994", "right": "issue:45412", "accept": false, - "reason": "SigLIP2 bad outputs and RT-DETR memory leak are different issues." + "reason": "SigLIP2 output issue and RT-DETR memory release problem are unrelated." }, { "left": "issue:44265", "right": "issue:45198", "accept": false, - "reason": "torch.export export failure with torch_compilable_check is unrelated to Wav2Vec2 save_pretrained/tokenization failures." + "reason": "torch.export failure with `torch_compilable_check` and Wav2Vec2 save/tokenization failure are unrelated." } ] }, @@ -7421,10 +7274,10 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:29127", "issue:29942", @@ -7451,6 +7304,7 @@ "issue:43756", "issue:43761", "issue:43824", + "issue:43931", "issue:44079", "issue:44186", "issue:44206", @@ -7476,230 +7330,230 @@ ], "soft_pairs": [ "issue:42915|issue:42994", - "issue:43278|issue:43381", "issue:44361|issue:45198", "issue:44206|issue:44479", - "issue:43756|issue:45440", - "issue:43257|issue:43278", "issue:44871|issue:44977", + "issue:43257|issue:43278", + "issue:43756|issue:45440", "issue:29942|issue:30064", "issue:44610|issue:45412", "issue:45103|issue:45372", "issue:43824|issue:44279", - "issue:45440|issue:45593", - "issue:45072|issue:45229", "issue:33357|issue:39692", + "issue:45440|issue:45593", "issue:29127|issue:34567", "issue:32090|issue:33290", + "issue:45072|issue:45229", "issue:43653|issue:44442", - "issue:43334|issue:43531", + "issue:43381|issue:43701", "issue:43526|issue:44186", + "issue:43334|issue:43531", "issue:44464|issue:45491", - "issue:43381|issue:43701", "issue:44977|issue:45245", "issue:29942|issue:36010", "issue:43262|issue:44206", - "issue:43761|issue:44079", "issue:29127|issue:33357", - "issue:43441|issue:45588", - "issue:29127|issue:35141" + "issue:43761|issue:44079", + "issue:29127|issue:35141", + "issue:42915|issue:43931", + "issue:43441|issue:45588" ], - "prepared_review_unit_hash": "26b5fb5748b1716ea4182d12e5388bb7ec5f374fd5b82bc3daa1d5c61ba49220", + "prepared_review_unit_hash": "4ed09d18c624dafd247c92e9d6e459a5b0bb6bf2f002b8c520c1b00fac56b5db", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { - "node_count": 47, - "item_count": 47, + "node_count": 48, + "item_count": 48, "soft_pair_count": 28, - "serialized_chars": 35536, - "estimated_input_tokens": 8884, - "estimated_eval_tokens": 18024 + "serialized_chars": 36120, + "estimated_input_tokens": 9030, + "estimated_eval_tokens": 18316 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is heterogeneous: the paired issues span unrelated models, tokenizers, processors, training/runtime errors, and doc/runtime regressions. None of the soft pairs look like true duplicates or the same fixable code-path problem.", - "confidence": 0.97, - "canonical_issue_reason": "No single canonical issue stands out; the items are not duplicates of one underlying bug and mostly concern different components and failure modes.", - "canonical_pr_reason": "No pull requests are present in the cluster.", - "best_issue_reason": "No clear global representative issue; the set is too mixed for one issue to safely summarize the rest.", - "best_pr_reason": "No pull requests are present in the cluster.", + "summary": "This cluster is heterogeneous: the soft-linked pairs mostly share a broad subsystem or surface-level symptom, but not the same concrete bug/change. I would not merge any of the soft edges. The most representative issue is the CLIPVisionModel hidden-states regression because it is a precise, reproducible code-path bug.", + "confidence": 0.84, + "canonical_issue_reason": "No clear duplicate theme across the cluster; issue 43761 is the most concrete, reproducible regression among the set, so it is the best representative issue.", + "canonical_pr_reason": null, + "best_issue_reason": "43761 has a narrow failure mode, a specific model path, and a straightforward regression signature, making it the most actionable issue in this mixed cluster.", + "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:42915", "right": "issue:42994", "accept": false, - "reason": "Different quantization problems: FineGrainedFP8Config failure vs model saving failure." - }, - { - "left": "issue:43278", - "right": "issue:43381", - "accept": false, - "reason": "Different symptoms and code paths: dtype drift in evaluate vs gradient checkpointing blocked in eval mode." + "reason": "Both involve Qwen3-MoE/quantization, but one is an FP8 config failure and the other is a quantized saving problem; different stages and likely different bugs." }, { "left": "issue:44361", "right": "issue:45198", "accept": false, - "reason": "Different tokenizer/model areas and failures: MLuke task AttributeError vs Wav2Vec2 save/tokenization issues." + "reason": "Different models and different failure surfaces: MLukeTokenizer task errors vs Wav2Vec2 save/tokenization failure." }, { "left": "issue:44206", "right": "issue:44479", "accept": false, - "reason": "Different processors/models and failure modes; not the same underlying regression." + "reason": "Unsupported feature-extractor arg vs video-input regression; same broad area, not the same code-path bug." }, { - "left": "issue:43756", - "right": "issue:45440", + "left": "issue:44871", + "right": "issue:44977", "accept": false, - "reason": "Different model families and distinct implementation divergences; too broad to be one bug." + "reason": "Tokenizer/model EOS config mismatch is unrelated to the flash-attention generation failure." }, { "left": "issue:43257", "right": "issue:43278", "accept": false, - "reason": "Accelerate/deepspeed weight conversion bug is unrelated to training/eval dtype changes." + "reason": "Loading/conversion of Qwen3-MoE weights is distinct from BF16-to-FP32 dtype drift during evaluate." }, { - "left": "issue:44871", - "right": "issue:44977", + "left": "issue:43756", + "right": "issue:45440", "accept": false, - "reason": "Different issues: eos_token_id config mismatch vs flash-attention generation failure." + "reason": "RoPE layer dropping and DeepSeek implementation divergence are different model discrepancies." }, { "left": "issue:29942", "right": "issue:30064", "accept": false, - "reason": "Flash Attention test failures and void segmentation map processing are unrelated." + "reason": "Failing Flash Attention 2 tests and void segmentation map processing are unrelated issues." }, { "left": "issue:44610", "right": "issue:45412", "accept": false, - "reason": "Processor input-size mismatch and RT-DETR memory release are different bug classes." + "reason": "Processor output-size mismatch and RT-DETR memory leaks are not the same underlying bug." }, { "left": "issue:45103", "right": "issue:45372", "accept": false, - "reason": "Auto-docstring annotation handling and mistral_common import breakage are unrelated." + "reason": "auto_docstring annotation parsing crash is unrelated to the mistral_common import dependency break." }, { "left": "issue:43824", "right": "issue:44279", "accept": false, - "reason": "Specific Qwen2.5-VL import error is not the same as a generic dependency issue." - }, - { - "left": "issue:45440", - "right": "issue:45593", - "accept": false, - "reason": "DeepSeekV3MoE divergence and D-FINE auxiliary-loss behavior are different model bugs." + "reason": "A specific missing import and a generic dependency issue do not indicate the same fix." }, { - "left": "issue:45072", - "right": "issue:45229", + "left": "issue:33357", + "right": "issue:39692", "accept": false, - "reason": "bfloat16 dtype mismatches are not the same as a multi-GPU CUDA OOM." + "reason": "MacOS CLIP bus error and SigLIP2 doc example errors are different problems." }, { - "left": "issue:33357", - "right": "issue:39692", + "left": "issue:45440", + "right": "issue:45593", "accept": false, - "reason": "MacOS bus error in CLIP loading and SigLIP2 documentation errors are distinct." + "reason": "Native model divergence and missing auxiliary losses are separate model-behavior bugs." }, { "left": "issue:29127", "right": "issue:34567", "accept": false, - "reason": "LayoutLMv3 error-message clarity and TrainerState token counting are unrelated." + "reason": "Error-message clarity for LayoutLMv3 is unrelated to TrainerState token-count tracking." }, { "left": "issue:32090", "right": "issue:33290", "accept": false, - "reason": "Trainer broadcast NoneType error and deepspeed Adafactor OOM are different failures." + "reason": "NoneType broadcast error and Adafactor/deepspeed OOM are different Trainer/deepspeed failures." + }, + { + "left": "issue:45072", + "right": "issue:45229", + "accept": false, + "reason": "Bfloat16 dtype mismatches are not the same as multi-GPU CUDA OOM." }, { "left": "issue:43653", "right": "issue:44442", "accept": false, - "reason": "BigBirdTokenizer special-token registration and AutoTokenizer loading FastSpeech2ConformerTokenizer are different issues." + "reason": "BigBird special-token registration and AutoTokenizer loading a FastSpeech2Conformer tokenizer are unrelated." }, { - "left": "issue:43334", - "right": "issue:43531", + "left": "issue:43381", + "right": "issue:43701", "accept": false, - "reason": "Qwen3-VL pad_token_id import failure is unrelated to Qwen3-MoE sliding-window behavior." + "reason": "Eval-mode gradient-checkpointing restriction and resume checkpoint key mismatch are separate training-state bugs." }, { "left": "issue:43526", "right": "issue:44186", "accept": false, - "reason": "BEiT reduce_labels bug and LayoutLMv2 NER/padding crash are different tokenizer/processor problems." + "reason": "reduce_labels returning one label and LayoutLMv2Tokenizer padding/truncation crashes are different tokenizer issues." }, { - "left": "issue:44464", - "right": "issue:45491", + "left": "issue:43334", + "right": "issue:43531", "accept": false, - "reason": "Compiled-forward chunked generation inconsistency and Gemma3 NaN embeddings are separate generation/runtime bugs." + "reason": "Missing pad_token_id in Qwen3-VL and a Qwen3-MoE sliding_window issue are distinct model/config regressions." }, { - "left": "issue:43381", - "right": "issue:43701", + "left": "issue:44464", + "right": "issue:45491", "accept": false, - "reason": "Eval-mode gradient checkpointing restriction is unrelated to resume_from_checkpoint key mismatch." + "reason": "Compiled-forward chunked generation inconsistency and Gemma3 NaNs from all-padding windows are not the same bug." }, { "left": "issue:44977", "right": "issue:45245", "accept": false, - "reason": "Flash-attention generation regression and category-count RuntimeError are unrelated." + "reason": "Flash-attention generation failure and category-count runtime limit are unrelated." }, { "left": "issue:29942", "right": "issue:36010", "accept": false, - "reason": "Flash Attention 2 test failures are not the same as the GenerationMixin import error." + "reason": "Flash Attention 2 test failures and GenerationMixin import error are different failure modes." }, { "left": "issue:43262", "right": "issue:44206", "accept": false, - "reason": "Audio chat-template sampling-rate default and LASR center-arg crash are unrelated processor bugs." + "reason": "Audio chat-template sampling-rate defaulting and unsupported center arg in a feature extractor are unrelated." + }, + { + "left": "issue:29127", + "right": "issue:33357", + "accept": false, + "reason": "LayoutLMv3 error messaging and a CLIP MacOS bus error do not share a concrete fix." }, { "left": "issue:43761", "right": "issue:44079", "accept": false, - "reason": "CLIPVisionModel not returning hidden states and ModelOutput key assignment are different code paths." + "reason": "The CLIPVisionModel hidden-states regression may involve ModelOutput handling, but this is not clearly the same concrete bug as generic key assignment when a key was previously None." }, { "left": "issue:29127", - "right": "issue:33357", + "right": "issue:35141", "accept": false, - "reason": "LayoutLMv3 error-message clarity and CLIP MacOS bus error are unrelated." + "reason": "LayoutLMv3 error handling and embedding reinitialization in post_init are unrelated." }, { - "left": "issue:43441", - "right": "issue:45588", + "left": "issue:42915", + "right": "issue:43931", "accept": false, - "reason": "Ministral FlashAttention failure and s_aux=None crash in flash_attention.py are distinct issues." + "reason": "Qwen3-MoE FP8 failure and Qwen3-VL weight-shape mismatch are different loading issues." }, { - "left": "issue:29127", - "right": "issue:35141", + "left": "issue:43441", + "right": "issue:45588", "accept": false, - "reason": "LayoutLMv3 error messaging and embedding reinitialization in post_init are unrelated." + "reason": "Ministral FlashAttention failure and sink-less flash_attention.py s_aux=None crash are different attention-path bugs." } ] }, @@ -7718,17 +7572,17 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:33290", "issue:34567", "issue:34689", + "issue:35141", "issue:39692", "issue:41628", - "issue:42915", "issue:43232", "issue:43316", "issue:43381", @@ -7774,237 +7628,244 @@ ], "soft_pairs": [ "issue:43232|issue:43388", - "issue:42915|issue:43931", - "issue:44442|issue:45072", "issue:43526|issue:44857", - "issue:44479|issue:45290", + "issue:44442|issue:45072", "issue:43723|issue:45479", - "issue:45003|issue:45440", + "issue:44479|issue:45290", "issue:43526|issue:44610", + "issue:45003|issue:45440", "issue:44743|issue:44811", - "issue:43931|issue:45216", "issue:43452|issue:45588", - "issue:43761|issue:44188", - "issue:43316|issue:43525", + "issue:43931|issue:45216", "issue:45588|issue:45600", "issue:44977|issue:45584", - "issue:43646|issue:44077", + "issue:43761|issue:44188", + "issue:43316|issue:43525", "issue:43575|issue:43701", + "issue:43646|issue:44077", "issue:43994|issue:44206", "issue:39692|issue:45491", - "issue:43873|issue:45588", "issue:43575|issue:44387", + "issue:43873|issue:45588", "issue:43673|issue:44743", - "issue:44442|issue:44898", "issue:33290|issue:34567", + "issue:44442|issue:44898", "issue:34689|issue:43611", "issue:41628|issue:45372", "issue:43493|issue:43827", "issue:43381|issue:43873", + "issue:33290|issue:34689", + "issue:33290|issue:35141", "issue:44077|issue:44479" ], - "prepared_review_unit_hash": "a0f7753ed7db75dec53aa65d50b227e7d61a4ee033c1a56f6b0741c68a559618", + "prepared_review_unit_hash": "bf2ed62e00b36489b5e3fa679536890ee45cfc5f7d3ad9909c0c4f7f50d6ac3d", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 29, - "serialized_chars": 36478, - "estimated_input_tokens": 9120, - "estimated_eval_tokens": 18496 + "soft_pair_count": 30, + "serialized_chars": 36854, + "estimated_input_tokens": 9214, + "estimated_eval_tokens": 18684 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly a loose collection of unrelated Transformers bugs/regressions across different models and subsystems. None of the soft pairs look like safe duplicates, so all candidate merges are rejected.", - "confidence": 0.93, - "canonical_issue_reason": "issue:43873 is the most central and broadly referenced open report in the set, with the highest discussion/inbound activity and a general subsystem impact (quantization/offloading).", + "summary": "This cluster is highly heterogeneous: it mixes unrelated tokenizer/loading, generation/cache, vision processor, quantization/offloading, documentation, and model-specific regression issues. None of the proposed soft pairs look like the same underlying bug or change, so all soft edges should be rejected.", + "confidence": 0.88, + "canonical_issue_reason": "Issue 43873 is the broadest and most active item here (open, with multiple inbound references) and is the closest thing to a cluster anchor, but the surrounding issues are too unrelated for it to be a true duplicate hub.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43873 is the best representative issue overall because it is active, well-discussed, and has external references, making it the most cluster-like anchor among otherwise disparate reports.", + "best_issue_reason": "Issue 43873 is the best administrative representative because it has the most activity and references, but it still does not meaningfully cover the rest of the set.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43232", "right": "issue:43388", "accept": false, - "reason": "Different failures: generation kwargs after GPU sync vs metric-gathering truncation of tuple labels. No shared code path." + "reason": "Generation kwargs update logic and metric label gathering are unrelated code paths." }, { - "left": "issue:42915", - "right": "issue:43931", + "left": "issue:43526", + "right": "issue:44857", "accept": false, - "reason": "Different models and symptoms: Qwen3Moe FP8 config failure vs Qwen3-VL weight-shape mismatch on load." + "reason": "ImageProcessor label reduction and AMP/CUDA loss crashes are different bugs." }, { "left": "issue:44442", "right": "issue:45072", "accept": false, - "reason": "Unrelated areas: tokenizer loading for FastSpeech2Conformer vs bfloat16 dtype mismatches in inference." + "reason": "Tokenizer loading failure and bfloat16 dtype mismatch are unrelated issues." }, { - "left": "issue:43526", - "right": "issue:44857", + "left": "issue:43723", + "right": "issue:45479", "accept": false, - "reason": "Different components: BeitImageProcessorFast label reduction bug vs LwDetrImageLoss AMP/CUDA crash." + "reason": "Tokenizer loading regression and sequence-classification zero-loss bug do not share the same fix." }, { "left": "issue:44479", "right": "issue:45290", "accept": false, - "reason": "Different subsystems: Qwen video-input regression vs chat-template handling of assistant tool-call messages." + "reason": "Video-input regression and chat template tool-call crash affect different subsystems." }, { - "left": "issue:43723", - "right": "issue:45479", + "left": "issue:43526", + "right": "issue:44610", "accept": false, - "reason": "Tokenizer loading regression vs sequence-classification loss degeneration; not the same bug." + "reason": "Label reduction in an image processor is unrelated to OmDet input-size mismatch." }, { "left": "issue:45003", "right": "issue:45440", "accept": false, - "reason": "sys.modules access safety issue in modeling_utils vs DeepseekV3MoE implementation drift; different code paths." + "reason": "Unsafe sys.modules access and DeepSeekV3MoE divergence are distinct problems." }, { - "left": "issue:43526", - "right": "issue:44610", + "left": "issue:44743", + "right": "issue:44811", "accept": false, - "reason": "Image-processor label handling vs OmDet-Turbo processor size mismatch; not the same failure." + "reason": "Qwen recurrent-state reset and Whisper batch_decode token handling are not the same bug." }, { - "left": "issue:44743", - "right": "issue:44811", + "left": "issue:43452", + "right": "issue:45588", "accept": false, - "reason": "Different behavior: recurrent state reset with cache vs Whisper batch_decode skip_special_tokens handling." + "reason": "GGUF loading breakage and flash-attention sink handling are different code paths." }, { "left": "issue:43931", "right": "issue:45216", "accept": false, - "reason": "Both involve Qwen, but one is a load-time weight mismatch and the other is a save_pretrained checkpoint regression; distinct code paths." + "reason": "Shape-mismatch loading and save_pretrained checkpoint corruption are related to the model family but not the same concrete defect." }, { - "left": "issue:43452", - "right": "issue:45588", + "left": "issue:45588", + "right": "issue:45600", "accept": false, - "reason": "Tokenizer/model loading with gguf_file vs flash-attention sinkless-model crash; unrelated." + "reason": "Flash-attention AttributeError and removed Sam3LiteText auto-mapping references are unrelated." + }, + { + "left": "issue:44977", + "right": "issue:45584", + "accept": false, + "reason": "Qwen flash-attention generation and Whisper empty-transcription generation failures are different bugs." }, { "left": "issue:43761", "right": "issue:44188", "accept": false, - "reason": "CLIPVisionModel hidden_states regression vs torch.compile attention-kernel divergence; different mechanisms." + "reason": "CLIP hidden_states regression and attention-kernel divergence are separate failures." }, { "left": "issue:43316", "right": "issue:43525", "accept": false, - "reason": "Both are config/API discrepancies, but they affect different configs and different missing attributes; not one bug." - }, - { - "left": "issue:45588", - "right": "issue:45600", - "accept": false, - "reason": "flash_attention crash on s_aux=None vs stale auto_mappings references to removed configs; unrelated." + "reason": "Gemma3TextConfig API mismatch and missing Llama4 pad_token_id are not the same issue." }, { - "left": "issue:44977", - "right": "issue:45584", + "left": "issue:43575", + "right": "issue:43701", "accept": false, - "reason": "Qwen flash-attention generation regression vs Whisper empty-transcription generation failure; different models and logic." + "reason": "OOM during large-model TP loading and resume_from_checkpoint key mismatch are unrelated." }, { "left": "issue:43646", "right": "issue:44077", "accept": false, - "reason": "General custom model initialization breakage vs a specific patchtsmixer post_init policy issue; too different to merge." - }, - { - "left": "issue:43575", - "right": "issue:43701", - "accept": false, - "reason": "OOM during tensor-parallel model load vs resume_from_checkpoint key mismatch; unrelated." + "reason": "Generic custom model initialization breakage and patchtsmixer post_init validation are not the same concrete bug." }, { "left": "issue:43994", "right": "issue:44206", "accept": false, - "reason": "SigLIP2 bad outputs from AutoModel/pipeline vs LasrFeatureExtractor unsupported center argument crash; different defects." + "reason": "SigLIP2 bad outputs and LasrFeatureExtractor center-arg crash are different problems." }, { "left": "issue:39692", "right": "issue:45491", "accept": false, - "reason": "SigLIP2 documentation/model mismatch vs Gemma3 mixed-length NaN embeddings; unrelated." + "reason": "Documentation example errors and Gemma3 NaN embeddings are unrelated." }, { - "left": "issue:43873", - "right": "issue:45588", + "left": "issue:43575", + "right": "issue:44387", "accept": false, - "reason": "Quantization/offloading behavior vs flash-attention s_aux=None crash; different subsystems." + "reason": "Tensor-parallel load OOM and int4 reserved-memory OOM have different causes and fixes." }, { - "left": "issue:43575", - "right": "issue:44387", + "left": "issue:43873", + "right": "issue:45588", "accept": false, - "reason": "Both mention OOM/quantization, but one is a specific Qwen2 TP load failure and the other is a broader int4 reserved-memory regression; not the same concrete bug." + "reason": "Quantization offloading issues and flash-attention sink-less crashes are unrelated." }, { "left": "issue:43673", "right": "issue:44743", "accept": false, - "reason": "Both involve cache/generation, but one is missing GenerationMixin cache in chunked_prefill and the other is recurrent-state reset with seq_len>1; distinct issues." + "reason": "Missing generation cache in v5.0.0 and Qwen recurrent-state reset are not the same bug." }, { - "left": "issue:44442", - "right": "issue:44898", + "left": "issue:33290", + "right": "issue:34567", "accept": false, - "reason": "Tokenizer loading failure vs Perceiver non-default-resolution image classification failure; unrelated." + "reason": "Adafactor/deepspeed OOM and TrainerState token-count tracking are unrelated." }, { - "left": "issue:33290", - "right": "issue:34567", + "left": "issue:44442", + "right": "issue:44898", "accept": false, - "reason": "OOM with Adafactor/DeepSpeed vs TrainerState token counter not updating; no overlap." + "reason": "Tokenizer loading failure and Perceiver image-resolution failure are different areas." }, { "left": "issue:34689", "right": "issue:43611", "accept": false, - "reason": "Both are model-loading regressions, but they concern different versions and different underlying breakages." + "reason": "Both involve loading, but they target different model families and different root causes." }, { "left": "issue:41628", "right": "issue:45372", "accept": false, - "reason": "Separate import errors in different dependencies: AutoImageProcessor vs ReasoningEffort from mistral_common." + "reason": "Different missing imports in different processor-loading paths; not the same defect." }, { "left": "issue:43493", "right": "issue:43827", "accept": false, - "reason": "SigLIP2 implementation discrepancy vs docs still using removed pipeline() APIs; unrelated." + "reason": "SigLIP2 implementation mismatch and stale docs after pipeline removal are unrelated." }, { "left": "issue:43381", "right": "issue:43873", "accept": false, - "reason": "Gradient-checkpointing eval-mode restriction vs quantization/offloading behavior; different bugs." + "reason": "Gradient-checkpointing eval-mode restriction and quantization offloading are separate issues." + }, + { + "left": "issue:33290", + "right": "issue:34689", + "accept": false, + "reason": "Optimizer OOM and model-loading regression do not share a code fix." + }, + { + "left": "issue:33290", + "right": "issue:35141", + "accept": false, + "reason": "OOM in training and embedding reinitialization during post_init are unrelated." }, { "left": "issue:44077", "right": "issue:44479", "accept": false, - "reason": "PatchTSTMixer post_init/API policy vs Qwen video-input regression; not the same code path." + "reason": "PatchTSMixer post_init policy and Qwen video-input regression are different bugs." } ] }, @@ -8023,10 +7884,10 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:16998", "issue:22355", @@ -8034,7 +7895,6 @@ "issue:28282", "issue:33290", "issue:34689", - "issue:35141", "issue:36010", "issue:36331", "issue:41950", @@ -8078,26 +7938,24 @@ "issue:45584" ], "soft_pairs": [ - "issue:33290|issue:35141", - "issue:33290|issue:34689", "issue:43720|issue:44442", - "issue:44190|issue:44496", - "issue:43749|issue:43931", "issue:43643|issue:44913", + "issue:43749|issue:43931", + "issue:44190|issue:44496", "issue:43873|issue:44871", "issue:43540|issue:44514", "issue:44162|issue:44792", "issue:43316|issue:44877", - "issue:44855|issue:45137", "issue:43381|issue:43856", "issue:33290|issue:36331", "issue:34689|issue:36010", + "issue:44855|issue:45137", "issue:42175|issue:43316", - "issue:43388|issue:43688", "issue:43404|issue:43441", + "issue:43388|issue:43688", "issue:43065|issue:44617", - "issue:41950|issue:43475", "issue:16998|issue:22355", + "issue:41950|issue:43475", "issue:43316|issue:43716", "issue:25251|issue:28282", "issue:45127|issue:45200", @@ -8106,196 +7964,184 @@ "issue:44871|issue:45584", "issue:44734|issue:45406" ], - "prepared_review_unit_hash": "740d5325def017cc4034a4efabf5e1f552afba11361694c9724c4e84f41275ec", + "prepared_review_unit_hash": "f3cd8ef27bb3f3e6858aeccfe903a6e10359cc207d03e568c2a9644e47d0a4aa", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 27, - "serialized_chars": 35846, - "estimated_input_tokens": 8962, - "estimated_eval_tokens": 18180 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 25, + "serialized_chars": 34627, + "estimated_input_tokens": 8657, + "estimated_eval_tokens": 17570 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is a false-positive mix of unrelated Transformers issues. The soft-similarity pairs share broad keywords (loading, config, multimodal, memory, serving), but they do not describe the same concrete bug or change path, so none should be merged as duplicates.", - "confidence": 0.97, - "canonical_issue_reason": "No single canonical issue fits: the items are heterogeneous standalone bugs/questions across unrelated subsystems, so there is no true duplicate center for the cluster.", + "summary": "This cluster is heterogeneous: the items cover unrelated bugs across loading, configs, pipelines, training, and multimodal models. None of the soft-similarity pairs look like the same underlying issue, so all should remain separate.", + "confidence": 0.94, + "canonical_issue_reason": "No single canonical issue stands out; the issues span distinct code paths and models, and the pairwise similarities are mostly superficial title overlap.", "canonical_pr_reason": null, - "best_issue_reason": "No global best issue is suitable as a representative duplicate target; activity or recency does not overcome the fact that these are different problems.", + "best_issue_reason": "If one issue must represent the cluster, issue 43761 is the clearest self-contained regression report, but it is not a true duplicate anchor for the rest of the set.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:33290", - "right": "issue:35141", - "accept": false, - "reason": "Optimizer OOM in DeepSpeed is unrelated to a post_init weight reinitialization bug during embedding resize." - }, - { - "left": "issue:33290", - "right": "issue:34689", - "accept": false, - "reason": "Training-memory OOM and a model-loading regression for Llama 3.2 Vision are different failure modes and code paths." - }, { "left": "issue:43720", "right": "issue:44442", "accept": false, - "reason": "BitNet packed-weight loading during accelerate vs AutoTokenizer failing for a FastSpeech2 tokenizer are unrelated loader/tokenizer issues." + "reason": "BitNet packed-weight loading vs AutoTokenizer/FastSpeech2 tokenizer loading; unrelated failure modes." }, { - "left": "issue:44190", - "right": "issue:44496", + "left": "issue:43643", + "right": "issue:44913", "accept": false, - "reason": "A dataset-loading problem in an example script is not the same as failing to recognize a model type from config.json." + "reason": "trust_remote_code config field loss vs GPTNeoX rotary_pct reset on reload; different config bugs." }, { "left": "issue:43749", "right": "issue:43931", "accept": false, - "reason": "FSDP CPU RAM efficient loading and Qwen3-VL weight-shape mismatch are both loading-related, but they are distinct bugs in different mechanisms." + "reason": "FSDP CPU RAM-efficient loading breakage vs Qwen3-VL weight-shape mismatch; different loading paths." }, { - "left": "issue:43643", - "right": "issue:44913", + "left": "issue:44190", + "right": "issue:44496", "accept": false, - "reason": "Missing fields from trust_remote_code AutoConfig return is not the same as rotary_pct resetting on config reload." + "reason": "local dataset script issue vs unrecognized model/config.json error; unrelated subsystems." }, { "left": "issue:43873", "right": "issue:44871", "accept": false, - "reason": "Quantization/offloading behavior and Gemma eos_token_id configuration are separate issues with different symptoms and fixes." + "reason": "quantization/offloading behavior vs Gemma eos_token_id mismatch; not the same bug." }, { "left": "issue:43540", "right": "issue:44514", "accept": false, - "reason": "Video-input validation in Qwen3OmniMoe is unrelated to batched apply_chat_template crashes in Qwen2_5_VLProcessor." + "reason": "Qwen3OmniMoe video-input processing vs Qwen2_5_VL batched chat-template padding crash; distinct code paths." }, { "left": "issue:44162", "right": "issue:44792", "accept": false, - "reason": "ESM2 breakage and a failing janus image-generation test are unrelated model-specific problems." + "reason": "ESM2 model breakage vs janus image-generation test failure; unrelated models and symptoms." }, { "left": "issue:43316", "right": "issue:44877", "accept": false, - "reason": "Gemma3TextConfig API discrepancy is not the same as strict config blocking granite_speech loading." - }, - { - "left": "issue:44855", - "right": "issue:45137", - "accept": false, - "reason": "Python 3.13 torch.jit parsing/IndentationError is unrelated to a DeepSpeed ZeRO3 deque underflow." + "reason": "Gemma3TextConfig API discrepancy vs strict granite_speech config loading; different config issues." }, { "left": "issue:43381", "right": "issue:43856", "accept": false, - "reason": "Gradient-checkpointing being disallowed in eval mode is a different bug from inefficient Qwen3 MoE training memory usage." + "reason": "gradient checkpointing in eval mode vs Qwen3 MoE training memory usage; different problems." }, { "left": "issue:33290", "right": "issue:36331", "accept": false, - "reason": "An OOM in Adafactor+DeepSpeed is not the same as a Trainer API signature break in compute_loss." + "reason": "Adafactor OOM in deepspeed vs CustomTrainer signature mismatch; unrelated training bugs." }, { "left": "issue:34689", "right": "issue:36010", "accept": false, - "reason": "Llama 3.2 Vision model loading regression and missing transformers.generation.GenerationMixin import are separate import/load failures." + "reason": "Llama 3.2 vision model loading regression vs GenerationMixin import error; different code paths." }, { - "left": "issue:42175", - "right": "issue:43316", + "left": "issue:44855", + "right": "issue:45137", "accept": false, - "reason": "Missing TensorFlow in a torch-only install extra has nothing to do with Gemma3TextConfig API differences." + "reason": "Python 3.13 IndentationError in torch.jit parsing vs DeepSpeed ZeRO3 deque underflow; unrelated." }, { - "left": "issue:43388", - "right": "issue:43688", + "left": "issue:42175", + "right": "issue:43316", "accept": false, - "reason": "gather_for_metrics dropping tuple labels and auxiliary-loss normalization are both training bugs, but not the same code-path problem." + "reason": "packaging/backends installation issue vs Gemma3TextConfig API discrepancy; not a duplicate." }, { "left": "issue:43404", "right": "issue:43441", "accept": false, - "reason": "Mistral3 weight tying and Ministral-3 FlashAttention failures affect different parts of model initialization/inference." + "reason": "Mistral3 lm_head tying bug vs Ministral-3 FlashAttention failure; same family but different concrete problems." }, { - "left": "issue:43065", - "right": "issue:44617", + "left": "issue:43388", + "right": "issue:43688", "accept": false, - "reason": "A dummy Conv2d in Sam3PixelDecoder is not the same as Sam3Video running out of memory." + "reason": "metrics batch-label truncation vs auxiliary-loss normalization; distinct training/eval logic." }, { - "left": "issue:41950", - "right": "issue:43475", + "left": "issue:43065", + "right": "issue:44617", "accept": false, - "reason": "A pipeline choosing the wrong processor class and a missing fpn_position_embeddings attribute are different SAM/video-related bugs." + "reason": "dummy Conv2d implementation question vs Sam3Video CUDA OOM; different issues." }, { "left": "issue:16998", "right": "issue:22355", "accept": false, - "reason": "A model_max_length question for DeBERTa-V3 is unrelated to a missing transformers.onnx module import error." + "reason": "model_max_length question vs missing transformers.onnx module; unrelated topics." + }, + { + "left": "issue:41950", + "right": "issue:43475", + "accept": false, + "reason": "video-classification pipeline processor lookup vs Sam3VisionEncoderOutput missing attribute; different bugs." }, { "left": "issue:43316", "right": "issue:43716", "accept": false, - "reason": "Gemma3TextConfig API inconsistency and Mistral3 image-preprocessor dtype mismatch are different model/config issues." + "reason": "Gemma3TextConfig API mismatch vs Mistral-3 image-preprocessor dtype mismatch; unrelated models." }, { "left": "issue:25251", "right": "issue:28282", "accept": false, - "reason": "Pipeline top_k output nesting and missing PyTorch during AutoModel import are unrelated." + "reason": "pipeline top_k output-shape change vs AutoModel PyTorch import error; not the same bug." }, { "left": "issue:45127", "right": "issue:45200", "accept": false, - "reason": "LoRA merge collapse with extended vocab and Gemma 4 mm_token_type_ids defaults are both model-behavior bugs, but not the same one." + "reason": "LoRA merge with extended vocabulary/tied embeddings vs Gemma 4 mm_token_type_ids defaulting; different mechanisms." }, { "left": "issue:43761", "right": "issue:44479", "accept": false, - "reason": "CLIPVisionModel hidden_states regression and Qwen video-input regression are different models, versions, and failures." + "reason": "CLIPVisionModel hidden_states regression vs broad v5 video-input regression across Qwen models; different subsystems." }, { "left": "issue:43295", "right": "issue:43825", "accept": false, - "reason": "Processor/tokenizer compatibility breakage and an incorrect translation-task error message are separate v5 regressions." + "reason": "processor.tokenizer/images-to-tokenizer regression vs translation-task error message; one API break, one messaging bug." }, { "left": "issue:44871", "right": "issue:45584", "accept": false, - "reason": "Gemma eos_token_id inconsistency and Whisper empty-transcription failure after align_special_tokens are distinct tokenization/generation bugs." + "reason": "Gemma eos_token_id config mismatch vs Whisper empty transcription after align_special_tokens; different models and code paths." }, { "left": "issue:44734", "right": "issue:45406", "accept": false, - "reason": "KV-cache continuation tensor indexing in serve is unrelated to Gemma4Processor missing _tokenizer in serve." + "reason": "serve KV-cache continuation indexing bug vs Gemma4Processor missing _tokenizer; unrelated failures." } ] }, @@ -8317,7 +8163,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:32090", "issue:35141", @@ -8330,7 +8176,6 @@ "issue:43575", "issue:43606", "issue:43646", - "issue:43650", "issue:43701", "issue:43742", "issue:43761", @@ -8341,7 +8186,6 @@ "issue:44060", "issue:44077", "issue:44190", - "issue:44220", "issue:44242", "issue:44464", "issue:44479", @@ -8366,28 +8210,29 @@ "issue:45381", "issue:45542", "issue:45563", - "issue:45584" + "issue:45584", + "issue:45600" ], "soft_pairs": [ "issue:44077|issue:44534", - "issue:43906|issue:45290", - "issue:43550|issue:43701", "issue:43295|issue:44871", + "issue:43550|issue:43701", "issue:43606|issue:43701", "issue:43646|issue:44913", - "issue:43761|issue:44242", + "issue:43906|issue:45290", "issue:44617|issue:45584", - "issue:43931|issue:44060", + "issue:43761|issue:44242", "issue:43452|issue:44496", + "issue:43931|issue:44060", "issue:45563|issue:45584", "issue:44521|issue:45381", "issue:43575|issue:43742", "issue:42617|issue:43575", "issue:44479|issue:44734", "issue:44933|issue:45362", - "issue:44464|issue:45563", "issue:41720|issue:43575", "issue:32090|issue:35141", + "issue:44464|issue:45563", "issue:43065|issue:44610", "issue:44464|issue:44871", "issue:44792|issue:44977", @@ -8395,212 +8240,206 @@ "issue:44534|issue:44913", "issue:41720|issue:45245", "issue:44938|issue:45542", - "issue:43650|issue:44220", + "issue:44792|issue:45600", "issue:44190|issue:44964", "issue:45127|issue:45357" ], - "prepared_review_unit_hash": "e5cc47c0631a74a05fe45b8f5d6fa7005b7706867842f4dad70e7daad9629ac3", + "prepared_review_unit_hash": "6a3f814b39c43276d7228d2d59fbfe6b1bec610785dd555d4b5c848dd1911857", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { - "node_count": 48, - "item_count": 48, + "node_count": 47, + "item_count": 47, "soft_pair_count": 29, - "serialized_chars": 36171, - "estimated_input_tokens": 9043, - "estimated_eval_tokens": 18342 + "serialized_chars": 35677, + "estimated_input_tokens": 8920, + "estimated_eval_tokens": 18096 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is heterogeneous: the items span unrelated regressions and bugs across model loading, generation, chat templates, configs, training, and docs. The soft-similarity pairs are mostly superficial keyword matches, not the same concrete code path, so none should be merged.", - "confidence": 0.96, - "canonical_issue_reason": null, + "summary": "This is a loose, heterogeneous cluster of Transformers issues spanning unrelated regressions, loading failures, generation bugs, and model-specific problems. None of the soft pairs look like true duplicates; they usually share only a broad subsystem or version context. Issue 44521 is the best cluster anchor because it is the most active and broadly applicable multimodal bug in the set.", + "confidence": 0.74, + "canonical_issue_reason": "Issue 44521 is the most central/open and has the strongest discussion/inbound reference activity, so it is the best representative anchor for this otherwise mixed cluster.", "canonical_pr_reason": null, - "best_issue_reason": "No single issue is a safe canonical for this cluster; the reports do not share one underlying bug or change, only broad Transformer/v5 wording and subsystem overlap.", + "best_issue_reason": "Issue 44521 is broad, currently active, and has the most external references, making it the most useful issue to track as the cluster's representative.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44077", "right": "issue:44534", "accept": false, - "reason": "Different bugs: one is about optional post_init in patchtsmixer, the other about non-persistent buffers being filled with junk." + "reason": "Different failure classes: optional post_init behavior in patchtsmixer vs junk-filled non-persistent buffers in v5." }, { - "left": "issue:43906", - "right": "issue:45290", + "left": "issue:43295", + "right": "issue:44871", "accept": false, - "reason": "Both involve chat/template behavior, but the failures differ: isolated reproduction of an older issue vs tool-call assistant messages with no content." + "reason": "Both involve model/processor config, but one is a tokenizer/processor regression and the other is an eos_token_id mismatch." }, { "left": "issue:43550", "right": "issue:43701", "accept": false, - "reason": "Unrelated problems: torch.compile with SDPA on Bamba vs resume_from_checkpoint key mismatch." - }, - { - "left": "issue:43295", - "right": "issue:44871", - "accept": false, - "reason": "Different regressions: processor.tokenizer/images handling vs eos_token_id config mismatch." + "reason": "Unrelated bugs: torch.compile SDPA failure for Bamba vs checkpoint key mismatch on resume." }, { "left": "issue:43606", "right": "issue:43701", "accept": false, - "reason": "Device-mismatch CPU offload bug is unrelated to checkpoint resume key mismatch." + "reason": "CPU offload device mismatch is a different code path from resume_from_checkpoint key mismatch." }, { "left": "issue:43646", "right": "issue:44913", "accept": false, - "reason": "Both are config/init-adjacent, but one is a broad custom model init regression and the other is a GPTNeoXConfig reload issue." + "reason": "Custom model init breakage is not the same as GPTNeoX config reload losing rotary_pct." }, { - "left": "issue:43761", - "right": "issue:44242", + "left": "issue:43906", + "right": "issue:45290", "accept": false, - "reason": "Different model paths: CLIPVisionModel hidden_states regression vs MoE load-balancing loss calculation." + "reason": "Both touch chat/template behavior, but one is an isolated reproduction of an older issue and the other is a tokenizer crash on tool-call assistant messages." }, { "left": "issue:44617", "right": "issue:45584", "accept": false, - "reason": "CUDA OOM in Sam3Video is unrelated to Whisper empty-transcription chat/template handling." + "reason": "Completely different models and symptoms: Sam3Video CUDA OOM vs Whisper empty transcription handling." }, { - "left": "issue:43931", - "right": "issue:44060", + "left": "issue:43761", + "right": "issue:44242", "accept": false, - "reason": "Qwen3-VL weight-shape mismatch and tied-weights warning are different failures." + "reason": "Different bugs in different models: CLIPVision hidden_states omission vs MoE load-balancing loss not added." }, { "left": "issue:43452", "right": "issue:44496", "accept": false, - "reason": "gguf_file/from_pretrained breakage is unrelated to an unrecognized model_type config error." + "reason": "Both are loading failures, but one is gguf_file handling and the other is an unrecognized config/model_type issue." + }, + { + "left": "issue:43931", + "right": "issue:44060", + "accept": false, + "reason": "Shape-mismatch loading for Qwen3-VL is unrelated to the tied-weights warning in Qwen3-Next." }, { "left": "issue:45563", "right": "issue:45584", "accept": false, - "reason": "A stale warning about num_return_sequences is not the same bug as Whisper failing on empty transcription." + "reason": "Paged generate warning bug is unrelated to Whisper empty transcription after align_special_tokens." }, { "left": "issue:44521", "right": "issue:45381", "accept": false, - "reason": "Both are multimodal/VL issues, but they affect different logic paths: assistant masks vs vision_position_ids." + "reason": "Both are multimodal, but assistant_masks being all zero is not the same bug as wrong vision_position_ids in Qwen2.5-VL video input." }, { "left": "issue:43575", "right": "issue:43742", "accept": false, - "reason": "Tensor-parallel OOM and a MobileLLM loading key error are unrelated." + "reason": "Tensor-parallel OOM for Qwen2-57B is a different problem from a MobileLLM config key error." }, { "left": "issue:42617", "right": "issue:43575", "accept": false, - "reason": "3d_parallel.py execution failure is not the same as Qwen2-57B tensor-parallel OOM." + "reason": "3d_parallel.py runtime failure is not the same as model-loading OOM with tensor parallelism." }, { "left": "issue:44479", "right": "issue:44734", "accept": false, - "reason": "Video-input regression in Qwen models and KV-cache continuation tensor indexing are different code paths." + "reason": "Video-input regression in VL models is a different code path from KV-cache continuation indexing in serve." }, { "left": "issue:44933", "right": "issue:45362", "accept": false, - "reason": "Missing image_utils import and Qwen3.5 chat crash are unrelated." - }, - { - "left": "issue:44464", - "right": "issue:45563", - "accept": false, - "reason": "Compiled-forward generation inconsistency is unrelated to a stale warning about num_return_sequences." + "reason": "Missing import from image_utils is a packaging/API issue, not the same as Qwen3.5 chat generation crashes." }, { "left": "issue:41720", "right": "issue:43575", "accept": false, - "reason": "Auto device mapping cuda assert on A800 is not the same issue as tensor-parallel OOM." + "reason": "cudaErrorAssert on auto device mapping is distinct from a tensor-parallel out-of-memory failure." }, { "left": "issue:32090", "right": "issue:35141", "accept": false, - "reason": "Trainer GPU broadcast TypeError and embedding reinitialization in post_init are different bugs." + "reason": "Trainer GPU broadcast NoneType error is unrelated to embedding resize/post_init reinitialization." + }, + { + "left": "issue:44464", + "right": "issue:45563", + "accept": false, + "reason": "Compiled-forward chunked generation inconsistency is a different bug from a stale warning in paged generate()." }, { "left": "issue:43065", "right": "issue:44610", "accept": false, - "reason": "Both are vision-model related, but one is a dummy Conv2d placeholder and the other is a processor/model input-size mismatch." + "reason": "Sam3PixelDecoder dummy Conv2d and OmDet-Turbo processor size mismatch are separate vision-model issues." }, { "left": "issue:44464", "right": "issue:44871", "accept": false, - "reason": "Generation inconsistency with compiled forward is unrelated to eos_token_id configuration inconsistency." + "reason": "Compiled generation inconsistency and eos_token_id config mismatch are unrelated." }, { "left": "issue:44792", "right": "issue:44977", "accept": false, - "reason": "Janus image-generation test failure and Qwen3.5 flash-attention generation issues are different failures." + "reason": "Janus image-generation test failure is not the same as Qwen3.5 flash-attention generation failure." }, { "left": "issue:43827", "right": "issue:43994", "accept": false, - "reason": "Docs still referencing pipeline() is unrelated to SIGLIP2 producing nonsensical outputs." + "reason": "Docs still referencing pipeline() is a documentation break, not the same as SigLIP2 producing bad outputs." }, { "left": "issue:44534", "right": "issue:44913", "accept": false, - "reason": "Non-persistent buffer junk and rotary_pct reload behavior are separate configuration/runtime bugs." + "reason": "Non-persistent buffer junk in v5 and GPTNeoX rotary_pct reload regression affect different mechanisms." }, { "left": "issue:41720", "right": "issue:45245", "accept": false, - "reason": "CUDA assert in Qwen3 auto device mapping is unrelated to the 2^24 category limit error." + "reason": "Qwen3 device-mapping assert and category-count limit error are unrelated." }, { "left": "issue:44938", "right": "issue:45542", "accept": false, - "reason": "Python 3.14 import/load failure is not the same as missing TensorFlow backend detection when only tensorboard is installed." - }, - { - "left": "issue:43650", - "right": "issue:44220", - "accept": false, - "reason": "The titles are too generic to indicate the same bug, and the audio feature extraction issue is a different code path." + "reason": "Python 3.14 load failure is an environment/runtime compatibility issue, not the TensorBoard-without-TensorFlow backend error." }, { "left": "issue:44190", "right": "issue:44964", "accept": false, - "reason": "Local dataset loading in a no-trainer script is unrelated to loading a multimodal Phi-4 model." + "reason": "Local dataset loading failure and Phi-4-multimodal model loading failure are different problems." }, { "left": "issue:45127", "right": "issue:45357", "accept": false, - "reason": "LoRA merge with extended vocabulary collapse and incorrect visual encoder keys in save_pretrained are different Qwen-related bugs." + "reason": "LoRA merge collapse with extended vocab and incorrect visual encoder save keys are separate regression areas." } ] }, @@ -8619,10 +8458,10 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:36246", "issue:38175", @@ -8631,36 +8470,34 @@ "issue:41628", "issue:41950", "issue:42175", - "issue:42907", "issue:43065", "issue:43116", "issue:43295", - "issue:43299", "issue:43388", "issue:43404", - "issue:43441", "issue:43479", "issue:43540", "issue:43550", "issue:43582", "issue:43644", + "issue:43650", "issue:43761", "issue:43976", "issue:44016", "issue:44077", "issue:44079", "issue:44112", - "issue:44186", "issue:44190", "issue:44220", "issue:44246", "issue:44279", "issue:44355", "issue:44466", + "issue:44514", + "issue:44561", "issue:44683", "issue:44734", "issue:44743", - "issue:44792", "issue:44855", "issue:44913", "issue:45003", @@ -8668,257 +8505,260 @@ "issue:45245", "issue:45276", "issue:45375", + "issue:45406", "issue:45446", "issue:45584", "issue:45588", - "issue:45600" + "issue:45600", + "issue:45632" ], "soft_pairs": [ - "issue:44792|issue:45600", "issue:43388|issue:43582", "issue:43761|issue:44743", "issue:44855|issue:45588", + "issue:43650|issue:44220", "issue:44355|issue:44855", "issue:43540|issue:44734", - "issue:43976|issue:44855", "issue:43644|issue:44913", "issue:45276|issue:45584", - "issue:43404|issue:45216", + "issue:43976|issue:44855", "issue:44077|issue:44079", + "issue:43404|issue:45216", "issue:43550|issue:44190", - "issue:43116|issue:44190", "issue:44112|issue:45600", + "issue:43116|issue:44190", "issue:43295|issue:45276", "issue:45245|issue:45584", "issue:41950|issue:44016", "issue:39692|issue:44190", - "issue:43479|issue:45375", + "issue:44734|issue:45632", "issue:36246|issue:41628", + "issue:43479|issue:45375", + "issue:45406|issue:45632", + "issue:44561|issue:45632", "issue:36246|issue:38617", - "issue:44186|issue:44734", + "issue:44514|issue:44734", "issue:38175|issue:43065", "issue:44016|issue:44220", "issue:42175|issue:44279", "issue:44683|issue:45446", "issue:44466|issue:44913", - "issue:44246|issue:45003", - "issue:43299|issue:45216", - "issue:42907|issue:43441" + "issue:44246|issue:45003" ], - "prepared_review_unit_hash": "c87d4ab43a1ef1e6f1e546393cba717c6524b6f07ce1b4e06c0d6c848f9048fb", + "prepared_review_unit_hash": "96052cd4bb9d5693a1218cce286e28f274ecd2a8ce54acd91b994cd755f18301", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 30, - "serialized_chars": 36785, - "estimated_input_tokens": 9197, - "estimated_eval_tokens": 18650 + "soft_pair_count": 31, + "serialized_chars": 37130, + "estimated_input_tokens": 9283, + "estimated_eval_tokens": 18822 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This is a heterogeneous bag of Transformers bugs and regressions; the soft links are mostly superficial and do not indicate true duplicates. No PRs are present.", + "summary": "These items are a broad mix of unrelated bugs, regressions, import errors, and docs/example issues. None of the soft-edge pairs look like the same underlying change or bug, so all are rejected.", "confidence": 0.93, - "canonical_issue_reason": "issue:45003 is the broadest open infrastructure-style bug in the set, but the cluster is too mixed to have a strong true canonical.", + "canonical_issue_reason": "Issue 44561 is a strong standalone report: it names a concrete regression, has a clear failure mode, and affects trust_remote_code models broadly.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45003 is the best fallback duplicate target because it is open, cross-cutting, and more general than the model-specific reports.", + "best_issue_reason": "Issue 44561 is the best overall canonical candidate among this set because it is specific, regression-oriented, and points to a well-defined code-path breakage.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:44792", - "right": "issue:45600", - "accept": false, - "reason": "Different failures: janus image-generation test vs removed Sam3LiteText config references in auto_mappings." - }, { "left": "issue:43388", "right": "issue:43582", "accept": false, - "reason": "Unrelated subsystems: metric gathering label trimming vs Apple Silicon allocator warmup TypeError." + "reason": "Different failures in different areas: metric gathering label truncation vs Apple Silicon allocator warmup TypeError." }, { "left": "issue:43761", "right": "issue:44743", "accept": false, - "reason": "Both involve model state handling, but one is CLIP hidden_states and the other is Qwen recurrent cache reset." + "reason": "Both are model-behavior bugs, but one is CLIPVision hidden_states regression and the other is Qwen recurrent-state caching reset." }, { "left": "issue:44855", "right": "issue:45588", "accept": false, - "reason": "Different bugs: Python 3.13 import parsing issue vs flash_attention crashing on s_aux=None." + "reason": "Completely unrelated: Python 3.13 import parse error in DebertaV2Model vs flash_attention crash on s_aux=None." + }, + { + "left": "issue:43650", + "right": "issue:44220", + "accept": false, + "reason": "`ADD THE DATA` is not a concrete duplicate of the `_torch_extract_fbank_features()` bug; no shared code-path." }, { "left": "issue:44355", "right": "issue:44855", "accept": false, - "reason": "One is a generic compiled-Python-file error; the other is a specific DebertaV2 import/parsing regression." + "reason": "Running compiled Python files is unrelated to the DebertaV2 import/parse issue." }, { "left": "issue:43540", "right": "issue:44734", "accept": false, - "reason": "Different areas: Qwen3OmniMoe video input validation vs serve KV-cache continuation indexing." - }, - { - "left": "issue:43976", - "right": "issue:44855", - "accept": false, - "reason": "Both are version/platform problems, but one is Python version support and the other is a Python 3.13 parser/import issue." + "reason": "Different code paths: Qwen3OmniMoe video input validation vs server KV-cache continuation tensor indexing." }, { "left": "issue:43644", "right": "issue:44913", "accept": false, - "reason": "Both are v5 regressions, but one is non-persistent buffer initialization and the other is config reload persistence." + "reason": "One is non-persistent buffer initialization junk, the other is GPTNeoX config reload behavior." }, { "left": "issue:45276", "right": "issue:45584", "accept": false, - "reason": "Unrelated model behaviors: Gemma4 embedding resize vs Whisper empty-transcription generation failure." + "reason": "Gemma4 embedding resize bug is unrelated to Whisper empty-transcription generation after token alignment." }, { - "left": "issue:43404", - "right": "issue:45216", + "left": "issue:43976", + "right": "issue:44855", "accept": false, - "reason": "Similar serialization theme, but different models and concrete bugs; not the same save_pretrained failure." + "reason": "Broad Python-version support issue is not the same as a Python 3.13 DebertaV2 import parsing error." }, { "left": "issue:44077", "right": "issue:44079", "accept": false, - "reason": "Unrelated core issues: patchtsmixer post_init policy vs ModelOutput key assignment." + "reason": "Optional post_init enforcement and ModelOutput key assignment are different abstractions and different bugs." }, { - "left": "issue:43550", - "right": "issue:44190", + "left": "issue:43404", + "right": "issue:45216", "accept": false, - "reason": "Different code paths: torch.compile SDPA failure vs local dataset loading in an example script." + "reason": "Both involve weights, but they are different failures: Mistral3 lm_head tying vs Qwen3.5 save_pretrained checkpoint corruption." }, { - "left": "issue:43116", + "left": "issue:43550", "right": "issue:44190", "accept": false, - "reason": "Both are example-script problems, but one is empty multilabel outputs and the other is dataset loading." + "reason": "torch.compile SDPA failure in Bamba is unrelated to local dataset loading in an example script." }, { "left": "issue:44112", "right": "issue:45600", "accept": false, - "reason": "Different CI failures: GraniteSpeech stale device override test vs auto_mappings referencing removed configs." + "reason": "Both hit CI, but one is a stale test and the other is a broken auto_mappings reference to removed configs." + }, + { + "left": "issue:43116", + "right": "issue:44190", + "accept": false, + "reason": "Both are example-script issues, but one is empty multi-label results and the other is local dataset loading." }, { "left": "issue:43295", "right": "issue:45276", "accept": false, - "reason": "Different regressions: processor/tokenizer API breakage vs token embedding resize not propagating." + "reason": "Processor/tokenizer regression is unrelated to Gemma4 embedding resize behavior." }, { "left": "issue:45245", "right": "issue:45584", "accept": false, - "reason": "No match: category-count overflow is unrelated to Whisper empty transcription handling." + "reason": "Category-count runtime error has nothing to do with Whisper's empty-transcription bug." }, { "left": "issue:41950", "right": "issue:44016", "accept": false, - "reason": "Different problem classes: pipeline processor lookup vs notebook syntax error." + "reason": "Video-classification pipeline bug and notebook syntax error are unrelated." }, { "left": "issue:39692", "right": "issue:44190", "accept": false, - "reason": "SigLIP2 documentation/quantization example errors are unrelated to the image-classification dataset-loading issue." + "reason": "SigLIP2 doc/model mismatch and quantization issues are unrelated to dataset loading." }, { - "left": "issue:43479", - "right": "issue:45375", + "left": "issue:44734", + "right": "issue:45632", "accept": false, - "reason": "Both are multimodal config bugs, but they affect different models and different missing/default fields." + "reason": "Server KV-cache tensor indexing and trust_remote_code cache-path collision are different bugs in different subsystems." }, { "left": "issue:36246", "right": "issue:41628", "accept": false, - "reason": "Both are import errors, but for different symbols and different API surfaces." + "reason": "Both are import errors, but they involve different missing symbols and different modules (`Qwen2_5_VLImageProcessor` vs `AutoImageProcessor`)." + }, + { + "left": "issue:43479", + "right": "issue:45375", + "accept": false, + "reason": "Different config bugs for different models: default multimodal config initialization vs missing deepstack_visual_indexes strict-field handling." + }, + { + "left": "issue:45406", + "right": "issue:45632", + "accept": false, + "reason": "Gemma4Processor missing `_tokenizer` and cache-path collisions are unrelated." + }, + { + "left": "issue:44561", + "right": "issue:45632", + "accept": false, + "reason": "`is_torch_fx_available` removal breaking trust_remote_code is unrelated to local-model cache path collisions." }, { "left": "issue:36246", "right": "issue:38617", "accept": false, - "reason": "Different missing imports: a model-specific image processor export vs layer_type_validation in configuration_utils." + "reason": "Both are import errors, but they are not the same missing API or same fix path." }, { - "left": "issue:44186", + "left": "issue:44514", "right": "issue:44734", "accept": false, - "reason": "Different failures: tokenizer padding/truncation crash vs server KV-cache continuation bug." + "reason": "Qwen2_5_VLProcessor batched chat-template crash is separate from server KV-cache continuation indexing." }, { "left": "issue:38175", "right": "issue:43065", "accept": false, - "reason": "Unrelated model-specific issues: zero probabilities in SigLIP2 vs dummy Conv2d in Sam3PixelDecoder." + "reason": "SigLIP2 zero-probabilities and Sam3PixelDecoder dummy Conv2d are unrelated model bugs." }, { "left": "issue:44016", "right": "issue:44220", "accept": false, - "reason": "Notebook syntax error and feature-extraction error are unrelated." + "reason": "Notebook syntax error and feature-extraction helper bug do not share an underlying cause." }, { "left": "issue:42175", "right": "issue:44279", "accept": false, - "reason": "Dependency/backend packaging issue vs a generic transformers dependency complaint; not the same bug." + "reason": "Dependency packaging for `.[torch]` is not the same as a general transformers dependency issue." }, { "left": "issue:44683", "right": "issue:45446", "accept": false, - "reason": "Same flex_attention area, but compiled flex_attention on torch>=2.9 and AuxRequest version-gating are distinct failures." + "reason": "Flex attention compiled failure on torch>=2.9 and an AuxRequest version-check bug are related only by subsystem, not the same fix." }, { "left": "issue:44466", "right": "issue:44913", "accept": false, - "reason": "Different serialization/config regressions: tied lm_head weights vs rotary_pct not persisting." + "reason": "lm_head.weight serialization inconsistency is unrelated to GPTNeoX rotary_pct reload behavior." }, { "left": "issue:44246", "right": "issue:45003", "accept": false, - "reason": "Import-time performance regression is different from unsafe sys.modules access, even if related to import behavior." - }, - { - "left": "issue:43299", - "right": "issue:45216", - "accept": false, - "reason": "Different models and symptoms: Qwen3VL loading breakage vs Qwen3.5 save_pretrained checkpoint corruption." - }, - { - "left": "issue:42907", - "right": "issue:43441", - "accept": false, - "reason": "Ministral save/dequantization failure is separate from the FlashAttention runtime failure." - }, - { - "left": "issue:45276", - "right": "issue:45584", - "accept": false, - "reason": "Different user-visible bugs in unrelated models; no shared underlying code-path problem." + "reason": "Import slowness and unsafe sys.modules access are different import-time problems with different remedies." } ] }, @@ -8940,23 +8780,24 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ - "issue:41950", + "issue:42907", "issue:43295", "issue:43299", "issue:43381", + "issue:43441", "issue:43479", "issue:43525", "issue:43526", "issue:43531", "issue:43577", "issue:43643", - "issue:43650", "issue:43673", "issue:43824", "issue:43854", "issue:43901", + "issue:43927", "issue:43976", "issue:44016", "issue:44062", @@ -8964,7 +8805,6 @@ "issue:44112", "issue:44242", "issue:44279", - "issue:44297", "issue:44336", "issue:44351", "issue:44368", @@ -8972,11 +8812,9 @@ "issue:44496", "issue:44521", "issue:44683", - "issue:44877", "issue:44933", "issue:44964", "issue:44987", - "issue:45020", "issue:45042", "issue:45081", "issue:45200", @@ -8987,264 +8825,252 @@ "issue:45357", "issue:45405", "issue:45542", + "issue:45561", "issue:45584", "issue:45593", - "issue:45600" + "issue:45600", + "issue:45632" ], "soft_pairs": [ + "issue:43299|issue:45216", + "issue:42907|issue:43441", "issue:43643|issue:44496", - "issue:44016|issue:44062", "issue:43295|issue:45335", + "issue:44016|issue:44062", "issue:44964|issue:45600", - "issue:43976|issue:44987", "issue:44112|issue:44964", - "issue:43673|issue:44336", + "issue:43976|issue:44987", + "issue:45561|issue:45632", "issue:43531|issue:45600", + "issue:43673|issue:44336", "issue:45335|issue:45584", "issue:43824|issue:44933", "issue:43976|issue:44279", - "issue:43299|issue:45357", "issue:44496|issue:45042", "issue:43854|issue:44964", "issue:43577|issue:45216", - "issue:44075|issue:44368", + "issue:43299|issue:45357", "issue:43526|issue:43901", + "issue:44075|issue:44368", "issue:44521|issue:45325", "issue:44242|issue:45200", "issue:43381|issue:45593", - "issue:44683|issue:45542", - "issue:44351|issue:45278", + "issue:43927|issue:45632", "issue:43901|issue:44496", + "issue:44351|issue:45278", + "issue:44683|issue:45542", "issue:43976|issue:45405", - "issue:41950|issue:43650", "issue:43479|issue:43525", - "issue:41950|issue:45020", - "issue:44462|issue:45081", - "issue:44297|issue:44462", - "issue:44496|issue:44877", - "issue:44279|issue:45405", - "issue:43299|issue:43854" + "issue:44462|issue:45081" ], - "prepared_review_unit_hash": "429800f0eb960a7765dd79724961bd99aed5abb31b8448dbd56c896a11c2375d", + "prepared_review_unit_hash": "0f4cbc5a0c5c3738f8d13c649ca7fe642435cc85a7c4d881c6b171b97268edb0", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 32, - "serialized_chars": 37278, - "estimated_input_tokens": 9320, - "estimated_eval_tokens": 18896 + "soft_pair_count": 30, + "serialized_chars": 36768, + "estimated_input_tokens": 9192, + "estimated_eval_tokens": 18640 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is broad and mostly heterogeneous: many items are separate loading/config/tokenizer/processor regressions that only share a general Transformers-version-breakage theme. None of the soft pairs look like the same underlying bug closely enough to merge.", - "confidence": 0.93, - "canonical_issue_reason": "issue:45020 is the broadest umbrella report here, covering recent version regressions that break model loading with remote_code; it is the closest representative of the dominant theme, though still not a duplicate of the more specific bugs.", + "summary": "This cluster is mostly a mix of unrelated Transformers bugs and regressions across different models/subsystems. None of the soft pairs look like clear same-bug duplicates under a strict triage standard; a few are loosely similar (especially import/loading regressions), but the concrete failure modes differ.", + "confidence": 0.89, + "canonical_issue_reason": "issue:45278 is the broadest umbrella item in the set, describing multiple import failures after an upgrade, so it is the closest thing to a representative issue; however, the rest of the items are mostly separate bugs rather than true duplicates.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45020 is the best issue to anchor triage because it is open, recent, and broad enough to subsume several of the other model-loading regressions at a high level.", + "best_issue_reason": "issue:45278 is the most general and broadly scoped issue in the list, making it the best representative anchor even though the cluster does not form a clean duplicate set.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43643", - "right": "issue:44496", + "left": "issue:43299", + "right": "issue:45216", "accept": false, - "reason": "Both are model-loading/config issues, but one is about missing fields from AutoConfig with trust_remote_code and the other is about an unrecognized model lacking model_type; different failure modes." + "reason": "Same general Qwen family, but one is a model-loading regression and the other is a bad save_pretrained checkpoint layout; different concrete bugs." }, { - "left": "issue:44016", - "right": "issue:44062", + "left": "issue:42907", + "right": "issue:43441", + "accept": false, + "reason": "Both mention Ministral, but one is about saving dequantized models and the other is a FlashAttention loading failure; not the same code path." + }, + { + "left": "issue:43643", + "right": "issue:44496", "accept": false, - "reason": "Notebook syntax error and AddedToken argument collision are unrelated bugs." + "reason": "Both are config/loading-related, but one is missing fields with trust_remote_code while the other is an unrecognized model_type error; distinct causes." }, { "left": "issue:43295", "right": "issue:45335", "accept": false, - "reason": "Processor.tokenizer/image handling regression vs t5gemma embedding resize bug; same general area only, not the same defect." + "reason": "Processor/tokenizer regression versus token embedding resize not propagating to decoder.embed_tokens; unrelated bugs." }, { - "left": "issue:44964", - "right": "issue:45600", + "left": "issue:44016", + "right": "issue:44062", "accept": false, - "reason": "Phi-4 multimodal model-loading failure and stale auto_mappings reference to removed Sam3LiteText configs are distinct breakages." + "reason": "Notebook syntax error and AddedToken argument collision are unrelated failures." }, { - "left": "issue:43976", - "right": "issue:44987", + "left": "issue:44964", + "right": "issue:45600", "accept": false, - "reason": "Python version support issue versus a specific loading failure for physical-intelligence/fast; not the same bug." + "reason": "Different model families and different failure modes: Phi-4 multimodal loading versus stale auto_mappings references." }, { "left": "issue:44112", "right": "issue:44964", "accept": false, - "reason": "CI stale device override test failure is unrelated to Phi-4 multimodal loading." + "reason": "CI test flake in GraniteSpeech versus a model-loading regression; no shared underlying bug." }, { - "left": "issue:43673", - "right": "issue:44336", + "left": "issue:43976", + "right": "issue:44987", + "accept": false, + "reason": "A Python version compatibility problem is not the same as a specific model-loading failure for physical-intelligence/fast." + }, + { + "left": "issue:45561", + "right": "issue:45632", "accept": false, - "reason": "Chunked_prefill GenerationMixin cache regression and ANSI codes in loading_report are separate concerns." + "reason": "Test-worker file race and trust_remote_code cache-path collision are both infrastructure issues, but they are different mechanisms and code paths." }, { "left": "issue:43531", "right": "issue:45600", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior and auto_mappings config references are unrelated." + "reason": "Qwen3-MoE sliding_window behavior versus stale auto_mappings config references; unrelated." + }, + { + "left": "issue:43673", + "right": "issue:44336", + "accept": false, + "reason": "Generation cache regression and ANSI escape output handling are unrelated." }, { "left": "issue:45335", "right": "issue:45584", "accept": false, - "reason": "t5gemma embedding resize behavior and Whisper empty transcription failure are different code paths." + "reason": "Token embedding resize bug versus Whisper empty-transcription generation failure; different models and code paths." }, { "left": "issue:43824", "right": "issue:44933", "accept": false, - "reason": "ImportError for Qwen2.5-VL class and missing image_utils import are both import issues but for different symbols and causes." + "reason": "Both are import errors, but they refer to different missing symbols and likely different underlying breakages." }, { "left": "issue:43976", "right": "issue:44279", "accept": false, - "reason": "Python compatibility regression versus a vague dependency issue; too unspecific and not the same underlying defect." - }, - { - "left": "issue:43299", - "right": "issue:45357", - "accept": false, - "reason": "Qwen3VL model loading failure and Qwen3.5 save_pretrained key regression are different lifecycle stages and symptoms." + "reason": "General dependency/version issue versus a vague transformers dependency issue; too broad and not the same concrete bug." }, { "left": "issue:44496", "right": "issue:45042", "accept": false, - "reason": "Unrecognized model/config error versus PIL image processors incorrectly requiring torchvision; unrelated failures." + "reason": "Unrecognized model config loading is unrelated to PIL backend processors incorrectly requiring torchvision." }, { "left": "issue:43854", "right": "issue:44964", "accept": false, - "reason": "GLM-4.7-Flash test loading failure and Phi-4 multimodal loading failure are separate model-specific issues." + "reason": "Two separate model-loading failures for different model families; not a duplicate." }, { "left": "issue:43577", "right": "issue:45216", "accept": false, - "reason": "Blip2 dtype propagation bug and Qwen3.5 save_pretrained regression are unrelated." + "reason": "Blip2 dtype propagation bug and Qwen3.5 checkpoint save regression are unrelated." }, { - "left": "issue:44075", - "right": "issue:44368", + "left": "issue:43299", + "right": "issue:45357", "accept": false, - "reason": "Optimizer SGD arguments not used and tie_word_embeddings warning are different problems." + "reason": "Both involve Qwen models, but one is loading failure and the other is incorrect visual encoder keys on save_pretrained; different symptoms and fixes." }, { "left": "issue:43526", "right": "issue:43901", "accept": false, - "reason": "BeitImageProcessorFast label reduction bug and TextClassificationPipeline docs mismatch are not the same change or bug." + "reason": "Image processor label reduction bug versus a docs mismatch about return_all_scores; unrelated." + }, + { + "left": "issue:44075", + "right": "issue:44368", + "accept": false, + "reason": "Unused SGD args and a tie_word_embeddings warning are unrelated." }, { "left": "issue:44521", "right": "issue:45325", "accept": false, - "reason": "Multimodal assistant masks being all zero and Qwen2.5-VL rope index scaling are both multimodal but affect different outputs and code paths." + "reason": "Both touch multimodal generation, but assistant mask handling and Qwen2.5-VL rope/position-id scaling are different code paths." }, { "left": "issue:44242", "right": "issue:45200", "accept": false, - "reason": "Router loss omission and Gemma 4 mm_token_type_ids defaulting are separate training issues." + "reason": "Load-balancing loss logic and mm_token_type_ids defaults are separate model-training issues." }, { "left": "issue:43381", "right": "issue:45593", "accept": false, - "reason": "Gradient checkpointing eval-mode restriction and D-FINE auxiliary loss omission are unrelated model-training behaviors." + "reason": "Gradient checkpointing in eval mode and D-FINE auxiliary-loss handling are unrelated." }, { - "left": "issue:44683", - "right": "issue:45542", + "left": "issue:43927", + "right": "issue:45632", + "accept": false, + "reason": "Save/load token ID loss in DiaConfig is unrelated to trust_remote_code cache-path collisions." + }, + { + "left": "issue:43901", + "right": "issue:44496", "accept": false, - "reason": "Compiled flex_attention on torch>=2.9 and tensorboard-without-TensorFlow backend error are unrelated environment/runtime issues." + "reason": "A pipeline docs mismatch does not share the same underlying bug as an unrecognized model config." }, { "left": "issue:44351", "right": "issue:45278", "accept": false, - "reason": "HybridCache import failure and broad import errors after upgrade are too general to treat as the same bug." + "reason": "HybridCache import failure may be one example of broader import regressions, but 45278 is only a generic meta report and not clearly the same concrete bug." }, { - "left": "issue:43901", - "right": "issue:44496", + "left": "issue:44683", + "right": "issue:45542", "accept": false, - "reason": "Documentation mismatch for TextClassificationPipeline and model-type/config loading failure are unrelated." + "reason": "Compiled flex_attention on torch>=2.9 and the TensorFlow/tensorboard backend issue are unrelated." }, { "left": "issue:43976", "right": "issue:45405", "accept": false, - "reason": "Python version compatibility and PEFT minimum-version bump are separate dependency/versioning issues." - }, - { - "left": "issue:41950", - "right": "issue:43650", - "accept": false, - "reason": "Video-classification looking for image processors is specific technical behavior; the 'ADD THE DATA' issue is not a concrete duplicate." + "reason": "Python compatibility and a PEFT version bump are different release issues." }, { "left": "issue:43479", "right": "issue:43525", "accept": false, - "reason": "Phi4MultimodalConfig default handling and Llama4Config missing pad_token_id are different config bugs." - }, - { - "left": "issue:41950", - "right": "issue:45020", - "accept": false, - "reason": "Specific video-classification processor lookup bug is only loosely related to broad remote_code loading regressions." + "reason": "Config default initialization for Phi4Multimodal and missing pad_token_id on Llama4Config are unrelated config bugs." }, { "left": "issue:44462", "right": "issue:45081", "accept": false, - "reason": "AutoTokenizer ignoring tokenizer.json and mistral regex patch crash are different tokenizer-loading problems." - }, - { - "left": "issue:44297", - "right": "issue:44462", - "accept": false, - "reason": "tokenizer.save_pretrained writing the wrong tokenizer_class and AutoTokenizer ignoring tokenizer.json are distinct save/load defects." - }, - { - "left": "issue:44496", - "right": "issue:44877", - "accept": false, - "reason": "Unrecognized model/config loading and strict granite_speech config rejection are different config-schema issues." - }, - { - "left": "issue:44279", - "right": "issue:45405", - "accept": false, - "reason": "Generic dependency issue and PEFT minimum-version bump are not the same actionable bug." - }, - { - "left": "issue:43299", - "right": "issue:43854", - "accept": false, - "reason": "Qwen3VL MoE loading regression and GLM-4.7-Flash test loading failure are model-specific and unrelated." + "reason": "Tokenizer JSON being ignored and a mistral regex patch crashing are different tokenizer-loading problems." } ] }, @@ -9266,30 +9092,28 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:38175", "issue:39692", - "issue:42175", + "issue:41950", "issue:42994", "issue:43065", "issue:43122", "issue:43262", "issue:43295", + "issue:43299", "issue:43317", "issue:43441", "issue:43450", - "issue:43475", "issue:43650", "issue:43653", "issue:43673", "issue:43723", "issue:43761", "issue:43784", - "issue:43824", + "issue:43854", "issue:43901", - "issue:43976", - "issue:43994", "issue:44016", "issue:44162", "issue:44261", @@ -9297,9 +9121,9 @@ "issue:44279", "issue:44291", "issue:44297", - "issue:44361", "issue:44462", "issue:44466", + "issue:44496", "issue:44521", "issue:44617", "issue:44623", @@ -9307,249 +9131,243 @@ "issue:44683", "issue:44749", "issue:44779", + "issue:44877", "issue:44898", "issue:44987", + "issue:45020", "issue:45276", "issue:45290", "issue:45397", + "issue:45405", "issue:45542", - "issue:45561", - "issue:45563", "issue:45593" ], "soft_pairs": [ - "issue:44462|issue:44779", + "issue:41950|issue:45020", + "issue:44297|issue:44462", + "issue:44279|issue:45405", + "issue:41950|issue:43650", + "issue:44496|issue:44877", + "issue:43299|issue:43854", "issue:38175|issue:44617", + "issue:44462|issue:44779", "issue:43295|issue:44779", "issue:39692|issue:43901", "issue:43650|issue:45290", "issue:43723|issue:44162", + "issue:43450|issue:44279", "issue:44016|issue:44291", "issue:43262|issue:44521", - "issue:43450|issue:44279", - "issue:43441|issue:44683", "issue:42994|issue:43317", + "issue:43441|issue:44683", "issue:44261|issue:44263", "issue:43065|issue:44898", + "issue:44466|issue:45276", "issue:44623|issue:45397", "issue:43122|issue:43650", - "issue:44466|issue:45276", "issue:44623|issue:44749", "issue:43784|issue:45542", - "issue:43673|issue:43761", "issue:44671|issue:44779", + "issue:43673|issue:43761", "issue:44987|issue:45542", - "issue:43653|issue:45593", - "issue:44297|issue:45397", - "issue:42175|issue:43976", - "issue:43901|issue:43994", - "issue:44361|issue:45593", - "issue:45561|issue:45563", - "issue:43475|issue:44016", - "issue:43824|issue:43976" + "issue:43653|issue:45593" ], - "prepared_review_unit_hash": "e1da6f31938234168dd6b536f38adc17efb3038097f8678a3ec6ce2456aae174", + "prepared_review_unit_hash": "76eccc8f15cb146bf651200c5a2cf40472cf6d8770d8f4341cb7b747e8a4a8cb", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 29, - "serialized_chars": 36275, - "estimated_input_tokens": 9069, - "estimated_eval_tokens": 18394 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 28, + "serialized_chars": 35388, + "estimated_input_tokens": 8847, + "estimated_eval_tokens": 17950 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly a heterogeneous set of closed issues with only a loose shared theme around v5 tokenizer/processor regressions. None of the soft-edge pairs look like the same concrete bug/change, so there are no safe duplicate merges here.", - "confidence": 0.34, - "canonical_issue_reason": "Issue 44779 is the closest thematic representative: it is a concrete v5 tokenizer regression with a clear before/after behavior change. That said, the cluster is too broad to treat it as a true duplicate anchor for the other reports.", + "summary": "This cluster is mostly a grab bag of distinct Transformers regressions and docs issues, not a single duplicate set. A few items are thematically adjacent (tokenizer/loading, processor/chat-template, v5 regressions), but the concrete failure modes differ enough that none of the soft edges should be merged.", + "confidence": 0.93, + "canonical_issue_reason": "No single canonical issue fits this cluster: it mixes unrelated bugs across tokenizers, processors, model loading, attention, quantization, docs, and model-specific failures.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 44779 is the best global representative because it is a user-facing, concrete regression tied to the v5 tokenizer path and overlaps most with the other tokenizer-related reports, even though it is not a duplicate of them.", + "best_issue_reason": "If forced to pick a representative issue, 45020 is the broadest v5/remote_code regression umbrella, but it is still too generic to serve as a true duplicate target for the rest.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44462", - "right": "issue:44779", + "left": "issue:41950", + "right": "issue:45020", + "accept": false, + "reason": "Different bugs: video-classification pipeline processor lookup vs broad remote_code model-loading breakage." + }, + { + "left": "issue:44297", + "right": "issue:44462", + "accept": false, + "reason": "Both tokenizer-related, but one is save_pretrained metadata/class mismatch and the other is AutoTokenizer ignoring tokenizer.json; different code paths." + }, + { + "left": "issue:44279", + "right": "issue:45405", + "accept": false, + "reason": "Unrelated: generic dependency problem vs a PEFT minimum-version bump issue." + }, + { + "left": "issue:41950", + "right": "issue:43650", + "accept": false, + "reason": "No overlap beyond being noisy issues; video pipeline processor lookup is unrelated to the placeholder 'ADD THE DATA' report." + }, + { + "left": "issue:44496", + "right": "issue:44877", + "accept": false, + "reason": "Different subsystems: strict config loading for granite_speech vs Perceiver resize/interpolate behavior." + }, + { + "left": "issue:43299", + "right": "issue:43854", "accept": false, - "reason": "Both are tokenizer-related regressions, but one is about AutoTokenizer ignoring tokenizer.json while the other is Deepseek tokenization changing in v5; different models and failure modes." + "reason": "Both involve model loading, but for different model families and likely different failure causes." }, { "left": "issue:38175", "right": "issue:44617", "accept": false, - "reason": "SigLIP2 zero probabilities and Sam3Video CUDA OOM are unrelated model/runtime failures." + "reason": "SigLIP2 zero-probabilities inference bug is unrelated to Sam3Video CUDA OOM." + }, + { + "left": "issue:44462", + "right": "issue:44779", + "accept": false, + "reason": "Tokenizer loading from repository vs DeepSeek tokenization correctness are distinct tokenizer bugs." }, { "left": "issue:43295", "right": "issue:44779", "accept": false, - "reason": "Processor.tokenizer regression with multimodal image handling is not the same bug as Deepseek tokenizer output changes." + "reason": "Processor.tokenizer regression with images passed to tokenizer is different from DeepSeek tokenizer output drift." }, { "left": "issue:39692", "right": "issue:43901", "accept": false, - "reason": "Both mention docs/examples, but they concern different pipelines and different errors; not the same change." + "reason": "Both docs-related, but different docs and different errors: SigLIP2 example failures vs return_all_scores documentation drift." }, { "left": "issue:43650", "right": "issue:45290", "accept": false, - "reason": "Placeholder issue title versus a chat-template crash on tool-call messages; no underlying overlap." + "reason": "Placeholder issue is not the same as the specific apply_chat_template tool-call crash." }, { "left": "issue:43723", "right": "issue:44162", "accept": false, - "reason": "AutoTokenizer loading failure and ESM2 breakage are separate issues affecting different code paths." + "reason": "AutoTokenizer.from_pretrained regression is not the same as ESM2 model breakage." + }, + { + "left": "issue:43450", + "right": "issue:44279", + "accept": false, + "reason": "Video processor batched-shape bug is unrelated to a dependency issue." }, { "left": "issue:44016", "right": "issue:44291", "accept": false, - "reason": "Notebook syntax error is unrelated to init_empty_weights/_is_hf_initialized model-loading failure." + "reason": "Notebook syntax error vs init_empty_weights unexpected argument TypeError are unrelated." }, { "left": "issue:43262", "right": "issue:44521", "accept": false, - "reason": "Both involve apply_chat_template, but one is audio sampling-rate defaulting and the other is multimodal assistant mask generation; different bugs." + "reason": "Both involve apply_chat_template, but one is audio sampling-rate defaulting and the other is multimodal assistant mask generation." }, { - "left": "issue:43450", - "right": "issue:44279", + "left": "issue:42994", + "right": "issue:43317", "accept": false, - "reason": "Video processor shape bug and a dependency issue are unrelated." + "reason": "Quantized model save failure and dequantized offload/load failure are different stages and failure modes." }, { "left": "issue:43441", "right": "issue:44683", "accept": false, - "reason": "FlashAttention failure for Ministral-3 and compiled flex_attention failing on torch>=2.9 are different attention-stack issues." - }, - { - "left": "issue:42994", - "right": "issue:43317", - "accept": false, - "reason": "Saving quantized models and loading dequantized models with device_map=auto are different lifecycle steps with different failures." + "reason": "FlashAttention failure on a specific model is not the same as compiled flex_attention failing on newer torch." }, { "left": "issue:44261", "right": "issue:44263", "accept": false, - "reason": "MLA layernorm precision/config problem is unrelated to GlmMoeDsaIndexer torch.split return values." + "reason": "Layernorm epsilon precision discussion is unrelated to torch.split return values in GlmMoeDsaIndexer." }, { "left": "issue:43065", "right": "issue:44898", "accept": false, - "reason": "Sam3PixelDecoder dummy conv2d and Perceiver non-default resolution failure are different vision-model bugs." + "reason": "Dummy Conv2d in Sam3PixelDecoder is unrelated to Perceiver image-classification resolution handling." + }, + { + "left": "issue:44466", + "right": "issue:45276", + "accept": false, + "reason": "Both touch serialization/weights, but one is device-dependent lm_head serialization and the other is resize_token_embeddings not propagating to tied embeddings." }, { "left": "issue:44623", "right": "issue:45397", "accept": false, - "reason": "Missing processor files on save_pretrained and gemma-4 zero3 from_pretrained are unrelated." + "reason": "processor.save_pretrained missing files is a different bug from gemma-4 zero3 from_pretrained loading." }, { "left": "issue:43122", "right": "issue:43650", "accept": false, - "reason": "Tokenizer version regression and a nonspecific placeholder issue are not duplicates." - }, - { - "left": "issue:44466", - "right": "issue:45276", - "accept": false, - "reason": "Serialization of tied lm_head weights and gemma4 resize_token_embeddings not propagating are related only broadly to weights; not the same concrete bug." + "reason": "Tokenizer version drift is unrelated to the placeholder issue." }, { "left": "issue:44623", "right": "issue:44749", "accept": false, - "reason": "processor.save_pretrained missing files and a performance regression after upgrade are unrelated." + "reason": "Missing processor files on save is unrelated to the reported slowdown after upgrading Transformers." }, { "left": "issue:43784", "right": "issue:45542", "accept": false, - "reason": "Import-time NameError for sentence-transformers nn import and missing tf backend from optional deps are different backend initialization problems." + "reason": "Import-time NameError in sentence-transformers is unrelated to the TensorBoard/TensorFlow backend installation issue." }, { - "left": "issue:43673", - "right": "issue:43761", + "left": "issue:44671", + "right": "issue:44779", "accept": false, - "reason": "Generation cache missing in chunked_prefill and CLIPVisionModel hidden_states=None are separate regression paths." + "reason": "CamemBERT masked-LM prediction regression is a different model-specific bug from DeepSeek tokenization." }, { - "left": "issue:44671", - "right": "issue:44779", + "left": "issue:43673", + "right": "issue:43761", "accept": false, - "reason": "CamemBERT masked LM predictions and Deepseek tokenization regressions are both v5 symptoms but affect different models/code paths." + "reason": "Missing GenerationMixin cache in chunked_prefill is unrelated to CLIPVisionModel not returning hidden_states." }, { "left": "issue:44987", "right": "issue:45542", "accept": false, - "reason": "Model loading failure and tensorboard-without-TensorFlow backend error are unrelated." + "reason": "Model loading failure for physical-intelligence/fast is unrelated to the TensorBoard-only backend issue." }, { "left": "issue:43653", "right": "issue:45593", "accept": false, - "reason": "BigBirdTokenizer special-token bug and D-FINE auxiliary-loss behavior are unrelated subsystems." - }, - { - "left": "issue:44297", - "right": "issue:45397", - "accept": false, - "reason": "Tokenizer class serialization mismatch and gemma-4 zero3 loading are different bugs." - }, - { - "left": "issue:42175", - "right": "issue:43976", - "accept": false, - "reason": "Packaging/backend dependency issue and Python-version incompatibility are distinct release/environment problems." - }, - { - "left": "issue:43901", - "right": "issue:43994", - "accept": false, - "reason": "Docs mismatch for return_all_scores and SigLIP2 incorrect pipeline results are different issues." - }, - { - "left": "issue:44361", - "right": "issue:45593", - "accept": false, - "reason": "MLukeTokenizer AttributeError on tasks and D-FINE auxiliary-loss handling are unrelated." - }, - { - "left": "issue:45561", - "right": "issue:45563", - "accept": false, - "reason": "pytest-xdist file race in testing utils and stale num_return_sequences warning are unrelated." - }, - { - "left": "issue:43475", - "right": "issue:44016", - "accept": false, - "reason": "Sam3Video missing attribute and notebook syntax error are unrelated." - }, - { - "left": "issue:43824", - "right": "issue:43976", - "accept": false, - "reason": "Qwen2_5_VL import failure and Python3.9/3.10 support issue are unrelated." + "reason": "BigBirdTokenizer special-token registration bug is unrelated to D-FINE auxiliary-loss behavior." } ] }, @@ -9568,37 +9386,41 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:36246", "issue:41628", "issue:41950", + "issue:42175", "issue:42491", "issue:42757", "issue:43295", "issue:43299", "issue:43352", - "issue:43441", + "issue:43475", "issue:43525", "issue:43526", "issue:43531", - "issue:43540", - "issue:43596", "issue:43673", + "issue:43824", "issue:43881", "issue:43901", "issue:43976", + "issue:43994", + "issue:44016", "issue:44162", "issue:44188", "issue:44220", "issue:44242", "issue:44246", "issue:44295", + "issue:44297", "issue:44336", "issue:44351", + "issue:44361", "issue:44373", "issue:44462", "issue:44485", @@ -9607,32 +9429,35 @@ "issue:44589", "issue:44617", "issue:44661", - "issue:44749", - "issue:44857", - "issue:44871", - "issue:44877", "issue:45003", "issue:45200", "issue:45250", "issue:45356", "issue:45362", - "issue:45375", "issue:45397", "issue:45542", "issue:45561", + "issue:45563", "issue:45593" ], "soft_pairs": [ - "issue:43352|issue:45250", + "issue:42175|issue:43976", + "issue:43901|issue:43994", + "issue:44297|issue:45397", + "issue:44361|issue:45593", + "issue:45561|issue:45563", + "issue:43475|issue:44016", + "issue:43824|issue:43976", "issue:43295|issue:44617", + "issue:43352|issue:45250", "issue:44589|issue:45362", "issue:43525|issue:43881", - "issue:44188|issue:44336", "issue:41628|issue:43976", + "issue:44188|issue:44336", + "issue:43901|issue:44246", "issue:44295|issue:45397", - "issue:41950|issue:44220", "issue:42491|issue:43299", - "issue:43901|issue:44246", + "issue:41950|issue:44220", "issue:44242|issue:45593", "issue:44336|issue:44373", "issue:44462|issue:45356", @@ -9645,216 +9470,216 @@ "issue:43526|issue:45003", "issue:43673|issue:44561", "issue:44336|issue:44485", - "issue:44162|issue:45200", - "issue:44242|issue:44857", - "issue:44295|issue:44749", - "issue:44877|issue:45375", - "issue:36246|issue:43596", - "issue:43441|issue:43540", - "issue:44246|issue:44871" + "issue:44162|issue:45200" ], - "prepared_review_unit_hash": "764edf8e4abbf15011fa63d4a90649137fb616b0b124dca3b42483258ff3b14e", + "prepared_review_unit_hash": "03d63de90f6ab2089f76b8d997e24cddb9570b00ffe1aff808534e853ad4a001", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 29, - "serialized_chars": 36069, - "estimated_input_tokens": 9018, - "estimated_eval_tokens": 18292 + "soft_pair_count": 30, + "serialized_chars": 36335, + "estimated_input_tokens": 9084, + "estimated_eval_tokens": 18424 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is a loose collection of unrelated Transformers issues with only superficial lexical overlap (mostly imports, Qwen, FlashAttention, or model-loading wording). I would not merge any of the soft pairs as duplicates.", - "confidence": 0.24, - "canonical_issue_reason": "No strong duplicate canon exists here because the items span many different code paths; if a single representative is needed, #44246 is the broadest/highest-activity issue, but it is still only a weak stand-in.", + "summary": "This cluster is a loose mix of Transformers issues around import failures, model-loading regressions, tokenizer/pipeline bugs, and unrelated docs/test/model-specific problems. There are no PRs here, and none of the soft pairs look like true duplicates of the same underlying bug.", + "confidence": 0.64, + "canonical_issue_reason": "issue:43824 is the strongest anchor: it has the most inbound references and discussion, and it represents the broad import/load-breakage theme shared by several nearby reports.", "canonical_pr_reason": null, - "best_issue_reason": "#44246 is the most generic and discussion-heavy issue in the set, so it is the closest thing to a cluster anchor even though it does not truly summarize the rest of the items.", + "best_issue_reason": "issue:43824 is the best single representative for the cluster because it is the most referenced/discussed and sits closest to the recurring import/loading regressions, even though the overall cluster is not tight.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43352", - "right": "issue:45250", + "left": "issue:42175", + "right": "issue:43976", + "accept": false, + "reason": "TensorFlow backend packaging under `.[torch]` is unrelated to the Python 3.9+/5.1.0 compatibility problem." + }, + { + "left": "issue:43901", + "right": "issue:43994", + "accept": false, + "reason": "Docs about `return_all_scores` do not match the SigLIP2 bad-output model behavior." + }, + { + "left": "issue:44297", + "right": "issue:45397", + "accept": false, + "reason": "Tokenizer class mismatch on save is a different failure mode from Gemma-4 `from_pretrained` breakage." + }, + { + "left": "issue:44361", + "right": "issue:45593", + "accept": false, + "reason": "MLukeTokenizer task AttributeError is unrelated to D-FINE auxiliary-loss behavior." + }, + { + "left": "issue:45561", + "right": "issue:45563", + "accept": false, + "reason": "A pytest-xdist file race is not the same bug as the stale `num_return_sequences` warning in paged generate." + }, + { + "left": "issue:43475", + "right": "issue:44016", + "accept": false, + "reason": "SAM 3 Video missing attribute and a notebook syntax error are entirely different problems." + }, + { + "left": "issue:43824", + "right": "issue:43976", "accept": false, - "reason": "Same broad FlashAttention wording, but one is a concrete Nemotron model support gap and the other is too generic to prove the same bug/change." + "reason": "Qwen2_5_VL import failure is unrelated to Transformers 5.1.0/Python version incompatibility." }, { "left": "issue:43295", "right": "issue:44617", "accept": false, - "reason": "Regression in processor/tokenizer handling is unrelated to the CUDA OOM report for Sam3Video." + "reason": "Processor/tokenizer regression is a different code path from the SAM3 Video OOM report." + }, + { + "left": "issue:43352", + "right": "issue:45250", + "accept": false, + "reason": "Unsupported Flash Attention 2.0 for Nemotron is not the same as a generic Flash Attention 2.0 issue." }, { "left": "issue:44589", "right": "issue:45362", "accept": false, - "reason": "Different failures and code paths: a storage-type import/type error versus a Qwen chat crash." + "reason": "Float8 storage lookup failure and Qwen3.5 chat crash are different model/runtime issues." }, { "left": "issue:43525", "right": "issue:43881", "accept": false, - "reason": "Llama4 pad_token_id config error and glm-4v-9b loading failure are distinct model-specific bugs." + "reason": "Missing `pad_token_id` in Llama4Config is unrelated to glm-4v-9b loading failure." + }, + { + "left": "issue:41628", + "right": "issue:43976", + "accept": false, + "reason": "`AutoImageProcessor` import failure is not the same as the Transformers 5.1.0/Python compatibility bug." }, { "left": "issue:44188", "right": "issue:44336", "accept": false, - "reason": "Attention-kernel divergence under torch.compile is unrelated to ANSI codes in loading_report." + "reason": "torch.compile attention divergence and ANSI codes in loading_report are unrelated." }, { - "left": "issue:41628", - "right": "issue:43976", + "left": "issue:43901", + "right": "issue:44246", "accept": false, - "reason": "Importing AutoImageProcessor and Python-version compatibility are different problems." + "reason": "A docs mismatch is not the same underlying issue as slow `import transformers`." }, { "left": "issue:44295", "right": "issue:45397", "accept": false, - "reason": "Position_ids buffer access and gemma-4 zero3 loading are separate issues." - }, - { - "left": "issue:41950", - "right": "issue:44220", - "accept": false, - "reason": "Video pipeline image-processor lookup is not the same as the fbank feature extraction bug." + "reason": "Registered-buffer `position_ids` access differs from the Gemma-4 zero3 loading regression." }, { "left": "issue:42491", "right": "issue:43299", "accept": false, - "reason": "Both involve Qwen3 MoE variants, but the reported load/setup failures are different." + "reason": "Both involve Qwen3 MoE, but one is a LoRA hf4.x\u2192hf5.x incompatibility and the other is a model-loading regression on v5 dev, so they are not the same bug." }, { - "left": "issue:43901", - "right": "issue:44246", + "left": "issue:41950", + "right": "issue:44220", "accept": false, - "reason": "A docs mismatch for return_all_scores does not match an import-performance complaint." + "reason": "Video-classification pipeline image-processor lookup and `_torch_extract_fbank_features()` are different pipelines." }, { "left": "issue:44242", "right": "issue:45593", "accept": false, - "reason": "Both mention auxiliary losses, but they affect different models and different gating flags." + "reason": "MoE load-balancing loss and D-FINE auxiliary losses are unrelated training objectives." }, { "left": "issue:44336", "right": "issue:44373", "accept": false, - "reason": "Terminal color output and a docstring bug are unrelated." + "reason": "ANSI output in loading_report and a wrong docstring for `position_ids` are not duplicates." }, { "left": "issue:44462", "right": "issue:45356", "accept": false, - "reason": "Tokenizer.json loading behavior and a Kimi-K2.5 codec/regex regression are not the same underlying bug." + "reason": "AutoTokenizer ignoring `tokenizer.json` is different from the Kimi-K2.5 codec/regression report." }, { "left": "issue:44661", "right": "issue:45542", "accept": false, - "reason": "Model-addition logic in tokenizer mappings is unrelated to the tensorboard/TensorFlow backend issue." + "reason": "TOKENIZER_MAPPING_NAMES model-addition failure is unrelated to the missing TensorFlow backend when only tensorboard is installed." }, { "left": "issue:45003", "right": "issue:45561", "accept": false, - "reason": "sys.modules access safety and xdist race conditions are different concurrency problems." + "reason": "Unsafe `sys.modules` access and the xdist captured-info race are different failure mechanisms." }, { "left": "issue:44246", "right": "issue:44496", "accept": false, - "reason": "Import slowness is not the same as unrecognized-model/config.model_type loading failure." + "reason": "Slow import timing is not the same as an unrecognized-model config error." }, { "left": "issue:36246", "right": "issue:42757", "accept": false, - "reason": "Both are import errors, but for different symbols and different dependency modules." + "reason": "Both are import errors, but they concern different modules and different missing symbols." }, { "left": "issue:43531", "right": "issue:45362", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior and Qwen3.5-35B chat crashes are distinct." + "reason": "Qwen3-MoE `sliding_window` behavior is a different issue from Qwen3.5 chat crashes." }, { "left": "issue:36246", "right": "issue:44351", "accept": false, - "reason": "Different missing exports: Qwen2_5_VLImageProcessor versus HybridCache." + "reason": "Qwen2_5_VL image-processor import failure is unrelated to missing `HybridCache` import." }, { "left": "issue:43526", "right": "issue:45003", "accept": false, - "reason": "A BeitImageProcessorFast label-reduction bug is unrelated to modeling_utils sys.modules access." + "reason": "BeitImageProcessorFast label reduction and unsafe `sys.modules` access are unrelated bugs." }, { "left": "issue:43673", "right": "issue:44561", "accept": false, - "reason": "Chunked prefill cache behavior and removal of is_torch_fx_available are separate regressions." + "reason": "Chunked-prefill cache behavior in v5 is a different code path from removal of `is_torch_fx_available` breaking trust-remote-code models." }, { "left": "issue:44336", "right": "issue:44485", "accept": false, - "reason": "ANSI output handling and GLM-5 RoPE implementation are unrelated." + "reason": "Loading-report ANSI codes are unrelated to GLM-5 RoPE implementation." }, { "left": "issue:44162", "right": "issue:45200", "accept": false, - "reason": "ESM2 breakage and Gemma 4 token_type_ids defaults are different model-specific bugs." - }, - { - "left": "issue:44242", - "right": "issue:44857", - "accept": false, - "reason": "Missing MoE load-balancing loss and LwDetrImageLoss AMP crash do not share the same code path." - }, - { - "left": "issue:44295", - "right": "issue:44749", - "accept": false, - "reason": "Position_ids buffer access and slow filtering after a version upgrade are unrelated." - }, - { - "left": "issue:44877", - "right": "issue:45375", - "accept": false, - "reason": "Both are config-shape issues, but for different models and different missing fields." - }, - { - "left": "issue:36246", - "right": "issue:43596", - "accept": false, - "reason": "Importing a missing image processor and a DeepSpeed/BertModel index error are unrelated." - }, - { - "left": "issue:43441", - "right": "issue:43540", - "accept": false, - "reason": "Both are Qwen-related video/FlashAttention reports, but they describe different failures and fixes." - }, - { - "left": "issue:44246", - "right": "issue:44871", - "accept": false, - "reason": "Import timing and Gemma-3 eos_token_id config mismatch are unrelated." + "reason": "ESM2 breakage and Gemma 4 mm token defaults are different model-specific regressions." } ] }, @@ -9876,8 +9701,9 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ + "issue:36246", "issue:41628", "issue:41950", "issue:42886", @@ -9888,26 +9714,27 @@ "issue:43262", "issue:43295", "issue:43408", + "issue:43441", "issue:43475", "issue:43540", - "issue:43646", + "issue:43596", "issue:43653", - "issue:43673", "issue:43901", - "issue:43931", "issue:44060", "issue:44077", "issue:44162", + "issue:44242", "issue:44246", - "issue:44297", + "issue:44295", "issue:44336", "issue:44368", "issue:44466", "issue:44496", - "issue:44623", - "issue:44734", + "issue:44749", "issue:44779", - "issue:44869", + "issue:44857", + "issue:44871", + "issue:44877", "issue:44933", "issue:44977", "issue:44987", @@ -9916,256 +9743,240 @@ "issue:45137", "issue:45200", "issue:45229", - "issue:45278", "issue:45292", "issue:45335", - "issue:45356", + "issue:45375", "issue:45459", "issue:45563", "issue:45584", - "issue:45588", - "issue:45600" + "issue:45588" ], "soft_pairs": [ + "issue:44242|issue:44857", + "issue:44295|issue:44749", + "issue:44246|issue:44871", + "issue:44877|issue:45375", + "issue:36246|issue:43596", "issue:43066|issue:44779", + "issue:43441|issue:43540", "issue:45292|issue:45584", - "issue:44987|issue:45459", "issue:44779|issue:45292", + "issue:44987|issue:45459", "issue:42886|issue:45229", "issue:41628|issue:41950", "issue:44995|issue:45200", "issue:43065|issue:43408", "issue:43901|issue:45003", "issue:43232|issue:44336", - "issue:44060|issue:44077", "issue:43257|issue:45137", "issue:44496|issue:45003", "issue:44995|issue:45588", + "issue:44060|issue:44077", "issue:43295|issue:45292", + "issue:43262|issue:44246", "issue:43653|issue:44162", "issue:43475|issue:43540", - "issue:43262|issue:44246", "issue:44368|issue:45563", "issue:44368|issue:44977", "issue:44466|issue:45335", - "issue:44933|issue:45459", - "issue:43673|issue:44734", - "issue:44869|issue:45356", - "issue:43931|issue:44368", - "issue:45137|issue:45600", - "issue:43232|issue:43673", - "issue:44297|issue:44623", - "issue:43673|issue:45278", - "issue:43646|issue:44162" + "issue:44933|issue:45459" ], - "prepared_review_unit_hash": "8f4d396688ec9f008b76aa64d55e2d63f558e1dafd48353a270859e826fc9a20", + "prepared_review_unit_hash": "716a855b2940d0aa5ee0652ffaf51f7fdca8a503e51f40a0253cb8720ec94aa1", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 47, "item_count": 47, - "soft_pair_count": 30, - "serialized_chars": 36100, - "estimated_input_tokens": 9025, - "estimated_eval_tokens": 18306 + "soft_pair_count": 28, + "serialized_chars": 35650, + "estimated_input_tokens": 8913, + "estimated_eval_tokens": 18082 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This looks like a loose semantic cluster of Transformers v5 regressions and API breakages rather than one tight duplicate set. I don\u2019t see any soft pair that is clearly the same concrete bug, so I reject all soft edges and treat 45278 as the broadest umbrella issue.", - "confidence": 0.72, - "canonical_issue_reason": "issue:45278 is the broadest umbrella report in the set: it describes many import failures after upgrading from 4.57.0 to 5.5.0, matching the cluster\u2019s overall import/regression theme better than the narrower, model-specific reports.", + "summary": "This cluster is broad and mostly heterogeneous: import/load regressions, tokenizer/config bugs, generation issues, and model-specific SAM/Qwen/DeepSpeed problems. I did not find any pair that clearly describes the same underlying bug/change closely enough to merge as duplicates.", + "confidence": 0.91, + "canonical_issue_reason": "If forced to pick one, issue 45003 is the broadest infrastructure-level bug in the set, but the cluster is not a tight duplicate group.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the best global representative because it is the most general, user-facing regression report among mostly narrow tokenizer/model-specific breakages.", + "best_issue_reason": "Issue 45003 is the best global representative because it is a general core-library bug rather than a model-specific symptom, though it still does not unify the cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44242", + "right": "issue:44857", + "accept": false, + "reason": "Different failures in different subsystems: MoE load-balancing loss vs LW-DETR AMP/CUDA crash." + }, + { + "left": "issue:44295", + "right": "issue:44749", + "accept": false, + "reason": "Position_ids buffer access and post-upgrade data slowdown are unrelated." + }, + { + "left": "issue:44246", + "right": "issue:44871", + "accept": false, + "reason": "Import latency bug vs Gemma eos_token_id config mismatch; no shared code path." + }, + { + "left": "issue:44877", + "right": "issue:45375", + "accept": false, + "reason": "Both involve config strictness, but they affect different model configs and different missing fields." + }, + { + "left": "issue:36246", + "right": "issue:43596", + "accept": false, + "reason": "ImportError for Qwen2.5 VL image processor vs DeepSpeed/BertModel index error are unrelated." + }, { "left": "issue:43066", "right": "issue:44779", "accept": false, - "reason": "Both are tokenizer regressions in v5, but one is about decoder-type selection and the other about DeepSeek tokenization correctness; not the same bug." + "reason": "Tokenizer decoder-type warning in v5 vs DeepSeek tokenizer incorrect output; same broad area, different bug." }, { - "left": "issue:45292", - "right": "issue:45584", + "left": "issue:43441", + "right": "issue:43540", "accept": false, - "reason": "Resize-token-embeddings propagation and Whisper empty-transcription failure are different code paths and symptoms." + "reason": "FlashAttention failure for Ministral-3 and video-processing ValueError for Qwen3OmniMoe are distinct." }, { - "left": "issue:44987", - "right": "issue:45459", + "left": "issue:45292", + "right": "issue:45584", "accept": false, - "reason": "One is a model-loading failure for a specific repo; the other is exception handling that masks tokenizer errors. Related area, not same issue." + "reason": "Embedding resize propagation bug vs Whisper empty-transcription generation failure are different code paths." }, { "left": "issue:44779", "right": "issue:45292", "accept": false, - "reason": "DeepSeek tokenization correctness and resize_token_embeddings behavior are unrelated defects." + "reason": "DeepSeek tokenizer regression is not the same as resize_token_embeddings not updating output embeddings." + }, + { + "left": "issue:44987", + "right": "issue:45459", + "accept": false, + "reason": "Model loading failure and protobuf-related tokenizer error masking are unrelated." }, { "left": "issue:42886", "right": "issue:45229", "accept": false, - "reason": "Offline cache loading and multi-GPU CUDA OOM are completely different failures." + "reason": "Offline cache tokenizer load bug vs multi-GPU CUDA OOM are not duplicates." }, { "left": "issue:41628", "right": "issue:41950", "accept": false, - "reason": "Importing AutoImageProcessor and a video-classification pipeline looking for image processors are adjacent, but not the same concrete bug." + "reason": "General AutoImageProcessor import failure vs video-classification pipeline picking image processors; related area, not same bug." }, { "left": "issue:44995", "right": "issue:45200", "accept": false, - "reason": "A stale cache crash on second forward pass is not the same as missing default mm_token_type_ids in Gemma 4." + "reason": "Stale cache crash in GlmMoeDsa vs mm_token_type_ids defaulting issue are unrelated." }, { "left": "issue:43065", "right": "issue:43408", "accept": false, - "reason": "Both involve SAM3, but one is a dummy Conv2d in the decoder and the other is a model-type mismatch warning; different problems." + "reason": "SAM3 pixel decoder dummy layer and sam3_video/sam3_tracker type warning are different defects." }, { "left": "issue:43901", "right": "issue:45003", "accept": false, - "reason": "Docs mismatch for return_all_scores is unrelated to unsafe sys.modules access in modeling_utils." + "reason": "Docs mismatch for return_all_scores is unrelated to sys.modules access in modeling_utils." }, { "left": "issue:43232", "right": "issue:44336", "accept": false, - "reason": "Generation kwargs handling and ANSI escape output in loading_report are unrelated." - }, - { - "left": "issue:44060", - "right": "issue:44077", - "accept": false, - "reason": "Tied-weights warning logic and patchtsmixer post_init policy are different model-configuration issues." + "reason": "Generation kwargs/sync_gpus bug and ANSI color output in loading_report are unrelated." }, { "left": "issue:43257", "right": "issue:45137", "accept": false, - "reason": "DeepSpeed/accelerate conversion failure and ZeRO3 deque underflow are different runtime errors." + "reason": "Qwen3 MoE weight conversion problem and ZeRO3 deque pop error are different DeepSpeed failures." }, { "left": "issue:44496", "right": "issue:45003", "accept": false, - "reason": "Unrecognized model config and sys.modules access are unrelated loading failures." + "reason": "Unrecognized model config and unsafe sys.modules access are separate loading issues." }, { "left": "issue:44995", "right": "issue:45588", "accept": false, - "reason": "Stale indexer cache on second forward pass is not the same as flash-attention crashing on s_aux=None." + "reason": "Different crashes: stale indexer cache vs flash_attention s_aux=None handling." + }, + { + "left": "issue:44060", + "right": "issue:44077", + "accept": false, + "reason": "Tied-weights warning bug and patchtsmixer post_init restriction are unrelated." }, { "left": "issue:43295", "right": "issue:45292", "accept": false, - "reason": "Processor.tokenizer regression and resize_token_embeddings/output_embeddings mismatch are separate API breakages." + "reason": "Processor.tokenizer/image handling regression is not the same as resize_token_embeddings not updating output embeddings." + }, + { + "left": "issue:43262", + "right": "issue:44246", + "accept": false, + "reason": "Audio chat-template sampling-rate default vs import slowness are unrelated." }, { "left": "issue:43653", "right": "issue:44162", "accept": false, - "reason": "BigBirdTokenizer special-token registration and ESM2 breakage do not point to the same defect." + "reason": "BigBirdTokenizer special-token registration bug and ESM2 regression are different model-specific issues." }, { "left": "issue:43475", "right": "issue:43540", "accept": false, - "reason": "Missing fpn_position_embeddings and Qwen3OmniMoe video-input processing failure are unrelated SAM3/video-model issues." - }, - { - "left": "issue:43262", - "right": "issue:44246", - "accept": false, - "reason": "Audio chat-template sampling-rate defaults and slow import performance are unrelated." + "reason": "Sam3VisionEncoderOutput missing field and Qwen3OmniMoe video ValueError are distinct SAM/Qwen bugs." }, { "left": "issue:44368", "right": "issue:45563", "accept": false, - "reason": "A tied-weights warning in Qwen3.5 fine-tuning is not the same as a stale num_return_sequences warning in paged generate()." + "reason": "Word-embedding tie warning and stale num_return_sequences warning are different warning bugs." }, { "left": "issue:44368", "right": "issue:44977", "accept": false, - "reason": "Qwen3.5 flash-attention generation failure and tied-weights warning are different symptoms and likely different fixes." + "reason": "Qwen3.5 tie_word_embeddings warning and DeepSeek tokenizer regression are unrelated." }, { "left": "issue:44466", "right": "issue:45335", "accept": false, - "reason": "Both involve embedding/weight handling, but one is serialization of lm_head.weight and the other is resize_token_embeddings not reaching decoder.embed_tokens; not the same bug." + "reason": "Serialization inconsistency across devices and t5gemma resize propagation bug are separate weight-handling issues." }, { "left": "issue:44933", "right": "issue:45459", "accept": false, - "reason": "A missing import from image_utils and hidden tokenizer errors from protobuf exception handling are unrelated." - }, - { - "left": "issue:43673", - "right": "issue:44734", - "accept": false, - "reason": "Chunked-prefill cache handling and /v1/responses KV-cache indexing are different generation-path bugs." - }, - { - "left": "issue:44869", - "right": "issue:45356", - "accept": false, - "reason": "Whisper timestamp decoding crash and Kimi-K2.5 tokenizer regression are unrelated tokenizer issues." - }, - { - "left": "issue:43931", - "right": "issue:44368", - "accept": false, - "reason": "Qwen3-VL shape mismatch on load and Qwen3.5 tied-weights warning are different problems." - }, - { - "left": "issue:45137", - "right": "issue:45600", - "accept": false, - "reason": "DeepSpeed ZeRO3 deque crash and stale Sam3LiteText config references in auto_mappings.py are unrelated." - }, - { - "left": "issue:43232", - "right": "issue:43673", - "accept": false, - "reason": "Both touch generation internals, but sync_gpus kwargs update and chunked_prefill cache absence are not the same concrete failure." - }, - { - "left": "issue:44297", - "right": "issue:44623", - "accept": false, - "reason": "Tokenizer save_pretrained metadata mismatch and processor.save_pretrained missing files are different serialization bugs." - }, - { - "left": "issue:43673", - "right": "issue:45278", - "accept": false, - "reason": "Cache handling in generation and broad import failures after upgrade are not the same bug." - }, - { - "left": "issue:43646", - "right": "issue:44162", - "accept": false, - "reason": "Custom model initialization breakage in v5 and ESM2 regression are different failure modes, even if both are upgrade-related." + "reason": "Missing import from image_utils and protobuf decode-error masking are unrelated." } ] }, @@ -10184,15 +9995,13 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:28282", "issue:30990", - "issue:35141", - "issue:36010", "issue:41628", "issue:42222", "issue:42371", @@ -10200,55 +10009,65 @@ "issue:42831", "issue:42994", "issue:43232", - "issue:43377", "issue:43475", "issue:43482", - "issue:43504", "issue:43525", - "issue:43526", "issue:43643", + "issue:43646", "issue:43673", "issue:43701", "issue:43704", "issue:43873", + "issue:43931", "issue:44038", - "issue:44164", + "issue:44162", "issue:44188", "issue:44222", - "issue:44242", - "issue:44351", + "issue:44297", "issue:44361", - "issue:44496", + "issue:44368", "issue:44623", "issue:44661", + "issue:44734", "issue:44749", - "issue:44792", + "issue:44869", "issue:44933", "issue:44945", "issue:45081", "issue:45092", "issue:45103", + "issue:45137", "issue:45200", "issue:45230", + "issue:45278", "issue:45310", + "issue:45356", "issue:45362", "issue:45375", "issue:45381", "issue:45397", "issue:45478", - "issue:45561" + "issue:45600" ], "soft_pairs": [ + "issue:43673|issue:44734", + "issue:44869|issue:45356", + "issue:45137|issue:45600", + "issue:43931|issue:44368", + "issue:43232|issue:43673", + "issue:44297|issue:44623", + "issue:43673|issue:45278", + "issue:43646|issue:44162", "issue:44361|issue:44749", "issue:42673|issue:43704", - "issue:44749|issue:45310", "issue:28282|issue:30990", + "issue:44749|issue:45310", "issue:45230|issue:45397", "issue:44038|issue:44623", "issue:42994|issue:43482", "issue:43701|issue:44749", - "issue:42371|issue:45092", "issue:43475|issue:45381", + "issue:42371|issue:45092", "issue:45375|issue:45478", "issue:43475|issue:43643", "issue:41628|issue:44933", @@ -10256,272 +10075,236 @@ "issue:45310|issue:45375", "issue:42994|issue:43525", "issue:42222|issue:45200", - "issue:42831|issue:44222", "issue:43873|issue:44945", "issue:43475|issue:44661", + "issue:42831|issue:44222", "issue:45310|issue:45397", "issue:45362|issue:45375", - "issue:43232|issue:44188", - "issue:44222|issue:45310", - "issue:41628|issue:44351", - "issue:44038|issue:45310", - "issue:42994|issue:44164", - "issue:44496|issue:45561", - "issue:43526|issue:45561", - "issue:43504|issue:45561", - "issue:43232|issue:44792", - "issue:43377|issue:44242", - "issue:43673|issue:44188", - "issue:36010|issue:41628", - "issue:30990|issue:35141" + "issue:43232|issue:44188" ], - "prepared_review_unit_hash": "e4af594eac8bdc983da8d0f80ee481cd570da2e96c0d20d8f6c714f4a0d3f575", + "prepared_review_unit_hash": "9f3295fb9ab485166bb024ca16c141eee772daa4385d74d7c8c13cd9cf0f2c39", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 35, - "serialized_chars": 37859, - "estimated_input_tokens": 9465, - "estimated_eval_tokens": 19186 + "soft_pair_count": 31, + "serialized_chars": 36705, + "estimated_input_tokens": 9177, + "estimated_eval_tokens": 18610 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly heterogeneous and the soft edges are overwhelmingly false positives. The only clear duplicate is the Qwen3ForCausalLM VRAM leak pair (42673/43704), which should be clustered together; the rest share only broad subsystem/version similarity, not the same concrete bug.", - "confidence": 0.83, - "canonical_issue_reason": "issue:42673 is the best canonical issue because it is the earlier, more established report for the exact Qwen3ForCausalLM multi-dataloader VRAM leak, with issue:43704 appearing to be the later duplicate.", + "summary": "This packet is still mostly heterogeneous, with many unrelated model-specific regressions and API breakages. There are at least two clear duplicate-like issue pairs by title/symptom: the confirmed Qwen3ForCausalLM VRAM leak pair (42673/43704) and another identical-title pair (45310/45478) about the Qwen3.5 Moe from_pretrained error, even though only the former was surfaced in soft_pairs. The rest of the soft candidates remain conservative non-matches.", + "confidence": 0.94, + "canonical_issue_reason": "issue:42673 is the clearest canonical report for the Qwen3ForCausalLM VRAM leak: it is earlier, more detailed, and matches issue:43704 exactly on title and symptom.", "canonical_pr_reason": null, - "best_issue_reason": "issue:42673 is the strongest representative of the only clearly duplicated bug in this set; the remaining issues are too diverse to serve as a single canonical for the whole cluster.", + "best_issue_reason": "issue:42673 is the best representative issue because it is the earliest and fuller report in the only confirmed duplicate pair, and it anchors the strongest duplicate signal in the set.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44361", - "right": "issue:44749", + "left": "issue:43673", + "right": "issue:44734", "accept": false, - "reason": "Different failures: MLukeTokenizer task AttributeError vs Chinese report about slow filtering after upgrade." + "reason": "Both are generation/cache-related, but they describe different failures in different code paths: chunked_prefill cache missing vs KV-cache continuation tensor indexing." }, { - "left": "issue:42673", - "right": "issue:43704", - "accept": true, - "reason": "Same exact bug report: Qwen3ForCausalLM VRAM leak in multiple dataloader threads; 43704 is a later duplicate of 42673." + "left": "issue:44869", + "right": "issue:45356", + "accept": false, + "reason": "Both involve tokenizer/decoding regressions, but one is Whisper timestamp decoding and the other is Kimi tokenizer codec handling; not the same bug." }, { - "left": "issue:44749", - "right": "issue:45310", + "left": "issue:45137", + "right": "issue:45600", "accept": false, - "reason": "Unrelated symptoms: data-filtering slowdown vs Qwen3.5 MoE from_pretrained error." + "reason": "DeepSpeed ZeRO3 deque error and Sam3LiteText auto-mapping CI breakage are unrelated." }, { - "left": "issue:28282", - "right": "issue:30990", + "left": "issue:43931", + "right": "issue:44368", "accept": false, - "reason": "Both are loading-related, but one is a PyTorch ImportError and the other is a Sentence Transformers hang; not the same bug." + "reason": "Qwen3-VL weight-shape mismatch and a tie_word_embeddings warning are different model/config issues." }, { - "left": "issue:45230", - "right": "issue:45397", + "left": "issue:43232", + "right": "issue:43673", "accept": false, - "reason": "Too generic on one side and a specific Gemma-4 zero3 from_pretrained issue on the other; no evidence of the same failure." + "reason": "These are separate generation bugs: sync_gpus kwargs handling versus missing GenerationMixin cache during chunked prefill." }, { - "left": "issue:44038", + "left": "issue:44297", "right": "issue:44623", "accept": false, - "reason": "Different concrete problems: quantization/offloading behavior vs missing processor save_pretrained files." + "reason": "Both are save_pretrained problems, but one is tokenizer metadata mismatch and the other is missing processor files; different components and failures." }, { - "left": "issue:42994", - "right": "issue:43482", + "left": "issue:43673", + "right": "issue:45278", "accept": false, - "reason": "Both involve quantized artifacts, but one is save failure and the other is Qwen2.5-GGUF loading under v5; not the same code-path." + "reason": "The v5 import-error report is broad and unrelated to the specific generation cache bug in 43673." }, { - "left": "issue:43701", - "right": "issue:44749", + "left": "issue:43646", + "right": "issue:44162", "accept": false, - "reason": "resume_from_checkpoint key mismatch is unrelated to the filtering slowdown report." + "reason": "Custom model initialization breakage and ESM2-specific breakage are too different to treat as the same underlying bug." }, { - "left": "issue:42371", - "right": "issue:45092", + "left": "issue:44361", + "right": "issue:44749", "accept": false, - "reason": "TF32 settings guidance and old InternVL2 meta-init incompatibility are different issues." + "reason": "MLukeTokenizer AttributeError and a large slowdown after upgrade are unrelated." }, { - "left": "issue:43475", - "right": "issue:45381", - "accept": false, - "reason": "Both are model/video related, but the missing fpn_position_embeddings attribute and wrong vision_position_ids are different bugs." - }, - { - "left": "issue:45375", - "right": "issue:45478", - "accept": false, - "reason": "Same model family, but one is a missing config field and the other is a from_pretrained failure; too little evidence they are the same defect." + "left": "issue:42673", + "right": "issue:43704", + "accept": true, + "reason": "Same title, same model, same symptom: VRAM leak when Qwen3ForCausalLM is used in multiple dataloader threads." }, { - "left": "issue:43475", - "right": "issue:43643", + "left": "issue:28282", + "right": "issue:30990", "accept": false, - "reason": "SAM 3 video attribute error is unrelated to AutoConfig trust_remote_code missing-fields behavior." + "reason": "PyTorch missing ImportError and Sentence Transformers hanging on load are not the same underlying issue." }, { - "left": "issue:41628", - "right": "issue:44933", + "left": "issue:44749", + "right": "issue:45310", "accept": false, - "reason": "Both are import/API issues, but AutoImageProcessor missing from transformers and a non-existent image_utils import are not the same bug." + "reason": "Performance regression in data filtering and Qwen3.5 MoE from_pretrained failure are different bugs." }, { - "left": "issue:45081", - "right": "issue:45103", + "left": "issue:45230", + "right": "issue:45397", "accept": false, - "reason": "Tokenizer patch crash and auto_docstring annotation crash are unrelated implementation problems." + "reason": "Generic bug report and Gemma-4 Zero3 from_pretrained failure are not the same issue." }, { - "left": "issue:45310", - "right": "issue:45375", + "left": "issue:44038", + "right": "issue:44623", "accept": false, - "reason": "Both touch Qwen3.5 MoE, but one is a generic from_pretrained error while the other is a specific missing config field in vision config." + "reason": "Qwen3-VL-Moe v5 bug and missing processor.save_pretrained files are unrelated." }, { "left": "issue:42994", - "right": "issue:43525", - "accept": false, - "reason": "Quantized model saving failure and Llama4Config pad_token_id missing are different configuration/loading bugs." - }, - { - "left": "issue:42222", - "right": "issue:45200", - "accept": false, - "reason": "VitPose model breakage and Gemma-4 mm_token_type_ids defaulting are unrelated model-specific issues." - }, - { - "left": "issue:42831", - "right": "issue:44222", + "right": "issue:43482", "accept": false, - "reason": "Both mention FP8, but accuracy degradation and save_pretrained failure are not the same underlying bug." + "reason": "Quantized model saving failure and Qwen2.5-GGUF loading failure are different operations and code paths." }, { - "left": "issue:43873", - "right": "issue:44945", + "left": "issue:43701", + "right": "issue:44749", "accept": false, - "reason": "Quantization offloading behavior and pipeline-parallel output correctness are different runtime issues." + "reason": "Checkpoint resume key mismatch is unrelated to the reported training slowdown." }, { "left": "issue:43475", - "right": "issue:44661", - "accept": false, - "reason": "SAM 3 video loading and tokenizer-mapping new-model registration are unrelated." - }, - { - "left": "issue:45310", - "right": "issue:45397", + "right": "issue:45381", "accept": false, - "reason": "Different model families and failures: Qwen3.5 MoE from_pretrained vs Gemma-4 zero3 from_pretrained." + "reason": "SAM 3 Video missing attribute and qwen2.5-vl video position-id bug are different model-specific regressions." }, { - "left": "issue:45362", - "right": "issue:45375", + "left": "issue:42371", + "right": "issue:45092", "accept": false, - "reason": "Qwen3.5-35B chat crash and missing deepstack_visual_indexes are different symptoms and likely different code paths." + "reason": "TF32 API guidance and InternVL2 meta-initialization incompatibility are unrelated." }, { - "left": "issue:43232", - "right": "issue:44188", + "left": "issue:45375", + "right": "issue:45478", "accept": false, - "reason": "Generation kwargs sync_gpus issue and torch.compile attention-kernel divergence are not the same bug." + "reason": "Missing deepstack_visual_indexes field in config and Qwen3.5 Moe from_pretrained error are different problems." }, { - "left": "issue:44222", - "right": "issue:45310", + "left": "issue:43475", + "right": "issue:43643", "accept": false, - "reason": "FP8 save_pretrained failure and Qwen3.5 MoE from_pretrained error are only loosely related by model family." + "reason": "SAM 3 Video output attribute error and AutoConfig missing fields with trust_remote_code are not the same bug." }, { "left": "issue:41628", - "right": "issue:44351", + "right": "issue:44933", "accept": false, - "reason": "Both are import errors, but missing AutoImageProcessor and missing HybridCache are distinct symbols and likely distinct fixes." + "reason": "These are both import-related, but they concern different symbols and likely different import paths; not enough to unify." }, { - "left": "issue:44038", - "right": "issue:45310", + "left": "issue:45081", + "right": "issue:45103", "accept": false, - "reason": "Qwen3-VL-Moe incompatibility and Qwen3.5 MoE from_pretrained error are related only at a broad model/version level." + "reason": "Tokenizer regex patch crash and auto_docstring future-annotations crash are unrelated." }, { - "left": "issue:42994", - "right": "issue:44164", + "left": "issue:45310", + "right": "issue:45375", "accept": false, - "reason": "Quantized model saving failure and extra_state save/from_pretrained handling are different serialization bugs." + "reason": "Both involve Qwen-related v5 regressions, but one is a from_pretrained error and the other is a config-field drop; different underlying failures." }, { - "left": "issue:44496", - "right": "issue:45561", + "left": "issue:42994", + "right": "issue:43525", "accept": false, - "reason": "Unrecognized model/config issue and pytest-xdist file race are unrelated." + "reason": "Quantized model saving failure and Llama4Config missing pad_token_id are different issues." }, { - "left": "issue:43526", - "right": "issue:45561", + "left": "issue:42222", + "right": "issue:45200", "accept": false, - "reason": "BeitImageProcessorFast reduce_labels bug is unrelated to the captured_info.txt race." + "reason": "VitPose breakage and Gemma-4 mm_token_type_ids defaulting are unrelated model-specific bugs." }, { - "left": "issue:43504", - "right": "issue:45561", + "left": "issue:43873", + "right": "issue:44945", "accept": false, - "reason": "Beit pretrained legacy-field loading and testing-utils race are unrelated." + "reason": "Quantization offloading behavior and pipeline parallelism output correctness are different problems." }, { - "left": "issue:43232", - "right": "issue:44792", + "left": "issue:43475", + "right": "issue:44661", "accept": false, - "reason": "Generation sync_gpus bug and janus image-generation test failure are not the same underlying issue." + "reason": "SAM 3 video encoder attribute error and add-new-model-like tokenizer mapping failure are unrelated." }, { - "left": "issue:43377", - "right": "issue:44242", + "left": "issue:42831", + "right": "issue:44222", "accept": false, - "reason": "MIMI padding-mask inconsistency and MoE load-balancing-loss omission are different model behaviors." + "reason": "FineGrainedFP8 accuracy regression and FP8 save_pretrained failure are distinct FP8-related issues, not the same bug." }, { - "left": "issue:43673", - "right": "issue:44188", + "left": "issue:45310", + "right": "issue:45397", "accept": false, - "reason": "Missing GenerationMixin cache in v5 chunked_prefill and attention-kernel divergence under torch.compile are separate generation regressions." + "reason": "Qwen3.5 Moe from_pretrained failure and Gemma-4 Zero3 from_pretrained failure are different model paths." }, { - "left": "issue:36010", - "right": "issue:41628", + "left": "issue:45362", + "right": "issue:45375", "accept": false, - "reason": "Both are import errors, but they involve different missing exports and should not be merged as one bug." + "reason": "Qwen3.5-35B chat crash and missing deepstack_visual_indexes config field are unrelated." }, { - "left": "issue:30990", - "right": "issue:35141", + "left": "issue:43232", + "right": "issue:44188", "accept": false, - "reason": "Sentence Transformers loading hang and embedding resize reinitialization are unrelated." + "reason": "Generation kwargs handling after sync_gpus and attention-kernel divergence under torch.compile are different code paths and symptoms." } ] }, "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative. The only clearly supported duplicate is issue:42673 / issue:43704, which is correctly identified as the canonical pair, and the other soft-edge rejections avoid overclaiming equivalence from broad subsystem similarity. No mergeability or evidence-overstatement problems stood out." + "accept": false, + "feedback": "The summary overstates uniqueness. Besides the accepted Qwen3ForCausalLM duplicate pair (42673/43704), the packet also contains another identical-title duplicate candidate: issue:45310 and issue:45478 both read \"[BUG] transformers>=5.4.0, Qwen3.5 Moe from_pretrained error\". Even if that pair was not surfaced in soft_pairs, the writeup should not claim there is only one duplicate-like pair in the set. The rest of the conservative pairwise reasoning is mostly grounded, but this omission makes the overall summary too strong." }, "evaluator_used": true, - "retried": false, + "retried": true, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -10534,335 +10317,295 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ - "issue:22355", - "issue:28282", "issue:30333", + "issue:30990", "issue:33290", - "issue:36331", + "issue:35141", + "issue:36010", "issue:41628", "issue:42175", - "issue:42757", - "issue:42831", "issue:42898", + "issue:42994", + "issue:43232", "issue:43278", - "issue:43295", + "issue:43377", "issue:43479", - "issue:43644", + "issue:43504", + "issue:43526", + "issue:43673", "issue:43723", "issue:43784", "issue:43824", "issue:43874", "issue:43976", + "issue:44038", "issue:44060", "issue:44079", + "issue:44164", "issue:44188", - "issue:44206", "issue:44222", - "issue:44263", - "issue:44297", - "issue:44360", + "issue:44242", + "issue:44351", "issue:44373", - "issue:44442", "issue:44448", - "issue:44483", - "issue:44484", + "issue:44496", "issue:44568", "issue:44623", "issue:44734", "issue:44779", + "issue:44792", "issue:44869", "issue:44933", "issue:44964", - "issue:44977", "issue:45092", "issue:45103", "issue:45125", "issue:45137", "issue:45310", "issue:45356", - "issue:45406", - "issue:45459" + "issue:45459", + "issue:45561" ], "soft_pairs": [ + "issue:41628|issue:44351", + "issue:44222|issue:45310", + "issue:42994|issue:44164", + "issue:44038|issue:45310", + "issue:44496|issue:45561", + "issue:43526|issue:45561", + "issue:43232|issue:44792", + "issue:43504|issue:45561", + "issue:43377|issue:44242", + "issue:36010|issue:41628", + "issue:43673|issue:44188", + "issue:30990|issue:35141", "issue:42898|issue:44568", - "issue:43479|issue:44869", "issue:43479|issue:44079", + "issue:43479|issue:44869", "issue:43976|issue:44933", "issue:42175|issue:44933", - "issue:43784|issue:43824", "issue:44964|issue:45137", + "issue:43784|issue:43824", "issue:44623|issue:45310", "issue:44188|issue:44373", "issue:44060|issue:45125", + "issue:43723|issue:44568", "issue:42898|issue:45356", "issue:44734|issue:45103", - "issue:43723|issue:44568", "issue:43278|issue:45137", "issue:42898|issue:44779", - "issue:43874|issue:45092", "issue:30333|issue:33290", + "issue:43874|issue:45092", "issue:42898|issue:44448", - "issue:41628|issue:45459", - "issue:44222|issue:44297", - "issue:42898|issue:43295", - "issue:43479|issue:43644", - "issue:44442|issue:45459", - "issue:44222|issue:44623", - "issue:42831|issue:44623", - "issue:44206|issue:45103", - "issue:44297|issue:45310", - "issue:41628|issue:42757", - "issue:22355|issue:28282", - "issue:44222|issue:44484", - "issue:44483|issue:45406", - "issue:44263|issue:44360", - "issue:43723|issue:44977", - "issue:44263|issue:45092", - "issue:30333|issue:36331" + "issue:41628|issue:45459" ], - "prepared_review_unit_hash": "5f3190113d228a21a391c53041fb545c5449d3cfef7d48f06ddb05b6849fae5f", + "prepared_review_unit_hash": "7235562a98130ca40aa000b24342bf404212115f1bf79b220407fe280ab08e12", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 35, - "serialized_chars": 38156, - "estimated_input_tokens": 9539, - "estimated_eval_tokens": 19334 + "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 cluster is heterogeneous: most items are unrelated transformers regressions across tokenization, multimodal processors, serving, training, packaging, and DeepSpeed. No soft pair looks like the same underlying bug; the closest shared theme is v5 tokenizer/processor behavior changes.", + "summary": "This is a loose collection of mostly unrelated Transformers v5-era bug reports (imports, tokenizer regressions, multimodal configs, save/load, generation, and backend issues). None of the soft pairs looks like the same concrete bug/change, so all are rejected.", "confidence": 0.89, - "canonical_issue_reason": "Issue 42898 is the best anchor for the cluster because it is the broadest v5 tokenizer-regression report and is closest to the small group of tokenizer/processor-related items; the other issues mostly describe distinct bugs in different code paths.", + "canonical_issue_reason": "issue:42898 is the broadest, most generic user-facing regression in the set and the best placeholder representative for this mostly v5-regression cluster, though it does not duplicate the others.", "canonical_pr_reason": null, - "best_issue_reason": "42898 is the most representative user-facing regression in the set and the clearest generalization point for the tokenizer-behavior subset, though the cluster as a whole is not a duplicate group.", + "best_issue_reason": "issue:42898 is the most reusable canonical issue because it describes a common v5 behavior break rather than a narrow model-specific or infrastructure-specific failure.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:42898", - "right": "issue:44568", - "accept": false, - "reason": "Both are tokenizer regressions, but they affect different behaviors: clean_up_tokenization_spaces vs add_special_tokens/BOS-EOS handling." - }, - { - "left": "issue:43479", - "right": "issue:44869", - "accept": false, - "reason": "Unrelated subsystems: Phi4MultimodalConfig default initialization vs Whisper timestamp decoding crash." - }, - { - "left": "issue:43479", - "right": "issue:44079", - "accept": false, - "reason": "Different bug classes: multimodal config defaults vs ModelOutput key assignment logic." - }, - { - "left": "issue:43976", - "right": "issue:44933", - "accept": false, - "reason": "Python version compatibility in Transformers 5.1.0 is unrelated to a missing image_utils import." - }, - { - "left": "issue:42175", - "right": "issue:44933", + "left": "issue:41628", + "right": "issue:44351", "accept": false, - "reason": "Packaging/backend extras mismatch is unrelated to an image_utils import failure." + "reason": "Both are import errors, but for different symbols and different code paths; this is shared symptom, not the same bug." }, { - "left": "issue:43784", - "right": "issue:43824", + "left": "issue:44222", + "right": "issue:45310", "accept": false, - "reason": "Different import failures in different libraries/models: sentence-transformers nn import vs Qwen2.5-VL class export." + "reason": "Both involve Qwen3.5/MoE, but one is FP8 save_pretrained and the other is a from_pretrained load failure; not the same fix." }, { - "left": "issue:44964", - "right": "issue:45137", + "left": "issue:42994", + "right": "issue:44164", "accept": false, - "reason": "One is a model-loading regression; the other is a DeepSpeed ZeRO3 deque error." + "reason": "Both touch persistence, but quantized model saving and extra_state handling are distinct serialization bugs." }, { - "left": "issue:44623", + "left": "issue:44038", "right": "issue:45310", "accept": false, - "reason": "processor.save_pretrained missing files and Qwen3.5 MoE from_pretrained failure are different code paths." + "reason": "Both mention Qwen VL/MoE, but they are different model/version failures and not the same code-path problem." }, { - "left": "issue:44188", - "right": "issue:44373", - "accept": false, - "reason": "torch.compile attention branching is unrelated to a docstring error." - }, - { - "left": "issue:44060", - "right": "issue:45125", + "left": "issue:44496", + "right": "issue:45561", "accept": false, - "reason": "Tied-weights warning behavior and missing _tp_plan are different model-configuration issues." + "reason": "Completely unrelated: model config loading versus a pytest-xdist race in testing utils." }, { - "left": "issue:42898", - "right": "issue:45356", + "left": "issue:43526", + "right": "issue:45561", "accept": false, - "reason": "Both are tokenizer-related regressions, but one is about whitespace cleanup and the other about codec handling/fix_mistral_regex warnings." + "reason": "Different subsystems and failure modes; image processor label reduction is unrelated to the test file race." }, { - "left": "issue:44734", - "right": "issue:45103", + "left": "issue:43232", + "right": "issue:44792", "accept": false, - "reason": "Serving KV-cache tensor indexing and auto_docstring annotation handling are unrelated." + "reason": "One is a generation kwargs bug after sync_gpus; the other is a Janus image generation test failure. Too different." }, { - "left": "issue:43723", - "right": "issue:44568", + "left": "issue:43504", + "right": "issue:45561", "accept": false, - "reason": "AutoTokenizer loading failure and add_special_tokens behavior are distinct tokenizer issues." + "reason": "Semantic-segmentation preset loading and a testing-utils race are unrelated." }, { - "left": "issue:43278", - "right": "issue:45137", + "left": "issue:43377", + "right": "issue:44242", "accept": false, - "reason": "BF16-to-FP32 dtype drift in evaluation is unrelated to a ZeRO3 deque underflow." + "reason": "Different bugs: padding mask batched-vs-single mismatch versus MoE load-balancing loss gating." }, { - "left": "issue:42898", - "right": "issue:44779", + "left": "issue:36010", + "right": "issue:41628", "accept": false, - "reason": "Both concern tokenization, but they describe different regressions and code paths." + "reason": "Both are import failures, but they are different missing exports with no shared concrete fix indicated." }, { - "left": "issue:43874", - "right": "issue:45092", + "left": "issue:43673", + "right": "issue:44188", "accept": false, - "reason": "Missing image processor method and remote-code/meta-init incompatibility are not the same bug." + "reason": "Generation cache support and attention-kernel divergence under torch.compile are separate problems." }, { - "left": "issue:30333", - "right": "issue:33290", + "left": "issue:30990", + "right": "issue:35141", "accept": false, - "reason": "MLflow reporting on training failure and Adafactor+DeepSpeed OOM are unrelated training problems." + "reason": "Stuck loading sentence-transformers is unrelated to token embedding reinitialization during resize." }, { "left": "issue:42898", - "right": "issue:44448", + "right": "issue:44568", "accept": false, - "reason": "Tokenizer whitespace cleanup regression is separate from a model-output difference between v4 and v5." + "reason": "Both are tokenizer regressions in v5, but they affect different behaviors and different tokenizers." }, { - "left": "issue:41628", - "right": "issue:45459", + "left": "issue:43479", + "right": "issue:44079", "accept": false, - "reason": "AutoImageProcessor import breakage and protobuf decode-error masking are different import/error-handling issues." + "reason": "Both involve None-handling, but in unrelated classes and code paths; not mergeable as one bug." }, { - "left": "issue:44222", - "right": "issue:44297", + "left": "issue:43479", + "right": "issue:44869", "accept": false, - "reason": "FP8 MoE save_pretrained behavior and tokenizer_class mismatch on save_pretrained are different failures." + "reason": "Multimodal config defaults and Whisper timestamp decoding are unrelated." }, { - "left": "issue:42898", - "right": "issue:43295", + "left": "issue:43976", + "right": "issue:44933", "accept": false, - "reason": "Tokenizer cleanup behavior change is unrelated to processor.tokenizer/image-to-tokenizer regression." + "reason": "Python-version compatibility and a missing import are unrelated issues." }, { - "left": "issue:43479", - "right": "issue:43644", + "left": "issue:42175", + "right": "issue:44933", "accept": false, - "reason": "Default config initialization and non-persistent buffer filling are unrelated model-state bugs." + "reason": "Backend dependency packaging and image_utils import exposure are unrelated." }, { - "left": "issue:44442", - "right": "issue:45459", + "left": "issue:44964", + "right": "issue:45137", "accept": false, - "reason": "Tokenizer loading failure for FastSpeech2Conformer and protobuf error masking are not the same issue." + "reason": "Model loading failure and DeepSpeed ZeRO3 deque handling are unrelated." }, { - "left": "issue:44222", - "right": "issue:44623", + "left": "issue:43784", + "right": "issue:43824", "accept": false, - "reason": "Both mention save_pretrained, but one is FP8 MoE-specific and the other is missing processor files." + "reason": "Different import errors affecting different APIs/models; no same underlying bug." }, { - "left": "issue:42831", - "right": "issue:44623", + "left": "issue:44623", + "right": "issue:45310", "accept": false, - "reason": "FP8 accuracy degradation and missing processor save files are different problems." + "reason": "Processor save_pretrained missing files is a different path from Qwen3.5 MoE from_pretrained loading." }, { - "left": "issue:44206", - "right": "issue:45103", + "left": "issue:44188", + "right": "issue:44373", "accept": false, - "reason": "Feature extractor center-arg crash and auto_docstring annotation crash are unrelated." + "reason": "Generation runtime behavior and a docstring typo are not the same bug." }, { - "left": "issue:44297", - "right": "issue:45310", + "left": "issue:44060", + "right": "issue:45125", "accept": false, - "reason": "Tokenizer config mismatch on save and Qwen3.5 MoE load failure are different issues." + "reason": "Both are Qwen3.5 MoE internals, but tied-weights warning and tensor-parallel plan support are different issues." }, { - "left": "issue:41628", - "right": "issue:42757", + "left": "issue:43723", + "right": "issue:44568", "accept": false, - "reason": "Missing AutoImageProcessor export and missing is_offline_mode export are separate import-regression bugs." + "reason": "Tokenizer loading in v5 and BOS/EOS add_special_tokens behavior are different regressions." }, { - "left": "issue:22355", - "right": "issue:28282", + "left": "issue:42898", + "right": "issue:45356", "accept": false, - "reason": "Missing transformers.onnx module and missing PyTorch for AutoModel are unrelated import/dependency issues." + "reason": "Both are tokenizer-related regressions, but the specific failure modes and affected code paths differ." }, { - "left": "issue:44222", - "right": "issue:44484", + "left": "issue:44734", + "right": "issue:45103", "accept": false, - "reason": "FP8 MoE save_pretrained bug is unrelated to the max_shard_size default question." + "reason": "Serving KV-cache indexing and auto-docstring annotation handling are unrelated." }, { - "left": "issue:44483", - "right": "issue:45406", + "left": "issue:43278", + "right": "issue:45137", "accept": false, - "reason": "v1/chat/completions request handling and Gemma4Processor _tokenizer missing attribute are different server/processor failures." + "reason": "Embedding dtype drift in evaluate and a ZeRO3 deque IndexError are unrelated." }, { - "left": "issue:44263", - "right": "issue:44360", + "left": "issue:42898", + "right": "issue:44779", "accept": false, - "reason": "torch.split return semantics and missing ReLU in the DSA indexer are not the same code-path problem." + "reason": "Both are tokenizer regressions in v5, but they are model-specific and not the same concrete bug." }, { - "left": "issue:43723", - "right": "issue:44977", + "left": "issue:30333", + "right": "issue:33290", "accept": false, - "reason": "AutoTokenizer loading regression and Qwen3.5 flash-attention generation issue are unrelated." + "reason": "MLflow reporting on failed jobs and DeepSpeed OOM are unrelated." }, { - "left": "issue:44263", + "left": "issue:43874", "right": "issue:45092", "accept": false, - "reason": "torch.split return values in GlmMoeDsaIndexer and remote-code/meta-init incompatibility are different bugs." - }, - { - "left": "issue:30333", - "right": "issue:36331", - "accept": false, - "reason": "MLflow reporting on failed training jobs and CustomTrainer.compute_loss signature mismatch are unrelated training issues." + "reason": "Different multimodal issues: a missing image-processor method versus legacy remote-code checkpoint meta-init incompatibility." } ] }, @@ -10881,72 +10624,87 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ + "issue:22355", "issue:28282", "issue:30333", "issue:30990", - "issue:33357", "issue:34689", "issue:35141", + "issue:36331", "issue:38175", "issue:41628", - "issue:42371", "issue:42757", "issue:42831", "issue:42886", - "issue:42907", + "issue:42898", "issue:42994", - "issue:43066", - "issue:43122", - "issue:43232", + "issue:43295", "issue:43479", "issue:43576", + "issue:43644", "issue:43723", "issue:43784", "issue:43824", - "issue:43976", "issue:44038", - "issue:44117", + "issue:44206", + "issue:44222", "issue:44261", "issue:44263", "issue:44295", "issue:44297", + "issue:44360", "issue:44373", "issue:44442", + "issue:44483", + "issue:44484", "issue:44485", "issue:44514", - "issue:44521", "issue:44623", - "issue:44704", - "issue:44743", "issue:44871", "issue:44913", - "issue:44945", + "issue:44977", "issue:44991", "issue:45092", "issue:45103", "issue:45278", - "issue:45290", "issue:45310", "issue:45357", - "issue:45593" + "issue:45406", + "issue:45459" ], "soft_pairs": [ + "issue:44222|issue:44297", + "issue:42898|issue:43295", + "issue:43479|issue:43644", + "issue:44442|issue:45459", + "issue:44222|issue:44623", + "issue:42831|issue:44623", + "issue:44206|issue:45103", + "issue:41628|issue:42757", + "issue:44297|issue:45310", + "issue:22355|issue:28282", + "issue:44222|issue:44484", + "issue:44483|issue:45406", + "issue:43723|issue:44977", + "issue:44263|issue:44360", + "issue:30333|issue:36331", + "issue:44263|issue:45092", "issue:30333|issue:34689", - "issue:44295|issue:44623", "issue:30333|issue:35141", "issue:28282|issue:30333", + "issue:44295|issue:44623", "issue:44514|issue:45103", "issue:43479|issue:44913", - "issue:44261|issue:45092", "issue:43723|issue:44871", - "issue:44373|issue:44485", + "issue:44261|issue:45092", "issue:43723|issue:44991", "issue:43723|issue:44442", + "issue:44373|issue:44485", "issue:45092|issue:45357", "issue:30990|issue:38175", "issue:42886|issue:42994", @@ -10954,241 +10712,240 @@ "issue:41628|issue:43824", "issue:42831|issue:44038", "issue:43576|issue:43784", - "issue:42757|issue:45278", - "issue:43122|issue:44521", - "issue:44263|issue:44373", - "issue:43232|issue:45593", - "issue:42886|issue:43066", - "issue:44117|issue:44704", - "issue:43122|issue:44514", - "issue:30990|issue:33357", - "issue:42371|issue:44263", - "issue:44295|issue:44297", - "issue:44704|issue:45290", - "issue:42907|issue:44945", - "issue:43976|issue:44945", - "issue:43232|issue:44743" + "issue:42757|issue:45278" ], - "prepared_review_unit_hash": "a6e13b1bae1e6f3f45e24a75cb58a3dfc52de0dd70e527d9855244c6fd8e29fa", + "prepared_review_unit_hash": "46c1584c60316f39b14eaebc1ef462ba6065f7a143c54d82795402c5bcf3cbff", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 32, - "serialized_chars": 37002, - "estimated_input_tokens": 9251, - "estimated_eval_tokens": 18758 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 35, + "serialized_chars": 37352, + "estimated_input_tokens": 9338, + "estimated_eval_tokens": 18932 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is only loosely related: many items are v5 import/tokenizer/loading regressions, but they describe different code paths and failure modes. I do not see any true duplicates among the soft pairs.", - "confidence": 0.88, - "canonical_issue_reason": "issue:43723 is the best representative because it is a broad, core API regression around tokenizer loading in v5 and overlaps with several nearby tokenizer-related reports without being overly narrow.", + "summary": "The set is mostly heterogeneous. Most soft pairs share a subsystem or symptom class, but not the same concrete bug, so they should not be merged as duplicates. The broadest issue is the v5 import-regression report, but it still doesn\u2019t cleanly cover the rest.", + "confidence": 0.43, + "canonical_issue_reason": "issue:45278 is the broadest umbrella here: it describes many import errors after upgrading to v5.5.0, which makes it the best candidate to subsume related import/load regressions.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43723 is the most central user-facing failure in the cluster: `AutoTokenizer.from_pretrained` loading breaks, which is a high-impact, broadly applicable regression theme.", + "best_issue_reason": "It is the most representative high-level issue in the cluster, centered on the recurring post-v5 import breakage theme rather than a narrow model-specific symptom.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:30333", - "right": "issue:34689", + "left": "issue:44222", + "right": "issue:44297", "accept": false, - "reason": "Different subsystems and failures: MLflow job reporting vs model loading for Llama vision." + "reason": "Both touch save_pretrained/tokenizer persistence, but one is about FP8 Moe model saving and the other about tokenizer_class metadata; different bugs." }, { - "left": "issue:44295", - "right": "issue:44623", + "left": "issue:42898", + "right": "issue:43295", "accept": false, - "reason": "Position_ids buffer/read issue is unrelated to processor.save_pretrained missing files." + "reason": "One is about clean_up_tokenization_spaces behavior, the other about processor.tokenizer access and image passing; unrelated regressions." }, { - "left": "issue:30333", - "right": "issue:35141", + "left": "issue:43479", + "right": "issue:43644", "accept": false, - "reason": "Training-job/MLflow reporting is unrelated to embedding resize/post_init reinitialization." + "reason": "Different failure modes: default multimodal config initialization vs non-persistent buffers being filled with junk." }, { - "left": "issue:28282", - "right": "issue:30333", + "left": "issue:44442", + "right": "issue:45459", "accept": false, - "reason": "ImportError for missing PyTorch and MLflow reporting are unrelated problems." + "reason": "Tokenizer load failure for a specific tokenizer is not the same as protobuf-related exception masking." }, { - "left": "issue:44514", + "left": "issue:44222", + "right": "issue:44623", + "accept": false, + "reason": "save_pretrained is shared broadly, but these are different artifacts and bugs: FP8 Moe saving vs missing processor files." + }, + { + "left": "issue:42831", + "right": "issue:44623", + "accept": false, + "reason": "An FP8 accuracy issue is not the same as processor.save_pretrained missing files." + }, + { + "left": "issue:44206", "right": "issue:45103", "accept": false, - "reason": "Both involve chat templates/processing, but one is a crash on batched input and the other is an auto-docstring annotation bug." + "reason": "One is a feature-extractor argument regression; the other is an auto-docstring AttributeError from future annotations." }, { - "left": "issue:43479", - "right": "issue:44913", + "left": "issue:41628", + "right": "issue:42757", "accept": false, - "reason": "Different configuration bugs: multimodal config defaults vs GPTNeoX rotary_pct persistence." + "reason": "Both are import errors, but for different missing symbols from different packages and likely different causes." }, { - "left": "issue:44261", - "right": "issue:45092", + "left": "issue:44297", + "right": "issue:45310", "accept": false, - "reason": "Precision error in MLA q_a_layernorm is unrelated to remote-code checkpoint/meta-init incompatibility." + "reason": "Tokenizer metadata mismatch is unrelated to the Qwen3.5 MoE from_pretrained error." }, { - "left": "issue:43723", - "right": "issue:44871", + "left": "issue:22355", + "right": "issue:28282", "accept": false, - "reason": "Tokenizer loading failure and Gemma-3 eos_token_id mismatch are different issues." + "reason": "Both are import problems, but one is missing transformers.onnx and the other is a missing PyTorch dependency; not the same bug." }, { - "left": "issue:44373", - "right": "issue:44485", + "left": "issue:44222", + "right": "issue:44484", "accept": false, - "reason": "Wrong docstring and GLM-5 RoPE implementation are unrelated." + "reason": "save_pretrained shard-size behavior is unrelated to FP8 Moe model saving failure." }, { - "left": "issue:43723", - "right": "issue:44991", + "left": "issue:44483", + "right": "issue:45406", "accept": false, - "reason": "Both are tokenizer load failures, but they affect different models and likely different underlying causes." + "reason": "An API request rejection and a Gemma4Processor _tokenizer AttributeError are different code paths." }, { "left": "issue:43723", - "right": "issue:44442", + "right": "issue:44977", "accept": false, - "reason": "General tokenizer loading issue and FastSpeech2ConformerTokenizer-specific failure are not the same concrete bug." + "reason": "Both involve loading/generation, but one is generic tokenizer loading and the other is Qwen3.5 flash-attention generation." }, { - "left": "issue:45092", - "right": "issue:45357", + "left": "issue:44263", + "right": "issue:44360", "accept": false, - "reason": "Meta-initialization incompatibility for old InternVL2 and incorrect visual encoder keys in save_pretrained are different paths." + "reason": "Both concern the DSA indexer, but one is about torch.split outputs and the other about a missing ReLU; different defects." }, { - "left": "issue:30990", - "right": "issue:38175", + "left": "issue:30333", + "right": "issue:36331", "accept": false, - "reason": "Sentence Transformers loading stall and zero probabilities in SIGLIP2 are unrelated symptoms." + "reason": "MLFlow job status reporting and CustomTrainer compute_loss signature handling are unrelated." }, { - "left": "issue:42886", - "right": "issue:42994", + "left": "issue:44263", + "right": "issue:45092", "accept": false, - "reason": "Offline tokenizer cache loading and quantized model saving failure are different code paths." + "reason": "Different models and failures: DSA indexer split behavior vs remote-code checkpoint incompatibility with meta init." }, { - "left": "issue:42831", - "right": "issue:45310", + "left": "issue:30333", + "right": "issue:34689", "accept": false, - "reason": "FineGrainedFP8 accuracy issue is not the same as Qwen3.5 MoE from_pretrained loading error." + "reason": "Training-job MLFlow reporting is unrelated to Llama 3.2 Vision model-loading regression." }, { - "left": "issue:41628", - "right": "issue:43824", + "left": "issue:30333", + "right": "issue:35141", "accept": false, - "reason": "Cannot import AutoImageProcessor and cannot import Qwen2_5_VLForConditionalGeneration are separate missing-symbol issues." + "reason": "Job reporting and embedding reinitialization after resize are unrelated." }, { - "left": "issue:42831", - "right": "issue:44038", + "left": "issue:28282", + "right": "issue:30333", "accept": false, - "reason": "Accuracy regression in FP8 is unrelated to Qwen3-VL-Moe model-specific bug." + "reason": "A missing PyTorch dependency import error is unrelated to MLFlow reporting on failed training jobs." }, { - "left": "issue:43576", - "right": "issue:43784", + "left": "issue:44295", + "right": "issue:44623", "accept": false, - "reason": "Broken `transformers env` command and sentence-transformers import NameError are different failures." + "reason": "Reading position_ids after buffer registration is not the same as missing files in processor.save_pretrained." }, { - "left": "issue:42757", - "right": "issue:45278", + "left": "issue:44514", + "right": "issue:45103", "accept": false, - "reason": "One is a specific missing hub symbol, the other is a broad report of many import errors; not the same underlying bug." + "reason": "A batched apply_chat_template crash is unrelated to the auto_docstring AttributeError." }, { - "left": "issue:43122", - "right": "issue:44521", + "left": "issue:43479", + "right": "issue:44913", "accept": false, - "reason": "Tokenization output changed across versions and assistant_masks all-zero for multimodal inputs are distinct bugs." + "reason": "Default multimodal config initialization is unrelated to GPTNeoXConfig rotary_pct reload behavior." }, { - "left": "issue:44263", - "right": "issue:44373", + "left": "issue:43723", + "right": "issue:44871", "accept": false, - "reason": "torch.split return-value issue is unrelated to a wrong docstring." + "reason": "Generic tokenizer loading failure and Gemma-3 eos_token_id inconsistency are different issues." }, { - "left": "issue:43232", - "right": "issue:45593", + "left": "issue:43723", + "right": "issue:44991", "accept": false, - "reason": "Generation kwargs update after sync_gpus and D-FINE auxiliary-loss behavior are unrelated." + "reason": "Both are tokenizer-related regressions, but they affect different models and appear to have different root causes." }, { - "left": "issue:42886", - "right": "issue:43066", + "left": "issue:43723", + "right": "issue:44442", "accept": false, - "reason": "Offline cache loading and wrong tokenizer decoder type are different tokenizer issues, not the same bug." + "reason": "Tokenizer loading failure and FastSpeech2ConformerTokenizer loading are both load issues, but not the same concrete bug." }, { - "left": "issue:44117", - "right": "issue:44704", + "left": "issue:44373", + "right": "issue:44485", "accept": false, - "reason": "TOKENIZER_MAPPING_NAMES returning None and AutoProcessor kwargs propagation are different loader bugs." + "reason": "A docstring mistake and a GLM-5 RoPE implementation discussion are not duplicates." }, { - "left": "issue:43122", - "right": "issue:44514", + "left": "issue:45092", + "right": "issue:45357", "accept": false, - "reason": "Version-dependent tokenization differences and chat-template crash with padding=False are not the same failure." + "reason": "Meta-init incompatibility for old InternVL2 checkpoints is unrelated to incorrect visual encoder keys in save_pretrained." }, { "left": "issue:30990", - "right": "issue:33357", + "right": "issue:38175", "accept": false, - "reason": "Loading stall for sentence-transformers and MacOS bus error on CLIP model are unrelated." + "reason": "Sentence-Transformers getting stuck loading and SigLIP2 zero probabilities are different problems." }, { - "left": "issue:42371", - "right": "issue:44263", + "left": "issue:42886", + "right": "issue:42994", "accept": false, - "reason": "TF32 settings guidance and torch.split return values are unrelated." + "reason": "Offline cache tokenizer loading and quantized model saving failure are separate bugs." }, { - "left": "issue:44295", - "right": "issue:44297", + "left": "issue:42831", + "right": "issue:45310", "accept": false, - "reason": "Position_ids buffer access bug and tokenizer_class mismatch in saved config are different save/load problems." + "reason": "FP8 accuracy issues are unrelated to Qwen3.5 MoE from_pretrained errors." }, { - "left": "issue:44704", - "right": "issue:45290", + "left": "issue:41628", + "right": "issue:43824", "accept": false, - "reason": "AutoProcessor kwargs forwarding and chat_template crash on tool-call assistant messages are separate bugs." + "reason": "Different missing imports: AutoImageProcessor versus Qwen2_5_VLForConditionalGeneration." }, { - "left": "issue:42907", - "right": "issue:44945", + "left": "issue:42831", + "right": "issue:44038", "accept": false, - "reason": "Dequantized model save failure and incorrect output under pipeline parallelism are unrelated." + "reason": "FP8 accuracy and Qwen3.5-v5 bug reports are not the same code-path problem." }, { - "left": "issue:43976", - "right": "issue:44945", + "left": "issue:43576", + "right": "issue:43784", "accept": false, - "reason": "Python version compatibility problem and pipeline-parallelism output bug are not the same issue." + "reason": "Broken `transformers env` command and sentence-transformers import NameError have different causes and effects." }, { - "left": "issue:43232", - "right": "issue:44743", + "left": "issue:42757", + "right": "issue:45278", "accept": false, - "reason": "Generation kwarg update bug and recurrent-state reset in modular_qwen3_5 are distinct code-path failures." + "reason": "The broad import-regression umbrella may include this symptom, but the specific missing is_offline_mode import is not itself the same bug as the whole cluster." } ] }, @@ -11207,62 +10964,75 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:29127", "issue:30990", + "issue:33357", "issue:36296", "issue:39401", "issue:41628", - "issue:42222", "issue:42371", - "issue:42757", "issue:42831", + "issue:42886", "issue:42907", + "issue:43066", "issue:43116", "issue:43122", "issue:43232", - "issue:43278", "issue:43408", - "issue:43441", "issue:43452", "issue:43475", "issue:43784", - "issue:43824", "issue:43937", + "issue:43976", "issue:43992", "issue:44038", + "issue:44117", "issue:44222", "issue:44261", + "issue:44263", "issue:44295", "issue:44297", - "issue:44351", "issue:44360", "issue:44373", "issue:44485", "issue:44488", + "issue:44514", "issue:44521", "issue:44625", "issue:44704", + "issue:44743", "issue:44779", "issue:44829", "issue:44945", "issue:44964", - "issue:44977", "issue:45200", - "issue:45216", "issue:45245", "issue:45278", - "issue:45446", - "issue:45478", + "issue:45290", + "issue:45593", "issue:45600" ], "soft_pairs": [ - "issue:43232|issue:45245", + "issue:43122|issue:44521", + "issue:44263|issue:44373", + "issue:43232|issue:45593", + "issue:42886|issue:43066", + "issue:44117|issue:44704", + "issue:43122|issue:44514", + "issue:30990|issue:33357", + "issue:42371|issue:44263", + "issue:44295|issue:44297", + "issue:44704|issue:45290", + "issue:42907|issue:44945", + "issue:43976|issue:44945", + "issue:43232|issue:44743", "issue:39401|issue:44488", + "issue:43232|issue:45245", "issue:42907|issue:43937", "issue:43408|issue:43475", "issue:41628|issue:45278", @@ -11271,9 +11041,9 @@ "issue:44360|issue:44485", "issue:43116|issue:45200", "issue:39401|issue:44521", + "issue:43122|issue:44779", "issue:29127|issue:30990", "issue:44038|issue:44297", - "issue:43122|issue:44779", "issue:44261|issue:44373", "issue:44038|issue:44295", "issue:42371|issue:42831", @@ -11281,218 +11051,216 @@ "issue:36296|issue:43116", "issue:44038|issue:44222", "issue:42907|issue:43452", - "issue:43992|issue:44704", - "issue:45216|issue:45478", - "issue:43824|issue:44351", - "issue:43122|issue:44977", - "issue:42907|issue:44222", - "issue:42757|issue:44351", - "issue:43278|issue:44945", - "issue:43784|issue:45446", - "issue:42222|issue:43441" + "issue:43992|issue:44704" ], - "prepared_review_unit_hash": "fa63d5dbfa3e217c9199cd8babad64e30b7b1e4070640d8bda852a2d0e5c90af", + "prepared_review_unit_hash": "54128892aaae869e6a6ccd91519a8c90862d6ed7f75e655bce0fcf3457464c93", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 47, "item_count": 47, - "soft_pair_count": 29, - "serialized_chars": 35335, - "estimated_input_tokens": 8834, - "estimated_eval_tokens": 17924 + "soft_pair_count": 34, + "serialized_chars": 36859, + "estimated_input_tokens": 9215, + "estimated_eval_tokens": 18686 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is a loose collection of unrelated Transformers issues, mostly import, tokenizer, model-loading, and training regressions across different model families. The soft pairs are largely superficial matches by topic or version, not the same underlying bug or change.", - "confidence": 0.93, - "canonical_issue_reason": "Issue 45216 is the cleanest, most concrete regression report in the set: it names a specific model family, a clear failure mode, and a version boundary for `save_pretrained`.", + "summary": "This cluster is highly heterogeneous: the items cover unrelated tokenizer, generation, import, multimodal, training, and model-specific bugs. None of the soft-edge pairs look like the same underlying issue closely enough to merge as duplicates.", + "confidence": 0.97, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Issue 45216 is the strongest representative issue because it is narrowly scoped, reproducible in nature, and tied to a specific regression surface rather than a broad symptom report.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43232", - "right": "issue:45245", + "left": "issue:43122", + "right": "issue:44521", "accept": false, - "reason": "Different failures: generation state update after `sync_gpus` vs category-count limit in a runtime error." + "reason": "Both mention tokenization/chat behavior, but one is a tokenizer-v4/v5 discrepancy and the other is zero assistant masks for multimodal inputs; different code paths and symptoms." }, { - "left": "issue:39401", - "right": "issue:44488", + "left": "issue:44263", + "right": "issue:44373", "accept": false, - "reason": "Tokenizer offset mapping bug is unrelated to a model-loading failure for `cjvt/sleng-bert`." + "reason": "One is a torch.split indexing bug in a model component, the other is a docstring issue for position_ids; not the same bug." }, { - "left": "issue:42907", - "right": "issue:43937", + "left": "issue:43232", + "right": "issue:45593", "accept": false, - "reason": "Saving dequantized Ministral/Devstral models is a different path from GLM-5 generation config validation." + "reason": "Generation sync/update logic vs D-FINE auxiliary loss handling are unrelated model subsystems." }, { - "left": "issue:43408", - "right": "issue:43475", + "left": "issue:42886", + "right": "issue:43066", "accept": false, - "reason": "Both are SAM 3 related, but one is a wrong model-type warning and the other is a missing attribute error; not clearly the same bug." + "reason": "Offline cache loading failure and wrong tokenizer decoder type are distinct tokenizer issues." }, { - "left": "issue:41628", - "right": "issue:45278", + "left": "issue:44117", + "right": "issue:44704", "accept": false, - "reason": "Both mention imports, but one is a specific missing symbol and the other is a broad upgrade breakage report." + "reason": "TOKENIZER_MAPPING_NAMES returning None is a registry bug; AutoProcessor not forwarding kwargs to cached_file is an API plumbing bug." }, { - "left": "issue:43784", - "right": "issue:45600", + "left": "issue:43122", + "right": "issue:44514", "accept": false, - "reason": "Sentence-transformers import `nn` NameError is unrelated to removed Sam3LiteText config references." + "reason": "Both involve tokenization, but one is differing tokenization outputs across versions and the other is a batched apply_chat_template crash with padding=False." }, { - "left": "issue:44625", - "right": "issue:44829", + "left": "issue:30990", + "right": "issue:33357", "accept": false, - "reason": "`num_labels` propagation and FA3 degenerate training are different model-behavior issues." + "reason": "Sentence Transformers loading hang and a MacOS bus error with a CLIP model are unrelated runtime failures." }, { - "left": "issue:44360", - "right": "issue:44485", + "left": "issue:42371", + "right": "issue:44263", "accept": false, - "reason": "DSA ReLU discussion is unrelated to GLM-5 RoPE implementation." + "reason": "TF32 configuration guidance and a torch.split return-value bug are unrelated." }, { - "left": "issue:43116", - "right": "issue:45200", + "left": "issue:44295", + "right": "issue:44297", "accept": false, - "reason": "Classification script returning empty results is unrelated to Gemma 4 multimodal token type defaults." + "reason": "Reading position_ids after buffer registration and tokenizer_class mismatch on save_pretrained are separate save/load issues." }, { - "left": "issue:39401", - "right": "issue:44521", + "left": "issue:44704", + "right": "issue:45290", "accept": false, - "reason": "Offset mapping errors and all-zero assistant masks are different tokenizer/template bugs." + "reason": "Both touch chat/template flows, but one is cached_file kwargs forwarding and the other is a crash on assistant tool-call messages; different failure points." }, { - "left": "issue:29127", - "right": "issue:30990", + "left": "issue:42907", + "right": "issue:44945", "accept": false, - "reason": "LayoutLMv3 box-message clarity and Sentence-Transformers loading hang are unrelated." + "reason": "Saving dequantized Ministral/Devstral models and incorrect output under pipeline parallelism are unrelated." }, { - "left": "issue:44038", - "right": "issue:44297", + "left": "issue:43976", + "right": "issue:44945", "accept": false, - "reason": "Qwen3-VL-Moe issue is not the same as tokenizer class metadata saved in config." + "reason": "Python-version compatibility failure and pipeline-parallel output corruption are not the same bug." }, { - "left": "issue:43122", - "right": "issue:44779", + "left": "issue:43232", + "right": "issue:44743", "accept": false, - "reason": "Both are tokenizer regressions, but they affect different model families and likely different code paths." + "reason": "Both involve generation/cache internals, but one is sync_gpus update handling and the other is recurrent-state reset in modular_qwen3_5.py; different concrete code paths." }, { - "left": "issue:44261", - "right": "issue:44373", + "left": "issue:39401", + "right": "issue:44488", "accept": false, - "reason": "Missing `rms_norm_eps` in MLA and a wrong docstring for `position_ids` are not the same defect." + "reason": "Wrong offset_mapping for Qwen3 tokenizer and failure to load cjvt/sleng-bert are distinct tokenizer problems." }, { - "left": "issue:44038", - "right": "issue:44222", + "left": "issue:43232", + "right": "issue:45245", "accept": false, - "reason": "Qwen3-VL-Moe loading bug is unrelated to FP8 `save_pretrained` issues." + "reason": "Generation kwargs update after sync_gpus is unrelated to the 2^24 categories runtime error." }, { - "left": "issue:42371", - "right": "issue:42831", + "left": "issue:42907", + "right": "issue:43937", "accept": false, - "reason": "TF32 API guidance and FineGrainedFP8 accuracy problems are different precision-related topics." + "reason": "Dequantized model save failure and invalid GenerationConfig for GLM-5 are unrelated." }, { - "left": "issue:42907", - "right": "issue:44964", + "left": "issue:43408", + "right": "issue:43475", "accept": false, - "reason": "Model save failures for Ministral/Devstral are unrelated to loading Phi-4 multimodal." + "reason": "Both are SAM 3 Video related, but one is a model-type warning and the other is a missing attribute on Sam3VisionEncoderOutput; not the same bug." }, { - "left": "issue:36296", - "right": "issue:43116", + "left": "issue:41628", + "right": "issue:45278", "accept": false, - "reason": "Tensor parallel training bug is not the same as empty outputs from a classification example script." + "reason": "AutoImageProcessor import failure is a specific symbol-export problem; the other reports many import errors after an upgrade and is much broader." }, { - "left": "issue:44038", - "right": "issue:44222", + "left": "issue:43784", + "right": "issue:45600", "accept": false, - "reason": "Shared FP8/Qwen adjacency is too broad; these describe different model/version and save/load problems." + "reason": "NameError importing sentence-transformers and auto_mappings references to removed Sam3LiteText configs are unrelated import/compatibility failures." }, { - "left": "issue:42907", - "right": "issue:43452", + "left": "issue:44625", + "right": "issue:44829", "accept": false, - "reason": "Dequantized model saving and `gguf_file` loading failures are separate mechanisms." + "reason": "num_labels propagation in Qwen3.5 and flash_attention_3 degenerate training are different model/configuration bugs." }, { - "left": "issue:43992", - "right": "issue:44704", + "left": "issue:44360", + "right": "issue:44485", "accept": false, - "reason": "Missing weight loading in UMT5Encoder is unrelated to `AutoProcessor` forwarding kwargs." + "reason": "Missing ReLU in a DSA indexer and GLM-5 RoPE implementation are unrelated architectural issues." }, { - "left": "issue:45216", - "right": "issue:45478", + "left": "issue:43116", + "right": "issue:45200", "accept": false, - "reason": "Both involve Qwen3.5 and version 5.x, but one is save-pretrained checkpoint corruption and the other is a from-pretrained load error." + "reason": "Empty multi-label results in an example script and Gemma 4 mm_token_type_ids defaulting are unrelated application bugs." }, { - "left": "issue:43824", - "right": "issue:44351", + "left": "issue:39401", + "right": "issue:44521", "accept": false, - "reason": "Both are import errors, but for different symbols and different breakages." + "reason": "Tokenizer offset mapping bug and multimodal assistant_mask zeroing are different failures." }, { "left": "issue:43122", - "right": "issue:44977", + "right": "issue:44779", "accept": false, - "reason": "Tokenization regression reports are model-specific here; no evidence they stem from the same bug." + "reason": "Both are tokenizer regressions in v5, but they affect different models and behaviors; not enough to treat as one duplicate bug." }, { - "left": "issue:42907", - "right": "issue:44222", + "left": "issue:29127", + "right": "issue:30990", "accept": false, - "reason": "Saving dequantized Ministral/Devstral models is not the same as FP8 MOE save_pretrained behavior." + "reason": "LayoutLMv3 error-message clarity and Sentence Transformers loading hang have no substantive overlap." }, { - "left": "issue:42757", - "right": "issue:44351", + "left": "issue:44038", + "right": "issue:44297", "accept": false, - "reason": "`is_offline_mode` from huggingface_hub and `HybridCache` from transformers are unrelated missing imports." + "reason": "Qwen3-VL-Moe bug and tokenizer_class mismatch on save_pretrained are unrelated." }, { - "left": "issue:43278", - "right": "issue:44945", + "left": "issue:44261", + "right": "issue:44373", "accept": false, - "reason": "Embedding dtype drift in evaluate is unrelated to incorrect outputs under pipeline parallelism." + "reason": "A numerical precision/config issue in MLA q_a_layernorm is not the same as a wrong docstring for position_ids." }, { - "left": "issue:43784", - "right": "issue:45446", + "left": "issue:44038", + "right": "issue:44222", "accept": false, - "reason": "Importing sentence-transformers with `nn` missing is unrelated to the flex_attention PyTorch version check." + "reason": "Both mention MOE/FP8-adjacent topics, but one is a Qwen3-VL-Moe load bug and the other is FP8 save_pretrained behavior; different concrete problems." }, { - "left": "issue:42222", - "right": "issue:43441", + "left": "issue:42907", + "right": "issue:43452", + "accept": false, + "reason": "Saving dequantized models and gguf_file breaking from_pretrained are distinct model-loading/saving bugs." + }, + { + "left": "issue:43992", + "right": "issue:44704", "accept": false, - "reason": "A broken VitPose module and a FlashAttention failure in Ministral-3 are different model-path issues." + "reason": "Missing embed_tokens.weight for UMT5Encoder and AutoProcessor kwargs forwarding are unrelated from_pretrained issues." } ] }, @@ -11514,22 +11282,27 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:22355", "issue:29127", "issue:33453", "issue:38617", "issue:39401", - "issue:41628", + "issue:42222", "issue:42371", "issue:42673", + "issue:42757", + "issue:42907", "issue:43064", "issue:43116", - "issue:43421", - "issue:43450", + "issue:43122", + "issue:43278", + "issue:43441", "issue:43493", "issue:43673", + "issue:43784", + "issue:43824", "issue:43825", "issue:43827", "issue:43874", @@ -11537,26 +11310,20 @@ "issue:43931", "issue:43937", "issue:43976", - "issue:43986", "issue:44038", "issue:44075", "issue:44117", "issue:44222", - "issue:44291", - "issue:44410", - "issue:44484", + "issue:44351", "issue:44485", "issue:44779", - "issue:44829", "issue:44936", "issue:44945", "issue:44977", - "issue:45071", "issue:45072", "issue:45083", "issue:45216", "issue:45278", - "issue:45310", "issue:45341", "issue:45405", "issue:45446", @@ -11566,9 +11333,17 @@ "issue:45588" ], "soft_pairs": [ + "issue:45216|issue:45478", + "issue:43824|issue:44351", + "issue:43122|issue:44977", + "issue:42907|issue:44222", + "issue:42757|issue:44351", + "issue:43278|issue:44945", + "issue:43784|issue:45446", + "issue:42222|issue:43441", "issue:42673|issue:45072", - "issue:43064|issue:43673", "issue:38617|issue:45278", + "issue:43064|issue:43673", "issue:43937|issue:44485", "issue:22355|issue:29127", "issue:42371|issue:43874", @@ -11584,227 +11359,226 @@ "issue:43931|issue:44945", "issue:45083|issue:45446", "issue:44117|issue:45588", - "issue:45341|issue:45561", - "issue:43937|issue:44977", "issue:43827|issue:45446", + "issue:43937|issue:44977", + "issue:45341|issue:45561", "issue:42673|issue:43906", - "issue:44291|issue:45071", - "issue:45405|issue:45446", - "issue:39401|issue:43421", - "issue:44484|issue:45310", - "issue:43450|issue:43986", - "issue:44829|issue:45216", - "issue:38617|issue:41628", - "issue:44410|issue:45310" + "issue:45405|issue:45446" ], - "prepared_review_unit_hash": "baf8abbfb3c43001d77f3a3eb5db87dcfe55b1c83f4ace7ff6bcdf984adbd0a8", + "prepared_review_unit_hash": "787b2d7c324517c2da68777872efb5e3993813c915429ba1b2f7bc6a3fc49af9", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 30, - "serialized_chars": 36397, - "estimated_input_tokens": 9100, - "estimated_eval_tokens": 18456 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "serialized_chars": 36001, + "estimated_input_tokens": 9001, + "estimated_eval_tokens": 18258 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly a grab bag of unrelated regression and import/tokenizer/model-specific issues; only a few pairs are loosely thematically related, but none look like the same underlying bug/change.", - "confidence": 0.42, - "canonical_issue_reason": "issue:45278 is the broadest representative of the cluster\u2019s import-regression theme and can serve as the umbrella issue among these largely disparate reports.", + "summary": "These are mostly superficially similar bug reports, but they do not describe the same concrete defect or mergeable fix. I found no true duplicate pair among the soft edges, so there is no safe canonical issue/PR for the cluster.", + "confidence": 0.93, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the most general and cluster-representative issue title here; it covers the widest user-facing failure mode without being overly specific to one model or component.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:42673", - "right": "issue:45072", + "left": "issue:45216", + "right": "issue:45478", "accept": false, - "reason": "Different failures in different areas: Qwen3ForCausalLM VRAM leak vs bfloat16 dtype mismatch in SwitchTransformers/TimmWrapperModel." + "reason": "Same model family and version range, but one is a save_pretrained checkpoint regression and the other is a from_pretrained load error; different code paths and symptoms." }, { - "left": "issue:43064", - "right": "issue:43673", + "left": "issue:43824", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but they concern different missing symbols with different causes." + }, + { + "left": "issue:43122", + "right": "issue:44977", + "accept": false, + "reason": "Tokenizer regression vs flash-attention generation failure; unrelated underlying bugs." + }, + { + "left": "issue:42907", + "right": "issue:44222", + "accept": false, + "reason": "Both involve saving quantized models, but they target different quantization formats and model families." + }, + { + "left": "issue:42757", + "right": "issue:44351", + "accept": false, + "reason": "Different missing imports; no shared failure mechanism beyond generic ImportError." + }, + { + "left": "issue:43278", + "right": "issue:44945", + "accept": false, + "reason": "Training/eval dtype mismatch is not the same defect as wrong outputs under pipeline parallelism." + }, + { + "left": "issue:43784", + "right": "issue:45446", + "accept": false, + "reason": "Sentence-transformers import breakage vs a flex_attention version check bug; unrelated." + }, + { + "left": "issue:42222", + "right": "issue:43441", + "accept": false, + "reason": "Different model families and different failure modes." + }, + { + "left": "issue:42673", + "right": "issue:45072", "accept": false, - "reason": "Trainer/FSDP optimizer-state bug is unrelated to GenerationMixin cache handling in chunked prefill." + "reason": "VRAM leak in threaded dataloading is unrelated to bfloat16 dtype mismatches." }, { "left": "issue:38617", "right": "issue:45278", "accept": false, - "reason": "Both are import-related, but one is a specific missing symbol and the other is a broad post-upgrade import-error report; not the same concrete bug." + "reason": "One is a specific missing import, the other is a broad report of many import errors; too coarse to treat as the same bug." + }, + { + "left": "issue:43064", + "right": "issue:43673", + "accept": false, + "reason": "Wrong optimizer state distribution and missing generation cache are distinct bugs." }, { "left": "issue:43937", "right": "issue:44485", "accept": false, - "reason": "Both mention GLM-5, but one is GenerationConfig validation and the other is RoPE implementation; different problems." + "reason": "GenerationConfig validation failure vs RoPE implementation discussion; not the same concrete issue." }, { "left": "issue:22355", "right": "issue:29127", "accept": false, - "reason": "No module transformers.onnx is a package/import issue; the other is a layoutlmv3 error-message clarity issue." + "reason": "Module import failure and a LayoutLMv3 error-message clarity issue are unrelated." }, { "left": "issue:42371", "right": "issue:43874", "accept": false, - "reason": "TF32 behavior settings and a missing image-patch helper in GLM46V are unrelated." + "reason": "TF32 settings guidance vs a missing image-patch helper method; different subsystems and bugs." }, { "left": "issue:43116", "right": "issue:43493", "accept": false, - "reason": "Multi-label classification example output bug is unrelated to SigLIP2 implementation mismatch." + "reason": "Example script multi-label output bug vs SigLIP2 implementation discrepancy; not the same defect." }, { "left": "issue:44075", "right": "issue:44936", "accept": false, - "reason": "Unused SGD arguments and trainer.evaluate() failing after train() are different trainer/optimizer issues." + "reason": "Unused SGD args and train-then-evaluate failure are separate training bugs." }, { "left": "issue:44222", "right": "issue:45478", "accept": false, - "reason": "Different directions of the save/load path and different symptoms; both involve Qwen3.5 MoE but not the same bug." + "reason": "Both mention Qwen3.5/MoE saving/loading, but one is FP8 save_pretrained and the other is a from_pretrained error." }, { "left": "issue:44038", "right": "issue:45478", "accept": false, - "reason": "Both are Qwen3/Qwen3.5 MoE-related, but one is a transformers 5.0 bug and the other is a from_pretrained error; not the same issue." + "reason": "Same broad model area, but one is a vague Qwen3-VL-Moe bug and the other is a specific Qwen3.5 MoE load error." }, { "left": "issue:43116", "right": "issue:43825", "accept": false, - "reason": "Example-script multi-label behavior and pipeline translation support messaging are unrelated." + "reason": "Example script behavior vs pipeline API error messaging; not the same bug." }, { "left": "issue:43976", "right": "issue:45446", "accept": false, - "reason": "Python-version compatibility and a PyTorch version check for AuxRequest import are separate compatibility bugs." + "reason": "Python version compatibility issue vs a PyTorch version-guard bug." }, { "left": "issue:43937", "right": "issue:45563", "accept": false, - "reason": "GLM-5 generation-config validation and a stale paged-generate warning are different generation issues." + "reason": "Invalid GenerationConfig and a stale warning on paged generate are unrelated." }, { "left": "issue:39401", "right": "issue:44779", "accept": false, - "reason": "Both are tokenizer regressions, but they affect different tokenizers and different observable failures." + "reason": "Both tokenizer regressions, but they affect different models and different behaviors (offset mapping vs tokenization output)." }, { "left": "issue:33453", "right": "issue:39401", "accept": false, - "reason": "Tokenizer loading regression and Qwen3 offset_mapping bug are not the same concrete failure." + "reason": "Tokenizer loading regression and offset_mapping bug are not the same concrete defect." }, { "left": "issue:43931", "right": "issue:44945", "accept": false, - "reason": "Qwen3-VL weight-shape loading mismatch is unrelated to pipeline-parallelism output corruption." + "reason": "Weight-shape mismatch on model load is unrelated to incorrect outputs under pipeline parallelism." }, { "left": "issue:45083", "right": "issue:45446", "accept": false, - "reason": "qwen3_omni_moe feature-length helper behavior and flex_attention version checking are unrelated." + "reason": "Multimodal feature helper behavior and a flex_attention import/version check are unrelated." }, { "left": "issue:44117", "right": "issue:45588", "accept": false, - "reason": "Tokenizer mapping fallback bug is unrelated to flash_attention.py crashing on s_aux=None." + "reason": "Tokenizer mapping assumption bug vs flash_attention crash on sink-less models; different code paths." }, { - "left": "issue:45341", - "right": "issue:45561", + "left": "issue:43827", + "right": "issue:45446", "accept": false, - "reason": "Generic testing_utils bug and xdist race on captured_info.txt are different test-infra issues." + "reason": "Documentation still referencing pipeline() is unrelated to the flex_attention import guard." }, { "left": "issue:43937", "right": "issue:44977", "accept": false, - "reason": "Both affect generation, but one is invalid GenerationConfig and the other is flash-attention output failure; not the same bug." + "reason": "Different GLM-5 generation-config bug vs Qwen3.5 flash-attention generation bug." }, { - "left": "issue:43827", - "right": "issue:45446", + "left": "issue:45341", + "right": "issue:45561", "accept": false, - "reason": "Docs still referencing pipeline() and a PyTorch version check bug do not describe the same issue." + "reason": "A generic testing_utils bug is not the same as a pytest-xdist race on captured_info.txt." }, { "left": "issue:42673", "right": "issue:43906", "accept": false, - "reason": "VRAM leak in Qwen3ForCausalLM is unrelated to an isolated reproduction of issue 38071." - }, - { - "left": "issue:44291", - "right": "issue:45071", - "accept": false, - "reason": "init_empty_weights constructor argument regression and PretrainedConfig type-checking regression are different v5 issues." + "reason": "An isolated reproduction of another issue is not itself the same bug as a VRAM leak." }, { "left": "issue:45405", "right": "issue:45446", "accept": false, - "reason": "Unreleased PEFT minimum version and a PyTorch import/version check bug are unrelated." - }, - { - "left": "issue:39401", - "right": "issue:43421", - "accept": false, - "reason": "Qwen3 tokenizer offset mapping and runtime post-processor updates for special tokens are different tokenizer behaviors." - }, - { - "left": "issue:44484", - "right": "issue:45310", - "accept": false, - "reason": "save_pretrained shard-size behavior and Qwen3.5 MoE from_pretrained failure are unrelated." - }, - { - "left": "issue:43450", - "right": "issue:43986", - "accept": false, - "reason": "Batched video-processor shape bug and AutoProcessor crash without torchvision are different video-processing issues." - }, - { - "left": "issue:44829", - "right": "issue:45216", - "accept": false, - "reason": "flash_attention_3 training degeneration and Qwen3.5 checkpoint save_pretrained regression are unrelated." - }, - { - "left": "issue:38617", - "right": "issue:41628", - "accept": false, - "reason": "Both are import errors, but they concern different missing names and likely different breakages." - }, - { - "left": "issue:44410", - "right": "issue:45310", - "accept": false, - "reason": "Missing qwen3next projections and Qwen3.5 MoE from_pretrained error are different model bugs." + "reason": "A dependency minimum-version bump issue is unrelated to the AuxRequest flex_attention import guard." } ] }, @@ -11826,9 +11600,10 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:38617", + "issue:39401", "issue:41628", "issue:42175", "issue:42222", @@ -11839,10 +11614,10 @@ "issue:43066", "issue:43097", "issue:43122", - "issue:43335", "issue:43408", + "issue:43421", "issue:43441", - "issue:43452", + "issue:43450", "issue:43577", "issue:43582", "issue:43673", @@ -11850,14 +11625,12 @@ "issue:43874", "issue:43931", "issue:43937", - "issue:43976", "issue:43986", - "issue:44038", "issue:44117", "issue:44220", "issue:44261", "issue:44263", - "issue:44368", + "issue:44291", "issue:44410", "issue:44483", "issue:44484", @@ -11866,11 +11639,12 @@ "issue:44496", "issue:44829", "issue:44933", - "issue:44987", "issue:45003", "issue:45071", "issue:45081", + "issue:45216", "issue:45278", + "issue:45310", "issue:45341", "issue:45459", "issue:45464", @@ -11878,6 +11652,13 @@ "issue:45542" ], "soft_pairs": [ + "issue:44291|issue:45071", + "issue:39401|issue:43421", + "issue:43450|issue:43986", + "issue:44484|issue:45310", + "issue:44829|issue:45216", + "issue:38617|issue:41628", + "issue:44410|issue:45310", "issue:44117|issue:45081", "issue:42673|issue:43582", "issue:43408|issue:43742", @@ -11885,19 +11666,19 @@ "issue:42673|issue:43577", "issue:42371|issue:44261", "issue:43937|issue:44496", + "issue:42175|issue:42222", "issue:38617|issue:44220", "issue:43012|issue:43577", - "issue:42175|issue:42222", "issue:44483|issue:45464", "issue:44933|issue:45278", + "issue:42617|issue:45341", "issue:44484|issue:45478", "issue:43066|issue:43122", - "issue:42617|issue:45341", "issue:43673|issue:45341", "issue:44410|issue:45478", - "issue:43874|issue:44261", "issue:43097|issue:44493", "issue:42222|issue:45459", + "issue:43874|issue:44261", "issue:43441|issue:44829", "issue:43012|issue:43408", "issue:43986|issue:44484", @@ -11905,260 +11686,246 @@ "issue:41628|issue:45071", "issue:45071|issue:45542", "issue:43931|issue:44410", - "issue:45003|issue:45341", - "issue:44117|issue:44987", - "issue:43986|issue:45341", - "issue:43931|issue:44038", - "issue:43097|issue:43452", - "issue:43335|issue:45071", - "issue:43408|issue:44368", - "issue:43874|issue:44263", - "issue:43976|issue:45071" + "issue:45003|issue:45341" ], - "prepared_review_unit_hash": "c2090c0ee7c7d99064f49044f3ff326aa02e169a5f6b9e33fb166f11f70b6d64", + "prepared_review_unit_hash": "b13c14c8e13dac9fb9bd15434edc9d166d64339caf3f7fa3213104e35e601f71", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 36, - "serialized_chars": 38336, - "estimated_input_tokens": 9584, - "estimated_eval_tokens": 19424 + "soft_pair_count": 35, + "serialized_chars": 37973, + "estimated_input_tokens": 9494, + "estimated_eval_tokens": 19244 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly a set of unrelated Transformers issues that only loosely match on broad themes like imports, model loading, tokenizer behavior, and backend/config regressions. The strongest umbrella issue is the broad 5.x import-regression report, but the soft-edge pairs are not the same underlying bug/change and should stay separate.", - "confidence": 0.91, - "canonical_issue_reason": "issue:45278 is the best umbrella representative because it explicitly covers many import errors after upgrading Transformers, which is the broadest recurring symptom in this cluster.", + "summary": "This cluster is highly heterogeneous: most items are distinct bug reports spanning tokenizers, model loading, multimodal processors, packaging/import regressions, and API behavior. I don\u2019t see a single underlying defect that cleanly subsumes the whole set.", + "confidence": 0.95, + "canonical_issue_reason": "No single issue cleanly represents the whole cluster; the items are mostly unrelated. If forced to pick a broad umbrella, #45278 is the closest because it describes many import errors after a version upgrade, but it does not actually cover most of the other reports.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the most suitable global issue because it is broad, regression-oriented, and can subsume multiple import-related reports better than the narrower model-specific bugs.", + "best_issue_reason": "#45278 is the broadest and most recent open issue in the set, so it is the best umbrella candidate for generic import-regression triage, though it is still not a true duplicate target for the rest of the cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44291", + "right": "issue:45071", + "accept": false, + "reason": "Both are version-regression loader failures, but one is an init_empty_weights/_is_hf_initialized TypeError and the other is a PretrainedConfig type-checking break; different code paths." + }, + { + "left": "issue:39401", + "right": "issue:43421", + "accept": false, + "reason": "Both involve tokenizers, but one is wrong offset mapping and the other is runtime special-token/post-processor updates; not the same bug." + }, + { + "left": "issue:43450", + "right": "issue:43986", + "accept": false, + "reason": "One is a batched video-processor shape bug; the other is an AutoProcessor crash without torchvision. Different failure modes." + }, + { + "left": "issue:44484", + "right": "issue:45310", + "accept": false, + "reason": "Unrelated issues: max_shard_size behavior versus a Qwen3.5 MoE from_pretrained error." + }, + { + "left": "issue:44829", + "right": "issue:45216", + "accept": false, + "reason": "One is FA3 training degeneration; the other is incorrect checkpoint saving for Qwen3.5. Different concrete problems." + }, + { + "left": "issue:38617", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but they concern different missing symbols and modules." + }, + { + "left": "issue:44410", + "right": "issue:45310", + "accept": false, + "reason": "Different model bugs: missing Qwen3Next projections versus Qwen3.5 MoE loading failure." + }, { "left": "issue:44117", "right": "issue:45081", "accept": false, - "reason": "Both involve tokenizer internals, but one is a mapping/None handling bug and the other is a Mistral regex patch crash; different code paths and failure modes." + "reason": "Tokenizer internals are involved in both, but one is TOKENIZER_MAPPING_NAMES returning None and the other is a Mistral regex patch crash." }, { "left": "issue:42673", "right": "issue:43582", "accept": false, - "reason": "One is a VRAM leak with multiple dataloader threads; the other is an Apple Silicon TypeError in allocator warmup. Not the same bug." + "reason": "VRAM leak in Qwen3ForCausalLM vs Apple Silicon caching_allocator_warmup TypeError; unrelated." }, { "left": "issue:43408", "right": "issue:43742", "accept": false, - "reason": "Both are loading errors, but they affect different models and likely different missing metadata/config issues." + "reason": "Different model-loading issues: sam3 type mismatch versus MobileLLM key error." }, { "left": "issue:42222", "right": "issue:45542", "accept": false, - "reason": "Both mention TensorFlow/backend packaging, but one is missing TF in the torch extra and the other is an undefined backend error from tensorboard-only installs; not one concrete change." + "reason": "Vitpose model breakage and a TensorFlow backend-install issue are unrelated." }, { "left": "issue:42673", "right": "issue:43577", "accept": false, - "reason": "VRAM leak under multithreaded loading is unrelated to BLIP2 dtype propagation." + "reason": "Both mention memory/dtype concerns, but the VRAM leak and Blip2 dtype loading bug are different code paths." }, { "left": "issue:42371", "right": "issue:44261", "accept": false, - "reason": "TF32 API settings warning is unrelated to MLA q_a_layernorm epsilon/precision behavior." + "reason": "TF32 API warning and MLA rms_norm_eps precision issue are unrelated." }, { "left": "issue:43937", "right": "issue:44496", "accept": false, - "reason": "A GenerationConfig validation failure is a different loading/config bug than an unrecognized model type in config.json." + "reason": "GenerationConfig validation for GLM-5 versus missing model_type for an unrecognized model are different loader/config problems." + }, + { + "left": "issue:42175", + "right": "issue:42222", + "accept": false, + "reason": "Package extra/backend dependency issue versus a vitpose model regression; no shared underlying bug." }, { "left": "issue:38617", "right": "issue:44220", "accept": false, - "reason": "ImportError for a missing symbol in configuration_utils is unrelated to an audio feature-extraction issue." + "reason": "ImportError for a missing config symbol is not the same as an audio feature-extraction failure." }, { "left": "issue:43012", "right": "issue:43577", "accept": false, - "reason": "A PyTorch warning on bfloat16 compilation is not the same as BLIP2 model/qformer dtype staying float32." - }, - { - "left": "issue:42175", - "right": "issue:42222", - "accept": false, - "reason": "TensorFlow backend packaging and broken vitpose models are unrelated issues." + "reason": "Both touch precision/dtype, but one is a PyTorch warning on compilation and the other is incorrect dtype propagation while loading Blip2." }, { "left": "issue:44483", "right": "issue:45464", "accept": false, - "reason": "Both hit chat/completions, but one is a v5 API compatibility break and the other is a streaming inference failure for a specific model." + "reason": "Both are chat/completions-related, but one is a general request rejection and the other is a streaming inference failure on a specific model." }, { "left": "issue:44933", "right": "issue:45278", "accept": false, - "reason": "Missing import from image_utils is narrower and distinct from the broad upgrade-related import regressions in 45278." + "reason": "The latter is a broad import-regression report, but this pair does not establish the same missing symbol or exact failure." + }, + { + "left": "issue:42617", + "right": "issue:45341", + "accept": false, + "reason": "A 3d_parallel runtime issue and a testing_utils bug are unrelated." }, { "left": "issue:44484", "right": "issue:45478", "accept": false, - "reason": "max_shard_size default behavior is unrelated to Qwen3.5 MoE from_pretrained loading failure." + "reason": "Different issues: shard-size behavior versus another Qwen3.5 MoE from_pretrained error report." }, { "left": "issue:43066", "right": "issue:43122", "accept": false, - "reason": "Tokenizer decoder type mismatch and tokenization differences across versions are related to tokenization, but not the same defect." - }, - { - "left": "issue:42617", - "right": "issue:45341", - "accept": false, - "reason": "Failure to run 3d_parallel.py is unrelated to the testing_utils bug." + "reason": "Both concern tokenizer behavior across v5, but one is decoder type and the other is tokenization output changes; not the same defect." }, { "left": "issue:43673", "right": "issue:45341", "accept": false, - "reason": "Generation cache missing in v5.0.0 is unrelated to the testing_utils issue." + "reason": "Generation cache missing in chunked_prefill is unrelated to a testing utility bug." }, { "left": "issue:44410", "right": "issue:45478", "accept": false, - "reason": "Missing projections in qwen3next layer 0 is a model architecture issue, not the Qwen3.5 MoE loading error." - }, - { - "left": "issue:43874", - "right": "issue:44261", - "accept": false, - "reason": "Missing get_number_of_image_patches and MLA layernorm epsilon mismatch are different multimodal bugs." + "reason": "Different Qwen3-related loader/model bugs, not the same concrete failure." }, { "left": "issue:43097", "right": "issue:44493", "accept": false, - "reason": "Removal of tie_embeddings_and_encoder_decoder and unexpected position-id keys are separate v5 migration issues." + "reason": "One is a removed config flag in v5; the other is unexpected position-id keys. Related theme, but not the same bug." }, { "left": "issue:42222", "right": "issue:45459", "accept": false, - "reason": "Vitpose model breakage is not the same as tokenizer protobuf-error masking." + "reason": "Vitpose model breakage and tokenizer error hiding when protobuf is absent are unrelated." + }, + { + "left": "issue:43874", + "right": "issue:44261", + "accept": false, + "reason": "Missing image-patch helper in GLM46V versus MLA layernorm epsilon precision issue; different subsystems." }, { "left": "issue:43441", "right": "issue:44829", "accept": false, - "reason": "FlashAttention failure for Ministral-3 and degenerate training with flash_attention_3 are both attention-related but not the same code-path problem." + "reason": "Ministral FlashAttention failure and FA3 degenerate training are different model/attention problems." }, { "left": "issue:43012", "right": "issue:43408", "accept": false, - "reason": "Precision warning on bfloat16 compilation is unrelated to sam3_video vs sam3_tracker config mismatch." - }, - { - "left": "issue:43986", - "right": "issue:44484", - "accept": false, - "reason": "AutoProcessor without torchvision crash is unrelated to max_shard_size default behavior." - }, - { - "left": "issue:44263", - "right": "issue:44485", - "accept": false, - "reason": "torch.split return values bug and GLM-5 RoPE implementation are different model-specific issues." - }, - { - "left": "issue:41628", - "right": "issue:45071", - "accept": false, - "reason": "AutoImageProcessor import failure and PreTrainedConfig type-checking breakage are both API regressions but not the same one." - }, - { - "left": "issue:45071", - "right": "issue:45542", - "accept": false, - "reason": "PreTrainedConfig type checking and undefined tf backend errors are unrelated." - }, - { - "left": "issue:43931", - "right": "issue:44410", - "accept": false, - "reason": "Qwen3-VL weight-shape mismatch and qwen3next missing projections are different model-loading defects." - }, - { - "left": "issue:45003", - "right": "issue:45341", - "accept": false, - "reason": "Unsafe sys.modules access in modeling_utils is unrelated to the testing_utils bug." - }, - { - "left": "issue:44117", - "right": "issue:44987", - "accept": false, - "reason": "TOKENIZER_MAPPING_NAMES returning None is a tokenizer registry issue; loading physical-intelligence/fast is a separate model-loading failure." + "reason": "Precision-warning behavior and a sam3_video/sam3_tracker type warning are unrelated." }, { "left": "issue:43986", - "right": "issue:45341", - "accept": false, - "reason": "AutoProcessor/torchvision crash is unrelated to the testing_utils bug." - }, - { - "left": "issue:43931", - "right": "issue:44038", + "right": "issue:44484", "accept": false, - "reason": "Qwen3-VL weight mismatch and Qwen3.5/V5 backend issue are different model/config failures." + "reason": "Video processor import/runtime crash versus save_pretrained shard sizing; not the same issue." }, { - "left": "issue:43097", - "right": "issue:43452", + "left": "issue:44263", + "right": "issue:44485", "accept": false, - "reason": "Embedding-tie removal and gguf_file tokenizer/model loading are distinct regressions." + "reason": "torch.split return handling in GlmMoeDsaIndexer is unrelated to GLM-5 RoPE implementation." }, { - "left": "issue:43335", + "left": "issue:41628", "right": "issue:45071", "accept": false, - "reason": "Sparse layer creation in SwitchTransformersConfig is unrelated to a PreTrainedConfig type-checking break." + "reason": "AutoImageProcessor import failure and PretrainedConfig type-checking break are different regressions." }, { - "left": "issue:43408", - "right": "issue:44368", + "left": "issue:45071", + "right": "issue:45542", "accept": false, - "reason": "sam3 model-type warning and tie_word_embeddings warning are different warning sources and model families." + "reason": "PretrainedConfig type checking and TensorFlow backend installation are unrelated." }, { - "left": "issue:43874", - "right": "issue:44263", + "left": "issue:43931", + "right": "issue:44410", "accept": false, - "reason": "Multimodal image-patch counting and GlmMoeDsaIndexer torch.split behavior are unrelated." + "reason": "Qwen3-VL weight-shape mismatch and qwen3next missing projections are different model-loading problems." }, { - "left": "issue:43976", - "right": "issue:45071", + "left": "issue:45003", + "right": "issue:45341", "accept": false, - "reason": "Python version incompatibility for Transformers 5.1.0 is unrelated to PreTrainedConfig type checking." + "reason": "Unsafe sys.modules access in modeling_utils is not the same as a testing_utils bug." } ] }, @@ -12177,12 +11944,11 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ - "issue:36683", "issue:38617", "issue:42757", "issue:42886", @@ -12191,19 +11957,20 @@ "issue:43064", "issue:43066", "issue:43097", - "issue:43208", + "issue:43335", "issue:43352", "issue:43381", + "issue:43408", + "issue:43452", "issue:43502", - "issue:43526", "issue:43531", "issue:43550", - "issue:43582", - "issue:43618", "issue:43824", "issue:43825", "issue:43873", + "issue:43874", "issue:43906", + "issue:43931", "issue:43976", "issue:43986", "issue:43992", @@ -12211,27 +11978,35 @@ "issue:44062", "issue:44117", "issue:44261", + "issue:44263", "issue:44315", "issue:44351", "issue:44368", "issue:44380", "issue:44410", - "issue:44483", "issue:44484", "issue:44485", - "issue:44514", "issue:44655", "issue:44704", "issue:44829", + "issue:44987", + "issue:45071", "issue:45103", "issue:45245", "issue:45341", "issue:45372", "issue:45375", - "issue:45479", "issue:45588" ], "soft_pairs": [ + "issue:44117|issue:44987", + "issue:43986|issue:45341", + "issue:43097|issue:43452", + "issue:43931|issue:44038", + "issue:43335|issue:45071", + "issue:43408|issue:44368", + "issue:43874|issue:44263", + "issue:43976|issue:45071", "issue:44829|issue:45245", "issue:43986|issue:45372", "issue:43064|issue:44315", @@ -12239,16 +12014,16 @@ "issue:38617|issue:42757", "issue:44261|issue:44485", "issue:44410|issue:45375", - "issue:38617|issue:44351", "issue:44038|issue:44410", + "issue:38617|issue:44351", "issue:44062|issue:44117", "issue:43097|issue:45588", - "issue:44704|issue:45103", "issue:43986|issue:44117", + "issue:44704|issue:45103", "issue:43502|issue:43992", + "issue:43097|issue:43873", "issue:43992|issue:44484", "issue:43824|issue:43986", - "issue:43097|issue:43873", "issue:43066|issue:43906", "issue:43352|issue:44380", "issue:43825|issue:44655", @@ -12256,242 +12031,234 @@ "issue:43012|issue:44368", "issue:43012|issue:43550", "issue:42886|issue:43381", - "issue:42907|issue:44655", - "issue:43208|issue:43550", - "issue:44380|issue:45479", - "issue:43352|issue:43976", - "issue:43064|issue:44380", - "issue:43208|issue:43526", - "issue:44483|issue:44514", - "issue:43618|issue:44380", - "issue:36683|issue:43582" + "issue:42907|issue:44655" ], - "prepared_review_unit_hash": "7258d997122636c24df91442c53041ca1419bd8d416e83637e6e70a27e798312", + "prepared_review_unit_hash": "4200dc2148cffb64509de27e2126b29db432f7f4a2d0bcec79102b0fa49b932d", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 33, - "serialized_chars": 37568, - "estimated_input_tokens": 9392, - "estimated_eval_tokens": 19040 + "serialized_chars": 37583, + "estimated_input_tokens": 9396, + "estimated_eval_tokens": 19048 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster looks heterogeneous: most items are unrelated model-specific bugs, import failures, tokenizer issues, or backend regressions. I do not see any soft-edge pair that is clearly the same underlying defect/change, so I would keep the issues separate.", - "confidence": 0.92, - "canonical_issue_reason": null, + "summary": "This cluster is heterogeneous: it mixes unrelated Transformers v5 regressions across imports, tokenizer/model loading, multimodal processors, training, and attention backends. None of the proposed soft pairs look like the same underlying bug/change, so no soft edge should be merged.", + "confidence": 0.93, + "canonical_issue_reason": "No single canonical duplicate: the items span many distinct failures and API regressions, so there is no clear one-bug anchor for the whole cluster.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43824 has the strongest activity/inbound signal among the set and a clear user-facing failure, but it still does not explain the rest of the cluster.", + "best_issue_reason": "issue:43097 is the strongest representative because it captures a broad v5 breaking-change regression with clear API impact, but it is still not a duplicate target for the rest of the cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44117", + "right": "issue:44987", + "accept": false, + "reason": "Tokenizer mapping None vs a specific model-loading failure for physical-intelligence/fast; different code paths and symptoms." + }, + { + "left": "issue:43986", + "right": "issue:45341", + "accept": false, + "reason": "Video-model loading without torchvision vs a small testing_utils bug; unrelated components." + }, + { + "left": "issue:43097", + "right": "issue:43452", + "accept": false, + "reason": "Removed config flag in v5 vs gguf_file handling for AutoTokenizer/AutoModel loading; not the same bug." + }, + { + "left": "issue:43931", + "right": "issue:44038", + "accept": false, + "reason": "Different Qwen3-VL model failures: weight-shape mismatch vs a Qwen3-VL-Moe bug." + }, + { + "left": "issue:43335", + "right": "issue:45071", + "accept": false, + "reason": "SwitchTransformers sparse-layer construction bug vs PretrainedConfig type-checking regression; unrelated." + }, + { + "left": "issue:43408", + "right": "issue:44368", + "accept": false, + "reason": "SAM3 video-type warning vs a Qwen3.5 tie_word_embeddings warning; different models and failure modes." + }, + { + "left": "issue:43874", + "right": "issue:44263", + "accept": false, + "reason": "Missing image-processor method in GLM46V vs torch.split return handling in GlmMoeDsaIndexer; unrelated." + }, + { + "left": "issue:43976", + "right": "issue:45071", + "accept": false, + "reason": "Python-version compatibility problem vs config type checking; not the same underlying issue." + }, { "left": "issue:44829", "right": "issue:45245", "accept": false, - "reason": "Different failures: flash-attention training degeneration vs category-cardinality runtime error." + "reason": "Degenerate training with flash_attention_3 vs categorical cardinality limit error; completely different problems." }, { "left": "issue:43986", "right": "issue:45372", "accept": false, - "reason": "Both are loading/import problems, but one is missing torchvision and the other is a mistral_common import regression." + "reason": "Missing torchvision for video processor loading vs mistral_common ReasoningEffort import failure; unrelated." }, { "left": "issue:43064", "right": "issue:44315", "accept": false, - "reason": "Different code paths: optimizer state corruption in FSDP2/PEFT vs Liger Kernel not applied with model_init." + "reason": "FSDP2/PEFT optimizer-state corruption vs Liger Kernel not applied with model_init; different training paths." }, { "left": "issue:43531", "right": "issue:45341", "accept": false, - "reason": "Qwen3-MoE sliding_window bug is unrelated to a testing_utils bug." + "reason": "Qwen3-MoE sliding_window bug vs a testing_utils issue; no shared bug." }, { "left": "issue:38617", "right": "issue:42757", "accept": false, - "reason": "Both are import errors, but for different symbols and different packages." + "reason": "Both are import errors, but for different symbols/modules and unrelated dependency paths." }, { "left": "issue:44261", "right": "issue:44485", "accept": false, - "reason": "MLA norm epsilon precision bug is unrelated to GLM-5 RoPE behavior." + "reason": "MLA q_a_layernorm epsilon/config precision issue vs GLM-5 RoPE implementation; distinct model internals." }, { "left": "issue:44410", "right": "issue:45375", "accept": false, - "reason": "One is missing attention projections, the other is a config field being dropped by strict validation." + "reason": "Missing projections in qwen3next vs missing deepstack_visual_indexes in Qwen3_5MoeVisionConfig; different configs and symptoms." }, { - "left": "issue:38617", - "right": "issue:44351", + "left": "issue:44038", + "right": "issue:44410", "accept": false, - "reason": "Different missing imports: layer_type_validation vs HybridCache." + "reason": "Qwen3-VL-Moe issue vs qwen3next projection bug; different architectures and failures." }, { - "left": "issue:44038", - "right": "issue:44410", + "left": "issue:38617", + "right": "issue:44351", "accept": false, - "reason": "Different Qwen variants and different symptoms; not the same fix." + "reason": "layer_type_validation import error vs HybridCache import error; separate missing exports." }, { "left": "issue:44062", "right": "issue:44117", "accept": false, - "reason": "Tokenizer construction error vs tokenizer mapping None; distinct root causes." + "reason": "AddedToken special-argument conflict vs TOKENIZER_MAPPING_NAMES returning None; different tokenizer code paths." }, { "left": "issue:43097", "right": "issue:45588", "accept": false, - "reason": "Removed config API vs flash_attention AttributeError; unrelated." + "reason": "v5 config removal vs flash_attention sink-less crash; unrelated subsystems." }, { - "left": "issue:44704", - "right": "issue:45103", + "left": "issue:43986", + "right": "issue:44117", "accept": false, - "reason": "AutoProcessor kwarg forwarding bug vs docstring/introspection crash with future annotations." + "reason": "Video processor loading without torchvision vs tokenizer mapping None; unrelated." }, { - "left": "issue:43986", - "right": "issue:44117", + "left": "issue:44704", + "right": "issue:45103", "accept": false, - "reason": "Video-model loading without torchvision is unrelated to tokenizer mapping None." + "reason": "AutoProcessor kwargs not forwarded to cached_file vs auto_docstring crash with future annotations; unrelated utility layers." }, { "left": "issue:43502", "right": "issue:43992", "accept": false, - "reason": "local_files_only network leak vs missing embed token weights during UMT5Encoder loading." + "reason": "local_files_only still causing network requests vs missing embed_tokens.weight in UMT5Encoder; different loading bugs." + }, + { + "left": "issue:43097", + "right": "issue:43873", + "accept": false, + "reason": "API removal in v5 vs offloading/quantization behavior; not the same issue." }, { "left": "issue:43992", "right": "issue:44484", "accept": false, - "reason": "Model weight-loading issue vs save_pretrained sharding-size question." + "reason": "Missing checkpoint weight in UMT5Encoder vs max_shard_size question; unrelated save/load behavior." }, { "left": "issue:43824", "right": "issue:43986", "accept": false, - "reason": "Export/import failure for a model class vs processor loading crash due to missing torchvision." - }, - { - "left": "issue:43097", - "right": "issue:43873", - "accept": false, - "reason": "Config API removal is not the same as quantization offloading behavior." + "reason": "Qwen2_5_VL import error vs video-model loading crash without torchvision; different models and root causes." }, { "left": "issue:43066", "right": "issue:43906", "accept": false, - "reason": "Wrong tokenizer decoder type and a separate reproduction issue are not the same bug." + "reason": "Wrong tokenizer decoder type vs an isolated reproduction of a separate issue; no concrete shared bug." }, { "left": "issue:43352", "right": "issue:44380", "accept": false, - "reason": "Unsupported FlashAttention for Nemotron is different from GPT2 attention scaling being ignored." + "reason": "Flash Attention 2 unsupported gate vs GPT2 attention-scaling ignored under SDPA/FlashAttention; different backend problems." }, { "left": "issue:43825", "right": "issue:44655", "accept": false, - "reason": "Error-message wording for translation tasks is unrelated to pipeline save_pretrained support." + "reason": "Pipeline translation-task error vs inability to save Pipeline objects; different pipeline concerns." }, { "left": "issue:38617", "right": "issue:43097", "accept": false, - "reason": "Different regressions: one missing import, one removed config attribute/API." + "reason": "ImportError for layer_type_validation vs removed tie_embeddings_and_encoder_decoder; unrelated regressions." }, { "left": "issue:43012", "right": "issue:44368", "accept": false, - "reason": "Compile warning on bfloat16 is unrelated to tie_word_embeddings warning." + "reason": "bfloat16 compile warning vs tie_word_embeddings warning during Qwen3.5 LoRA; same general warning category, but not the same bug." }, { "left": "issue:43012", "right": "issue:43550", "accept": false, - "reason": "A warning about precision differs from a model correctness bug under torch.compile + SDPA." + "reason": "PyTorch precision warning during compile vs Bamba SDPA compile failure; different failure modes." }, { "left": "issue:42886", "right": "issue:43381", "accept": false, - "reason": "Offline cache loading and gradient-checkpointing-in-eval are unrelated." + "reason": "Offline tokenizer cache loading vs gradient checkpointing in eval mode; unrelated." }, { "left": "issue:42907", "right": "issue:44655", "accept": false, - "reason": "Saving dequantized models is a different problem from saving Pipeline objects." - }, - { - "left": "issue:43208", - "right": "issue:43550", - "accept": false, - "reason": "xLSTM training blockers are unrelated to Bamba compile/SDPA failure." - }, - { - "left": "issue:44380", - "right": "issue:45479", - "accept": false, - "reason": "Attention scaling backend bug is unrelated to zero-loss sequence classification." - }, - { - "left": "issue:43352", - "right": "issue:43976", - "accept": false, - "reason": "Model-specific attention support bug vs Python version compatibility issue." - }, - { - "left": "issue:43064", - "right": "issue:44380", - "accept": false, - "reason": "Distributed optimizer-state corruption is unrelated to GPT2 attention scaling." - }, - { - "left": "issue:43208", - "right": "issue:43526", - "accept": false, - "reason": "xLSTM training issues do not match the BeitImageProcessorFast label reduction bug." - }, - { - "left": "issue:44483", - "right": "issue:44514", - "accept": false, - "reason": "Chat-completions request rejection and batched chat-template crash are different surfaces and likely different fixes." - }, - { - "left": "issue:43618", - "right": "issue:44380", - "accept": false, - "reason": "CLIPOutput attentions assignment regression is unrelated to GPT2 attention scaling." - }, - { - "left": "issue:36683", - "right": "issue:43582", - "accept": false, - "reason": "Gemma3Config vocab_size AttributeError has nothing to do with Apple Silicon allocator warmup TypeError." + "reason": "Failed save of dequantized Ministrals vs saving Pipeline objects; both involve save_pretrained, but distinct object types and causes." } ] }, @@ -12510,26 +12277,28 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:36010", "issue:36683", "issue:38617", - "issue:41669", "issue:42757", "issue:42994", - "issue:43010", "issue:43012", "issue:43064", "issue:43066", + "issue:43208", "issue:43299", "issue:43352", "issue:43475", "issue:43502", "issue:43525", + "issue:43526", + "issue:43550", + "issue:43582", "issue:43618", "issue:43756", "issue:43761", @@ -12544,26 +12313,33 @@ "issue:44188", "issue:44230", "issue:44242", - "issue:44246", "issue:44263", "issue:44380", "issue:44483", "issue:44485", "issue:44492", + "issue:44514", "issue:44655", "issue:44683", "issue:44938", "issue:45216", - "issue:45278", "issue:45290", "issue:45310", - "issue:45375", "issue:45381", "issue:45440", "issue:45478", + "issue:45479", "issue:45593" ], "soft_pairs": [ + "issue:43208|issue:43550", + "issue:44380|issue:45479", + "issue:43352|issue:43976", + "issue:43064|issue:44380", + "issue:43208|issue:43526", + "issue:44483|issue:44514", + "issue:43618|issue:44380", + "issue:36683|issue:43582", "issue:43618|issue:43761", "issue:43012|issue:44683", "issue:44483|issue:45290", @@ -12572,13 +12348,13 @@ "issue:44483|issue:45381", "issue:43299|issue:43867", "issue:38617|issue:43502", + "issue:43901|issue:44655", "issue:43756|issue:44485", "issue:42994|issue:44655", - "issue:43901|issue:44655", "issue:43867|issue:45216", "issue:36683|issue:43475", - "issue:43352|issue:43937", "issue:44655|issue:45478", + "issue:43352|issue:43937", "issue:43066|issue:45381", "issue:44077|issue:44380", "issue:43064|issue:44492", @@ -12591,249 +12367,253 @@ "issue:43618|issue:45216", "issue:43352|issue:45593", "issue:43992|issue:45310", - "issue:36683|issue:44242", - "issue:43010|issue:45278", - "issue:36683|issue:43352", - "issue:41669|issue:44246", - "issue:43867|issue:45375", - "issue:36683|issue:43064" + "issue:36683|issue:44242" ], - "prepared_review_unit_hash": "a11efddf41576518676cffc600af291b88d81ffe14ba76df21819670472c5604", + "prepared_review_unit_hash": "868e9c0ac85c00d2176448438500caf85a0fa5280a7fb9b3d4a3ae0bfa1c11a8", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 33, - "serialized_chars": 36545, - "estimated_input_tokens": 9137, - "estimated_eval_tokens": 18530 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 36, + "serialized_chars": 38123, + "estimated_input_tokens": 9531, + "estimated_eval_tokens": 19318 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous: many are distinct Transformers regressions around model configs, loading/saving, chat templates, and backend-specific behavior. Only one soft pair looks like a plausible duplicate; the rest are too symptom- or model-specific to merge safely.", - "confidence": 0.84, - "canonical_issue_reason": "Issue 45278 is the broadest umbrella in the set: it captures the general import-regression theme better than the many model-specific bug reports.", + "summary": "Mostly unrelated Transformers issues; the only clear duplicate pair is the Qwen3.5 MoE from_pretrained regression. No pull requests were present.", + "confidence": 0.89, + "canonical_issue_reason": "issue:45310 is the earlier, more specific report of the shared Qwen3.5 MoE from_pretrained failure, and issue:45478 reads as a later duplicate of the same version-regression.", "canonical_pr_reason": null, - "best_issue_reason": "45278 is the best representative issue for the cluster overall because it is the most general user-facing regression report among otherwise unrelated failures.", + "best_issue_reason": "issue:45310 is the best cluster representative because it captures the concrete bug shape and version scope most clearly, with a near-identical follow-up report duplicating it.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43208", + "right": "issue:43550", + "accept": false, + "reason": "Different models and failure modes: xLSTM training bugs vs Bamba torch.compile/SDPA issue." + }, + { + "left": "issue:44380", + "right": "issue:45479", + "accept": false, + "reason": "Both are model bugs, but one is GPT-2 attention scaling and the other is a sequence-classification zero-loss bug; different code paths." + }, + { + "left": "issue:43352", + "right": "issue:43976", + "accept": false, + "reason": "Unrelated problems: Flash Attention 2 support for Nemotron vs Python-version compatibility." + }, + { + "left": "issue:43064", + "right": "issue:44380", + "accept": false, + "reason": "FSDP2 optimizer-state corruption is unrelated to GPT-2 attention scaling under SDPA/FlashAttention." + }, + { + "left": "issue:43208", + "right": "issue:43526", + "accept": false, + "reason": "xLSTM training bugs and BeitImageProcessorFast label reduction are different subsystems and symptoms." + }, + { + "left": "issue:44483", + "right": "issue:44514", + "accept": false, + "reason": "Both touch chat-related APIs, but one is request acceptance and the other is batched chat template padding behavior." + }, + { + "left": "issue:43618", + "right": "issue:44380", + "accept": false, + "reason": "CLIP output attentions regression is not the same bug as GPT-2 attention scaling being ignored." + }, + { + "left": "issue:36683", + "right": "issue:43582", + "accept": false, + "reason": "Gemma3Config missing vocab_size and Apple Silicon allocator TypeError are unrelated." + }, { "left": "issue:43618", "right": "issue:43761", "accept": false, - "reason": "Both are CLIP regressions, but one is about attentions and the other about hidden_states; different failure modes." + "reason": "Both involve CLIP regressions, but one is missing attentions assignment and the other is hidden_states=None; not the same defect." }, { "left": "issue:43012", "right": "issue:44683", "accept": false, - "reason": "One is a bfloat16 precision warning during compile, the other is a flex_attention compile failure on newer torch." + "reason": "A warning about bf16 precision is distinct from a compiled flex_attention failure on torch>=2.9." }, { "left": "issue:44483", "right": "issue:45290", "accept": false, - "reason": "Different code paths: chat-completions request validation vs apply_chat_template crashing on tool-call messages." + "reason": "Different chat-template/API failures: request validation vs assistant tool-call content handling." }, { "left": "issue:44038", "right": "issue:44230", "accept": false, - "reason": "Same model family, but one is a v5 loading bug and the other is fp8 inference support; not the same bug." + "reason": "Both mention Qwen VL/MoE, but one is broad v5 loading support and the other is fp8 inference support; different requests." }, { "left": "issue:42757", "right": "issue:43824", "accept": false, - "reason": "Both are import errors, but they reference different missing symbols from different packages." + "reason": "Both are import errors, but for different missing symbols and likely different fixes." }, { "left": "issue:44483", "right": "issue:45381", "accept": false, - "reason": "Unrelated issues: API request acceptance vs Qwen2.5-VL video position ids." + "reason": "Chat/completions request handling is unrelated to Qwen2.5-VL vision_position_ids generation." }, { "left": "issue:43299", "right": "issue:43867", "accept": false, - "reason": "Qwen3-VL-Moe loading breakage and sorted-state_dict load error are different loading problems." + "reason": "Qwen3VL-Moe loading breakage and sorted-state_dict load error are not the same underlying issue." }, { "left": "issue:38617", "right": "issue:43502", "accept": false, - "reason": "ImportError for a removed helper is unrelated to local_files_only still making network requests." + "reason": "ImportError from configuration_utils and local_files_only network leakage are different bug classes." + }, + { + "left": "issue:43901", + "right": "issue:44655", + "accept": false, + "reason": "Documentation mismatch for return_all_scores is unrelated to saving Pipeline objects." }, { "left": "issue:43756", "right": "issue:44485", "accept": false, - "reason": "Both mention RoPE, but they concern different models and different implementation defects." + "reason": "Smollm3 RoPE layer dropout and GLM-5 RoPE implementation discussion are different model-specific issues." }, { "left": "issue:42994", "right": "issue:44655", "accept": false, - "reason": "Quantized model saving and Pipeline.save_pretrained are separate save-path issues." - }, - { - "left": "issue:43901", - "right": "issue:44655", - "accept": false, - "reason": "Docs mismatch for return_all_scores is unrelated to Pipeline serialization failure." + "reason": "Quantized model saving failure is not the same as Pipeline save_pretrained serialization failure." }, { "left": "issue:43867", "right": "issue:45216", "accept": false, - "reason": "Both involve checkpoints, but one is a load error from state_dict ordering and the other is a save_pretrained regression." + "reason": "Both concern loading/saving, but one is sorted state_dict loading and the other is Qwen3.5 checkpoint correctness on save_pretrained." }, { "left": "issue:36683", "right": "issue:43475", "accept": false, - "reason": "Different missing attributes on different model configs/outputs; not the same underlying bug." + "reason": "Gemma3Config missing vocab_size and Sam3VisionEncoderOutput missing fpn_position_embeddings are different attribute errors." }, { - "left": "issue:43352", - "right": "issue:43937", + "left": "issue:44655", + "right": "issue:45478", "accept": false, - "reason": "Flash-Attention support limitation and invalid GenerationConfig are unrelated." + "reason": "Pipeline serialization and Qwen3.5 MoE from_pretrained are unrelated." }, { - "left": "issue:44655", - "right": "issue:45478", + "left": "issue:43352", + "right": "issue:43937", "accept": false, - "reason": "Pipeline saving and Qwen3.5 MoE loading errors are different lifecycle stages and different failures." + "reason": "Flash Attention support for Nemotron and GLM-5 GenerationConfig validation are different issues." }, { "left": "issue:43066", "right": "issue:45381", "accept": false, - "reason": "Tokenizer decoder type regression is unrelated to Qwen2.5-VL video position ids." + "reason": "Tokenizer decoder type mismatch is unrelated to Qwen2.5-VL video position IDs." }, { "left": "issue:44077", "right": "issue:44380", "accept": false, - "reason": "Different subsystems: patchtsmixer post_init validation vs GPT2 attention scaling under SDPA/FlashAttention." + "reason": "A patchtsmixer post_init policy issue is unrelated to GPT-2 attention scaling under SDPA/FlashAttention." }, { "left": "issue:43064", "right": "issue:44492", "accept": false, - "reason": "Distributed optimizer-state corruption is unrelated to a cache-strategy typo." + "reason": "Optimizer-state corruption and a typo in cache strategies are not the same bug." }, { "left": "issue:44263", "right": "issue:45440", "accept": false, - "reason": "torch.split behavior in an indexer and DeepSeekV3MoE divergence are different code paths." + "reason": "Different MoE-related code paths and models; not the same concrete defect." }, { "left": "issue:43976", "right": "issue:44938", "accept": false, - "reason": "Both are Python-version compatibility reports, but for different versions and likely different root causes." - }, - { - "left": "issue:36683", - "right": "issue:44077", - "accept": false, - "reason": "Gemma3 config attribute loss is unrelated to patchtsmixer post_init handling." - }, - { - "left": "issue:36683", - "right": "issue:43525", - "accept": false, - "reason": "Both are missing config fields, but they affect different models and different attributes." - }, - { - "left": "issue:36010", - "right": "issue:42757", - "accept": false, - "reason": "Both are import errors, but for different exports and different failure causes." - }, - { - "left": "issue:44188", - "right": "issue:44380", - "accept": false, - "reason": "Different attention/backend issues; one is kernel divergence under compile, the other ignores scaling config under SDPA/FlashAttention." + "reason": "Both are environment compatibility reports, but for different Python versions and failure causes." }, { "left": "issue:43618", "right": "issue:45216", "accept": false, - "reason": "CLIP output regression and Qwen3.5 save_pretrained regression are unrelated." + "reason": "CLIP attentions regression and Qwen3.5 save_pretrained corruption are unrelated." }, { "left": "issue:43352", "right": "issue:45593", "accept": false, - "reason": "Flash-Attention support limitation is unrelated to missing auxiliary losses when denoising is off." + "reason": "Flash Attention support for Nemotron and D-FINE auxiliary-loss logic are different subsystems." }, { "left": "issue:43992", "right": "issue:45310", "accept": false, - "reason": "Different models and different from_pretrained failures; not the same bug." + "reason": "UMT5 missing embed_tokens.weight and Qwen3.5 MoE from_pretrained are unrelated model-loading bugs." }, { "left": "issue:36683", "right": "issue:44242", "accept": false, - "reason": "Missing vocab_size on Gemma3Config is unrelated to load-balancing loss being skipped." - }, - { - "left": "issue:43010", - "right": "issue:45278", - "accept": false, - "reason": "Cache update no_grad decoration is unrelated to generic import errors after upgrade." - }, - { - "left": "issue:36683", - "right": "issue:43352", - "accept": false, - "reason": "Missing config field on Gemma3Config and Flash-Attention support on Nemotron are unrelated." + "reason": "Gemma3Config attribute error and missing load-balancing loss are different problems." }, { - "left": "issue:41669", - "right": "issue:44246", + "left": "issue:45310", + "right": "issue:45478", "accept": true, - "reason": "Both point to import-time slowdown; the generic 'import transformers takes long' report matches the import-* regression." + "reason": "Same concrete Qwen3.5 MoE from_pretrained failure with the same version regression; these look like duplicates that one fix could resolve together." }, { - "left": "issue:43867", - "right": "issue:45375", + "left": "issue:44188", + "right": "issue:44380", "accept": false, - "reason": "A sorted-state_dict loading error is unrelated to a missing config field in Qwen3_5MoeVisionConfig." + "reason": "Both involve attention/compile behavior, but one is divergent kernels from branching under torch.compile and the other is scaling config being ignored in backend selection." }, { - "left": "issue:36683", - "right": "issue:43064", + "left": "issue:36010", + "right": "issue:42757", "accept": false, - "reason": "Config attribute absence and distributed optimizer-state corruption are unrelated." + "reason": "Both are import errors, but for different exports from different modules and no shared concrete bug path." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative about the soft edges. The single accepted pair (41669/44246) is reasonably supported as an import-time slowdown regression, and the rest of the false verdicts do not overstate duplicate evidence." - }, - "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 }, @@ -12845,22 +12625,23 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:28282", - "issue:30333", - "issue:30990", - "issue:31795", "issue:33453", "issue:36296", + "issue:36683", + "issue:41669", "issue:42548", "issue:42890", "issue:43010", + "issue:43064", "issue:43065", "issue:43232", + "issue:43352", "issue:43502", "issue:43575", "issue:43618", @@ -12873,22 +12654,21 @@ "issue:44077", "issue:44112", "issue:44222", - "issue:44315", + "issue:44246", "issue:44351", "issue:44355", "issue:44360", - "issue:44368", "issue:44387", "issue:44484", "issue:44485", "issue:44556", "issue:44749", "issue:44857", - "issue:44871", "issue:44938", "issue:44964", "issue:45071", "issue:45125", + "issue:45278", "issue:45341", "issue:45357", "issue:45375", @@ -12900,6 +12680,11 @@ "issue:45600" ], "soft_pairs": [ + "issue:43010|issue:45278", + "issue:36683|issue:43352", + "issue:41669|issue:44246", + "issue:43867|issue:45375", + "issue:36683|issue:43064", "issue:42890|issue:45561", "issue:43992|issue:45478", "issue:44938|issue:45071", @@ -12917,8 +12702,8 @@ "issue:42890|issue:45600", "issue:42890|issue:44112", "issue:43010|issue:44075", - "issue:43723|issue:44556", "issue:43502|issue:44062", + "issue:43723|issue:44556", "issue:42890|issue:45341", "issue:44222|issue:45125", "issue:44387|issue:44556", @@ -12926,260 +12711,248 @@ "issue:43010|issue:43232", "issue:42548|issue:44351", "issue:45125|issue:45478", - "issue:45125|issue:45375", "issue:44355|issue:44749", - "issue:43502|issue:44485", - "issue:30990|issue:31795", - "issue:44075|issue:44871", - "issue:44315|issue:44360", - "issue:30333|issue:33453", - "issue:43010|issue:44368", - "issue:43502|issue:44222" + "issue:45125|issue:45375", + "issue:43502|issue:44485" ], - "prepared_review_unit_hash": "8aecbf51f0f43eea1ce7ce406ce0287bd43b85baa17d16468d86118abdbc5653", + "prepared_review_unit_hash": "bc45c234b685a155e7aad7879932f23317729e6cea89d949a042066af2ea63f3", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 35, - "serialized_chars": 37752, - "estimated_input_tokens": 9438, - "estimated_eval_tokens": 19132 + "soft_pair_count": 34, + "serialized_chars": 37341, + "estimated_input_tokens": 9336, + "estimated_eval_tokens": 18928 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly unrelated issues spanning model loading, testing, quantization, and config/export regressions. The only strong duplicate-like edge is the Qwen3.5-MoE tensor-parallel load path, where a missing `_tp_plan` plausibly explains the later generic `from_pretrained` failure.", - "confidence": 0.64, - "canonical_issue_reason": "issue:45125 is the most specific root-cause report: it names the missing `_tp_plan` on `Qwen3_5MoeForConditionalGeneration`, which likely explains the broader `from_pretrained` error in the later Qwen3.5-MoE report.", + "summary": "The set is mostly a grab bag of unrelated Transformers issues. The only clear soft duplicate is the import-time slowdown pair; most other pairs share a subsystem or release version but not the same concrete bug.", + "confidence": 0.6, + "canonical_issue_reason": "issue:41669 is the most concrete root-cause report for the import slowdown; issue:44246 is the vaguer symptom report and fits as the duplicate.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45125 is the clearest, most actionable representative of the Qwen3.5-MoE load failure because it identifies the concrete code-path defect rather than just the symptom.", + "best_issue_reason": "issue:41669 is the best representative because it identifies the specific cause and is actionable, unlike the broader symptom-only report.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43010", + "right": "issue:45278", + "accept": false, + "reason": "Both touch import/generation ergonomics, but one is a cache no_grad concern and the other is a broad import-regression report; different bugs." + }, + { + "left": "issue:36683", + "right": "issue:43352", + "accept": false, + "reason": "Gemma3 config vocab_size and Nemotron flash-attn support are unrelated model-specific failures." + }, + { + "left": "issue:41669", + "right": "issue:44246", + "accept": true, + "reason": "Both describe the same import-time slowdown; 41669 gives the concrete cause (model import *) and 44246 reports the symptom." + }, + { + "left": "issue:43867", + "right": "issue:45375", + "accept": false, + "reason": "One is a state_dict loading error, the other is a Qwen3.5 vision config field being dropped; not the same code path." + }, + { + "left": "issue:36683", + "right": "issue:43064", + "accept": false, + "reason": "Different failures: missing Gemma3Config attribute vs FSDP2/PEFT optimizer-state mismatch." + }, { "left": "issue:42890", "right": "issue:45561", "accept": false, - "reason": "Both are test/CI-related, but one is a missing `set_seed()` in SamHQ tests and the other is a pytest-xdist file race; different bugs and code paths." + "reason": "Both are test-related, but one is missing set_seed coverage and the other is an xdist file race; distinct bugs." }, { "left": "issue:43992", "right": "issue:45478", "accept": false, - "reason": "Different model families and failures: UMT5 missing `embed_tokens.weight` vs Qwen3.5-MoE `from_pretrained` error." + "reason": "Different Qwen/UMT5 load failures with different symptoms and likely different causes." }, { "left": "issue:44938", "right": "issue:45071", "accept": false, - "reason": "Python 3.14 import/load failure is unrelated to a v5.4.0 type-checking regression in `PretrainedConfig`." + "reason": "Both are version-related regressions, but one is Python 3.14 loading and the other is PretrainedConfig type checking." }, { "left": "issue:43867", "right": "issue:45357", "accept": false, - "reason": "One is a sorted-state-dict load error; the other is incorrect visual encoder keys being saved. Related to loading/saving, but not the same bug." + "reason": "A state_dict sorting/load issue is not the same as incorrect visual encoder keys in save_pretrained." }, { "left": "issue:43010", "right": "issue:43976", "accept": false, - "reason": "`@torch.no_grad` on cache/layer updates is unrelated to a Python version compatibility problem." + "reason": "No-no_grad cache update and Python-version support failure are unrelated." }, { "left": "issue:44938", "right": "issue:45381", "accept": false, - "reason": "A Python 3.14 load failure is not the same as the Qwen2.5-VL `vision_position_ids` bug." + "reason": "Python 3.14 import/load failure and Qwen2.5-VL video position ids are different problems." }, { "left": "issue:44360", "right": "issue:45440", "accept": false, - "reason": "Different algorithmic issues: DSA indexer activation choice vs DeepseekV3MoE implementation divergence." + "reason": "DSA indexer/ReLU discussion and DeepSeekV3MoE divergence are unrelated model implementation issues." }, { "left": "issue:43618", "right": "issue:44077", "accept": false, - "reason": "CLIPOutput attentions regression and PatchTSMixer `post_init` validation are unrelated." + "reason": "CLIPOutput attentions and patchtsmixer post_init policy do not match the same bug." }, { "left": "issue:36296", "right": "issue:43575", "accept": false, - "reason": "Both mention tensor parallelism, but one is a training bug and the other is an OOM on model load; not the same concrete defect." + "reason": "Tensor-parallel training bug vs TP OOM on loading a large model: related area, but not the same underlying issue." }, { "left": "issue:43867", "right": "issue:44484", "accept": false, - "reason": "Model load failure from sorted state dict is unrelated to the `max_shard_size` documentation/default question." + "reason": "Loading error from sorted state_dict is unrelated to max_shard_size behavior in save_pretrained." }, { "left": "issue:43618", "right": "issue:45588", "accept": false, - "reason": "CLIPOutput attentions regression and flash-attention `s_aux=None` crash are separate code paths." + "reason": "Different crash sites and causes: CLIP attentions vs flash_attention on sink-less models." }, { "left": "issue:43618", "right": "issue:44857", "accept": false, - "reason": "CLIPOutput attentions regression is unrelated to LwDetrImageLoss AMP/CUDA crashing." + "reason": "Different issues in different code paths; not duplicates." }, { "left": "issue:28282", "right": "issue:33453", "accept": false, - "reason": "PyTorch-missing import error and tokenizer-loading regression are different problems." + "reason": "AutoModel PyTorch import error and tokenizer loading regression are unrelated." }, { "left": "issue:42890", "right": "issue:44964", "accept": false, - "reason": "A flaky integration test due to missing seed is not the same as a Phi-4 multimodal model load failure." + "reason": "Test seeding failures and Phi-4 multimodal model loading are unrelated." }, { "left": "issue:42890", "right": "issue:45600", "accept": false, - "reason": "Test seeding flakiness and stale auto-mapping references are different issues." + "reason": "A test seeding problem is not the same as stale auto_mappings references breaking CI." }, { "left": "issue:42890", "right": "issue:44112", "accept": false, - "reason": "Both are CI/test-related, but they affect different tests and have different failure causes." + "reason": "Both are CI/test failures, but the specific causes differ." }, { "left": "issue:43010", "right": "issue:44075", "accept": false, - "reason": "`no_grad` decoration for cache updates is unrelated to SGD argument handling." + "reason": "Cache update no_grad and SGD args ignored are different behavior bugs." }, { - "left": "issue:43723", - "right": "issue:44556", + "left": "issue:43502", + "right": "issue:44062", "accept": false, - "reason": "Tokenizer-loading issues and checkpoint reloading after version upgrade are distinct load paths and likely different root causes." + "reason": "Offline download enforcement and AddedToken argument handling are unrelated tokenizer/loading issues." }, { - "left": "issue:43502", - "right": "issue:44062", + "left": "issue:43723", + "right": "issue:44556", "accept": false, - "reason": "`local_files_only=True` still making requests is unrelated to `AddedToken(..., special=...)` argument duplication." + "reason": "Tokenizer loading in v5 and checkpoint reload incompatibility after upgrade are not the same concrete bug." }, { "left": "issue:42890", "right": "issue:45341", "accept": false, - "reason": "A missing seed in one test file and a generic testing_utils bug are not the same bug." + "reason": "Missing set_seed in tests and a testing_utils bug are too different without clearer evidence." }, { "left": "issue:44222", "right": "issue:45125", "accept": false, - "reason": "FP8 `save_pretrained` for MoE and missing `_tp_plan` for tensor parallelism are different defects." + "reason": "FP8 save_pretrained for MoE and missing _tp_plan for Qwen3_5Moe are different features/failures." }, { "left": "issue:44387", "right": "issue:44556", "accept": false, - "reason": "Int4 quantization memory growth and checkpoint reload compatibility after upgrade are different problems." + "reason": "Quantization memory OOM and checkpoint reload incompatibility are unrelated." }, { "left": "issue:43010", "right": "issue:43065", "accept": false, - "reason": "Cache/layer update decoration and a dummy `nn.Conv2d` in Sam3PixelDecoder are unrelated." + "reason": "Cache/layer no_grad and Sam3PixelDecoder dummy Conv2d are unrelated implementation issues." }, { "left": "issue:43010", "right": "issue:43232", "accept": false, - "reason": "Both mention update logic, but one is about `torch.no_grad` on cache updates and the other about generation kwargs after `sync_gpus`; not the same failure." + "reason": "Generic generation kwargs handling and cache update no_sync behavior are different bugs." }, { "left": "issue:42548", "right": "issue:44351", "accept": false, - "reason": "Separate import/export regressions: `PreTrainedModel` vs `HybridCache`." + "reason": "Cannot import PreTrainedModel and cannot import HybridCache are distinct import/export regressions." }, { "left": "issue:45125", "right": "issue:45478", - "accept": true, - "reason": "Same Qwen3.5-MoE loading path; the later generic `from_pretrained` error plausibly stems from the missing `_tp_plan` tensor-parallel definition named in 45125." - }, - { - "left": "issue:45125", - "right": "issue:45375", "accept": false, - "reason": "Missing `_tp_plan` for the model class and missing `deepstack_visual_indexes` in config are different schema/code issues." + "reason": "Both involve Qwen3.5 MoE, but one is tensor-parallel metadata and the other is a from_pretrained loading error." }, { "left": "issue:44355", "right": "issue:44749", "accept": false, - "reason": "Compiled Python file errors and slow filtering after upgrading from 4.57.3 to 5.3.0 are unrelated." - }, - { - "left": "issue:43502", - "right": "issue:44485", - "accept": false, - "reason": "Offline API requests and GLM-5 RoPE implementation discussion are different concerns." - }, - { - "left": "issue:30990", - "right": "issue:31795", - "accept": false, - "reason": "Sentence-transformer loading hang and documentation confusion in `model.forward` are unrelated." + "reason": "Compiled Python file errors and a performance regression after upgrade are not the same issue." }, { - "left": "issue:44075", - "right": "issue:44871", - "accept": false, - "reason": "Unused SGD args and Gemma-3 EOS token config mismatch are different issues." - }, - { - "left": "issue:44315", - "right": "issue:44360", - "accept": false, - "reason": "Liger Kernel not applied in `model_init` and DSA indexer lacking ReLU are unrelated." - }, - { - "left": "issue:30333", - "right": "issue:33453", - "accept": false, - "reason": "MLFlow reporting on failed training jobs is not the same as tokenizer-loading regression." - }, - { - "left": "issue:43010", - "right": "issue:44368", + "left": "issue:45125", + "right": "issue:45375", "accept": false, - "reason": "Cache/layer `no_grad` decoration and a Qwen3.5 LoRA warning about `tie_word_embeddings` are unrelated." + "reason": "Missing _tp_plan and missing deepstack_visual_indexes are different Qwen3.5 model/config problems." }, { "left": "issue:43502", - "right": "issue:44222", + "right": "issue:44485", "accept": false, - "reason": "Offline request leakage and FP8 MoE save behavior are separate bugs." + "reason": "Offline API blocking and GLM-5 RoPE implementation are unrelated." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays appropriately cautious. The accepted Qwen3.5-MoE pair is the only clearly duplicate-like edge, and the rejection reasons for the other pairs are conservative rather than overconfident. No PR-mergeability issue applies here since these are issue pairs, not PR pairs." + "feedback": "The summary is grounded in the packet and stays conservative. The only accepted soft edge, issue:41669 vs issue:44246, is well supported by the titles and the import-slowdown theme. The remaining rejections read as cautious and do not overclaim duplicates. No mergeability concerns apply since these are issue pairs, not PR pairs." }, "evaluator_used": true, "retried": false, @@ -13195,12 +12968,13 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:30333", + "issue:30990", "issue:31795", "issue:33453", "issue:34689", @@ -13208,11 +12982,10 @@ "issue:38617", "issue:41628", "issue:41669", - "issue:42371", "issue:42548", "issue:42757", "issue:42831", - "issue:42890", + "issue:43010", "issue:43299", "issue:43502", "issue:43526", @@ -13223,152 +12996,190 @@ "issue:43874", "issue:43901", "issue:44038", + "issue:44075", "issue:44222", "issue:44230", - "issue:44246", "issue:44261", "issue:44273", + "issue:44315", "issue:44351", "issue:44355", "issue:44360", + "issue:44368", "issue:44393", "issue:44485", "issue:44492", "issue:44556", "issue:44623", "issue:44655", - "issue:44704", + "issue:44871", "issue:44908", "issue:44961", "issue:45003", "issue:45071", - "issue:45092", "issue:45125", "issue:45230", "issue:45468", "issue:45542" ], "soft_pairs": [ + "issue:30990|issue:31795", + "issue:44075|issue:44871", + "issue:44315|issue:44360", + "issue:30333|issue:33453", + "issue:43010|issue:44368", + "issue:43502|issue:44222", "issue:43299|issue:44556", "issue:43502|issue:44961", "issue:44222|issue:44230", - "issue:30333|issue:36296", "issue:44355|issue:44655", + "issue:30333|issue:36296", "issue:44355|issue:45071", "issue:42831|issue:43874", - "issue:42757|issue:43576", "issue:33453|issue:34689", + "issue:42757|issue:43576", "issue:33453|issue:36296", "issue:43827|issue:44961", "issue:43576|issue:45071", "issue:43576|issue:43824", - "issue:43673|issue:44492", "issue:38617|issue:43576", + "issue:43673|issue:44492", "issue:44961|issue:45468", "issue:31795|issue:38617", "issue:43576|issue:44351", - "issue:44908|issue:44961", "issue:41628|issue:42548", + "issue:44908|issue:44961", "issue:44485|issue:44961", "issue:36296|issue:43901", "issue:36296|issue:43526", "issue:41628|issue:44355", "issue:44273|issue:45003", "issue:44261|issue:44360", - "issue:44273|issue:45542", "issue:44623|issue:45230", + "issue:44273|issue:45542", "issue:43576|issue:44556", "issue:44038|issue:45125", "issue:44393|issue:45071", - "issue:41669|issue:43673", - "issue:44556|issue:45092", - "issue:42371|issue:44492", - "issue:42890|issue:44908", - "issue:44704|issue:44908", - "issue:44246|issue:44273" + "issue:41669|issue:43673" ], - "prepared_review_unit_hash": "b8641747c94b0e1aa22da41759ad88c1c4779c3855e086682d3e496d94596712", + "prepared_review_unit_hash": "43c46936dabf8bac77d0fe6b71c11ebd2f6c5deb41751d62bc61df348f5c09ed", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 37, - "serialized_chars": 37441, - "estimated_input_tokens": 9361, - "estimated_eval_tokens": 18978 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 38, + "serialized_chars": 38352, + "estimated_input_tokens": 9588, + "estimated_eval_tokens": 19432 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a loose collection of Transformers issues around v5 compatibility, import/loading regressions, and model-specific bugs. They are thematically similar but generally not the same underlying defect.", - "confidence": 0.56, - "canonical_issue_reason": "Issue 44556 is the clearest broad, user-facing regression: reloading checkpoints trained on v4.57 fails after upgrading to v5.2/v5.3. It best represents the cluster\u2019s recurring v5 loading/compatibility theme.", + "summary": "This cluster is highly heterogeneous: it mixes unrelated import errors, model-loading regressions, docs issues, cache/FP8/tensor-parallel bugs, and CLI/runtime problems. I don\u2019t see any safe duplicate merges, and there are no PRs to evaluate.", + "confidence": 0.19, + "canonical_issue_reason": "If forced to pick one, issue 43576 is the broadest v5 regression-style report and the closest thing to a generic umbrella issue, but it does not \u05d1\u05d0\u05de\u05ea subsume the rest of the cluster.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 44556 is the most representative and broadly applicable problem in the set, with explicit version scope and concrete loading failure. It is a better cluster anchor than the more niche import/model-specific reports.", + "best_issue_reason": "Issue 43576 is the best single representative only because it is broad and version-gated; however, the overall set is too mixed for a strong canonical issue.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:30990", + "right": "issue:31795", + "accept": false, + "reason": "Unrelated symptoms: a loading hang vs documentation confusion about model.forward arguments." + }, + { + "left": "issue:44075", + "right": "issue:44871", + "accept": false, + "reason": "Different bugs in different areas: SGD optimizer arguments vs Gemma EOS token configuration." + }, + { + "left": "issue:44315", + "right": "issue:44360", + "accept": false, + "reason": "Liger Kernel application bug and DSA indexer ReLU complaint are unrelated." + }, + { + "left": "issue:30333", + "right": "issue:33453", + "accept": false, + "reason": "MLflow job-status reporting and tokenizer loading regression are different code paths." + }, + { + "left": "issue:43010", + "right": "issue:44368", + "accept": false, + "reason": "Cache update no_grad issue is unrelated to tie_word_embeddings warnings." + }, + { + "left": "issue:43502", + "right": "issue:44222", + "accept": false, + "reason": "local_files_only network leakage and FP8 save_pretrained are separate failures." + }, { "left": "issue:43299", "right": "issue:44556", "accept": false, - "reason": "Both mention v5 loading breakage, but one is Qwen3VL MoE model loading and the other is generic checkpoint reload failure; no evidence they share the same code path." + "reason": "Both are loading regressions, but they involve different models and failure modes; not the same concrete bug." }, { "left": "issue:43502", "right": "issue:44961", "accept": false, - "reason": "Local-files-only network leakage and a meaningless 'racoon' report are unrelated." + "reason": "API requests despite local_files_only is unrelated to the racoon issue." }, { "left": "issue:44222", "right": "issue:44230", "accept": false, - "reason": "FP8 save_pretrained behavior and FP8 inference support for Qwen3-VL/Qwen3.5 MoE are different issues and likely different code paths." + "reason": "Same FP8/MoE theme, but one is save_pretrained behavior and the other is inference support; too different to merge." }, { - "left": "issue:30333", - "right": "issue:36296", + "left": "issue:44355", + "right": "issue:44655", "accept": false, - "reason": "MLflow reporting on failed training jobs is unrelated to a tensor-parallel training bug." + "reason": "Compiled Python file errors and Pipeline save_pretrained are unrelated." }, { - "left": "issue:44355", - "right": "issue:44655", + "left": "issue:30333", + "right": "issue:36296", "accept": false, - "reason": "Compiled Python file errors and Pipeline.save_pretrained failures are separate behaviors." + "reason": "MLflow reporting failure and tensor parallel training bug do not share the same underlying cause." }, { "left": "issue:44355", "right": "issue:45071", "accept": false, - "reason": "Compiled-file runtime errors and PretrainedConfig type-checking regressions are unrelated." + "reason": "Compiled-file runtime errors are unrelated to PretrainedConfig type checking regressions." }, { "left": "issue:42831", "right": "issue:43874", "accept": false, - "reason": "FineGrainedFP8 accuracy issues and a missing image-patch helper in a processor are different bugs." + "reason": "FineGrainedFP8 accuracy issue and missing image-processor method are different bugs." }, { - "left": "issue:42757", - "right": "issue:43576", + "left": "issue:33453", + "right": "issue:34689", "accept": false, - "reason": "Missing huggingface_hub symbol import and the transformers env command failure are distinct symptoms." + "reason": "Both are loading-related, but one is a tokenizer regression and the other is a specific Llama 3.2 vision model-loading breakage." }, { - "left": "issue:33453", - "right": "issue:34689", + "left": "issue:42757", + "right": "issue:43576", "accept": false, - "reason": "Tokenizer loading regression and Llama 3.2 vision model loading breakage are not the same defect." + "reason": "ImportError from huggingface_hub and broken transformers env command are separate issues." }, { "left": "issue:33453", @@ -13380,163 +13191,133 @@ "left": "issue:43827", "right": "issue:44961", "accept": false, - "reason": "Documentation referencing removed pipeline APIs and the unrelated 'racoon' issue do not match." + "reason": "Docs still referencing pipeline() is unrelated to racoon." }, { "left": "issue:43576", "right": "issue:45071", "accept": false, - "reason": "Broken env command and PretrainedConfig type-checking are different failures." + "reason": "Both are v5 regressions, but one is a broken CLI command and the other is a type-checking issue; not the same code path." }, { "left": "issue:43576", "right": "issue:43824", "accept": false, - "reason": "Env command breakage and Qwen2.5-VL import failure are separate import paths and symptoms." - }, - { - "left": "issue:43673", - "right": "issue:44492", - "accept": false, - "reason": "Missing GenerationMixin cache in chunked prefill and a cache-strategy typo are not the same bug." + "reason": "Broken env command and missing Qwen2_5_VLForConditionalGeneration import are different failures." }, { "left": "issue:38617", "right": "issue:43576", "accept": false, - "reason": "An import error for layer_type_validation and a broken env command are unrelated." + "reason": "Missing layer_type_validation import and broken env command are unrelated import/CLI problems." + }, + { + "left": "issue:43673", + "right": "issue:44492", + "accept": false, + "reason": "Chunked_prefill cache missing and a typo in cache strategies are not the same bug." }, { "left": "issue:44961", "right": "issue:45468", "accept": false, - "reason": "'racoon' is not a meaningful bug report and Gemma-4 audio positional encoding is a model-specific bug." + "reason": "A placeholder racoon issue is unrelated to Gemma-4 audio positional encoding." }, { "left": "issue:31795", "right": "issue:38617", "accept": false, - "reason": "Documentation confusion in forward args and an import error from configuration_utils are unrelated." + "reason": "Documentation confusion and an ImportError are different issue types with different fixes." }, { "left": "issue:43576", "right": "issue:44351", "accept": false, - "reason": "Broken env command and missing HybridCache import are different import-related failures, not the same issue." + "reason": "Broken env command and missing HybridCache import are both v5-related but not the same concrete defect." }, { - "left": "issue:44908", - "right": "issue:44961", + "left": "issue:41628", + "right": "issue:42548", "accept": false, - "reason": "Scheduler kwargs handling and the unrelated 'racoon' issue do not match." + "reason": "Both are import errors, but they concern different exported symbols and likely different loader paths." }, { - "left": "issue:41628", - "right": "issue:42548", + "left": "issue:44908", + "right": "issue:44961", "accept": false, - "reason": "Missing AutoImageProcessor and missing PreTrainedModel are similar in category but not the same concrete bug." + "reason": "Scheduler kwargs bug and racoon are unrelated." }, { "left": "issue:44485", "right": "issue:44961", "accept": false, - "reason": "GLM-5 RoPE implementation discussion and the unrelated 'racoon' issue are not the same." + "reason": "GLM-5 RoPE implementation discussion is unrelated to racoon." }, { "left": "issue:36296", "right": "issue:43901", "accept": false, - "reason": "Tensor-parallel training bug and TextClassificationPipeline docs mismatch are unrelated." + "reason": "Tensor parallel training bug and docs mentioning return_all_scores are unrelated." }, { "left": "issue:36296", "right": "issue:43526", "accept": false, - "reason": "Tensor-parallel training bug and BeitImageProcessorFast reduce_labels bug are different code paths." + "reason": "Tensor parallel training and BeitImageProcessorFast reduce_labels are unrelated." }, { "left": "issue:41628", "right": "issue:44355", "accept": false, - "reason": "Top-level import failure and compiled Python file errors are different failures." + "reason": "ImportError for AutoImageProcessor and compiled-file errors are not the same issue." }, { "left": "issue:44273", "right": "issue:45003", "accept": false, - "reason": "Lazy loading malfunction and unsafe sys.modules access are related in theme but not demonstrably the same bug." + "reason": "Lazy loading malfunction and unsafe sys.modules access are different bug reports." }, { "left": "issue:44261", "right": "issue:44360", "accept": false, - "reason": "A precision issue in MLA q_a_layernorm and a DSA indexer ReLU absence are unrelated model/implementation problems." + "reason": "MLA q_a_layernorm epsilon mismatch and missing ReLU in DSA indexer are unrelated." }, { - "left": "issue:44273", - "right": "issue:45542", + "left": "issue:44623", + "right": "issue:45230", "accept": false, - "reason": "Lazy loading and a TensorFlow backend import error are different issues." + "reason": "Processor save_pretrained missing files and a generic bug report do not establish a shared underlying bug." }, { - "left": "issue:44623", - "right": "issue:45230", + "left": "issue:44273", + "right": "issue:45542", "accept": false, - "reason": "Processor.save_pretrained missing files and a generic bug report are not the same defect." + "reason": "Lazy loading and undefined tf backend error are different problems." }, { "left": "issue:43576", "right": "issue:44556", "accept": false, - "reason": "Both are v5 regressions, but one is the env command and the other is checkpoint reload after upgrading; not the same concrete bug." + "reason": "Broken env command and checkpoint reload failure after upgrading to v5.2/v5.3 are distinct regressions." }, { "left": "issue:44038", "right": "issue:45125", "accept": false, - "reason": "General Qwen3-VL-Moe breakage and missing _tp_plan for tensor parallelism are different issues." + "reason": "Qwen3-VL-Moe loading bug and missing _tp_plan for tensor parallelism are different code paths." }, { "left": "issue:44393", "right": "issue:45071", "accept": false, - "reason": "Qwen3-VL 2D bounding-box output problems and PretrainedConfig type checking are unrelated." + "reason": "Qwen3-VL 2D box output error and PretrainedConfig type-checking regression are unrelated." }, { "left": "issue:41669", "right": "issue:43673", "accept": false, - "reason": "Import-time performance from removing import * and a missing GenerationMixin cache in chunked prefill are different defects." - }, - { - "left": "issue:44556", - "right": "issue:45092", - "accept": false, - "reason": "Generic checkpoint reload failure and InternVL2 remote-code/meta-init incompatibility are different loading problems." - }, - { - "left": "issue:42371", - "right": "issue:44492", - "accept": false, - "reason": "TF32 API-setting guidance and a cache-strategy typo are unrelated." - }, - { - "left": "issue:42890", - "right": "issue:44908", - "accept": false, - "reason": "Test flakiness from missing set_seed and scheduler kwargs handling are unrelated." - }, - { - "left": "issue:44704", - "right": "issue:44908", - "accept": false, - "reason": "AutoProcessor kwargs forwarding and inverse_sqrt scheduler kwargs handling are different APIs and bugs." - }, - { - "left": "issue:44246", - "right": "issue:44273", - "accept": false, - "reason": "Import performance variability and lazy loading correctness are not the same underlying issue." + "reason": "Import-star cleanup in models and missing GenerationMixin cache during chunked_prefill are different changes." } ] }, @@ -13555,10 +13336,10 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:31515", "issue:31795", @@ -13575,12 +13356,12 @@ "issue:43519", "issue:43576", "issue:43606", - "issue:43618", "issue:43704", "issue:43723", "issue:43827", "issue:43976", "issue:44077", + "issue:44246", "issue:44261", "issue:44263", "issue:44273", @@ -13595,6 +13376,7 @@ "issue:44556", "issue:44623", "issue:44655", + "issue:44704", "issue:44829", "issue:44861", "issue:44908", @@ -13603,17 +13385,21 @@ "issue:45071", "issue:45092", "issue:45230", - "issue:45290", "issue:45310", "issue:45341", "issue:45468", "issue:45478" ], "soft_pairs": [ + "issue:44556|issue:45092", + "issue:42371|issue:44492", + "issue:42890|issue:44908", + "issue:44704|issue:44908", + "issue:44246|issue:44273", "issue:43408|issue:44315", "issue:44297|issue:45230", - "issue:43576|issue:44908", "issue:43352|issue:44393", + "issue:43576|issue:44908", "issue:43976|issue:44393", "issue:44908|issue:45071", "issue:44295|issue:45230", @@ -13648,325 +13434,323 @@ "issue:44263|issue:45468", "issue:44261|issue:45468", "issue:43606|issue:45468", - "issue:42890|issue:43704", "issue:42913|issue:43066", - "issue:44908|issue:44998", - "issue:44861|issue:45290", - "issue:44998|issue:45341", - "issue:44492|issue:44998", - "issue:43618|issue:44998", - "issue:44556|issue:44998" + "issue:42890|issue:43704", + "issue:44908|issue:44998" ], - "prepared_review_unit_hash": "4ae1862d44caaf52c3dcacdade2d3130e9b89c28a29333a3f54df29319bd2520", + "prepared_review_unit_hash": "2f1a6c3146f9f6aef6f43e633bba86536aa2493ab5902d72058799d42db9201e", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 46, - "serialized_chars": 40810, - "estimated_input_tokens": 10203, - "estimated_eval_tokens": 20662 + "serialized_chars": 40776, + "estimated_input_tokens": 10194, + "estimated_eval_tokens": 20644 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Heterogeneous cluster dominated by v5-era loading/tokenizer/model-API regression reports, plus several unrelated docs/tests/perf items. None of the soft pairs look like the same concrete bug/change, so all are rejected.", - "confidence": 0.93, - "canonical_issue_reason": "issue:44556 is the broadest, most representative loading-regression report in the set (v4.57 checkpoints failing after upgrade to v5.2/v5.3).", + "summary": "This packet is mostly a set of unrelated issue reports. I\u2019m not accepting the two title-similar pairs as duplicates: 44556/45092 and 44246/44273 only have thematic overlap, with no body/diff evidence that they share the same root cause or would be fixed cleanly by one change.", + "confidence": 0.9, + "canonical_issue_reason": "issue:44556 is the clearest standalone report of the v5 checkpoint-reload regression theme and the strongest representative issue in this set.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44556 is the best cluster anchor because it captures the central user-visible regression theme: checkpoint reload failures after the v5 transition.", + "best_issue_reason": "issue:44556 is the best overall anchor here because it is specific, high-signal, and describes a concrete loading failure rather than a vague symptom.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44556", + "right": "issue:45092", + "accept": false, + "reason": "Only title-level similarity about v5 checkpoint/model loading; no body or diff evidence that the same code path or root cause is involved." + }, + { + "left": "issue:42371", + "right": "issue:44492", + "accept": false, + "reason": "TF32 configuration guidance and a cache-strategy typo are different bugs in different areas." + }, + { + "left": "issue:42890", + "right": "issue:44908", + "accept": false, + "reason": "Test flakiness from missing seeds is unrelated to inverse_sqrt scheduler kwargs handling." + }, + { + "left": "issue:44704", + "right": "issue:44908", + "accept": false, + "reason": "AutoProcessor kwargs forwarding and scheduler kwargs are separate code paths with different failures." + }, + { + "left": "issue:44246", + "right": "issue:44273", + "accept": false, + "reason": "Only thematic overlap around loading/import performance; no evidence they are the same underlying bug or one fix would cover both." + }, { "left": "issue:43408", "right": "issue:44315", "accept": false, - "reason": "Model-type warning on sam3_video vs sam3_tracker is unrelated to Liger Kernel application with model_init." + "reason": "Wrong model-type warning and Liger Kernel not applied with model_init are unrelated symptoms." }, { "left": "issue:44297", "right": "issue:45230", "accept": false, - "reason": "Tokenizer class mismatch in save_pretrained is a specific serialization bug; 45230 is an unspecified bug report." + "reason": "Tokenizer_class mismatch on save_pretrained is not the same as a generic bug report." }, { - "left": "issue:43576", - "right": "issue:44908", + "left": "issue:43352", + "right": "issue:44393", "accept": false, - "reason": "Broken `transformers env` CLI and inverse_sqrt scheduler kwargs are different code paths and failures." + "reason": "Flash Attention 2 support warning and Qwen3-VL bbox output issues are different model problems." }, { - "left": "issue:43352", - "right": "issue:44393", + "left": "issue:43576", + "right": "issue:44908", "accept": false, - "reason": "Flash Attention 2.0 support error for NemotronH differs from Qwen3-VL 2D bbox output corruption." + "reason": "Broken transformers env command is unrelated to scheduler kwargs handling." }, { "left": "issue:43976", "right": "issue:44393", "accept": false, - "reason": "Python version compatibility issue is unrelated to Qwen3-VL bounding box output behavior." + "reason": "Python version support issue and Qwen3-VL output bug do not share a concrete code path." }, { "left": "issue:44908", "right": "issue:45071", "accept": false, - "reason": "Scheduler kwargs handling and PretrainedConfig type-checking are unrelated regressions." + "reason": "Scheduler kwargs handling and PretrainedConfig type checking are unrelated." }, { "left": "issue:44295", "right": "issue:45230", "accept": false, - "reason": "position_ids buffer access error is a concrete tensor/buffer bug, not the same as the generic bug report." + "reason": "position_ids buffer access error is unrelated to a vague generic bug report." }, { "left": "issue:41669", "right": "issue:44351", "accept": false, - "reason": "Import-star cleanup/performance issue is unrelated to the HybridCache import failure." + "reason": "Import-star performance slowdown and missing HybridCache import are different problems." }, { "left": "issue:41669", "right": "issue:45341", "accept": false, - "reason": "Model import cleanup has no concrete overlap with a testing_utils bug." + "reason": "Import-time slowdown and a testing_utils bug are unrelated." }, { "left": "issue:44492", "right": "issue:44945", "accept": false, - "reason": "Cache-strategy typo and pipeline-parallelism output error are unrelated." + "reason": "Cache-strategy typo and pipeline-parallelism output corruption are different bugs." }, { "left": "issue:41669", "right": "issue:44492", "accept": false, - "reason": "Large import cleanup and a cache-strategy typo are not the same underlying change." + "reason": "Model import performance regression and cache-strategy typo are unrelated." }, { "left": "issue:44315", "right": "issue:44829", "accept": false, - "reason": "Liger Kernel not applied in model_init is different from flash_attention_3 training degeneration." + "reason": "Liger Kernel application issue and flash_attention_3 training degeneration are distinct problems." }, { "left": "issue:44393", "right": "issue:45478", "accept": false, - "reason": "These are different Qwen3-VL-related bugs: bbox hallucination vs Qwen3.5 MoE loading failure." + "reason": "Qwen3-VL bounding-box hallucination/error and Qwen3.5 MoE from_pretrained failure are different model issues." }, { "left": "issue:31795", "right": "issue:33453", "accept": false, - "reason": "Documentation confusion for forward arguments is not the same as a tokenizer loading regression." + "reason": "Documentation confusion about model.forward is not the same as a tokenizer-loading regression." }, { "left": "issue:43827", "right": "issue:44908", "accept": false, - "reason": "Docs still referencing pipeline() after removals is unrelated to scheduler kwargs handling." + "reason": "Docs still referencing pipeline() and scheduler kwargs handling are unrelated." }, { "left": "issue:44077", "right": "issue:44861", "accept": false, - "reason": "PatchTSMixer post_init policy and _tied_weights_keys list crash are different model-internal issues." + "reason": "post_init policy and _tied_weights_keys AttributeError are separate model-internal issues." }, { "left": "issue:41669", "right": "issue:44908", "accept": false, - "reason": "Import cleanup/performance work does not match the scheduler bug." + "reason": "Import-time performance slowdown and scheduler config handling have no overlap in code path." }, { "left": "issue:43723", "right": "issue:44393", "accept": false, - "reason": "Tokenizer loading in v5 and Qwen3-VL bounding-box output are different subsystems and symptoms." + "reason": "Tokenizer loading regression and Qwen3-VL bbox output bug are unrelated." }, { "left": "issue:44655", "right": "issue:44861", "accept": false, - "reason": "Pipeline save_pretrained failure and tied-weights-key AttributeError are unrelated serialization bugs." + "reason": "Saving pipeline objects and tied-weight key handling are different failure modes." }, { "left": "issue:43576", "right": "issue:44273", "accept": false, - "reason": "Broken env CLI and lazy-loading behavior are different issues." + "reason": "Broken env command and lazy-loading/import slowdown are different features and bugs." }, { "left": "issue:44360", "right": "issue:45468", "accept": false, - "reason": "DSA indexer ReLU concern is not the same as Gemma-4 audio positional encoding." + "reason": "DSA ReLU concern and Gemma4 audio positional encoding are unrelated." }, { "left": "issue:45230", "right": "issue:45310", "accept": false, - "reason": "Generic bug report and Qwen3.5 MoE from_pretrained error are not duplicates." + "reason": "Generic bug report is too vague to be the same as the specific Qwen3.5 MoE from_pretrained error." }, { "left": "issue:44273", "right": "issue:44908", "accept": false, - "reason": "Lazy loading failure does not match the inverse_sqrt scheduler kwargs bug." + "reason": "Lazy loading is not working properly and scheduler kwargs handling are separate subsystems." }, { "left": "issue:41669", "right": "issue:43704", "accept": false, - "reason": "Model import cleanup is unrelated to VRAM leakage in Qwen3ForCausalLM." + "reason": "Import-time slowdown and VRAM leak in dataloader threads are unrelated." }, { "left": "issue:43519", "right": "issue:44485", "accept": false, - "reason": "Incorrect timestamp calculation in Qwen3VL Processor is unrelated to GLM-5 RoPE implementation." + "reason": "Timestamp calculation bug and GLM-5 RoPE implementation are different model-specific problems." }, { "left": "issue:43519", "right": "issue:44908", "accept": false, - "reason": "Processor timestamp math and scheduler kwargs handling are different problems." + "reason": "Processor timestamp math and scheduler kwargs handling are unrelated." }, { "left": "issue:31795", "right": "issue:34689", "accept": false, - "reason": "Model.forward docs confusion is unrelated to Llama 3.2 model loading regression." + "reason": "Documentation confusion and Llama 3.2 Vision loading regression are not the same bug." }, { "left": "issue:31515", "right": "issue:31795", "accept": false, - "reason": "Slow from_pretrained checkpoint loading and forward documentation confusion are different issues." + "reason": "Checkpoint loading slowdown and forward documentation confusion are unrelated." }, { "left": "issue:44315", "right": "issue:45092", "accept": false, - "reason": "Liger Kernel application in model_init is unrelated to old InternVL2 checkpoints failing meta initialization." + "reason": "Liger Kernel application and v5 checkpoint/meta-init loading failure are different code paths." }, { "left": "issue:43704", "right": "issue:44485", "accept": false, - "reason": "VRAM leakage and GLM-5 RoPE implementation are different code-path bugs." + "reason": "VRAM leak in dataloader threads is unrelated to RoPE implementation issues." }, { "left": "issue:44485", "right": "issue:45468", "accept": false, - "reason": "GLM-5 RoPE math and Gemma-4 audio positional encoding are not the same change." + "reason": "GLM-5 RoPE discussion and Gemma4 audio positional encoding are different model implementations." }, { "left": "issue:42371", "right": "issue:43704", "accept": false, - "reason": "TF32 API settings guidance is unrelated to a VRAM leak in Qwen3ForCausalLM." + "reason": "TF32 settings and VRAM leak in dataloader threads are unrelated." }, { "left": "issue:43502", "right": "issue:43519", "accept": false, - "reason": "local_files_only network requests and processor timestamp computation are unrelated regressions." + "reason": "local_files_only network requests and Qwen3VL timestamp calculation are separate bugs." }, { "left": "issue:43519", "right": "issue:44623", "accept": false, - "reason": "Processor timestamp math does not match missing files in processor.save_pretrained." + "reason": "Timestamp computation bug and processor.save_pretrained missing files are different issues." }, { "left": "issue:43519", "right": "issue:43704", "accept": false, - "reason": "Timestamp calculation bug and VRAM leak are different failure modes." + "reason": "Timestamp computation bug and VRAM leak are unrelated." }, { "left": "issue:44263", "right": "issue:45468", "accept": false, - "reason": "torch.split return-value issue in GlmMoeDsaIndexer is unrelated to Gemma-4 audio positional encoding." + "reason": "torch.split return semantics and Gemma4 audio positional encoding are different problems." }, { "left": "issue:44261", "right": "issue:45468", "accept": false, - "reason": "MLA q_a_layernorm epsilon discussion is not the same as Gemma-4 audio positional encoding." + "reason": "MLA q_a_layernorm precision/config issue is unrelated to Gemma4 audio positional encoding." }, { "left": "issue:43606", "right": "issue:45468", "accept": false, - "reason": "CPU offload device mismatch in suno/bark-small is unrelated to Gemma-4 audio positional encoding." - }, - { - "left": "issue:42890", - "right": "issue:43704", - "accept": false, - "reason": "Missing set_seed in SAM-HQ tests is a flaky test issue, not a VRAM leak." + "reason": "CPU offload device mismatch is unrelated to Gemma4 audio positional encoding." }, { "left": "issue:42913", "right": "issue:43066", "accept": false, - "reason": "General tokenizer behavior differences and wrong decoder type in v5 are related broadly, but not the same concrete bug." - }, - { - "left": "issue:44908", - "right": "issue:44998", - "accept": false, - "reason": "Scheduler kwargs bug is unrelated to the placeholder/invalid issue title." - }, - { - "left": "issue:44861", - "right": "issue:45290", - "accept": false, - "reason": "Tied-weights-key AttributeError and chat template tool-call crash are distinct code paths." - }, - { - "left": "issue:44998", - "right": "issue:45341", - "accept": false, - "reason": "Invalid placeholder issue and testing_utils bug are unrelated." + "reason": "Tokenizer behavior differences and wrong decoder type in v5 are related thematically but not the same concrete bug." }, { - "left": "issue:44492", - "right": "issue:44998", - "accept": false, - "reason": "Cache-strategy typo is unrelated to the placeholder/invalid issue." - }, - { - "left": "issue:43618", - "right": "issue:44998", + "left": "issue:42890", + "right": "issue:43704", "accept": false, - "reason": "CLIPOutput attentions regression is unrelated to the placeholder/invalid issue." + "reason": "Test seeding flakiness is unrelated to VRAM leakage." }, { - "left": "issue:44556", + "left": "issue:44908", "right": "issue:44998", "accept": false, - "reason": "Checkpoint reload regression is unrelated to the placeholder/invalid issue." + "reason": "Scheduler configuration bug and an unrelated placeholder issue are not a match." } ] }, - "evaluator_result": null, - "evaluator_used": false, - "retried": false, + "evaluator_result": { + "accept": false, + "feedback": "The writeup is mostly conservative, but it still overstates the evidence for the two accepted soft edges. In the packet, 44556/45092 and 44246/44273 are only supported by title-level thematic similarity; there is no body/diff evidence showing the same root cause or that a single PR would cleanly fix both. I\u2019d keep those pairs as tentative rather than accepted duplicate clusters." + }, + "evaluator_used": true, + "retried": true, "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null @@ -13979,10 +13763,10 @@ "review_unit_count": 43, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-373", + "cluster_id": "cluster-15354-374", "nodes": [ "issue:30333", "issue:31515", @@ -13992,12 +13776,23 @@ "issue:43298", "issue:43525", "issue:43572", + "issue:43618", "issue:44230", + "issue:44492", + "issue:44556", "issue:44623", "issue:44861", - "issue:45310" + "issue:44998", + "issue:45290", + "issue:45310", + "issue:45341" ], "soft_pairs": [ + "issue:44861|issue:45290", + "issue:44998|issue:45341", + "issue:44492|issue:44998", + "issue:43618|issue:44998", + "issue:44556|issue:44998", "issue:43525|issue:44861", "issue:43572|issue:44861", "issue:31515|issue:38617", @@ -14008,88 +13803,118 @@ "issue:31515|issue:33453", "issue:43298|issue:44230" ], - "prepared_review_unit_hash": "1d667f37a6cbb46452086f049dfcd5c154548ed500b8294b856acdc5ff33eb1c", + "prepared_review_unit_hash": "55065f5b7a5682e02817892a07b80cd0bb68e1231277967451f0fb63768bfbd6", "component_budget": { - "node_count": 373, - "item_count": 373, - "soft_pair_count": 1390, - "serialized_chars": 717810, - "estimated_input_tokens": 179453, - "estimated_eval_tokens": 359162 + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 }, "budget": { - "node_count": 12, - "item_count": 12, - "soft_pair_count": 9, - "serialized_chars": 9477, - "estimated_input_tokens": 2370, - "estimated_eval_tokens": 4996 + "node_count": 18, + "item_count": 18, + "soft_pair_count": 14, + "serialized_chars": 14257, + "estimated_input_tokens": 3565, + "estimated_eval_tokens": 7386 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is noisy and heterogeneous: most items are distinct loading/configuration/runtime bugs that only share broad vocabulary like from_pretrained, loading, or config attributes. There is no clear duplicate PR set here.", - "confidence": 0.88, - "canonical_issue_reason": "Issue 45310 is the clearest, most concrete representative of the shared loading/regression theme: it has a specific error, version boundary, and model target. The other issues are largely different subsystems or failure modes.", + "summary": "The cluster is highly heterogeneous: most items are unrelated bugs, and every soft-similarity pair appears to be a false positive. I would not merge any of these issues as duplicates.", + "confidence": 0.95, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "45310 is the best anchor for the cluster because it is specific enough to identify a concrete bug while still being close to the most common overlapping keywords in the set.", + "best_issue_reason": "No single issue is a safe canonical representative because the connected items span unrelated subsystems and failure modes.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44861", + "right": "issue:45290", + "accept": false, + "reason": "Different bugs in different paths: tied-weight key handling vs chat template/tool-call serialization." + }, + { + "left": "issue:44998", + "right": "issue:45341", + "accept": false, + "reason": "One is a nonsense-title issue and the other is a testing_utils bug; no shared symptom or code path." + }, + { + "left": "issue:44492", + "right": "issue:44998", + "accept": false, + "reason": "A typo in cache strategy docs/config is unrelated to the unrelated 'Unemployment' issue." + }, + { + "left": "issue:43618", + "right": "issue:44998", + "accept": false, + "reason": "CLIPOutput attentions regression is unrelated to the other issue." + }, + { + "left": "issue:44556", + "right": "issue:44998", + "accept": false, + "reason": "Checkpoint reload incompatibility is not the same as the unrelated 'Unemployment' issue." + }, { "left": "issue:43525", "right": "issue:44861", "accept": false, - "reason": "Both are AttributeError reports, but they hit different code paths: Llama4Config missing pad_token_id vs _tied_weights_keys handling in weight-key extraction." + "reason": "Llama4Config pad_token_id attribute missing is unrelated to tied-weight key list handling." }, { "left": "issue:43572", "right": "issue:44861", "accept": false, - "reason": "StableLmConfig pad_token_idx missing after a 5.0 update is unrelated to the tied-weights list crash." + "reason": "StableLmConfig pad_token_idx regression is a different config attribute bug than the tied-weight crash." }, { "left": "issue:31515", "right": "issue:38617", "accept": false, - "reason": "Slow checkpoint loading in from_pretrained is a performance issue, while layer_type_validation import failure is an import/API regression." + "reason": "Slow from_pretrained checkpoint loading is unrelated to an ImportError for layer_type_validation." }, { "left": "issue:44230", "right": "issue:44623", "accept": false, - "reason": "FP8 inference support for Qwen models is unrelated to processor.save_pretrained omitting files." + "reason": "FP8 Qwen model support and missing processor save_pretrained files are different issues." }, { "left": "issue:31515", "right": "issue:36296", "accept": false, - "reason": "Checkpoint loading slowness and tensor-parallel training bugs are different failure modes in different flows." + "reason": "Tokenizer/checkpoint loading slowness is not the same as a tensor-parallel training bug." }, { "left": "issue:30333", "right": "issue:31515", "accept": false, - "reason": "MLFlow reporting after training failure is a job-status integration issue, not a from_pretrained loading problem." + "reason": "MLflow reporting on failed training jobs and slow checkpoint loading are unrelated problems." }, { "left": "issue:44230", "right": "issue:45310", "accept": false, - "reason": "Both mention Qwen3.5/MoE, but one is FP8 support while the other is a from_pretrained error in a specific transformers version; not the same bug." + "reason": "Qwen3-VL/Qwen3.5 FP8 support request and a from_pretrained error on Qwen3.5 MoE are not the same concrete bug." }, { "left": "issue:31515", "right": "issue:33453", "accept": false, - "reason": "Tokenizer loading regression and slow checkpoint loading are related only at a very broad loading level, not the same underlying defect." + "reason": "Both involve loading, but one is checkpoint load slowness and the other is a tokenizer loading regression; not the same bug." }, { "left": "issue:43298", "right": "issue:44230", "accept": false, - "reason": "Continuous batching not supporting audio models is a different capability gap than FP8 support for Qwen models." + "reason": "Continuous batching audio-model support and FP8 Qwen inference support are distinct feature gaps." } ] }, @@ -14108,8 +13933,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-26350-2", "nodes": [ @@ -14119,12 +13944,12 @@ "soft_pairs": [ "issue:26350|issue:33260" ], - "prepared_review_unit_hash": "793cf21b3a0313d992dc1027e1800d886325d71a4cd30dbce30898eeb50f4052", + "prepared_review_unit_hash": "ad8d1b620509c568a6a760a93a5e059838298c90968b34d1ad4ed61ae5ebe562", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1589, + "serialized_chars": 1590, "estimated_input_tokens": 398, "estimated_eval_tokens": 1052 }, @@ -14132,7 +13957,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1589, + "serialized_chars": 1590, "estimated_input_tokens": 398, "estimated_eval_tokens": 1052 }, @@ -14141,18 +13966,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are two unrelated community-contribution issues: one for Flash Attention 2 support across more architectures, and one for GGUF support across more architectures. They share a broad theme but not the same underlying bug or change.", + "summary": "These are not duplicates: one requests Flash Attention 2 support for more architectures, the other requests GGUF support for more architectures. They share a broad \u201ccommunity contribution\u201d theme but describe different feature work.", "confidence": 0.97, "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Neither issue is a duplicate of the other; they concern different features and different implementation work, so there is no single canonical issue within this pair.", + "best_issue_reason": "Issue 26350 is the stronger representative thread in this cluster because it has substantially more discussion and is the older, more established request; however, it should not be treated as a duplicate of 33260.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:26350", "right": "issue:33260", "accept": false, - "reason": "Different requested features and code paths (Flash Attention 2 vs GGUF support). Similar wording about adding support for more architectures is too broad to treat as the same underlying issue." + "reason": "Different requested features and code paths: Flash Attention 2 architecture support vs GGUF architecture support. Similar framing, but not the same underlying change." } ] }, @@ -14171,8 +13996,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-27088-4", "nodes": [ @@ -14189,7 +14014,7 @@ "issue:43834|issue:44365", "issue:44365|issue:44370" ], - "prepared_review_unit_hash": "9de1c4f0621af4432891c0702b5c558baef7ea7bd19cf93cd4d91d7fa03d02dc", + "prepared_review_unit_hash": "2148375c0b5f798b8c6e75714948c6cc19bfc19dc443baaf8853195fcd1247fe", "component_budget": { "node_count": 4, "item_count": 4, @@ -14211,48 +14036,48 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are highly similar docs-translation request issues, but the visible language-specific vs placeholder/template wording is not enough to confidently treat them as exact duplicates. I\u2019d keep the concrete Turkish issue as the most useful representative and avoid merging the others on similarity alone.", - "confidence": 0.59, - "canonical_issue_reason": "Issue 27088 is the only concrete, language-specific request ('Turkish'); the others are placeholder/template-style titles and are less representative as a canonical thread.", + "summary": "All four issues are language-translation requests using the same template. The Turkish-specific issue is the most concrete, but the other three appear to be separate template instances rather than the same underlying request; high text similarity alone is not enough to merge them as duplicates.", + "confidence": 0.71, + "canonical_issue_reason": "issue:27088 is the only concrete, specific request (Turkish). The others are generic placeholder-style variants, so this is the clearest representative of the actual problem being reported.", "canonical_pr_reason": null, - "best_issue_reason": "27088 is the clearest user-facing issue in the set and the only one with an explicit target language, so it is the best issue to retain if one must be chosen.", + "best_issue_reason": "issue:27088 is the best standalone issue because it names a specific language and has the least ambiguity; the other issues look like templated duplicates or separate language requests.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:27088", "right": "issue:44370", "accept": false, - "reason": "Very similar template wording, but the explicit Turkish request vs. a placeholder-style translation request is not enough to prove the same underlying issue." + "reason": "Both are translation-request templates, but one is specifically Turkish while the other is a generic placeholder-style issue. That is not enough to prove the same underlying request." }, { "left": "issue:27088", "right": "issue:44365", "accept": false, - "reason": "Looks like the same i18n template, but the language-specific request differs in substance; similarity alone is insufficient for a duplicate merge." + "reason": "High similarity likely comes from the shared i18n template; the language target is not the same concrete request, so this should not be merged as a duplicate." }, { "left": "issue:27088", "right": "issue:43834", "accept": false, - "reason": "This is a near-match in template text, but not enough evidence that it is the same concrete translation request." + "reason": "The titles/body patterns are similar, but this looks like a different translation request instance rather than the same Turkish issue." }, { "left": "issue:43834", "right": "issue:44370", "accept": false, - "reason": "Both are generic translation-request templates, but the available text does not confirm they target the same language or exact request." + "reason": "These are near-identical template issues, but there is no evidence they target the exact same language/request; template similarity alone is insufficient." }, { "left": "issue:43834", "right": "issue:44365", "accept": false, - "reason": "The bodies are extremely similar, yet the placeholder titles are too generic to confirm a true duplicate." + "reason": "Both look like generic translation-request variants, but not enough evidence that they are the same underlying bug/change." }, { "left": "issue:44365", "right": "issue:44370", "accept": false, - "reason": "Close template match, but there is no explicit evidence they are the same underlying translation task." + "reason": "Near-duplicate wording is likely due to the shared template, but they still appear to be separate issue instances without proof of the same concrete request." } ] }, @@ -14271,13 +14096,14 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-36817-13", + "cluster_id": "cluster-36817-14", "nodes": [ "issue:36817", "issue:37015", + "issue:41115", "issue:41211", "issue:42503", "issue:42738", @@ -14298,11 +14124,14 @@ "issue:37015|issue:43909", "issue:37015|issue:42503", "issue:37015|issue:45027", + "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:42503|issue:45027", "issue:42738|issue:45027", "issue:43671|issue:43837", "issue:43671|issue:45027", @@ -14317,76 +14146,100 @@ "issue:43837|issue:45027", "issue:43837|issue:45177" ], - "prepared_review_unit_hash": "c2b2c2a188c62033345d6b3c8c29fc5e07a2b828c09c9b86386d6cc091f0fba2", + "prepared_review_unit_hash": "65b828b3117a9d9d6cfbb4f9604d3489c66ca1d7a13e12b4647103307d97f1ee", "component_budget": { - "node_count": 13, - "item_count": 13, - "soft_pair_count": 25, - "serialized_chars": 16011, - "estimated_input_tokens": 4003, - "estimated_eval_tokens": 8262 + "node_count": 14, + "item_count": 14, + "soft_pair_count": 28, + "serialized_chars": 17644, + "estimated_input_tokens": 4411, + "estimated_eval_tokens": 9078 }, "budget": { - "node_count": 13, - "item_count": 13, - "soft_pair_count": 25, - "serialized_chars": 16011, - "estimated_input_tokens": 4003, - "estimated_eval_tokens": 8262 + "node_count": 14, + "item_count": 14, + "soft_pair_count": 28, + "serialized_chars": 17644, + "estimated_input_tokens": 4411, + "estimated_eval_tokens": 9078 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are topical lookalikes, not duplicates: they span different model requests across unrelated families and modalities (text encoders, audio/TTS/ASR, OCR, sparse transformers, perception). The shared pattern is just \"add support for model X\", not one underlying bug or change.", - "confidence": 0.99, - "canonical_issue_reason": "No single canonical issue: the items request support for distinct models/features, so there is no shared underlying defect or code change to deduplicate against.", + "summary": "These items are thematically similar model-request issues, but they are not duplicates: each asks for a different model, task, or modality (e.g. BERT variants, audio ASR/TTS, OCR, sparse transformers).", + "confidence": 0.98, + "canonical_issue_reason": "No single canonical issue: the cluster spans distinct model requests rather than the same underlying bug/change.", "canonical_pr_reason": null, - "best_issue_reason": "No best issue for a duplicate cluster: none of these issues is a clear superset or the same request as the others.", + "best_issue_reason": "No clear global representative for deduplication because the requests target different models and code paths.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:36817", "right": "issue:41211", "accept": false, - "reason": "Different model requests (EuroBert vs DEIMv2); only the broad \"add model\" theme overlaps." + "reason": "EuroBERT config vs DEIMv2 are different model additions with different implementations." }, { "left": "issue:36817", "right": "issue:43671", "accept": false, - "reason": "EuroBert config support vs Qwen3-TTS support are different models and different modalities." + "reason": "EuroBERT vs Qwen3-TTS are unrelated model families and modalities." }, { "left": "issue:37015", "right": "issue:43837", "accept": false, - "reason": "NeoBERT and Qwen3-ASR are unrelated requests; no shared code-path bug." + "reason": "NeoBERT and Qwen3-ASR are different models; ASR support is not the same change as adding a BERT variant." }, { "left": "issue:37015", "right": "issue:44121", "accept": false, - "reason": "NeoBERT model addition vs weight-sparse transformer request are different changes." + "reason": "NeoBERT vs a weight-sparse transformer request are different architectures and code paths." }, { "left": "issue:37015", "right": "issue:43909", "accept": false, - "reason": "NeoBERT and LFM2.5 Audio target different model families/modalities." + "reason": "NeoBERT is unrelated to LFM2.5 Audio; different family and modality." }, { "left": "issue:37015", "right": "issue:42503", "accept": false, - "reason": "NeoBERT and ModernVBERT are separate model support requests, not the same issue." + "reason": "NeoBERT and ModernVBERT are different model requests, not the same bug/change." }, { "left": "issue:37015", "right": "issue:45027", "accept": false, - "reason": "NeoBERT vs Voxtral-4B-TTS support are distinct model additions." + "reason": "NeoBERT vs Voxtral TTS are unrelated model/support requests." + }, + { + "left": "issue:41115", + "right": "issue:43837", + "accept": false, + "reason": "MiniCPM3 architecture support and Qwen3-ASR support are distinct model integrations." + }, + { + "left": "issue:41115", + "right": "issue:44121", + "accept": false, + "reason": "MiniCPM3 vs weight-sparse transformer are different requested changes." + }, + { + "left": "issue:41115", + "right": "issue:42503", + "accept": false, + "reason": "MiniCPM3 and ModernVBERT are separate model additions." + }, + { + "left": "issue:41115", + "right": "issue:45027", + "accept": false, + "reason": "MiniCPM3 and Voxtral TTS target different models and modalities." }, { "left": "issue:41211", @@ -14398,103 +14251,97 @@ "left": "issue:42503", "right": "issue:43837", "accept": false, - "reason": "ModernVBERT models vs Qwen3-ASR support are different additions." + "reason": "ModernVBERT and Qwen3-ASR are different model/task integrations." }, { "left": "issue:42503", "right": "issue:43671", "accept": false, - "reason": "ModernVBERT and Qwen3-TTS are different model families and tasks." + "reason": "ModernVBERT and Qwen3-TTS are unrelated model requests." }, { "left": "issue:42503", "right": "issue:42738", "accept": false, - "reason": "ModernVBERT models vs BERT-like models with RoPE are only loosely related, not the same concrete request." - }, - { - "left": "issue:42503", - "right": "issue:45027", - "accept": false, - "reason": "ModernVBERT and Voxtral-4B-TTS are unrelated model support requests." + "reason": "ModernVBERT is a concrete model request; BERT-like models with RoPE is a broader architecture discussion, not the same change." }, { "left": "issue:42738", "right": "issue:45027", "accept": false, - "reason": "BERT-like models with RoPE vs Voxtral TTS do not describe the same change." + "reason": "A generic BERT-with-RoPE request is unrelated to Voxtral TTS support." }, { "left": "issue:43671", "right": "issue:43837", "accept": false, - "reason": "Qwen3-TTS and Qwen3-ASR are sibling but distinct tasks; not one mergeable PR/issue." + "reason": "Qwen3-TTS and Qwen3-ASR share a prefix but are different concrete support changes (TTS vs ASR)." }, { "left": "issue:43671", - "right": "issue:43909", + "right": "issue:45027", "accept": false, - "reason": "Qwen3-TTS and LFM2.5 Audio are different audio model requests." + "reason": "Qwen3-TTS and Voxtral TTS are different model integrations." }, { "left": "issue:43671", - "right": "issue:44121", + "right": "issue:45177", "accept": false, - "reason": "Qwen3-TTS support and sparse-transformer support are unrelated." + "reason": "Qwen3-TTS and DeepSeek-OCR2 are different modalities and implementations." }, { "left": "issue:43671", - "right": "issue:45027", + "right": "issue:44121", "accept": false, - "reason": "Qwen3-TTS and Voxtral-4B-TTS are separate model integrations." + "reason": "Qwen3-TTS support is unrelated to a weight-sparse transformer request." }, { "left": "issue:43671", - "right": "issue:45177", + "right": "issue:43909", "accept": false, - "reason": "Qwen3-TTS support and DeepSeek-OCR2 support are different model additions." + "reason": "Qwen3-TTS and LFM2.5 Audio are different audio-model requests, not the same underlying change." }, { "left": "issue:43837", "right": "issue:43909", "accept": false, - "reason": "Qwen3-ASR and LFM2.5 Audio are distinct audio model requests." + "reason": "Qwen3-ASR and LFM2.5 Audio are distinct audio model requests with different code paths." }, { "left": "issue:43837", - "right": "issue:44205", + "right": "issue:45322", "accept": false, - "reason": "Qwen3-ASR and SAM3-LiteText cover different modalities and code paths." + "reason": "Qwen3-ASR support and EUPE are unrelated model requests." }, { "left": "issue:43837", "right": "issue:44121", "accept": false, - "reason": "Qwen3-ASR support is unrelated to the sparse-transformer request." + "reason": "Qwen3-ASR and a weight-sparse transformer request are different changes." }, { "left": "issue:43909", "right": "issue:44205", "accept": false, - "reason": "LFM2.5 Audio vs SAM3-LiteText are different model support requests." + "reason": "LFM2.5 Audio support and SAM3-LiteText are different model additions." }, { "left": "issue:44121", "right": "issue:45322", "accept": false, - "reason": "Sparse-transformer support and EUPE perception encoder support are separate changes." + "reason": "Weight-sparse transformer and EUPE are unrelated research-model requests." }, { "left": "issue:43837", "right": "issue:45027", "accept": false, - "reason": "Qwen3-ASR and Voxtral-4B-TTS are different speech-model integrations." + "reason": "Qwen3-ASR and Voxtral TTS differ by model and task; not a duplicate." }, { "left": "issue:43837", "right": "issue:45177", "accept": false, - "reason": "Qwen3-ASR and DeepSeek-OCR2 are unrelated modalities and code paths." + "reason": "Qwen3-ASR and DeepSeek-OCR2 are different model requests." } ] }, @@ -14513,8 +14360,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-37934-6", "nodes": [ @@ -14535,82 +14382,82 @@ "issue:43668|issue:44031", "issue:43668|issue:43813" ], - "prepared_review_unit_hash": "d0f15d22051ebc55d9d42c3f839f7942f014fddd5608d11829601236088123d0", + "prepared_review_unit_hash": "bb2cc08e747d7e77db1527f9f7b77d434c7014832549efc89efb6073efcf1bd3", "component_budget": { "node_count": 6, "item_count": 6, "soft_pair_count": 8, - "serialized_chars": 6294, - "estimated_input_tokens": 1574, - "estimated_eval_tokens": 3404 + "serialized_chars": 6291, + "estimated_input_tokens": 1573, + "estimated_eval_tokens": 3402 }, "budget": { "node_count": 6, "item_count": 6, "soft_pair_count": 8, - "serialized_chars": 6294, - "estimated_input_tokens": 1574, - "estimated_eval_tokens": 3404 + "serialized_chars": 6291, + "estimated_input_tokens": 1573, + "estimated_eval_tokens": 3402 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These issues are only loosely similar at a topical level (all are small bugs/typos/config problems), but they concern different models, APIs, and failure modes. I do not see a duplicate cluster here.", - "confidence": 0.95, - "canonical_issue_reason": null, + "summary": "These items are only loosely text-similar; they describe different bugs in different areas (model norms, loss handling, config typing, a typo, and tokenizer warnings), so they should not be deduplicated together.", + "confidence": 0.98, + "canonical_issue_reason": "No single canonical issue: the cluster spans unrelated problems across different components and bug types.", "canonical_pr_reason": null, - "best_issue_reason": "No single issue is a strong canonical representative because the set is not a duplicate group; the reported problems span unrelated components and fixes.", + "best_issue_reason": "No issue here is a good global representative for the whole set, because they are not the same underlying defect.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:37934", "right": "issue:43668", "accept": false, - "reason": "Different areas: Llama4TextL2Norm vs ModernBERTConfig. One questions whether a norm layer is RMSNorm; the other is a type-hint issue in a config field." + "reason": "Different models and defects: Llama4 norm semantics vs ModernBERTConfig type-hint correctness." }, { "left": "issue:42936", "right": "issue:43240", "accept": false, - "reason": "Both relate to loss/masking behavior, but one is about an unused ignore_value in Mask2Former while the other is about kwargs not being forwarded to a loss function; different bugs and likely different fixes." + "reason": "Mask2Former ignore_value usage is a separate loss-parameter bug from kwargs not being forwarded to the loss function." }, { "left": "issue:42936", "right": "issue:44031", "accept": false, - "reason": "Mask2Former ignore_value handling is unrelated to tokenizer regex warnings after a version change." + "reason": "Unrelated subsystems: a model loss argument issue vs tokenizer regex warning behavior." }, { "left": "issue:42936", "right": "issue:43813", "accept": false, - "reason": "Mask2Former ignore_value handling and a typo in a quantization operation path are unrelated." + "reason": "Different underlying problem: unused ignore_value vs a typo in a quantization attribute name." }, { "left": "issue:42936", "right": "issue:43668", "accept": false, - "reason": "Different models and different kinds of defects: unused ignore_value vs incorrect type hint." + "reason": "These concern different models and bug classes, not the same code-path failure." }, { "left": "issue:43240", "right": "issue:43668", "accept": false, - "reason": "Loss kwargs propagation bug is unrelated to a ModernBERTConfig annotation mistake." + "reason": "Loss kwargs forwarding and a config type-hint error are unrelated." }, { "left": "issue:43668", "right": "issue:44031", "accept": false, - "reason": "A config type-hint issue is not the same underlying problem as tokenizer regex warning behavior." + "reason": "A ModernBERT config annotation issue is not the same as the tokenizer regex warning bug." }, { "left": "issue:43668", "right": "issue:43813", "accept": false, - "reason": "Incorrect type hint in config vs typo in a quantization attribute reference are distinct issues." + "reason": "Type-hint mistake vs literal typo in a different quantization-related string." } ] }, @@ -14629,8 +14476,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-41084-2", "nodes": [ @@ -14640,7 +14487,7 @@ "soft_pairs": [ "issue:41084|issue:43037" ], - "prepared_review_unit_hash": "d30f2b9b2bbbb83456fac183d9a7219e62980b97fdb76a243cbb9a3a42817de9", + "prepared_review_unit_hash": "ff882ecfdd7846ea64e48964f8f053805d271ca58e6f3ba487a29533b675ca33", "component_budget": { "node_count": 2, "item_count": 2, @@ -14662,18 +14509,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two issues do not look like duplicates: one is a vague request about block decoding, the other is a specific request for DeepSeek v3.2 support. They may both relate to model/runtime support, but they do not describe the same underlying bug or change.", - "confidence": 0.91, + "summary": "The two issues are unrelated: one is about Block Decoding and the other is a request for DeepSeek v3.2 model support, so they should not be deduplicated.", + "confidence": 0.96, "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Issue #43037 is the better anchor because it names a concrete target (DeepSeek v3.2 support) and is more actionable than the very broad 'Set Block Decoding' request.", + "best_issue_reason": "If one had to be highlighted, #43037 is the more specific, actionable request, but it is not a duplicate of #41084.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:41084", "right": "issue:43037", "accept": false, - "reason": "Different requests: one is about block decoding behavior, the other is about adding support for a specific DeepSeek model version. They do not share a concrete fix or bug." + "reason": "Different topics and likely different code paths: Block Decoding vs model support for DeepSeek v3.2. Similarity is too weak to treat as the same underlying issue." } ] }, @@ -14692,8 +14539,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-43598-2", "nodes": [ @@ -14703,7 +14550,7 @@ "soft_pairs": [ "issue:43598|issue:43600" ], - "prepared_review_unit_hash": "73aabaa8a5e5622e93b9c99c00e2aa57e39036b52b8ae19bddc0f0853675820a", + "prepared_review_unit_hash": "838b2c5d64b6819652f7fe8558f40fe979826318d318a7e5340d3e597809f1d9", "component_budget": { "node_count": 2, "item_count": 2, @@ -14725,18 +14572,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two closed issues are thematically related (custom trainers in Trainer), but they describe different problems: one is about column-removal behavior/customizability, the other about FLOPs estimation. They should not be deduplicated.", + "summary": "The two issues are related only at a high level to Trainer customization, but they describe different problems: one is about `remove_unused_column`, the other about FLOPS estimation for custom trainers. They should not be clustered as duplicates.", "confidence": 0.91, - "canonical_issue_reason": "Issue 43598 is the more concrete and user-facing Trainer behavior bug around `remove_unused_column`; it\u2019s a better representative of the cluster than the FLOPs-estimation request.", + "canonical_issue_reason": "Issue #43598 is the more specific customization concern around `remove_unused_column` in `Trainer`, and it is better suited as the representative issue for that narrow topic.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43598 is the strongest standalone issue because it names a specific Trainer behavior and a clear customization concern.", + "best_issue_reason": "#43598 is the clearer, more actionable report with a concrete Trainer behavior to revisit; #43600 is a separate concern about FLOPS accounting and should remain distinct.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43598", "right": "issue:43600", "accept": false, - "reason": "Related only by broad Trainer/custom-trainer context; they target different code paths and fixes (input-column handling vs FLOPs accounting), so they are not the same underlying bug." + "reason": "They mention Trainer customization, but one is about column removal behavior and the other about FLOPS estimation. These are different code paths and different fixes." } ] }, @@ -14754,9 +14601,9 @@ "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", - "reason": null, - "source": "cache", - "cache_hit": true, + "reason": null, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-43684-2", "nodes": [ @@ -14766,12 +14613,12 @@ "soft_pairs": [ "issue:43684|issue:44405" ], - "prepared_review_unit_hash": "8c25d09e22d50b0f045e33c5d3670ff252360d41988e2c3f0282c7a1455de6bd", + "prepared_review_unit_hash": "37218c8cb1bcd3773dedee66f9130321e3a0ad936562cfc73088da017d90561e", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1612, + "serialized_chars": 1611, "estimated_input_tokens": 403, "estimated_eval_tokens": 1062 }, @@ -14779,7 +14626,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1612, + "serialized_chars": 1611, "estimated_input_tokens": 403, "estimated_eval_tokens": 1062 }, @@ -14788,18 +14635,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both issues are about adding missing Hugging Face model support, but they target different models and different API surfaces: Qwen3-Omni registration for AutoModel/AutoModelForConditionalGeneration vs. Qwen3.5 sequence classification support. They are related at a broad subsystem level, not the same underlying bug.", - "confidence": 0.92, - "canonical_issue_reason": "Issue 43684 is the broader, more general model-registration request and best represents this cluster\u2019s theme of missing AutoModel support.", + "summary": "These are two different feature requests for different Qwen model support paths: one for Qwen3-Omni auto-registration, the other for Qwen3.5 sequence-classification support. They are not duplicates.", + "confidence": 0.97, + "canonical_issue_reason": "Issue 43684 is the broader/cleaner anchor because it asks for AutoModel and AutoModelForConditionalGeneration registration support, while 44405 is a separate, task-specific AutoModelForSequenceClassification request for a different Qwen variant.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43684 is the clearest representative because it asks for direct AutoModel registration changes rather than a more specific head/task extension.", + "best_issue_reason": "43684 is the best representative if one issue must be chosen, since it targets general auto-class registration; 44405 is a distinct head-specific request and should not be merged into it.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43684", "right": "issue:44405", "accept": false, - "reason": "Different model families and different functionality: Qwen3-Omni auto-registration vs Qwen3.5 sequence-classification head support. They are not the same concrete change and would not plausibly be one merged fix." + "reason": "Different underlying changes: Qwen3-Omni registration for auto classes vs Qwen3.5 sequence-classification support. Different model family and different task head, so not the same bug or fix." } ] }, @@ -14818,8 +14665,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-43835-4", "nodes": [ @@ -14836,7 +14683,7 @@ "issue:43845|issue:43859", "issue:43846|issue:43859" ], - "prepared_review_unit_hash": "a07602c38fb88e34907ec0306079b3157f1e2342a85208b51a26536153a98ffb", + "prepared_review_unit_hash": "a92bcc515c8921ceed06ab44a9dcec731b333292f66b00fea325c9d5f709fc1e", "component_budget": { "node_count": 4, "item_count": 4, @@ -14858,54 +14705,54 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The three \"huggingface\" issues look like a duplicate set; \"Fett\" appears unrelated. No PRs are present.", + "summary": "Three issues are near-identical duplicate reports with the title \"huggingface \"; the \"Fett\" issue is unrelated on the available evidence. I\u2019d cluster the three huggingface issues together and keep them separate from 43835.", "confidence": 0.71, - "canonical_issue_reason": "issue:43845 is the earliest of the repeated \"huggingface\" reports and is as plausible a representative as the others; 43835 has a different title and no corroborating overlap.", + "canonical_issue_reason": "Issue 43859 is the best canonical representative among the duplicate huggingface reports because it matches the repeated title and has the most discussion activity, while the others appear to be the same report.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43845 is the best cluster representative because it is the earliest of the matching \"huggingface\" issues and has no evidence making it less representative than 43846/43859.", + "best_issue_reason": "43859 is the strongest issue to keep as the cluster representative: same duplicated title as the other matching issues and slightly more activity, so it is the most informative anchor for triage.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43835", "right": "issue:43845", "accept": false, - "reason": "Different titles and no shared filenames/targets or other concrete evidence of the same underlying issue." + "reason": "Different titles and no shared body or target evidence; not enough to treat \"Fett\" and \"huggingface\" as the same underlying issue." }, { "left": "issue:43835", "right": "issue:43846", "accept": false, - "reason": "Different titles and no shared filenames/targets or other concrete evidence of the same underlying issue." + "reason": "Different titles and no concrete evidence of the same bug/change." }, { "left": "issue:43835", "right": "issue:43859", "accept": false, - "reason": "Different titles and no shared filenames/targets or other concrete evidence of the same underlying issue." + "reason": "Different titles and no shared issue target or descriptive evidence; should not be merged." }, { "left": "issue:43845", "right": "issue:43846", "accept": true, - "reason": "Same generic title and very similar metadata/body size, created minutes apart, so they likely describe the same issue." + "reason": "Same title, very high textual similarity, and no contrary evidence; these look like duplicate reports of the same issue." }, { "left": "issue:43845", "right": "issue:43859", "accept": true, - "reason": "Same title and strong soft similarity; despite a shorter body, it still looks like the same underlying issue report." + "reason": "Same title and strong similarity; these appear to be the same underlying report." }, { "left": "issue:43846", "right": "issue:43859", "accept": true, - "reason": "Same title and strong soft similarity; the metadata suggests another near-duplicate of the same report." + "reason": "Same title and strong similarity with no distinguishing details; likely duplicates." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet: the three \"huggingface\" issues share the same title and strong soft-similarity evidence, while \"Fett\" is a separate title with only weak similarity. The chosen representative is the earliest matching issue, and the soft-edge verdicts stay conservative given the available evidence." + "feedback": "The clustering is grounded in the packet: 43845/43846/43859 share the same title and strong soft-similarity evidence, while 43835 has a different title and only weak soft similarity. Choosing 43859 as the canonical representative is also conservative because it has the only discussion activity. " }, "evaluator_used": true, "retried": false, @@ -14921,8 +14768,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-44371-5", "nodes": [ @@ -14943,88 +14790,88 @@ "issue:44572|issue:44937", "issue:44573|issue:44937" ], - "prepared_review_unit_hash": "4df6a5ca53679af733d2442f1139742d6cb293a6a7efe06c56dbee45946ac346", + "prepared_review_unit_hash": "b921ee5f6beb117d409d2218412d4ee66a9d39e33afbd400bd292145d865e555", "component_budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 9, - "serialized_chars": 5788, - "estimated_input_tokens": 1447, - "estimated_eval_tokens": 3150 + "serialized_chars": 5794, + "estimated_input_tokens": 1449, + "estimated_eval_tokens": 3154 }, "budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 9, - "serialized_chars": 5788, - "estimated_input_tokens": 1447, - "estimated_eval_tokens": 3150 + "serialized_chars": 5794, + "estimated_input_tokens": 1449, + "estimated_eval_tokens": 3154 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster looks like mostly spam/placeholder issues with one vague documentation request; there is no evidence that any pair refers to the same underlying bug or change.", - "confidence": 0.71, - "canonical_issue_reason": "issue:44418 is the only item that reads like a potentially legitimate issue; the others are explicit spam-like titles or equally empty placeholders.", + "summary": "All items look like unrelated low-signal or spam issues; there is no substantive evidence that any two describe the same underlying bug or request.", + "confidence": 0.98, + "canonical_issue_reason": "issue:44418 is the only item with a non-placeholder topical title, so it is the least bad representative if one must be chosen; however, it is still too generic to be a strong canonical issue.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44418 is the best available issue candidate, but only weakly so because its title is generic and the body is not available here.", + "best_issue_reason": "issue:44418 is the most usable anchor only because it has an actual topic label rather than a spam placeholder; none of the issues are strong enough to serve as a meaningful canonical report.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44371", "right": "issue:44572", "accept": false, - "reason": "Both are spam-like placeholders with no concrete shared bug or feature description." + "reason": "Both titles are identical spam placeholders with no body/detail, so this is not evidence of the same underlying issue." }, { "left": "issue:44371", "right": "issue:44573", "accept": false, - "reason": "Both are spam-like placeholders; no evidence they describe the same underlying problem." + "reason": "Both are generic spam placeholders; similarity is not enough to infer a shared bug or request." }, { "left": "issue:44371", "right": "issue:44418", "accept": false, - "reason": "A spam placeholder and a vague documentation request are not the same issue." + "reason": "One is a spam placeholder and the other is a vague documentation request; no concrete shared problem is shown." }, { "left": "issue:44371", "right": "issue:44937", "accept": false, - "reason": "A spam placeholder and an unrelated title about 'Google LLC' do not indicate the same bug or change." + "reason": "A spam placeholder and an unrelated branded title do not indicate the same underlying issue." }, { "left": "issue:44418", "right": "issue:44572", "accept": false, - "reason": "A generic documentation suggestion and a spam placeholder are not duplicates." + "reason": "A generic documentation suggestion and a spam placeholder are not the same substantive report." }, { "left": "issue:44418", "right": "issue:44573", "accept": false, - "reason": "A generic documentation suggestion and a spam placeholder are not duplicates." + "reason": "The two titles are too generic and one is clear spam; there is no shared concrete issue." }, { "left": "issue:44572", "right": "issue:44573", "accept": false, - "reason": "Both are spam placeholders, but the titles/body are too uninformative to justify treating them as the same underlying issue." + "reason": "Identical spam placeholders are not sufficient evidence of duplicate substantive content." }, { "left": "issue:44572", "right": "issue:44937", "accept": false, - "reason": "No concrete overlap in the titles suggests the same underlying issue." + "reason": "A spam placeholder and an unrelated brand-name title do not describe the same bug or change." }, { "left": "issue:44573", "right": "issue:44937", "accept": false, - "reason": "No concrete overlap in the titles suggests the same underlying issue." + "reason": "No concrete overlap beyond generic spammy wording; not a duplicate pair." } ] }, @@ -15043,8 +14890,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-45145-2", "nodes": [ @@ -15054,12 +14901,12 @@ "soft_pairs": [ "issue:45145|issue:45151" ], - "prepared_review_unit_hash": "802985424a8838b55340e81fa6c68447bba0d46f47405f1de5dd010ad12c491e", + "prepared_review_unit_hash": "b1517103c377d88d4edaf8b204c2f1f235d0c8fd3e57a6f9d9d62bc121f0178b", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1645, + "serialized_chars": 1646, "estimated_input_tokens": 412, "estimated_eval_tokens": 1080 }, @@ -15067,7 +14914,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1645, + "serialized_chars": 1646, "estimated_input_tokens": 412, "estimated_eval_tokens": 1080 }, @@ -15076,28 +14923,28 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two closed issues are likely duplicates: they have the same title, were opened close together, and the similarity signal supports a shared underlying report. The evidence is enough to treat one as the canonical representative, but not enough to claim they are fully identical with high certainty.", - "confidence": 0.86, - "canonical_issue_reason": "#45145 is the better canonical issue because it was opened first and already has an inbound reference, so it is the more established representative of this likely duplicate pair.", + "summary": "The two closed issues share an identical title and close body lengths, and 45145 is earlier with one inbound reference. That makes 45145 the better consolidation target, but the packet only provides soft-similarity evidence, so I would not treat the pair as conclusively duplicate with high confidence.", + "confidence": 0.78, + "canonical_issue_reason": "Issue 45145 is the earlier report and has an inbound reference, so it is the more established thread to keep as the canonical issue. The evidence here is limited to identical titles and soft similarity, so the choice is pragmatic rather than definitive.", "canonical_pr_reason": null, - "best_issue_reason": "#45145 is the strongest issue representative for the cluster because it is earlier and has external reference traffic, while #45151 does not add distinct scope.", + "best_issue_reason": "45145 is the best issue representative because it predates 45151 and already has inbound linkage, while the available evidence does not strongly distinguish the two beyond soft similarity.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45145", "right": "issue:45151", - "accept": true, - "reason": "The issues share the same title and a similarity signal, and their timing/body size are close enough to treat them as likely duplicates of the same underlying report." + "accept": false, + "reason": "Reject: the packet only marks this as soft similarity and explicitly says deterministic acceptance is false. Identical titles and similar body lengths suggest a possible duplicate, but there is not enough direct content evidence to confidently merge them as the same report." } ] }, "evaluator_result": { "accept": false, - "feedback": "The duplicate call is a bit too confident for the evidence provided. The packet only supports identical titles, close timing, similar body sizes, one inbound reference, and a soft-similarity signal; it does not support stronger characterizations like \"near-identical\" or \"article-style issue.\" Please make the summary more conservative (e.g., \"likely duplicate\") and avoid adding unsupported details." + "feedback": "The canonical choice is plausible, but the soft-edge verdict is too strong for the packet: the pair is only linked by soft similarity, and the packet explicitly marks the pair as not deterministically acceptable. The summary also overstates the evidence by saying the bodies are \"very similar\" / \"same report duplicated\" without direct content comparison in the packet. A more conservative stance would note identical titles, similar body lengths, and 45145\u2019s earlier timestamp plus inbound reference, but stop short of asserting duplication with high confidence." }, "evaluator_used": true, "retried": true, - "accepted_nontrivial_soft_edge": true, + "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null }, @@ -15202,12 +15049,12 @@ "pull_request:43823|pull_request:45213", "pull_request:43251|pull_request:43254" ], - "prepared_review_unit_hash": "4e7290f38414f689701233e7f9be4947a4480d05dba7dd03adda8f9d314a60e8", + "prepared_review_unit_hash": "4d91f79365bfd5170a0abdce3d9b1ff8f084393f331f803f6bc6a655b6aae8fc", "component_budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 18, - "serialized_chars": 35176, + "serialized_chars": 35175, "estimated_input_tokens": 8794, "estimated_eval_tokens": 17844 }, @@ -15215,7 +15062,7 @@ "node_count": 13, "item_count": 13, "soft_pair_count": 18, - "serialized_chars": 35176, + "serialized_chars": 35175, "estimated_input_tokens": 8794, "estimated_eval_tokens": 17844 }, @@ -15224,126 +15071,126 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is mostly noisy and contains several unrelated pull requests. The only clear duplicate-like pair is the two `fixed_cross_entropy` PRs, which both address the same loss-utility kwargs support. All other soft edges look unrelated by title, touched files, or code path.", - "confidence": 0.95, + "summary": "Mostly unrelated PRs are bundled by loose similarity. The only true duplicate-looking pair is the fixed_cross_entropy kwargs fix (43251/43254).", + "confidence": 0.86, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #43251 is the best canonical PR here: it has an explicit issue target, touches the core `fixed_cross_entropy` implementation, and is the more complete version of the same fix.", + "canonical_pr_reason": "PR 43251 is the best representative of the only real duplicate pair: it directly targets issue 43240 and cleanly implements the cross_entropy kwargs forwarding fix.", "best_issue_reason": null, - "best_pr_reason": "PR #43251 is the strongest representative of the only real duplicate pair in the set, and it is directly tied to issue 43240.", + "best_pr_reason": "PR 43251 is the strongest overall candidate: same code path as 43254, explicit issue linkage, and the more complete bugfix framing.", "soft_edge_verdicts": [ { "left": "pull_request:39895", "right": "pull_request:43424", "accept": false, - "reason": "Unrelated changes: VideoPrism model/docs versus ExecuTorch dynamic-shape export tests." + "reason": "Different domains: new VideoPrism model docs/code vs an ExecuTorch dynamic-shape test." }, { "left": "pull_request:41855", "right": "pull_request:43823", "accept": false, - "reason": "Different areas: Mistral tokenizer methods versus adding a new MobileLLM model." + "reason": "Tokenizer helper methods vs adding a new MobileLLM model; not the same change." }, { "left": "pull_request:41855", "right": "pull_request:43424", "accept": false, - "reason": "Tokenizer API additions are unrelated to ExecuTorch export tests." + "reason": "Mistral tokenizer methods and ExecuTorch export tests are unrelated." }, { "left": "pull_request:42668", "right": "pull_request:43823", "accept": false, - "reason": "Processor auto-loading robustness is unrelated to MobileLLM model addition." + "reason": "Processor auto-loading robustness vs introducing MobileLLM; only broad processor/model theme overlaps." }, { "left": "pull_request:43251", "right": "pull_request:43823", "accept": false, - "reason": "Loss-function kwargs support and MobileLLM model addition are unrelated." + "reason": "Cross-entropy kwargs fix and a new model addition are unrelated code paths." }, { "left": "pull_request:43251", "right": "pull_request:44827", "accept": false, - "reason": "Different code paths: cross-entropy helper versus Mistral4 test/model fixes." + "reason": "Loss utility fix vs Mistral4/model/PEFT-related changes; not the same bug." }, { "left": "pull_request:43424", "right": "pull_request:44827", "accept": false, - "reason": "ExecuTorch export testing is unrelated to Mistral4 fixes." + "reason": "ExecuTorch dynamic-shape export tests do not match the Mistral4 test/model fix." }, { "left": "pull_request:43424", "right": "pull_request:43823", "accept": false, - "reason": "Dynamic-shape export tests are unrelated to MobileLLM model code." + "reason": "ExecuTorch export testing and MobileLLM model addition are unrelated." }, { "left": "pull_request:43823", "right": "pull_request:43995", "accept": false, - "reason": "Adding MobileLLM is unrelated to Falcon output-interface refactoring." + "reason": "Adding MobileLLM and refactoring Falcon output collection are different model-specific changes." }, { "left": "pull_request:43823", "right": "pull_request:45622", "accept": false, - "reason": "MobileLLM model addition is unrelated to PEFT constructor fixes." + "reason": "MobileLLM introduction vs PEFT constructor internals; no shared concrete fix." }, { "left": "pull_request:43995", "right": "pull_request:45213", "accept": false, - "reason": "Falcon model refactor and model-creation skill content are unrelated." + "reason": "Falcon refactor is unrelated to the model-creation skill/meta PR." }, { "left": "pull_request:43995", "right": "pull_request:44827", "accept": false, - "reason": "Falcon output-collection refactor is unrelated to Mistral4 test fixes." + "reason": "Falcon output-collection refactor and Mistral4 test fixes are different model paths." }, { "left": "pull_request:44827", "right": "pull_request:45622", "accept": false, - "reason": "Mistral4 test/model changes and PEFT constructor internals do not fix the same bug." + "reason": "Mistral4 test/model fixes and PEFT constructor internals are not the same concrete bug, despite superficial overlap." }, { "left": "pull_request:44827", "right": "pull_request:45587", "accept": false, - "reason": "Mistral4 fixes are unrelated to continuous batching documentation." + "reason": "Mistral4/code fixes vs documentation on continuous batching memory management." }, { "left": "pull_request:44827", "right": "pull_request:45170", "accept": false, - "reason": "Mistral4 fixes are unrelated to the CLIP-like `layrnorm` rename/conversion cleanup." + "reason": "Mistral4 fixes are unrelated to the layrnorm->layernorm renaming sweep." }, { "left": "pull_request:44827", "right": "pull_request:45213", "accept": false, - "reason": "Mistral4 fixes are unrelated to the model-creation skill PR." - }, - { - "left": "pull_request:43823", - "right": "pull_request:45213", - "accept": false, - "reason": "MobileLLM model addition is unrelated to the model-creation skill scaffolding PR." + "reason": "Mistral4 model/test work is unrelated to the meta model-creation skill PR." }, { "left": "pull_request:43251", "right": "pull_request:43254", "accept": true, - "reason": "Both PRs modify `fixed_cross_entropy` for the same underlying kwargs support; they are effectively the same change in the same code path." + "reason": "Same file, same issue target 43240, and both implement the same cross_entropy kwargs-forwarding fix." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45213", + "accept": false, + "reason": "MobileLLM model addition vs a meta skill/documentation PR; no shared code fix." } ] }, "evaluator_result": { "accept": true, - "feedback": "The analysis is grounded in the packet. The only accepted soft edge is the clearly mergeable pair `pull_request:43251` / `pull_request:43254`, which both modify `src/transformers/loss/loss_utils.py` to add kwargs support to the same `fixed_cross_entropy` path and share issue target `43240`. The remaining soft edges are conservatively rejected as unrelated by file area and bug context. One minor note: phrases like \"more complete version\" are a bit interpretive, but not enough to undermine the overall precision here." + "feedback": "The summary is grounded in the packet and stays conservative. The only accepted duplicate pair is the clearly linked fixed_cross_entropy kwargs fix (43251/43254), and the other soft pairs are reasonably rejected as unrelated or at most loosely similar rather than mergeable into one bugfix PR." }, "evaluator_used": true, "retried": false, @@ -15370,12 +15217,12 @@ "soft_pairs": [ "pull_request:40546|pull_request:42781" ], - "prepared_review_unit_hash": "e30e57c82603b72fde150ddd8954ea72acdf969142881066a93abb433d042519", + "prepared_review_unit_hash": "94b2ead41312d1c75c358f72a301b6421334f42f69d7dac8bb0026954c18b07d", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 7225, + "serialized_chars": 7226, "estimated_input_tokens": 1807, "estimated_eval_tokens": 3870 }, @@ -15383,7 +15230,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 7225, + "serialized_chars": 7226, "estimated_input_tokens": 1807, "estimated_eval_tokens": 3870 }, @@ -15392,18 +15239,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are related VibeVoice PRs, but they are not duplicates: 40546 is the base VibeVoice implementation, while 42781 adds a separate VibeVoice Realtime/acoustic-tokenizer expansion. The overlap in auto-registration and docs is expected for two PRs in the same model family.", + "summary": "Both PRs are about the VibeVoice family, but they are not the same change: #40546 implements the core VibeVoice integration, while #42781 is a draft add-on for VibeVoice Realtime with an acoustic tokenizer and generation tweaks.", "confidence": 0.92, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 40546 is the better canonical candidate for the cluster because it is the original, non-draft VibeVoice implementation with substantial review activity; 42781 is a later, distinct realtime follow-up.", + "canonical_pr_reason": "#40546 is the earlier, more complete base implementation of VibeVoice and has substantial review activity; #42781 is a later draft that builds on the same model family but targets realtime support.", "best_issue_reason": null, - "best_pr_reason": "PR 40546 is the strongest standalone PR in this cluster: it is the main VibeVoice landing, non-draft, and more mature than the draft realtime extension.", + "best_pr_reason": "#40546 is the best representative of the cluster because it covers the primary integration and is far more mature than the draft realtime extension.", "soft_edge_verdicts": [ { "left": "pull_request:40546", "right": "pull_request:42781", "accept": false, - "reason": "Do not merge: they share VibeVoice plumbing and docs, but 42781 is a separate realtime/acoustic-tokenizer extension rather than the same concrete code-path change as 40546." + "reason": "They share the VibeVoice codebase, but the concrete changes are different: one is the original model integration, the other is a draft realtime variant with additional tokenizer/generation work. This is related work, not the same underlying bug or change." } ] }, @@ -15433,12 +15280,12 @@ "soft_pairs": [ "pull_request:40755|pull_request:41224" ], - "prepared_review_unit_hash": "a80d20d50cbfbeb0f633577f78033991c14be36f5e983594abed2af1c84273ce", + "prepared_review_unit_hash": "471bc1970432799dc4197b6974defc8c1d588f3ab7aa19f653bdb067a78309e6", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4676, + "serialized_chars": 4675, "estimated_input_tokens": 1169, "estimated_eval_tokens": 2594 }, @@ -15446,7 +15293,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4676, + "serialized_chars": 4675, "estimated_input_tokens": 1169, "estimated_eval_tokens": 2594 }, @@ -15455,18 +15302,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two pull requests are unrelated feature additions: one adds TimesFM covariate forecasting, the other adds DINOv3 image-classification support. They are not duplicates and should not be clustered together as the same underlying change.", - "confidence": 0.97, + "summary": "The two PRs are unrelated feature additions in different model families: TimesFM covariate forecasting vs. DINOv3 image classification support. They should not be clustered as duplicates.", + "confidence": 0.99, "canonical_issue_reason": null, - "canonical_pr_reason": "No single canonical PR for this cluster: #40755 and #41224 touch different models, different code paths, and solve different problems.", + "canonical_pr_reason": "No single PR is a clear canonical for the cluster because the items are unrelated; if forced, PR #40755 is the broader standalone feature with more implementation depth.", "best_issue_reason": null, - "best_pr_reason": "PR #40755 is the broader standalone change in this cluster, with a substantial model, utility, docs, and test update for a new forecasting capability.", + "best_pr_reason": "PR #40755 is the better cluster representative only by size/scope, but it is not a semantic match to PR #41224 and should not imply duplication.", "soft_edge_verdicts": [ { "left": "pull_request:40755", "right": "pull_request:41224", "accept": false, - "reason": "Different features in different model families (TimesFM covariates vs. DINOv3 image classification); no shared bug or mergeable code-path fix." + "reason": "Different models, different tasks, and different code paths: TimesFM forecasting with covariates vs. DINOv3 image classification. No evidence they fix the same underlying bug or could be merged into one PR." } ] }, @@ -15562,7 +15409,7 @@ "soft_pairs": [ "pull_request:41797|pull_request:45186" ], - "prepared_review_unit_hash": "ae5e564d9e17274026e7bfea7cc8a50ca30dacbdf98414468d533b1b86492295", + "prepared_review_unit_hash": "fa0dda77675745a6de0c8b882e73a88bda88b0377e98fcf4f9c18588a20b2b63", "component_budget": { "node_count": 2, "item_count": 2, @@ -15584,18 +15431,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are two unrelated pull requests adding different model integrations: DeepSeek OCR and Isaac. The overlap is mostly boilerplate registry/docs wiring common to new-model onboarding, not the same bug or change.", + "summary": "These are two separate model-addition PRs with similar scaffold files, but they implement different architectures and code paths (DeepSeek OCR vs Isaac). They should not be treated as duplicates.", "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": null, + "canonical_pr_reason": "No single canonical PR: each submission adds a different model package, docs, autos, tests, and model-specific implementation for a distinct architecture.", "best_issue_reason": null, - "best_pr_reason": null, + "best_pr_reason": "Neither PR is a good global representative for the cluster because the similarity is mostly boilerplate from new-model integration rather than the same underlying change.", "soft_edge_verdicts": [ { "left": "pull_request:41797", "right": "pull_request:45186", "accept": false, - "reason": "Different models and different code paths. Shared files are generic onboarding/registry touchpoints, not evidence of the same underlying change or something that could be merged into one PR." + "reason": "Reject: both are new-model integration PRs, but for different models (DeepSeek OCR vs Isaac) with different implementation files and model-specific behavior; they do not fix the same code-path problem and would not plausibly merge into one PR." } ] }, @@ -15625,12 +15472,12 @@ "soft_pairs": [ "pull_request:42166|pull_request:45426" ], - "prepared_review_unit_hash": "efaba93f915216a4a8a937776533daa32c797e9bdab668f0a357bca685f21edc", + "prepared_review_unit_hash": "ce8dd96152cebfb51ed746af1b8c4baad518a0af1baa4233a596f9dae202a2d2", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5407, + "serialized_chars": 5408, "estimated_input_tokens": 1352, "estimated_eval_tokens": 2960 }, @@ -15638,7 +15485,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5407, + "serialized_chars": 5408, "estimated_input_tokens": 1352, "estimated_eval_tokens": 2960 }, @@ -15647,18 +15494,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two unrelated model-addition PRs. They share some registration boilerplate, but one adds InternVLFlash and docs/tests, while the other adds AXK1 and auto-docstring wiring. They do not look like the same underlying change.", - "confidence": 0.95, + "summary": "Two separate model-addition PRs, not duplicates: one introduces InternVLFlash, the other introduces AXK1. They share generic auto-registration/documentation files, but they target different models and code paths.", + "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR: the PRs target different models and different implementation paths, so they are not duplicates of one change.", + "canonical_pr_reason": "PR 42166 is the more complete and established integration (more files, docs, tests, and review activity), but it is not a duplicate of 45426.", "best_issue_reason": null, - "best_pr_reason": "PR 42166 is the stronger standalone PR if one must be picked: it has broader implementation and test/docs coverage, but it is still unrelated to PR 45426.", + "best_pr_reason": "PR 42166 is the best representative of the cluster only by maturity and completeness; 45426 is a separate AXK1 addition with no evidence of being the same change.", "soft_edge_verdicts": [ { "left": "pull_request:42166", "right": "pull_request:45426", "accept": false, - "reason": "Reject: both touch model-registration boilerplate, but they add different models (InternVLFlash vs AXK1) with distinct code, docs, and tests. They do not fix the same concrete bug/change and would not be merged into one PR." + "reason": "Different model integrations (InternVLFlash vs AXK1). Shared auto-registry scaffolding is incidental and not the same concrete feature or bug fix." } ] }, @@ -15695,70 +15542,70 @@ "pull_request:43291|pull_request:44815", "pull_request:43665|pull_request:44815" ], - "prepared_review_unit_hash": "4040116108cf142361c95a46dc81bdc502b0b827c360b70ba69955f27722fa4f", + "prepared_review_unit_hash": "661b99a165240e0ca813366c9dc70884d3eb7517243fe45e4a0acc737e83fd3a", "component_budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 10167, - "estimated_input_tokens": 2542, - "estimated_eval_tokens": 5340 + "serialized_chars": 10170, + "estimated_input_tokens": 2543, + "estimated_eval_tokens": 5342 }, "budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 10167, - "estimated_input_tokens": 2542, - "estimated_eval_tokens": 5340 + "serialized_chars": 10170, + "estimated_input_tokens": 2543, + "estimated_eval_tokens": 5342 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These four PRs are not duplicates of one another; they cover separate areas (Whisper ASR behavior, Whisper test cleanup, unrelated model test edits, and FP8/dequant loading changes). The only commonality is shallow similarity in titles or tests touching nearby domains.", - "confidence": 0.98, + "summary": "These PRs are mostly unrelated despite some superficial model-area overlap. The two Whisper PRs touch different code paths, while the CLIP/ViT test edit and the FP8 dequant fix are clearly separate.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #42227 is the most canonical standalone fix: it addresses a specific Whisper pipeline bug, has an explicit issue target, and contains a focused code change with tests.", + "canonical_pr_reason": "PR 42227 is the strongest standalone bug fix: it changes the ASR pipeline to actually forward `return_language` into the Whisper generation path and adds targeted tests.", "best_issue_reason": null, - "best_pr_reason": "PR #42227 is the strongest representative of a real bug fix; the others are either test-only, clearly unrelated, or broader draft work.", + "best_pr_reason": "PR 42227 is the best representative of a concrete user-facing fix; the others are either test-only, obviously unrelated, or broad multi-file refactors/fixes.", "soft_edge_verdicts": [ { "left": "pull_request:42227", "right": "pull_request:43291", "accept": false, - "reason": "42227 fixes Whisper return_language plumbing; 43291 is a separate Whisper tokenizer/test cleanup. Same subsystem, but not the same bug or mergeable change." + "reason": "Both are Whisper-related, but they fix different problems in different layers: ASR pipeline parameter forwarding vs tokenizer decode/timestamp handling. They do not look mergeable as one PR." }, { "left": "pull_request:42227", "right": "pull_request:43665", "accept": false, - "reason": "42227 is an ASR pipeline fix; 43665 is unrelated test-file noise across CLIP/ViT. No shared code-path or concrete bug." + "reason": "Unrelated changes. 42227 fixes Whisper return-language forwarding; 43665 is a test-file-only edit in CLIP/ViT and does not share the same bug or code path." }, { "left": "pull_request:42227", "right": "pull_request:44815", "accept": false, - "reason": "Whisper ASR return-language handling and FP8/dequant loading are unrelated changes in different subsystems." + "reason": "Different subsystems and different bugs: Whisper ASR pipeline vs FP8 dequant/model-loading changes. No common underlying fix." }, { "left": "pull_request:43291", "right": "pull_request:43665", "accept": false, - "reason": "Both touch tests, but one is Whisper tokenizer behavior and the other is unrelated CLIP/ViT test edits. Not the same underlying change." + "reason": "Whisper tokenizer work vs unrelated CLIP/ViT test edits. No shared concrete issue." }, { "left": "pull_request:43291", "right": "pull_request:44815", "accept": false, - "reason": "Whisper tokenizer/test work does not match FP8 dequant/model-loading changes." + "reason": "Different areas and different fixes. The Whisper tokenizer change is unrelated to FP8 dequant/loading work." }, { "left": "pull_request:43665", "right": "pull_request:44815", "accept": false, - "reason": "Unrelated test-file changes versus a substantive FP8/dequant implementation fix; no shared bug or code path." + "reason": "These are clearly unrelated; one is nonsensical test-file edits, the other is a substantial FP8/dequant implementation change." } ] }, @@ -15788,12 +15635,12 @@ "soft_pairs": [ "pull_request:42975|pull_request:42976" ], - "prepared_review_unit_hash": "303205f541c607005d284f0563010f8b29389c1414dee35bf712064c2815561f", + "prepared_review_unit_hash": "58b856be31fef752c97b8d77ad05161ad9571103fc8424f715e96475de5aaa48", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5935, + "serialized_chars": 5934, "estimated_input_tokens": 1484, "estimated_eval_tokens": 3224 }, @@ -15801,7 +15648,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5935, + "serialized_chars": 5934, "estimated_input_tokens": 1484, "estimated_eval_tokens": 3224 }, @@ -15810,18 +15657,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are two separate GitHub Actions maintenance PRs. They overlap in a few workflow files, but one is focused on Node 24 compatibility for core actions, while the other updates Docker build-related actions and other workflow dependencies. They do not look like the same underlying change.", - "confidence": 0.92, + "summary": "Two workflow-dependency upgrade PRs with overlapping filenames but different action/version changes; they are related maintenance, not the same fix/change.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 42975 is the more representative change: it has a clear compatibility goal and a broader, coherent set of workflow action upgrades.", + "canonical_pr_reason": "PR #42975 is the better canonical PR candidate because it has the broader, more explicit goal ('Upgrade GitHub Actions for Node 24 compatibility') and touches a larger set of workflow action versions in a single compatibility-driven sweep.", "best_issue_reason": null, - "best_pr_reason": "PR 42975 is the best fit for the cluster because it is the more focused and substantial workflow-actions upgrade, whereas 42976 is a separate dependency refresh centered on Docker build actions.", + "best_pr_reason": "PR #42975 is the best representative of the cluster since it is the more general workflow-action compatibility upgrade and appears more central than the narrower docker-action bump in #42976.", "soft_edge_verdicts": [ { "left": "pull_request:42975", "right": "pull_request:42976", "accept": false, - "reason": "Different maintenance changes: 42975 upgrades actions for Node 24 compatibility, while 42976 updates docker/build-push-action and related workflow versions. Shared workflow files alone are not enough to treat them as the same PR." + "reason": "Reject: both are GitHub Actions version bumps, but they change different actions and different workflow surfaces (checkout/cache/upload-artifact vs docker/build-push-action). They do not look like the same underlying bug or concrete code-path fix." } ] }, @@ -15843,7 +15690,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-42978-9", + "cluster_id": "cluster-42978-10", "nodes": [ "pull_request:42978", "pull_request:43448", @@ -15853,7 +15700,8 @@ "pull_request:45283", "pull_request:45490", "pull_request:45616", - "pull_request:45626" + "pull_request:45626", + "pull_request:45630" ], "soft_pairs": [ "pull_request:42978|pull_request:43448", @@ -15867,108 +15715,122 @@ "pull_request:43973|pull_request:45283", "pull_request:44601|pull_request:45626", "pull_request:45283|pull_request:45626", - "pull_request:45490|pull_request:45626" + "pull_request:45490|pull_request:45626", + "pull_request:45490|pull_request:45630", + "pull_request:45626|pull_request:45630" ], - "prepared_review_unit_hash": "9676561db9b3b4c8a24852ae3c1e314487b0bcde673bb0c3f3e10e46b524af85", + "prepared_review_unit_hash": "4e1e2d0adc6d93b03bf55f37a89c9c17bc15dae33f71f0f25238cc3dc7d08e52", "component_budget": { - "node_count": 9, - "item_count": 9, - "soft_pair_count": 12, - "serialized_chars": 29082, - "estimated_input_tokens": 7271, - "estimated_eval_tokens": 14798 + "node_count": 10, + "item_count": 10, + "soft_pair_count": 14, + "serialized_chars": 33117, + "estimated_input_tokens": 8280, + "estimated_eval_tokens": 16816 }, "budget": { - "node_count": 9, - "item_count": 9, - "soft_pair_count": 12, - "serialized_chars": 29082, - "estimated_input_tokens": 7271, - "estimated_eval_tokens": 14798 + "node_count": 10, + "item_count": 10, + "soft_pair_count": 14, + "serialized_chars": 33117, + "estimated_input_tokens": 8280, + "estimated_eval_tokens": 16816 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster groups several unrelated PRs that all add new model support or related integration plumbing. They share template-like files and auto-registry edits, but they do not appear to fix the same concrete bug or implement the same change.", - "confidence": 0.94, + "summary": "This cluster is not a duplicate set. It mixes unrelated model-add PRs (ViT NEPA, Molmo, Molmo2, CTSM, DeepSeek V4, Kimi2-6, PP-FormulaNet, Lfm2Audio) plus two infrastructure changes (pipeline parallel support, Qwen3.5 GGUF loading). The shared filenames are mostly broad auto/doc scaffolding, not the same underlying change.", + "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "No single PR is a true duplicate canonical here. If one must be chosen, #45626 is the most structurally central of the later model-support additions, but it is still a distinct feature PR rather than the same change as the others.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "#45626 is the broadest and most recent model-support PR in the cluster, with multiple soft links to other model-addition PRs. Still, it is not a good duplicate anchor because the underlying models and code paths differ.", + "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "pull_request:42978", "right": "pull_request:43448", "accept": false, - "reason": "Different model additions: ViT NEPA vs Molmo. Overlap is only in shared scaffolding/docs/auto-registry edits, not the same implementation." + "reason": "Different model additions: ViT NEPA vs Molmo. Shared docs/auto registry edits are boilerplate, not the same change." }, { "left": "pull_request:42978", "right": "pull_request:43451", "accept": false, - "reason": "Different model additions: ViT NEPA vs Molmo2. Shared framework files do not indicate the same concrete change." + "reason": "Different model additions: ViT NEPA vs Molmo2. Same broad model-onboarding pattern, but not the same model or code path." }, { "left": "pull_request:42978", "right": "pull_request:45490", "accept": false, - "reason": "ViT NEPA and CTSM are unrelated model-support PRs; similarity comes from boilerplate model-registration work." + "reason": "Different model additions: ViT NEPA vs CTSM. No overlapping bug or change target beyond generic docs/auto wiring." }, { "left": "pull_request:43448", "right": "pull_request:43451", "accept": false, - "reason": "Molmo and Molmo2 are related names but appear to be distinct model families with separate files and support code." + "reason": "Molmo and Molmo2 are distinct model integrations with different files and behavior; they are not the same underlying PR." }, { "left": "pull_request:43448", "right": "pull_request:45490", "accept": false, - "reason": "Molmo vs CTSM are different model integrations; shared auto/docs changes are not enough to merge them as duplicates." + "reason": "Molmo vs CTSM are unrelated model additions; shared repo plumbing is too generic to merge as duplicates." }, { "left": "pull_request:43448", "right": "pull_request:45616", "accept": false, - "reason": "Molmo and DeepSeek V4 are unrelated model additions with different code paths and artifacts." + "reason": "Molmo and DeepSeek V4 are separate model integrations with different architectures and files." }, { "left": "pull_request:43451", "right": "pull_request:45490", "accept": false, - "reason": "Molmo2 and CTSM are distinct model-support changes, not the same bug fix or feature." + "reason": "Molmo2 vs CTSM are different model additions; no shared concrete bug or implementation path." }, { "left": "pull_request:43451", "right": "pull_request:45616", "accept": false, - "reason": "Molmo2 and DeepSeek V4 are different model additions; overlap is limited to shared registry/doc plumbing." + "reason": "Molmo2 and DeepSeek V4 are unrelated model integrations; shared auto-registration is incidental." }, { "left": "pull_request:43973", "right": "pull_request:45283", "accept": false, - "reason": "Lfm2 Audio model support and Qwen3.5 GGUF loading support address different subsystems and problems." + "reason": "Lfm2Audio model support and Qwen3.5 GGUF loading are unrelated changes; one is model onboarding, the other is loading-format support." }, { "left": "pull_request:44601", "right": "pull_request:45626", "accept": false, - "reason": "Native pipeline-parallel loading support is infrastructure work; PP-FormulaNet is a model addition. Not the same change." + "reason": "Native pipeline-parallel loading support is infrastructure work, while PP-FormulaNet is a model-add PR; they do not fix the same code-path problem." }, { "left": "pull_request:45283", "right": "pull_request:45626", "accept": false, - "reason": "Qwen3.5 GGUF loading support and PP-FormulaNet model support target different code paths and are not mergeable as one PR." + "reason": "Qwen3.5 GGUF mapping changes and PP-FormulaNet model support are different features with different targets." }, { "left": "pull_request:45490", "right": "pull_request:45626", "accept": false, - "reason": "CTSM model support and PP-FormulaNet model support are separate model additions with different implementation details." + "reason": "CTSM model addition and PP-FormulaNet model support are separate model PRs, not duplicates." + }, + { + "left": "pull_request:45490", + "right": "pull_request:45630", + "accept": false, + "reason": "CTSM and Kimi2-6 are distinct model additions with different implementations and test coverage." + }, + { + "left": "pull_request:45626", + "right": "pull_request:45630", + "accept": false, + "reason": "PP-FormulaNet and Kimi2-6 are unrelated model additions; the overlap is only generic onboarding files." } ] }, @@ -16001,12 +15863,12 @@ "pull_request:43488|pull_request:45476", "pull_request:43532|pull_request:45476" ], - "prepared_review_unit_hash": "e10c00576cf8612b9593a4c95063921eccc214f8a47e66cb77077dc622bc6ac7", + "prepared_review_unit_hash": "b3131465548bef1fa2e299b189e40654d592439467b2a1a31cce3533f7e7f785", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 7467, + "serialized_chars": 7468, "estimated_input_tokens": 1867, "estimated_eval_tokens": 3990 }, @@ -16014,7 +15876,7 @@ "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 7467, + "serialized_chars": 7468, "estimated_input_tokens": 1867, "estimated_eval_tokens": 3990 }, @@ -16023,30 +15885,30 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are three unrelated open \"don't merge\" PRs with superficial overlap on tests/workflows. The shared `tests/models/vit/test_modeling_vit.py` touch is incidental; they do not fix the same bug or implement the same change.", + "summary": "These three pull requests are not duplicates of one another. They are all \"don't merge\"/demo-style changes, but they touch different code paths and subsystems: packaging/versioning, CI/workflow plumbing, and a workflow-caller plus unrelated tokenization/test edits. The shared vit test filename appears incidental rather than indicating the same change.", "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": "No single underlying PR change ties these together. If one representative is needed, #43532 is the most coherent/substantive workflow-oriented change, but it is not a duplicate of the others.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "#43532 is the best representative only in the sense that it is the most coherent and substantial of the three; however, the set does not form a true duplicate cluster.", + "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "pull_request:43488", "right": "pull_request:43532", "accept": false, - "reason": "43488 is a setup/version/dependency tweak; 43532 is a workflow and test harness rewrite. Shared vit test filename is incidental, not the same change." + "reason": "Different concrete changes: 43488 edits setup/dependency/version metadata and a ViT test, while 43532 rewrites self-comment CI workflows and testing utilities. Shared test filename is not enough to make them the same fix." }, { "left": "pull_request:43488", "right": "pull_request:45476", "accept": false, - "reason": "43488 changes packaging/versioning, while 45476 adds a CI workflow and unrelated code/test edits. No common bug or code-path fix." + "reason": "43488 is packaging/version/dependency housekeeping; 45476 adds a PR CI caller workflow and unrelated dummy edits in CLIP/Chinese-CLIP/ViT files. No single underlying bug or change matches." }, { "left": "pull_request:43532", "right": "pull_request:45476", "accept": false, - "reason": "Both touch CI/test infrastructure, but they are different workflow changes with different file sets and goals. Not plausibly mergeable as one PR." + "reason": "Both mention tests/workflows, but they target different code paths and repos: 43532 changes self-comment/self-scheduled/slack notification logic, while 45476 adds a workflow-caller and unrelated tokenization/test edits. Not mergeable as one PR." } ] }, @@ -16076,12 +15938,12 @@ "soft_pairs": [ "pull_request:43612|pull_request:43613" ], - "prepared_review_unit_hash": "d48b2cac9ffaccaf384c25d502eb6784dbb16e59da830d6bbf70946e44748ef3", + "prepared_review_unit_hash": "25d55e9326efa426b03fcc769db20a121adebd7abf12862a2d0d2b7e6dcd7652", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 6083, + "serialized_chars": 6082, "estimated_input_tokens": 1521, "estimated_eval_tokens": 3298 }, @@ -16089,7 +15951,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 6083, + "serialized_chars": 6082, "estimated_input_tokens": 1521, "estimated_eval_tokens": 3298 }, @@ -16098,18 +15960,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open PRs add similarly named but distinct pipeline features: concept segmentation vs visual segmentation. They share documentation and registry plumbing, but they target different underlying tasks and model families, so they should not be deduplicated.", - "confidence": 0.98, + "summary": "These are related pipeline-addition PRs, but they implement different features: promptable concept segmentation vs promptable visual segmentation, with different task docs, pipeline modules, and model/test coverage. They should not be merged as duplicates.", + "confidence": 0.95, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR: these are separate feature additions with different tasks, model backends, and test coverage.", + "canonical_pr_reason": "No canonical PR: the two PRs target different segmentation pipelines and different underlying integrations, so they are not the same change.", "best_issue_reason": null, - "best_pr_reason": "PR 43613 is the broader single artifact to keep if one must be chosen, but it still should not subsume PR 43612 because the underlying pipeline feature is different.", + "best_pr_reason": "If a representative is needed, PR 43613 is the broader feature PR, touching more model integrations and tests, but it is still not a duplicate of 43612.", "soft_edge_verdicts": [ { "left": "pull_request:43612", "right": "pull_request:43613", "accept": false, - "reason": "Both add promptable segmentation pipelines, but one is for concept segmentation and the other for visual segmentation; they touch different concrete code paths and model integrations, so they are not the same change." + "reason": "Same general area, but not the same underlying change. One adds promptable concept segmentation and the other adds promptable visual segmentation, with different docs, pipeline files, and model/test targets." } ] }, @@ -16139,40 +16001,40 @@ "soft_pairs": [ "pull_request:43651|pull_request:43663" ], - "prepared_review_unit_hash": "c91f146e599c03664fc584ad4e0dd996821ca6cd7f5c7c91fb6b4f71d33723ff", + "prepared_review_unit_hash": "68b3d90c3f85dcb3b6c96790e7c9d56b2e399c8f289fbbc0b917b6527abaadc8", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4292, - "estimated_input_tokens": 1073, - "estimated_eval_tokens": 2402 + "serialized_chars": 4293, + "estimated_input_tokens": 1074, + "estimated_eval_tokens": 2404 }, "budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4292, - "estimated_input_tokens": 1073, - "estimated_eval_tokens": 2402 + "serialized_chars": 4293, + "estimated_input_tokens": 1074, + "estimated_eval_tokens": 2404 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both pull requests touch `trainer.py` and add customization hooks, but they address different trainer behaviors: gradient-accumulation loss scaling vs. signature-column filtering. They are related in theme, not duplicates.", - "confidence": 0.95, + "summary": "These are two unrelated Trainer enhancement PRs that only overlap on the same file and subsystem. One changes gradient-accumulation loss scaling, the other factors out signature-column inspection for custom trainers/PEFT handling.", + "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": null, + "canonical_pr_reason": "PR 43651 is a slightly stronger canonical representative because it has more discussion and a clearer end-to-end behavioral change; 43663 is a separate, independent refactor/extension point.", "best_issue_reason": null, - "best_pr_reason": "PR 43651 is the stronger representative of the cluster because it changes core training-step loss scaling behavior and adds a narrowly scoped extension point; PR 43663 is a separate column-filtering hook.", + "best_pr_reason": "PR 43651 is the better cluster representative overall, but only by convention; the PRs are not duplicates and should not be merged into one triage bucket as the same fix.", "soft_edge_verdicts": [ { "left": "pull_request:43651", "right": "pull_request:43663", "accept": false, - "reason": "Different code paths and goals: one controls gradient-accumulation loss scaling in `training_step`, the other refactors signature-based column filtering for inputs. Same file/subsystem, but not the same underlying change." + "reason": "Different underlying problems: 43651 fixes loss normalization during gradient accumulation, while 43663 adds an overridable signature-column helper for trainer input filtering. Same file/subsystem is not enough to treat them as the same change." } ] }, @@ -16204,7 +16066,7 @@ "pull_request:43656|pull_request:43842", "pull_request:43836|pull_request:43842" ], - "prepared_review_unit_hash": "7c5f32b17fb9dfe47251738b5ef1081bb6f2f1e1c74cc8efa4556d365093b551", + "prepared_review_unit_hash": "ef859ae9ccf165169fc29c86d809480ce17573e63b703af51b58ab9f8826f290", "component_budget": { "node_count": 3, "item_count": 3, @@ -16226,33 +16088,33 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "All three PRs target the same CLI serve.py TypeAdapter annotation/import NameError class of bug. PR 43842 is the cleanest and most focused fix; 43836 looks like an alternate/earlier fix for the same problem, while 43656 is broader and less explicit.", - "confidence": 0.84, + "summary": "43842 looks like the cleanest representative for the concrete `TypeAdapter`/pydantic NameError fix in `src/transformers/cli/serve.py`. 43836 is closely related and appears to be the same file-level fix family, while 43656 is only superficially similar and seems broader and tied to a different explicit issue target.", + "confidence": 0.79, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43842 is the most targeted fix: it directly addresses the TypeAdapter NameError when pydantic is absent by guarding the import under TYPE_CHECKING and quoting the annotation, with minimal unrelated churn.", + "canonical_pr_reason": "PR 43842 is the most focused patch for the specific CLI `TypeAdapter` NameError path, with the clearest narrow fix shape and explicit pydantic-not-installed context.", "best_issue_reason": null, - "best_pr_reason": "43842 is the best representative of the cluster because it fixes the concrete runtime NameError most directly, stays narrowly scoped to serve.py, and its title/diff match the failure mode more clearly than the other PRs.", + "best_pr_reason": "PR 43842 is the best representative because it is the most targeted and least invasive fix for the concrete runtime failure in `serve.py`.", "soft_edge_verdicts": [ { "left": "pull_request:43656", "right": "pull_request:43842", - "accept": true, - "reason": "Same underlying serve.py TypeAdapter NameError in the CLI; both are alternative fixes for the same annotation/runtime import problem and could plausibly be combined." + "accept": false, + "reason": "Both touch `src/transformers/cli/serve.py`, but 43656 is broader and only softly similar to 43842; its different explicit issue target and wider diff make it unsafe to treat as the same underlying bugfix." }, { "left": "pull_request:43836", "right": "pull_request:43842", "accept": true, - "reason": "Same concrete bug in the same file and code path: both adjust TypeAdapter handling to avoid a NameError when pydantic is unavailable." + "reason": "These are tightly related fixes in the same file, share the same explicit issue target, and both address the same `TypeAdapter` NameError/annotation evaluation problem in the CLI serve path." } ] }, "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet, and the soft-edge calls are conservative enough: all three PRs are in the same file, share the TypeAdapter/annotation NameError theme, and the proposed representative (43842) is the most narrowly targeted fix. The pairwise acceptances also look mergeable as alternate fixes for the same bugfix." + "accept": false, + "feedback": "The summary is a bit too strong for the packet. 43836 and 43842 are well-supported as closely related fixes in the same file and even share an issue target, but 43656 only has soft_similarity with 43842 and a different explicit issue target. Its previewed diff also looks broader than a TypeAdapter-only patch. So I would not state that all three are clearly the same concrete bugfix or that the 43656\u219443842 pair is definitely mergeable without more evidence." }, "evaluator_used": true, - "retried": false, + "retried": true, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -16439,334 +16301,316 @@ "pull_request:44044|pull_request:44154", "pull_request:44024|pull_request:44076" ], - "prepared_review_unit_hash": "92c4e5e67b46b16ae1f549455f851d1a258ee7808aa12739f926ba0a7de1d51f", + "prepared_review_unit_hash": "9a8e3d4fec07214ea05d3b70985cde2248d4fec0b5472f6d432ba0d0b4d141af", "component_budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 77, - "serialized_chars": 84501, - "estimated_input_tokens": 21126, - "estimated_eval_tokens": 42508 + "serialized_chars": 84507, + "estimated_input_tokens": 21127, + "estimated_eval_tokens": 42510 }, "budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 72, - "serialized_chars": 76933, - "estimated_input_tokens": 19234, - "estimated_eval_tokens": 38724 + "serialized_chars": 76941, + "estimated_input_tokens": 19236, + "estimated_eval_tokens": 38728 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is a mixed set of model-specific output-tracing refactors. Most overlaps are only at the shared standardized-decorator pattern or the shared #43979 tracking issue; the strongest same-file similarities are within GPT-Neo and GPT-J/CodeGen, but the packet does not conclusively show duplicate fixes for the softer edges.", - "confidence": 0.84, + "summary": "Mostly a wave of model-by-model output-tracing refactors. The closest duplicates are the GPT-J/CodeGen cluster and the GPT-Neo pair; the rest are separate model implementations that only share the same refactor pattern.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #44722 is the clearest representative of the GPT-J/CodeGen subgroup because it spans both codegen and gptj files and explicitly links #43979.", + "canonical_pr_reason": "pull_request:44722 is the best canonical PR for the GPT-J/CodeGen subcluster: it is the broadest file-level refactor, covering both modeling_codegen.py and modeling_gptj.py, and subsumes the narrower GPT-J-only variant.", "best_issue_reason": null, - "best_pr_reason": "PR #44722 is the best global representative because it is the only candidate here that combines the GPT-J/CodeGen code paths with an explicit #43979 linkage.", + "best_pr_reason": "pull_request:44722 is the strongest overall representative because it most completely captures the shared GPT-J/CodeGen output-tracing change and overlaps the narrower GPT-J-only PRs.", "soft_edge_verdicts": [ { "left": "pull_request:43996", "right": "pull_request:44085", "accept": false, - "reason": "Shared output-tracing theme and #43979 linkage, but they are different model families and the packet does not show the same concrete fix." + "reason": "CVT/FNet and GPT-J are different concrete model code paths; only the high-level output-tracing theme matches." }, { "left": "pull_request:43996", "right": "pull_request:44044", "accept": false, - "reason": "Only the broad tracing refactor pattern is shared; CVT/FNet and DeBERTa-v2 are different concrete code paths." + "reason": "CVT/FNet and DeBERTa are unrelated model implementations with different forward paths." }, { "left": "pull_request:44066", "right": "pull_request:44085", - "accept": false, - "reason": "Both touch GPT-J/CodeGen output tracing, but the packet does not clearly establish the same revision or mergeable duplicate fix." + "accept": true, + "reason": "Both are GPT-J output-tracing refactors in src/transformers/models/gptj/modeling_gptj.py; 44066 just bundles the extra CodeGen companion change, so this is the same underlying GPT-J edit." }, { "left": "pull_request:44007", "right": "pull_request:44072", "accept": false, - "reason": "Both are standardized output-tracing refactors, but for different model families and different code paths." + "reason": "RegNet and EfficientNet are separate image-model implementations; not the same change." }, { "left": "pull_request:44072", "right": "pull_request:44722", "accept": false, - "reason": "EfficientNet and GPT-J/CodeGen are unrelated implementations; shared issue-theme overlap is not enough." + "reason": "EfficientNet and GPT-J/CodeGen are different model code paths." }, { "left": "pull_request:44066", "right": "pull_request:44072", "accept": false, - "reason": "GPT-J/CodeGen and EfficientNet are different model paths; this looks like pattern similarity only." + "reason": "GPT-J/CodeGen output tracing and EfficientNet output tracing are different concrete edits." }, { "left": "pull_request:44013", "right": "pull_request:44044", "accept": false, - "reason": "MobileNetV2 and DeBERTa-v2 are separate code paths despite both touching output tracing." + "reason": "MobileNetV2 and DeBERTa are unrelated model implementations." }, { "left": "pull_request:44066", "right": "pull_request:44086", "accept": false, - "reason": "GPT-J/CodeGen and MGP-STR are unrelated model implementations." + "reason": "GPT-J/CodeGen and MGP-STR touch different files and different model code paths." }, { "left": "pull_request:44066", "right": "pull_request:44071", "accept": false, - "reason": "Different architectures and code paths; the shared decorator migration pattern is not enough." + "reason": "GPT-J/CodeGen and MPT are different concrete implementations." }, { "left": "pull_request:44018", "right": "pull_request:44068", - "accept": false, - "reason": "Same GPT-Neo file family, but the packet does not prove these are the same fix rather than sequential refactors." + "accept": true, + "reason": "Both are GPT-Neo output-tracing refactors in the same GPT-Neo file/test area, so they look like the same underlying change." }, { "left": "pull_request:44066", "right": "pull_request:44068", "accept": false, - "reason": "GPT-J/CodeGen and GPT-Neo are different model code paths." + "reason": "GPT-J/CodeGen and GPT-Neo are different model code paths; similar refactor style is not enough." }, { "left": "pull_request:44018", "right": "pull_request:44066", "accept": false, - "reason": "GPT-Neo and GPT-J/CodeGen are separate implementations." + "reason": "GPT-Neo and GPT-J/CodeGen are related refactors but not the same concrete change." }, { "left": "pull_request:44019", "right": "pull_request:44722", "accept": false, - "reason": "ResNet output tracing and GPT-J/CodeGen output tracing are unrelated concrete changes." + "reason": "ResNet and GPT-J/CodeGen are unrelated model-specific edits." }, { "left": "pull_request:44086", "right": "pull_request:44722", "accept": false, - "reason": "MGP-STR and GPT-J/CodeGen are different model families." + "reason": "MGP-STR and GPT-J/CodeGen are different concrete model implementations." }, { "left": "pull_request:44019", "right": "pull_request:44085", "accept": false, - "reason": "ResNet and GPT-J touch different code paths." + "reason": "ResNet and GPT-J are separate model implementations." }, { "left": "pull_request:44018", "right": "pull_request:44019", "accept": false, - "reason": "GPT-Neo and ResNet are unrelated model implementations." + "reason": "GPT-Neo and ResNet are unrelated code paths." }, { "left": "pull_request:44019", "right": "pull_request:44071", "accept": false, - "reason": "ResNet and MPT are different code paths." + "reason": "ResNet and MPT are different model implementations." }, { "left": "pull_request:44068", "right": "pull_request:44116", "accept": false, - "reason": "GPT-Neo and Flaubert are different model families." + "reason": "GPT-Neo and Flaubert/XLM are different code paths." }, { "left": "pull_request:44068", "right": "pull_request:44722", "accept": false, - "reason": "Same GPT-Neo/GPT-J-style refactor theme, but not enough evidence that these are the same fix." + "reason": "GPT-Neo and GPT-J/CodeGen are different model refactors; same wave, not the same change." }, { "left": "pull_request:44071", "right": "pull_request:44722", "accept": false, - "reason": "MPT and GPT-J/CodeGen are unrelated concrete code paths." - }, - { - "left": "pull_request:44018", - "right": "pull_request:44129", - "accept": false, - "reason": "GPT-Neo and SpeechT5 are different model implementations." - }, - { - "left": "pull_request:44018", - "right": "pull_request:44086", - "accept": false, - "reason": "GPT-Neo and MGP-STR are unrelated code paths." - }, - { - "left": "pull_request:44018", - "right": "pull_request:44085", - "accept": false, - "reason": "GPT-Neo and GPT-J are different model families." - }, - { - "left": "pull_request:44068", - "right": "pull_request:44086", - "accept": false, - "reason": "GPT-Neo and MGP-STR are unrelated changes." - }, - { - "left": "pull_request:44071", - "right": "pull_request:44085", - "accept": false, - "reason": "MPT and GPT-J are different concrete code paths." + "reason": "MPT and GPT-J/CodeGen are unrelated model implementations." }, { "left": "pull_request:44059", "right": "pull_request:44086", "accept": false, - "reason": "GPT-2 and MGP-STR are unrelated models." + "reason": "GPT-2 and MGP-STR are different concrete model paths." }, { "left": "pull_request:44085", "right": "pull_request:44086", "accept": false, - "reason": "GPT-J and MGP-STR are unrelated code paths." + "reason": "GPT-J and MGP-STR are unrelated concrete changes." }, { "left": "pull_request:44059", "right": "pull_request:44722", "accept": false, - "reason": "GPT-2 and GPT-J/CodeGen are separate model implementations." + "reason": "GPT-2 and GPT-J/CodeGen are distinct model refactors." }, { "left": "pull_request:44098", "right": "pull_request:44101", "accept": false, - "reason": "ViLT and Flaubert/XLM are unrelated concrete code paths." - }, - { - "left": "pull_request:44018", - "right": "pull_request:44071", - "accept": false, - "reason": "GPT-Neo and MPT are different model families." + "reason": "ViLT and Flaubert/XLM are different model families and different code paths." }, { "left": "pull_request:44017", "right": "pull_request:44722", "accept": false, - "reason": "SegFormer and GPT-J/CodeGen are unrelated changes." + "reason": "Segformer and GPT-J/CodeGen are not the same underlying change." }, { "left": "pull_request:44017", "right": "pull_request:44161", "accept": false, - "reason": "SegFormer and LongT5 are different code paths." + "reason": "Segformer and LongT5 are different implementations." }, { "left": "pull_request:44017", "right": "pull_request:44073", "accept": false, - "reason": "SegFormer and VisualBERT are unrelated model implementations." + "reason": "Segformer and VisualBert are different concrete model edits." }, { "left": "pull_request:44068", "right": "pull_request:44071", "accept": false, - "reason": "GPT-Neo and MPT are different code paths." + "reason": "GPT-Neo and MPT are different model code paths." }, { "left": "pull_request:44071", "right": "pull_request:44076", "accept": false, - "reason": "MPT and ImageGPT are unrelated models." + "reason": "MPT and ImageGPT are unrelated model-specific refactors." }, { "left": "pull_request:44074", "right": "pull_request:44101", "accept": false, - "reason": "TextNet and Flaubert/XLM are different implementations." + "reason": "TextNet and Flaubert/XLM are different model implementations." }, { "left": "pull_request:44056", - "right": "pull_request:44161", + "right": "pull_request:44101", "accept": false, - "reason": "MPNet and LongT5 are unrelated code paths." + "reason": "MPNet and Flaubert/XLM are unrelated concrete changes." }, { "left": "pull_request:43997", - "right": "pull_request:44018", + "right": "pull_request:44017", "accept": false, - "reason": "RegNet and GPT-Neo are different model families." + "reason": "RegNet and Segformer are different architectures." }, { - "left": "pull_request:44056", - "right": "pull_request:44068", + "left": "pull_request:43997", + "right": "pull_request:44056", "accept": false, - "reason": "MPNet and GPT-Neo are unrelated changes." + "reason": "RegNet and MPNet are unrelated implementations." }, { - "left": "pull_request:44074", + "left": "pull_request:44071", + "right": "pull_request:44129", + "accept": false, + "reason": "MPT and SpeechT5 share only the output-tracing pattern, not the same code path." + }, + { + "left": "pull_request:43996", "right": "pull_request:44161", "accept": false, - "reason": "TextNet and LongT5 are different concrete code paths." + "reason": "CVT/FNet and LongT5 are unrelated concrete edits." }, { - "left": "pull_request:43997", - "right": "pull_request:44056", + "left": "pull_request:43996", + "right": "pull_request:44017", "accept": false, - "reason": "RegNet and MPNet are different code paths." + "reason": "CVT/FNet and Segformer are different model code paths." }, { - "left": "pull_request:43997", - "right": "pull_request:44161", + "left": "pull_request:44010", + "right": "pull_request:44071", "accept": false, - "reason": "RegNet and LongT5 are unrelated model implementations." + "reason": "SqueezeBert and MPT are different model implementations." }, { - "left": "pull_request:44071", + "left": "pull_request:44010", + "right": "pull_request:44073", + "accept": false, + "reason": "SqueezeBert and VisualBert are not the same underlying bug or change." + }, + { + "left": "pull_request:44018", "right": "pull_request:44129", "accept": false, - "reason": "MPT and SpeechT5 are unrelated model families." + "reason": "GPT-Neo and SpeechT5 are distinct model-specific refactors." }, { - "left": "pull_request:43996", + "left": "pull_request:43997", + "right": "pull_request:44018", + "accept": false, + "reason": "RegNet and GPT-Neo are unrelated model implementations." + }, + { + "left": "pull_request:43997", "right": "pull_request:44161", "accept": false, - "reason": "CVT/FNet and LongT5 are different concrete implementations." + "reason": "RegNet and LongT5 have no concrete code-path overlap." }, { - "left": "pull_request:43996", - "right": "pull_request:44017", + "left": "pull_request:44074", + "right": "pull_request:44161", + "accept": false, + "reason": "TextNet and LongT5 are separate model-specific changes." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44071", "accept": false, - "reason": "CVT/FNet and SegFormer are unrelated code paths." + "reason": "RegNet and MPT only share the broad refactor theme, not the same edit." }, { "left": "pull_request:44010", "right": "pull_request:44044", "accept": false, - "reason": "SqueezeBERT and DeBERTa-v2 are different model families." + "reason": "SqueezeBert and DeBERTa are unrelated concrete changes." }, { "left": "pull_request:44044", "right": "pull_request:44074", "accept": false, - "reason": "DeBERTa-v2 and TextNet are unrelated implementations." - }, - { - "left": "pull_request:44024", - "right": "pull_request:44076", - "accept": false, - "reason": "FocalNet and ImageGPT are different model families." + "reason": "DeBERTa and TextNet are separate model refactors." }, { "left": "pull_request:44066", "right": "pull_request:44722", - "accept": false, - "reason": "Same GPT-J/CodeGen output-tracing area, but the packet still does not clearly show a single shared fix." + "accept": true, + "reason": "Same GPT-J/CodeGen output-tracing refactor family with overlapping file-level changes; 44722 is the broader later version." }, { "left": "pull_request:44085", "right": "pull_request:44722", - "accept": false, - "reason": "Both target GPT-J output tracing, but the evidence is insufficient to call them duplicate revisions of one change." + "accept": true, + "reason": "Both target GPT-J output tracing in the same file family; 44722 adds the CodeGen companion change." }, { "left": "pull_request:44085", @@ -16774,27 +16618,45 @@ "accept": false, "reason": "GPT-J and SpeechT5 are unrelated model code paths." }, + { + "left": "pull_request:43996", + "right": "pull_request:44007", + "accept": false, + "reason": "CVT/FNet and RegNet are different architectures." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44129", + "accept": false, + "reason": "CVT/FNet and SpeechT5 are different concrete changes." + }, { "left": "pull_request:44044", "right": "pull_request:44129", "accept": false, - "reason": "DeBERTa-v2 and SpeechT5 are separate implementations." + "reason": "DeBERTa and SpeechT5 are unrelated model-specific edits." }, { "left": "pull_request:44044", "right": "pull_request:44154", "accept": false, - "reason": "DeBERTa-v2 and VITS are unrelated code paths." + "reason": "DeBERTa and ViLT are different model implementations; same refactor style is not enough." + }, + { + "left": "pull_request:44024", + "right": "pull_request:44076", + "accept": false, + "reason": "FocalNet and ImageGPT are different concrete model paths." } ] }, "evaluator_result": { "accept": false, - "feedback": "The cluster-level takeaway is mostly grounded, but the soft-edge acceptances are a bit too assertive for the packet. In particular, the claims that 44018\u219444068 are the \u201csame encoder/block path\u201d and that 44066/44085/44722 are clear \u201crevision/superset\u201d relationships go beyond what is explicitly shown; the packet supports shared GPT-J/GPT-Neo file paths and the same issue target, but not a definitive duplicate-revision conclusion. The best-PR rationale also leans on \u2018mature\u2019/\u2018broadest\u2019 language that isn\u2019t directly evidenced beyond larger scope and explicit #43979 linkage. Please soften those accept verdicts to tentative relatedness unless the packet clearly shows the same code path and same fix." + "feedback": "Reject: the overall clustering is mostly grounded, but one soft-edge rationale is not precise enough. In particular, the 44066 vs 44085 note mislabels the pair as CVT/FNet vs GPT-J; both PRs are in the GPT-J/CodeGen family and share the same underlying output-tracing file area. More generally, keep the pair reasons tied to the exact PR contents and avoid broad model-family labels when the packet shows a closer same-file overlap." }, "evaluator_used": true, "retried": true, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -16825,20 +16687,20 @@ "pull_request:43997|pull_request:44010", "pull_request:44010|pull_request:44129" ], - "prepared_review_unit_hash": "381d7e684da3db6dae085a998573800f133b654b9ea41bea3317d82c426f84d0", + "prepared_review_unit_hash": "fab376b91c26278c8513a71afc5b414e828cf2c47e09cd19e314b13893bc747e", "component_budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 77, - "serialized_chars": 84501, - "estimated_input_tokens": 21126, - "estimated_eval_tokens": 42508 + "serialized_chars": 84507, + "estimated_input_tokens": 21127, + "estimated_eval_tokens": 42510 }, "budget": { "node_count": 6, "item_count": 6, "soft_pair_count": 5, - "serialized_chars": 13068, + "serialized_chars": 13066, "estimated_input_tokens": 3267, "estimated_eval_tokens": 6790 }, @@ -16847,42 +16709,42 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These PRs all follow the same infrastructure pattern\u2014migrating model code to standardized output tracing/capture helpers\u2014but they target different model implementations and code paths, so they are not duplicates of one another.", - "confidence": 0.88, + "summary": "These PRs are all model-specific refactors for standardized output tracing/capture, but they affect different architectures and code paths. They are thematically similar, not duplicates of the same change.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44129 is the strongest representative because it has an explicit issue link and a clear, self-contained refactor of SpeechT5\u2019s output tracing path.", + "canonical_pr_reason": "PR 44129 is the best anchor for this cluster because it has an explicit issue target (#43979) and a concrete SpeechT5 output-tracing refactor, while the others are separate model migrations.", "best_issue_reason": null, - "best_pr_reason": "PR 44129 is the best single representative of the cluster because it is the most explicitly scoped and traceable to a tracking issue, while still fitting the shared output-tracing refactor theme.", + "best_pr_reason": "PR 44129 is the strongest representative: it is tied to a tracked issue and makes a specific behavior change in one concrete model path. The other PRs are similar refactors, but each is model-local and not mergeable into a single duplicate PR.", "soft_edge_verdicts": [ { "left": "pull_request:44073", "right": "pull_request:44074", "accept": false, - "reason": "Same refactor family, but different models (VisualBert vs TextNet) and different implementations; they are not the same concrete change and would not be merged into one PR." + "reason": "Same refactor theme, but different models (VisualBert vs TextNet) and different files; these do not fix the same underlying bug and would not be merged into one PR." }, { "left": "pull_request:44056", "right": "pull_request:44073", "accept": false, - "reason": "Both are standardized output-tracing refactors, but for different model code paths (MPNet vs VisualBert); similar pattern is not enough to treat them as duplicates." + "reason": "Both standardize output tracing, but MPNet and VisualBert are unrelated code paths with different layer hooks and model behavior." }, { "left": "pull_request:44056", "right": "pull_request:44074", "accept": false, - "reason": "Different model targets and module-specific tracing logic; this is a shared migration pattern, not the same underlying bug or change." + "reason": "These are separate model migrations in different architectures; similarity is only at the abstraction level, not the concrete change." }, { "left": "pull_request:43997", "right": "pull_request:44010", "accept": false, - "reason": "RegNet and SqueezeBert are unrelated model implementations; the shared decorator migration theme does not make these the same PR-worthy fix." + "reason": "RegNet and SqueezeBert are distinct models with different output plumbing; this is shared refactor pattern, not the same fix." }, { "left": "pull_request:44010", "right": "pull_request:44129", "accept": false, - "reason": "Both touch output collection, but they affect different architectures and concrete forward paths, so they are not a single mergeable fix." + "reason": "Different models and different output semantics; SpeechT5 has an explicit tracked issue, while SqueezeBert is a separate migration." } ] }, @@ -16940,6 +16802,7 @@ "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", @@ -16961,280 +16824,274 @@ "pull_request:44028|pull_request:44030", "pull_request:44029|pull_request:44030" ], - "prepared_review_unit_hash": "7e4dda37592ac5260b800cb8501601721e5a2ae3f48ef3bace5e62776daa789b", + "prepared_review_unit_hash": "86bd509fa3dea8c762ecdb9a744480991765b3e84d897f5f2c95497876aea6e6", "component_budget": { "node_count": 13, "item_count": 13, - "soft_pair_count": 39, - "serialized_chars": 39786, - "estimated_input_tokens": 9947, - "estimated_eval_tokens": 20150 + "soft_pair_count": 40, + "serialized_chars": 40172, + "estimated_input_tokens": 10043, + "estimated_eval_tokens": 20342 }, "budget": { "node_count": 13, "item_count": 13, - "soft_pair_count": 39, - "serialized_chars": 39786, - "estimated_input_tokens": 9947, - "estimated_eval_tokens": 20150 + "soft_pair_count": 40, + "serialized_chars": 40172, + "estimated_input_tokens": 10043, + "estimated_eval_tokens": 20342 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are model-specific output-tracing refactor PRs that share a common template but do not fix the same bug or change the same code path. They should be triaged separately; none of the soft-similarity links are true duplicates.", - "confidence": 0.88, + "summary": "These are all similar output-tracing refactors, but they target different model implementations and code paths. They are not duplicates of the same underlying bug/change, so none of the soft edges should be merged.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44025 is the most representative exemplar of the cluster\u2019s repeated refactor pattern: it applies the tracing/output-capture transition across two closely related depth models and uses the standard can_return_tuple-based shape change. It is central as a pattern sample, not because it is a duplicate of the others.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "PR 44025 is the best single representative for the group because it is a fairly broad, clean example of the output-tracing refactor across related files. Still, it is not a merge target for the others since they affect different models and code paths.", + "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "pull_request:43998", "right": "pull_request:44002", "accept": false, - "reason": "Different model families and files; same refactor theme only, not the same concrete bug/change." + "reason": "Different model files and architectures; same refactor theme, not the same concrete change." }, { "left": "pull_request:43998", "right": "pull_request:44000", "accept": false, - "reason": "Different subsystems (timm_backbone vs vision_text_dual_encoder); only similar output-tracing cleanup." + "reason": "Different model implementations; similar output-tracing cleanup only." }, { "left": "pull_request:43998", "right": "pull_request:44001", "accept": false, - "reason": "Different models and code paths; both are refactors, not duplicates." + "reason": "Different model code paths; not plausibly one merged PR for a single bug/change." }, { "left": "pull_request:43998", "right": "pull_request:44003", "accept": false, - "reason": "Different model families; no shared concrete behavior fix, just analogous tracing refactors." - }, - { - "left": "pull_request:43998", - "right": "pull_request:44004", - "accept": false, - "reason": "CodeGen and timm_backbone are unrelated model implementations; same broad refactor style only." + "reason": "Only shares the general refactor pattern; the affected models are unrelated." }, { "left": "pull_request:43998", "right": "pull_request:44029", "accept": false, - "reason": "Different models and forward paths; similar wording does not imply the same change." + "reason": "Different target model and file; not the same underlying fix." }, { "left": "pull_request:43999", "right": "pull_request:44001", "accept": false, - "reason": "MobileNetV1 and UnivNet are unrelated code paths; both only modernize output handling." + "reason": "Separate models and implementations; same housekeeping pattern only." }, { "left": "pull_request:43999", "right": "pull_request:44002", "accept": false, - "reason": "Different models and responsibilities; no common bug or shared patch target." + "reason": "Not the same code path or bug; just another tracing refactor." }, { "left": "pull_request:43999", "right": "pull_request:44025", "accept": false, - "reason": "Different architectures and files; only a shared output-tracing refactor pattern." + "reason": "Different model families and files; no shared concrete defect." }, { "left": "pull_request:43999", "right": "pull_request:44026", "accept": false, - "reason": "Different model families; same refactor motif, not one underlying fix." + "reason": "Both are refactors, but for different model wrappers/code paths." }, { "left": "pull_request:43999", "right": "pull_request:44027", "accept": false, - "reason": "Vision encoder-decoder and MobileNetV1 are unrelated; not mergeable as one PR." + "reason": "Different encoder-decoder model; not mergeable as one PR fixing one issue." }, { "left": "pull_request:44000", "right": "pull_request:44001", "accept": false, - "reason": "Different model stacks (vision/text vs audio decoder); similar refactor language only." + "reason": "Different model implementations; same refactor style only." }, { "left": "pull_request:44000", "right": "pull_request:44002", "accept": false, - "reason": "Different code paths and model types; no evidence of the same defect." + "reason": "Unrelated model files and behavior; not the same concrete change." }, { "left": "pull_request:44000", "right": "pull_request:44003", "accept": false, - "reason": "These refactor different multimodal/model-family implementations; not the same concrete change." + "reason": "Different subsystems and code paths; too broad to be a duplicate." }, { "left": "pull_request:44000", - "right": "pull_request:44004", + "right": "pull_request:44025", "accept": false, - "reason": "CodeGen and vision-text dual encoder are unrelated; same tracing pattern is too broad." + "reason": "Same tracing theme, but distinct models and outputs." }, { "left": "pull_request:44001", "right": "pull_request:44002", "accept": false, - "reason": "UnivNet and UperNet are unrelated models; only share generic output-refactor intent." + "reason": "Separate model-specific refactors; no single underlying bug." }, { "left": "pull_request:44001", "right": "pull_request:44003", "accept": false, - "reason": "Audio generation vs Mamba/LM code paths; not the same bug or patch." + "reason": "Different architectures and filenames; not a duplicate PR pair." }, { "left": "pull_request:44001", "right": "pull_request:44025", "accept": false, - "reason": "Different model families and files; similar can_return_tuple migration only." + "reason": "Different models; similar API cleanup only." }, { "left": "pull_request:44002", - "right": "pull_request:44003", + "right": "pull_request:44029", "accept": false, - "reason": "Different model families and targets; same refactor campaign, not same change." + "reason": "Different model families and code paths; not one change." }, { "left": "pull_request:44002", - "right": "pull_request:44004", + "right": "pull_request:44003", + "accept": false, + "reason": "No shared concrete bug; only a shared refactoring pattern." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44028", "accept": false, - "reason": "UperNet and CodeGen touch unrelated code paths; no duplicate evidence beyond theme." + "reason": "Falcon/Mamba vs SuperPoint are unrelated implementations." }, { "left": "pull_request:44003", "right": "pull_request:44004", "accept": false, - "reason": "Falcon/Mamba and CodeGen are unrelated; the shared output-tracing wording is insufficient." + "reason": "Different model internals; not plausibly merged as one PR." }, { "left": "pull_request:43998", "right": "pull_request:44004", "accept": false, - "reason": "Timm backbone and CodeGen are different implementations; not the same underlying issue." + "reason": "Different model code paths; same broad tracing refactor only." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44004", + "accept": false, + "reason": "Different models and behavior changes; not the same bug or feature." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44004", + "accept": false, + "reason": "Different target files and implementations; too broad to dedupe." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44004", + "accept": false, + "reason": "Codegen and vision-text dual encoder are unrelated concrete changes." }, { "left": "pull_request:44025", "right": "pull_request:44026", "accept": false, - "reason": "Depth Anything and Vision Encoder-Decoder are unrelated models; only the refactor template matches." + "reason": "Both are output-tracing refactors, but for distinct encoder-decoder wrappers." }, { "left": "pull_request:44025", "right": "pull_request:44027", "accept": false, - "reason": "Different model families and behavior; similar tracing cleanup does not make them duplicates." + "reason": "Different model families and forward paths; not the same fix." }, { "left": "pull_request:44025", "right": "pull_request:44028", "accept": false, - "reason": "Depth estimation vs SuperPoint are distinct code paths; no shared concrete bug." + "reason": "Different model code and tests; not one underlying change." }, { "left": "pull_request:44025", "right": "pull_request:44029", "accept": false, - "reason": "Different model architectures and files; same output-tracing theme only." + "reason": "Depth Anything and RWKV are unrelated concrete implementations." }, { "left": "pull_request:44025", "right": "pull_request:44030", "accept": false, - "reason": "Depth Anything and DPR are unrelated; these are separate refactors." + "reason": "Different model targets; same refactor theme only." }, { "left": "pull_request:44026", - "right": "pull_request:44027", + "right": "pull_request:44029", "accept": false, - "reason": "Vision and speech encoder-decoder wrappers are separate implementations; not one PR." + "reason": "Distinct model wrappers and code paths; not mergeable as one PR." }, { "left": "pull_request:44026", - "right": "pull_request:44028", + "right": "pull_request:44027", "accept": false, - "reason": "Vision encoder-decoder and SuperPoint differ materially in code path and model behavior." + "reason": "Different encoder-decoder models; no common underlying defect." }, { "left": "pull_request:44026", - "right": "pull_request:44029", + "right": "pull_request:44028", "accept": false, - "reason": "Different models and forward logic; only a generic tracing refactor is shared." + "reason": "Unrelated model implementations; only generic similarity." }, { "left": "pull_request:44026", "right": "pull_request:44030", "accept": false, - "reason": "Vision encoder-decoder and DPR are unrelated; not the same concrete fix." + "reason": "Different model subsystems; not the same change." }, { "left": "pull_request:44027", "right": "pull_request:44028", "accept": false, - "reason": "Speech encoder-decoder and SuperPoint are distinct modules; shared refactor wording is too broad." + "reason": "Speech encoder-decoder and SuperPoint are different code paths entirely." }, { "left": "pull_request:44027", "right": "pull_request:44029", "accept": false, - "reason": "Different architectures and code paths; not a mergeable duplicate." + "reason": "Different model families; no shared concrete bug." }, { "left": "pull_request:44027", "right": "pull_request:44030", "accept": false, - "reason": "Speech encoder-decoder and DPR are unrelated; only the output-tracing pattern overlaps." + "reason": "Different targets and behavior; not a duplicate PR." }, { "left": "pull_request:44028", "right": "pull_request:44029", "accept": false, - "reason": "SuperPoint and RWKV are unrelated models; no evidence of the same underlying bug/change." + "reason": "Different architectures and files; same refactor motif only." }, { "left": "pull_request:44028", "right": "pull_request:44030", "accept": false, - "reason": "Different model families and implementation details; not a duplicate." + "reason": "Separate model implementations; not the same underlying fix." }, { "left": "pull_request:44029", "right": "pull_request:44030", "accept": false, - "reason": "RWKV and DPR touch very different code paths; similar refactor style only." - }, - { - "left": "pull_request:44003", - "right": "pull_request:44029", - "accept": false, - "reason": "Mamba/Falcon-Mamba and RWKV are separate recurrent model implementations; not the same patch." - }, - { - "left": "pull_request:44000", - "right": "pull_request:44025", - "accept": false, - "reason": "Vision-text dual encoder and depth estimation are unrelated; only the refactor template matches." - }, - { - "left": "pull_request:44001", - "right": "pull_request:44004", - "accept": false, - "reason": "UnivNet and CodeGen are unrelated; the shared output-tracing pattern is not enough to merge." - }, - { - "left": "pull_request:44002", - "right": "pull_request:44029", - "accept": false, - "reason": "UperNet and RWKV are different code paths and models; not the same underlying change." + "reason": "RWKV and DPR are unrelated models; cannot be merged as one concrete PR." } ] }, @@ -17267,7 +17124,7 @@ "pull_request:44662|pull_request:45075", "pull_request:45075|pull_request:45401" ], - "prepared_review_unit_hash": "13975a48bddc31ffc5f6f452462e728399eac976a19c0c24b95b71c951d4762d", + "prepared_review_unit_hash": "5bd462574ec678926dad52daf9985bdc3166fc8f315e2fcb8cd66c0fccef5cdc", "component_budget": { "node_count": 3, "item_count": 3, @@ -17289,30 +17146,30 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "All three PRs are separate model integrations, not duplicates: PenguinVL, Deepseek-OCR-2, and Voxtral TTS touch shared Transformers scaffolding but implement different code paths and model-specific files. None should be merged as a duplicate of another.", - "confidence": 0.98, + "summary": "All three PRs are separate model-addition implementations for different architectures (PenguinVL, DeepSeek-OCR-2, Voxtral TTS). They share only boilerplate integration files and docs registration, so they are not duplicates.", + "confidence": 0.99, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR: the three pull requests add unrelated model implementations, so none represents the same underlying change.", + "canonical_pr_reason": "No canonical PR among these: each PR targets a different model with distinct configs, processors, and modeling code.", "best_issue_reason": null, - "best_pr_reason": "No single best PR for deduplication: each PR is a distinct model addition with different model-specific modules, tests, and docs.", + "best_pr_reason": "PR #44662 is the most complete/representative implementation in the set, with broad model, image-processing, processing, docs, and test coverage.", "soft_edge_verdicts": [ { "left": "pull_request:44662", "right": "pull_request:45401", "accept": false, - "reason": "Different model families and code paths: PenguinVL vision-language implementation vs Voxtral TTS text-to-speech support. Shared auto-registration/docs are boilerplate, not evidence of the same change." + "reason": "Different models and codepaths: PenguinVL vs Voxtral TTS. Shared auto/docs files are just integration scaffolding, not the same bug or change." }, { "left": "pull_request:44662", "right": "pull_request:45075", "accept": false, - "reason": "Different targets: PenguinVL and Deepseek-OCR-2 are separate model implementations with distinct configs, processors, and modeling files. Overlap is limited to generic Transformers integration points." + "reason": "Different model implementations (PenguinVL vs DeepSeek-OCR-2) with unrelated modeling, conversion, and test files. Not mergeable as one fix." }, { "left": "pull_request:45075", "right": "pull_request:45401", "accept": false, - "reason": "Different concrete functionality: Deepseek-OCR-2 is an OCR/vision model, while Voxtral TTS is a speech generation model. They do not fix the same bug or implement the same feature." + "reason": "DeepSeek-OCR-2 and Voxtral TTS are distinct model additions touching different logic and artifacts; overlap is only generic registry/docs boilerplate." } ] }, @@ -17342,7 +17199,7 @@ "soft_pairs": [ "pull_request:44979|pull_request:45363" ], - "prepared_review_unit_hash": "3ae53d2df016420380f84362b902ab2278ea053c1e92255187f4518189e6cb4f", + "prepared_review_unit_hash": "87438852cca3efb6caab9f559a68504e66d6a60519924ac47058b9ff2f892c4f", "component_budget": { "node_count": 2, "item_count": 2, @@ -17364,18 +17221,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are related to module/kernel fusion, but they are not the same change: one adds a new Module Fusion API, while the other wires up n-to-1 kernel fusion through KernelConfig and an example. They are adjacent, not duplicates.", - "confidence": 0.89, + "summary": "Two related but distinct pull requests around module/kernel fusion. One introduces a new Module Fusion API scaffold, while the other wires n-to-1 kernel fusion through KernelConfig and model loading. They share a feature area, but they are not the same concrete change.", + "confidence": 0.87, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45363 is the more concrete end-user feature implementation: it integrates kernel fusion into model loading/runtime via KernelConfig and touches the relevant integration points.", + "canonical_pr_reason": "PR #45363 is the stronger canonical PR for the cluster: it is the broader, more user-facing implementation of kernel fusion via KernelConfig across loading/integration paths, whereas #44979 is mainly the underlying Module Fusion API scaffolding.", "best_issue_reason": null, - "best_pr_reason": "PR 44979 is the more foundational API/design piece, but PR 45363 is the better representative of the cluster because it exercises the feature in a complete workflow and shows the intended external behavior.", + "best_pr_reason": "PR #45363 is the best representative because it covers the concrete end-to-end fusion behavior and multiple integration points, making it the most complete expression of the cluster\u2019s feature theme.", "soft_edge_verdicts": [ { "left": "pull_request:44979", "right": "pull_request:45363", "accept": false, - "reason": "Different scopes and code paths: 44979 introduces a generic Module Fusion API, while 45363 implements n-to-1 kernel fusion via KernelConfig plus integration/example code. Related, but not the same concrete fix and not something to merge as one PR." + "reason": "Related fusion work, but not the same code-path change. #44979 adds a new Module Fusion API/module_fusion.py scaffold, while #45363 implements n-to-1 kernel fusion via KernelConfig and integration changes. They would not plausibly be merged as one single PR without collapsing distinct layers of the feature." } ] }, @@ -17405,7 +17262,7 @@ "soft_pairs": [ "pull_request:45086|pull_request:45317" ], - "prepared_review_unit_hash": "57565fd55d2c0553df27bcdaaf87a6210f1ebe0a60e4968e92fe1dc80e5a4d15", + "prepared_review_unit_hash": "b7e0704b31f03fee64399c486c1d0bb2faa141fce568bebf317340f83f72241a", "component_budget": { "node_count": 2, "item_count": 2, @@ -17427,18 +17284,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both pull requests address the same Mistral regex AttributeError in `tokenization_utils_tokenizers.py` and implement the same code fix; `45317` is the more complete version because it adds tests.", + "summary": "Both PRs fix the same concrete bug in `_patch_mistral_regex`: using `tokenizer.backend_tokenizer.pre_tokenizer` caused an AttributeError, and both switch to `tokenizer.pre_tokenizer`. The second PR is a clearer, more complete implementation because it includes test coverage.", "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45317 is the more complete fix for the same bug: same code-path change plus test coverage, making it the better canonical PR.", + "canonical_pr_reason": "pull_request:45317 is the better canonical PR: it addresses the same bug as 45086 but is more complete, with test changes and a clearer title tied to the exact failure mode.", "best_issue_reason": null, - "best_pr_reason": "PR 45317 is the best representative because it contains the same core patch as 45086 and includes additional validation/tests.", + "best_pr_reason": "pull_request:45317 is the best overall PR because it fixes the same code path as 45086 and adds regression tests, making it the more complete merge candidate.", "soft_edge_verdicts": [ { "left": "pull_request:45086", "right": "pull_request:45317", "accept": true, - "reason": "Same underlying AttributeError fix in the same file/code path, with effectively identical patch intent and the same explicit issue target." + "reason": "Same underlying bug and same code path in `tokenization_utils_tokenizers.py`; the diffs are effectively the same fix, with 45317 adding tests." } ] }, @@ -17468,7 +17325,7 @@ "soft_pairs": [ "pull_request:45115|pull_request:45569" ], - "prepared_review_unit_hash": "b549e4e8b6ba379ec416fdbf35657f66fbad77edb6e9d8124cff038f443cb2b6", + "prepared_review_unit_hash": "8977d3259a77e06e7c5c632e8a082bfc95071efae99f70ca41f56ed5938e75e1", "component_budget": { "node_count": 2, "item_count": 2, @@ -17490,18 +17347,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are related NemotronH model-family changes, but they are not the same PR: one is a focused refactor/backward-compat conversion-mapping update, while the other splits NemotronH into dense/sparse variants and updates docs/configs/tests. I would not treat them as duplicates.", - "confidence": 0.92, + "summary": "The two PRs are thematically related around NemotronH, but they address different changes: one is a conversion-mapping/model inheritance refactor, while the other splits NemotronH into dense and sparse model families with docs/tests updates. They are not the same underlying change and should not be merged as duplicates.", + "confidence": 0.89, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45569 is the better canonical PR because it covers the broader, user-facing model restructuring and includes the docs/tests/configuration work; PR 45115 is a narrower refactor centered on conversion mapping and inheritance.", + "canonical_pr_reason": "PR #45569 is the broader, more central architecture refactor, introducing the dense/sparse model split and associated registry/docs/test updates.", "best_issue_reason": null, - "best_pr_reason": "PR 45569 is the strongest representative of the cluster since it implements the main architectural change end-to-end, while PR 45115 looks like a partial supporting refactor rather than the primary feature branch.", + "best_pr_reason": "PR #45569 is the best representative of the cluster because it covers the main public-facing NemotronH restructuring, while #45115 is a narrower conversion-mapping/inheritance adjustment.", "soft_edge_verdicts": [ { "left": "pull_request:45115", "right": "pull_request:45569", "accept": false, - "reason": "They overlap on NemotronH internals, but the concrete changes differ: 45115 focuses on conversion mapping and GraniteMoeHybrid-style inheritance, while 45569 introduces separate dense/sparse model variants plus docs and tests. They do not appear mergeable into one PR for the same underlying fix." + "reason": "Different concrete changes: #45115 focuses on checkpoint conversion mapping and structural renames for NemotronH compatibility, whereas #45569 creates separate NemotronH dense/sparse model variants and updates docs/tests. Related but not the same code-path fix." } ] }, @@ -17531,7 +17388,7 @@ "soft_pairs": [ "pull_request:45332|pull_request:45333" ], - "prepared_review_unit_hash": "79f977d606b615b2f1ed7c9e34d396d9002fb1fc3777a71e4e33281fbccd6939", + "prepared_review_unit_hash": "61f7a1dc27ee1ce1592e27e151bad0f6f2184cfd449135eaefa17c8ba9915192", "component_budget": { "node_count": 2, "item_count": 2, @@ -17553,18 +17410,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are related but distinct PRs: one introduces heterogeneous config plumbing, the other adds heterogeneous model/runtime support on top of it. They share infrastructure files, but they do not fix the same concrete problem and should not be treated as duplicates.", - "confidence": 0.94, + "summary": "Two related pull requests for heterogeneous-model work, but they are not duplicates: one adds per-layer config plumbing, the other adds broader heterogeneous modeling support built on top of that plumbing.", + "confidence": 0.89, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45332 is the broader, more end-to-end change: it adds heterogeneous model support and updates cache/masking/modeling paths, building on the config layer. If choosing one PR as representative of the cluster, this is the more complete umbrella change.", + "canonical_pr_reason": "PR #45332 is the broader, more central change: it adds heterogeneous model support across modeling/cache/masking and naturally subsumes the config plumbing work.", "best_issue_reason": null, - "best_pr_reason": "PR #45332 is the best standalone representative because it covers the larger functional surface and is closer to the user-visible capability being added, while #45333 is a supporting prerequisite focused on config representation.", + "best_pr_reason": "PR #45332 is the best representative artifact for the cluster because it covers the end-to-end heterogeneous-model feature rather than only the configuration layer.", "soft_edge_verdicts": [ { "left": "pull_request:45332", "right": "pull_request:45333", "accept": false, - "reason": "They are complementary layers of the same feature area, but not the same mergeable fix. #45333 adds per-layer config support; #45332 adds heterogeneous model/cache/masking behavior and can\u2019t be considered a duplicate of the config-only PR." + "reason": "Related feature work, but not the same underlying change: #45333 only adds per-layer config support, while #45332 implements the larger heterogeneous modeling path and several runtime integrations. They would not plausibly be merged as one PR." } ] }, @@ -17603,76 +17460,76 @@ "pull_request:45592|pull_request:45615", "pull_request:45596|pull_request:45615" ], - "prepared_review_unit_hash": "21ad7b4149029759a02556c2bc6cdb1bee62cf795aacb89547245fa317aa708f", + "prepared_review_unit_hash": "1b7fda14751503616bdfd180ca7f1a7060c379fc1fb79f2abdd55deeedeb0229", "component_budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 7, - "serialized_chars": 13271, - "estimated_input_tokens": 3318, - "estimated_eval_tokens": 6892 + "serialized_chars": 13275, + "estimated_input_tokens": 3319, + "estimated_eval_tokens": 6894 }, "budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 7, - "serialized_chars": 13271, - "estimated_input_tokens": 3318, - "estimated_eval_tokens": 6892 + "serialized_chars": 13275, + "estimated_input_tokens": 3319, + "estimated_eval_tokens": 6894 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is mostly a mix of unrelated model-specific PRs; a few are superficially similar because they touch XPU/model-parallel test expectations, but they do not fix the same underlying bug or change.", - "confidence": 0.79, + "summary": "One substantive code fix PR (AltCLIP/ChineseCLIP model-parallel handling) sits alongside several unrelated test-only expectation updates for other models. The cluster is not a set of true duplicates.", + "confidence": 0.91, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45487 is the strongest canonical PR: it makes a concrete code-level model-parallel fix (device handling plus no-split modules) across altclip/ChineseClip, rather than only adjusting tests.", + "canonical_pr_reason": "PR 45487 is the strongest representative of the cluster: it fixes an actual model-parallel code-path bug with implementation changes (not just test expectations) and affects multiple related model files.", "best_issue_reason": null, - "best_pr_reason": "PR 45487 is the best overall representative of a real bug fix in the cluster; it addresses the underlying model-parallel code path directly and is more substantive than the test-only expectation updates.", + "best_pr_reason": "PR 45487 is the best standalone representative because it addresses the underlying runtime issue directly, while the other PRs are narrower test-only adjustments or unrelated model-specific fixes.", "soft_edge_verdicts": [ { "left": "pull_request:45394", "right": "pull_request:45596", "accept": false, - "reason": "Both are XPU/model test-related, but one fixes X-CLIP model splitting while the other only changes BLT test expectations; different models and different bugs." + "reason": "Different models and different problems: XCLIP model-parallel split-module fix vs BLT XPU test expectation updates." }, { "left": "pull_request:45487", "right": "pull_request:45592", "accept": false, - "reason": "AltCLIP/ChineseClip model-parallel code fixes are unrelated to a FastVLM test padding-side adjustment." + "reason": "AltCLIP/ChineseCLIP runtime/model-parallel fix is unrelated to FastVLM test padding-side changes." }, { "left": "pull_request:45487", "right": "pull_request:45596", "accept": false, - "reason": "These target different model families and different failure modes; BLT XPU expectations are not the same underlying issue as altclip/chinese_clip model-parallel handling." + "reason": "Different underlying bug/change; one is a broad model-parallel code fix, the other is BLT-specific XPU test expectations." }, { "left": "pull_request:45487", "right": "pull_request:45615", "accept": false, - "reason": "Model-parallel fixes for altclip/ChineseClip are unrelated to qianfan_ocr XPU expectation updates." + "reason": "ChineseCLIP/AltCLIP model-parallel fix and Qianfan OCR XPU expectations are model-specific and do not share the same concrete code path." }, { "left": "pull_request:45592", "right": "pull_request:45596", "accept": false, - "reason": "Both are test-centric, but they cover different models and different runtime quirks; they are not one concrete bug/change." + "reason": "Both are test-oriented, but they target different models and different failures, so they are not the same change." }, { "left": "pull_request:45592", "right": "pull_request:45615", "accept": false, - "reason": "FastVLM padding-side test fix and qianfan_ocr XPU expectations are separate model-specific test updates." + "reason": "FastVLM padding-side test adjustment is unrelated to Qianfan OCR XPU expectation updates." }, { "left": "pull_request:45596", "right": "pull_request:45615", "accept": false, - "reason": "Both add XPU expectations, but for different models and different outputs; they should not be merged as the same change." + "reason": "Both add XPU-specific test expectations, but they are for different models and expected outputs, not one shared bug fix." } ] }, @@ -17702,7 +17559,7 @@ "soft_pairs": [ "pull_request:45415|pull_request:45425" ], - "prepared_review_unit_hash": "829a66123706fc8b9e935a64233fcb091a56ab509aac7b44131969d88d8900a0", + "prepared_review_unit_hash": "d436a76c44eb3fddf78e17b6a3fb51def215043e587f4230dc9097d1c1da9175", "component_budget": { "node_count": 2, "item_count": 2, @@ -17724,18 +17581,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are both typing-related PRs, but they target different changes: 45415 is a broad repo-wide type-checking sweep, while 45425 adds specific typing protocols and model-utils integrations. They are not the same underlying change.", - "confidence": 0.97, + "summary": "These are related only at a very broad type-checking level, but they are not the same PR: one is a sweeping type-check cleanup across many files, while the other adds specific typing helpers and targeted modeling fixes.", + "confidence": 0.91, "canonical_issue_reason": null, - "canonical_pr_reason": "45425 is the more focused, self-contained typing refactor; 45415 is a broad type-checking sweep across many files.", + "canonical_pr_reason": "PR 45415 is the broader umbrella change: it touches many files and updates type-checking config, so it is the more canonical representative of the cluster.", "best_issue_reason": null, - "best_pr_reason": "45425 is the better representative PR because it has a narrower, coherent code-change scope and is easier to review as a single change.", + "best_pr_reason": "PR 45415 is the best overall representative because it is the largest, most general type-checking pass in the set; 45425 is narrower and more specialized.", "soft_edge_verdicts": [ { "left": "pull_request:45415", "right": "pull_request:45425", "accept": false, - "reason": "Both are about typing, but 45415 is a broad per-file type-checking pass and 45425 is a targeted typing/protocol change in _typing/modeling_utils. Same subsystem, different concrete change; not mergeable as one PR." + "reason": "Reject: both are typing-related, but they address different scopes and code paths. 45415 is a repo-wide type-checking sweep, while 45425 adds concrete typing protocols/helpers and fixes around modeling utilities; they would not plausibly be merged as one PR." } ] }, diff --git a/analysis/current/manifest.json b/analysis/current/manifest.json index 40dd34b079c7443c08d9552162606b877272856c..a1f721e9e42aeeb031b36fd68f371c6f58233528 100644 --- a/analysis/current/manifest.json +++ b/analysis/current/manifest.json @@ -1,8 +1,8 @@ { - "analysis_id": "hybrid-model-20260424t120023z", + "analysis_id": "hybrid-model-20260424t180025z", "archived_artifacts": { - "hybrid": "snapshots/20260424T120023Z/analysis-runs/hybrid-model-20260424t120023z/analysis-report-hybrid.json", - "hybrid_reviews": "snapshots/20260424T120023Z/analysis-runs/hybrid-model-20260424t120023z/analysis-report-hybrid.llm-reviews.json" + "hybrid": "snapshots/20260424T180025Z/analysis-runs/hybrid-model-20260424t180025z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260424T180025Z/analysis-runs/hybrid-model-20260424t180025z/analysis-report-hybrid.llm-reviews.json" }, "artifacts": { "hybrid": "analysis/current/analysis-report-hybrid.json", @@ -10,9 +10,9 @@ }, "channel": "canonical", "model": null, - "published_at": "2026-04-24T12:06:32Z", + "published_at": "2026-04-24T18:16:19Z", "repo": "huggingface/transformers", "schema_version": 1, - "snapshot_id": "20260424T120023Z", + "snapshot_id": "20260424T180025Z", "variant": "hybrid" } diff --git a/snapshots/20260424T180025Z/analysis-runs/hybrid-model-20260424t180025z/analysis-report-hybrid.json b/snapshots/20260424T180025Z/analysis-runs/hybrid-model-20260424t180025z/analysis-report-hybrid.json new file mode 100644 index 0000000000000000000000000000000000000000..969a1c1f434ecc76802eaaf500a4cc57c5d641f9 --- /dev/null +++ b/snapshots/20260424T180025Z/analysis-runs/hybrid-model-20260424t180025z/analysis-report-hybrid.json @@ -0,0 +1,1751 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260424T180025Z", + "generated_at": "2026-04-24T18:16:17Z", + "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": 0.75, + "canonical_issue_number": 41211, + "canonical_pr_number": 44339, + "issue_numbers": [ + 41211 + ], + "pr_numbers": [ + 41356, + 44339 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 41356, + "right_pr_number": 44339, + "code_similarity": 0.155, + "size_similarity": 0.094, + "file_overlap": 0.273, + "area_overlap": 0.078, + "patch_similarity": 0.183, + "shared_filenames": [ + "docs/source/en/model_doc/deimv2.md", + "src/transformers/models/deimv2/__init__.py", + "src/transformers/models/deimv2/configuration_deimv2.py", + "src/transformers/models/deimv2/modeling_deimv2.py", + "tests/models/deimv2/__init__.py", + "tests/models/deimv2/test_modeling_deimv2.py" + ], + "shared_file_areas": [ + { + "filename": "docs/source/en/model_doc/deimv2.md", + "left_ranges": [ + [ + 1, + 132 + ] + ], + "right_ranges": [ + [ + 1, + 65 + ] + ] + }, + { + "filename": "src/transformers/models/deimv2/__init__.py", + "left_ranges": [ + [ + 1, + 15 + ] + ], + "right_ranges": [ + [ + 1, + 29 + ] + ] + }, + { + "filename": "src/transformers/models/deimv2/configuration_deimv2.py", + "left_ranges": [ + [ + 1, + 74 + ] + ], + "right_ranges": [ + [ + 1, + 266 + ] + ] + }, + { + "filename": "tests/models/deimv2/test_modeling_deimv2.py", + "left_ranges": [ + [ + 1, + 15 + ] + ], + "right_ranges": [ + [ + 1, + 1734 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43240-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #43240.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 43240, + "canonical_pr_number": 43251, + "issue_numbers": [ + 43240 + ], + "pr_numbers": [ + 43251, + 43254 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 43251, + "right_pr_number": 43254, + "code_similarity": 0.794, + "size_similarity": 0.64, + "file_overlap": 1.0, + "area_overlap": 0.667, + "patch_similarity": 0.882, + "shared_filenames": [ + "src/transformers/loss/loss_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/loss/loss_utils.py", + "left_ranges": [ + [ + 30, + 50 + ] + ], + "right_ranges": [ + [ + 30, + 43 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43824-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #43824.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 43824, + "canonical_pr_number": 43836, + "issue_numbers": [ + 43824 + ], + "pr_numbers": [ + 43836, + 43842 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 43836, + "right_pr_number": 43842, + "code_similarity": 0.332, + "size_similarity": 0.088, + "file_overlap": 1.0, + "area_overlap": 0.033, + "patch_similarity": 0.017, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 359, + 429 + ], + [ + 584, + 590 + ], + [ + 1892, + 1910 + ], + [ + 1917, + 1923 + ] + ], + "right_ranges": [ + [ + 54, + 61 + ], + [ + 587, + 593 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45081-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45081.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 45081, + "canonical_pr_number": 45317, + "issue_numbers": [ + 45081 + ], + "pr_numbers": [ + 45086, + 45317 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 45086, + "right_pr_number": 45317, + "code_similarity": 0.589, + "size_similarity": 0.34, + "file_overlap": 0.5, + "area_overlap": 1.0, + "patch_similarity": 0.136, + "shared_filenames": [ + "src/transformers/tokenization_utils_tokenizers.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/tokenization_utils_tokenizers.py", + "left_ranges": [ + [ + 1360, + 1370 + ], + [ + 1374, + 1380 + ] + ], + "right_ranges": [ + [ + 1360, + 1370 + ], + [ + 1374, + 1380 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-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-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, shared_issue_target evidence." + }, + { + "cluster_id": "cluster-43240-3", + "canonical_pr_number": 43251, + "duplicate_pr_numbers": [ + 43254 + ], + "target_issue_number": 43240, + "reason": "PRs in cluster-43240-3 are treated as duplicates because they converge on issue #43240 with closing_reference, shared_issue_target evidence." + }, + { + "cluster_id": "cluster-43698-3", + "canonical_pr_number": 43779, + "duplicate_pr_numbers": [ + 43816 + ], + "target_issue_number": 43698, + "reason": "PRs in cluster-43698-3 are treated as duplicates because they converge on issue #43698 with closing_reference, shared_issue_target evidence." + }, + { + "cluster_id": "cluster-43824-3", + "canonical_pr_number": 43836, + "duplicate_pr_numbers": [ + 43842 + ], + "target_issue_number": 43824, + "reason": "PRs in cluster-43824-3 are treated as duplicates because they converge on issue #43824 with closing_reference, shared_issue_target evidence." + }, + { + "cluster_id": "cluster-43979-11", + "canonical_pr_number": 44007, + "duplicate_pr_numbers": [ + 43996, + 44013, + 44044, + 44066, + 44072, + 44085, + 44129, + 44154, + 44722 + ], + "target_issue_number": 43979, + "reason": "PRs in cluster-43979-11 are treated as duplicates because they converge on issue #43979 with closing_reference, shared_issue_target, soft_similarity evidence." + }, + { + "cluster_id": "cluster-44018-2", + "canonical_pr_number": 44068, + "duplicate_pr_numbers": [ + 44018 + ], + "target_issue_number": null, + "reason": "PRs in cluster-44018-2 are treated as duplicates because they share soft_similarity evidence." + }, + { + "cluster_id": "cluster-45081-3", + "canonical_pr_number": 45317, + "duplicate_pr_numbers": [ + 45086 + ], + "target_issue_number": 45081, + "reason": "PRs in cluster-45081-3 are treated as duplicates because they converge on issue #45081 with closing_reference, shared_issue_target, soft_similarity evidence." + } + ], + "best_issue": { + "cluster_id": "cluster-41211-3", + "issue_number": 41211, + "reason": "Issue #41211 is the strongest global issue candidate because it is open, belongs to a cluster with 3 artifacts, and carries 6 discussion comments plus 6 inbound references.", + "score": 148.0 + }, + "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/20260424T180025Z/analysis-runs/hybrid-model-20260424t180025z/analysis-report-hybrid.llm-reviews.json b/snapshots/20260424T180025Z/analysis-runs/hybrid-model-20260424t180025z/analysis-report-hybrid.llm-reviews.json new file mode 100644 index 0000000000000000000000000000000000000000..6802f4c9e6de7c7b9b8cccf0a7744bad60375c5e --- /dev/null +++ b/snapshots/20260424T180025Z/analysis-runs/hybrid-model-20260424t180025z/analysis-report-hybrid.llm-reviews.json @@ -0,0 +1,17607 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260424T180025Z", + "generated_at": "2026-04-24T18:16:17Z", + "model": "gpt-5.4-mini?service_tier=flex", + "reviews": [ + { + "label": "issue", + "component_index": 1, + "component_count": 13, + "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": "3bd1aa1e5016ec9382b72cbe7c74a64e990c7c4e0b250800fedbd71ab44829a9", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 2479, + "estimated_input_tokens": 620, + "estimated_eval_tokens": 1496 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 2479, + "estimated_input_tokens": 620, + "estimated_eval_tokens": 1496 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These issues do not appear to be duplicates of one another: one is about TAPAS tokenization, one about auth-related private model downloads, and one about a model-loading failure for bert-base-uncased. The only somewhat related pair is the last two, but they describe different failure modes and should not be merged.", + "confidence": 0.9, + "canonical_issue_reason": "Issue 16618 is the most generally framed model-loading report, so it is the best single representative of the cluster if one must be chosen.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 16618 is the strongest standalone issue for triage because it is broad, clearly user-facing, and has the most discussion activity among the set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:13244", + "right": "issue:16618", + "accept": false, + "reason": "Different topics and code paths: TAPAS tokenization vs generic model loading for bert-base-uncased." + }, + { + "left": "issue:15980", + "right": "issue:16618", + "accept": false, + "reason": "Both involve model loading, but one is specifically an unauthenticated private-model download error while the other is a generic inability to load bert-base-uncased; not the same underlying bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 1, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "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:43296", + "issue:43366", + "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:44661", + "issue:44805", + "issue:44841", + "issue:44863", + "issue:44918", + "issue:45070", + "issue:45081", + "issue:45084", + "issue:45161", + "issue:45237", + "issue:45362", + "issue:45464", + "issue:45507" + ], + "soft_pairs": [ + "issue:44322|issue:45464", + "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:43638|issue:44805", + "issue:43596|issue:44805", + "issue:44805|issue:45161", + "issue:44805|issue:44918", + "issue:44661|issue:44805", + "issue:34634|issue:35545", + "issue:30277|issue:43638", + "issue:43596|issue:43638", + "issue:43975|issue:44457", + "issue:43039|issue:45161", + "issue:44292|issue:44457", + "issue:34928|issue:44805", + "issue:24643|issue:30277", + "issue:43975|issue:45237", + "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:43541|issue:43716", + "issue:43828|issue:44292", + "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:43716|issue:44918", + "issue:43039|issue:43828", + "issue:30277|issue:36331", + "issue:43039|issue:44805", + "issue:34928|issue:36010", + "issue:41762|issue:43596", + "issue:43901|issue:44512", + "issue:39290|issue:41720", + "issue:43039|issue:44560", + "issue:43866|issue:44863", + "issue:43854|issue:43866", + "issue:43425|issue:45070", + "issue:41093|issue:43638", + "issue:39290|issue:43531", + "issue:43404|issue:43866", + "issue:45362|issue:45464", + "issue:43792|issue:45070", + "issue:43541|issue:43828", + "issue:36010|issue:39290", + "issue:44841|issue:45084", + "issue:41093|issue:41762", + "issue:43296|issue:43366" + ], + "prepared_review_unit_hash": "b09f576435fcf2d9c74b2cdf4b8a4c6a872d3e820b00fad10d5df17d08c66eec", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 63, + "serialized_chars": 46475, + "estimated_input_tokens": 11619, + "estimated_eval_tokens": 23494 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most items are unrelated, with one clear duplicate cluster around DeepSpeed ZeRO-3 / index-out-of-bounds loading failures for BERT/Gemma-style models. A smaller docs-only similarity cluster exists, but the evidence is weaker and broader than the ZeRO-3 bug cluster.", + "confidence": 0.72, + "canonical_issue_reason": "issue:44805 is the best representative of the ZeRO-3 loading failure cluster because its title is the most general form of the shared index-out-of-bounds/mask-shape error and it maps cleanly to the other Bert/ZeRO-3 variants.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44805 is the strongest canonical issue candidate among the provided items; it is the broadest and most reusable description of the shared underlying bug.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44322", + "right": "issue:45464", + "accept": false, + "reason": "Different Qwen3.5 failures and different code paths; same model family only, not the same bug." + }, + { + "left": "issue:43716", + "right": "issue:45237", + "accept": false, + "reason": "Different failure modes: dtype mismatch vs AMD GPU execution failure." + }, + { + "left": "issue:43828", + "right": "issue:45237", + "accept": false, + "reason": "Autocast dtype mismatch is unrelated to AMD GPU support issues." + }, + { + "left": "issue:45237", + "right": "issue:45507", + "accept": false, + "reason": "Different problem areas; one is GPU backend support, the other is an invalid method call in a model implementation." + }, + { + "left": "issue:44292", + "right": "issue:45237", + "accept": false, + "reason": "Different model/runtime failures with no clear shared code-path." + }, + { + "left": "issue:30277", + "right": "issue:35545", + "accept": false, + "reason": "DeepSpeed collective mismatch and ONNX export error are unrelated." + }, + { + "left": "issue:35545", + "right": "issue:42915", + "accept": false, + "reason": "Different model/export paths and different symptoms." + }, + { + "left": "issue:35545", + "right": "issue:41720", + "accept": false, + "reason": "ONNX export error and auto device-mapping cuda assert are not the same bug." + }, + { + "left": "issue:44509", + "right": "issue:44512", + "accept": false, + "reason": "Both are docs regressions in v5, but they reference different removed features and do not clearly share one concrete change." + }, + { + "left": "issue:35545", + "right": "issue:36010", + "accept": false, + "reason": "ONNX export and GenerationMixin import breakage are unrelated." + }, + { + "left": "issue:43638", + "right": "issue:44805", + "accept": true, + "reason": "Same ZeRO-3 index-0-out-of-bounds failure pattern on Bert-family loading." + }, + { + "left": "issue:43596", + "right": "issue:44805", + "accept": true, + "reason": "Same underlying ZeRO-3 loading/index-out-of-bounds bug, just on a different Bert variant." + }, + { + "left": "issue:44805", + "right": "issue:45161", + "accept": false, + "reason": "One is a ZeRO-3 loading bug; the other is a GPT-OSS tensor-parallel issue." + }, + { + "left": "issue:44661", + "right": "issue:44805", + "accept": false, + "reason": "Tokenizer mapping generation bug is unrelated to ZeRO-3 loading errors." + }, + { + "left": "issue:34634", + "right": "issue:35545", + "accept": false, + "reason": "BarkProcessor preset handling and ONNX export are unrelated." + }, + { + "left": "issue:30277", + "right": "issue:43638", + "accept": false, + "reason": "Both are DeepSpeed-related, but the symptoms and code paths differ materially." + }, + { + "left": "issue:43596", + "right": "issue:43638", + "accept": true, + "reason": "Near-identical ZeRO-3 index-out-of-bounds failures on BertModel loading." + }, + { + "left": "issue:43975", + "right": "issue:44457", + "accept": false, + "reason": "Different model-specific inference/detokenization bugs." + }, + { + "left": "issue:43039", + "right": "issue:45161", + "accept": false, + "reason": "Liger Kernel cross-entropy call and GPT-OSS tensor-parallel failure are different issues." + }, + { + "left": "issue:44292", + "right": "issue:44457", + "accept": false, + "reason": "Different model/runtime problems with no shared bug." + }, + { + "left": "issue:34928", + "right": "issue:44805", + "accept": false, + "reason": "Activation checkpointing/FSDP mismatch is unrelated to ZeRO-3 index-out-of-bounds loading." + }, + { + "left": "issue:24643", + "right": "issue:30277", + "accept": false, + "reason": "Different DeepSpeed errors and different failure conditions." + }, + { + "left": "issue:43975", + "right": "issue:45237", + "accept": false, + "reason": "Different model families and different runtime failures." + }, + { + "left": "issue:43638", + "right": "issue:45161", + "accept": false, + "reason": "Bert ZeRO-3 loading error is unrelated to GPT-OSS tensor parallelism." + }, + { + "left": "issue:34928", + "right": "issue:36331", + "accept": false, + "reason": "Activation checkpointing/FSDP tensor mismatch is unrelated to the custom trainer loss signature issue." + }, + { + "left": "issue:43596", + "right": "issue:45161", + "accept": false, + "reason": "Different model and different failure path." + }, + { + "left": "issue:43716", + "right": "issue:45507", + "accept": false, + "reason": "Dtype mismatch and invalid method invocation are unrelated." + }, + { + "left": "issue:39290", + "right": "issue:45081", + "accept": false, + "reason": "Different model/configuration issues with no shared concrete bug." + }, + { + "left": "issue:43828", + "right": "issue:45161", + "accept": false, + "reason": "Autocast dtype mismatch is unrelated to GPT-OSS TP failure." + }, + { + "left": "issue:43425", + "right": "issue:44292", + "accept": false, + "reason": "Torch version incompatibility and NVFP4 model execution error are unrelated." + }, + { + "left": "issue:44918", + "right": "issue:45161", + "accept": false, + "reason": "TRL embedding unpacking and GPT-OSS tensor-parallel failures are unrelated." + }, + { + "left": "issue:34928", + "right": "issue:41720", + "accept": false, + "reason": "FSDP checkpointing error and Qwen3 auto-device-map cuda assert are different bugs." + }, + { + "left": "issue:43827", + "right": "issue:44512", + "accept": false, + "reason": "Both are v5 docs regressions, but they concern different removed items and are not clearly one change." + }, + { + "left": "issue:43716", + "right": "issue:44560", + "accept": false, + "reason": "Different model-specific dtype/video pipeline failures." + }, + { + "left": "issue:43716", + "right": "issue:44918", + "accept": false, + "reason": "Different model/input handling failures." + }, + { + "left": "issue:43039", + "right": "issue:43828", + "accept": false, + "reason": "Different model/runtime paths; one is kernel selection, the other is autocast mismatch." + }, + { + "left": "issue:30277", + "right": "issue:36331", + "accept": false, + "reason": "DeepSpeed collective mismatch and trainer signature mismatch are unrelated." + }, + { + "left": "issue:43039", + "right": "issue:44805", + "accept": false, + "reason": "Liger Kernel cross-entropy call does not match ZeRO-3 loading failures." + }, + { + "left": "issue:34928", + "right": "issue:36010", + "accept": false, + "reason": "Checkpointing/FSDP issue and GenerationMixin import breakage are unrelated." + }, + { + "left": "issue:41762", + "right": "issue:43638", + "accept": true, + "reason": "Same ZeRO-3 index-out-of-bounds loading bug, presented on different model names." + }, + { + "left": "issue:43901", + "right": "issue:44512", + "accept": false, + "reason": "Different stale-doc references and no clear single underlying change." + }, + { + "left": "issue:39290", + "right": "issue:41720", + "accept": false, + "reason": "Different Qwen/Gemma runtime issues with distinct failure signatures." + }, + { + "left": "issue:43866", + "right": "issue:44863", + "accept": false, + "reason": "Checkpoint corruption and NemotronH loading failure are not the same bug." + }, + { + "left": "issue:43854", + "right": "issue:43866", + "accept": false, + "reason": "Unit-test load failure and checkpoint corruption are different problems." + }, + { + "left": "issue:43425", + "right": "issue:45070", + "accept": false, + "reason": "Torch incompatibility and pydantic field breakage are unrelated." + }, + { + "left": "issue:41093", + "right": "issue:43638", + "accept": false, + "reason": "Mask-shape mismatch and ZeRO-3 index-out-of-bounds are different failure modes." + }, + { + "left": "issue:39290", + "right": "issue:43531", + "accept": false, + "reason": "Different Qwen/Gemma config issues, not the same bug." + }, + { + "left": "issue:43404", + "right": "issue:43866", + "accept": false, + "reason": "lm_head tying bug and checkpoint corruption are unrelated." + }, + { + "left": "issue:45362", + "right": "issue:45464", + "accept": false, + "reason": "Same model family, but different symptoms and execution paths; not the same concrete bug." + }, + { + "left": "issue:43792", + "right": "issue:45070", + "accept": false, + "reason": "Whisper runtime failure and pydantic field regression are unrelated." + }, + { + "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 error and Gemma3/vLLM config issue are unrelated." + }, + { + "left": "issue:44841", + "right": "issue:45084", + "accept": false, + "reason": "Processor failure and template compilation error are unrelated." + }, + { + "left": "issue:41093", + "right": "issue:41762", + "accept": false, + "reason": "Both are shape/index problems, but the reported failure modes and likely code paths differ." + }, + { + "left": "issue:43296", + "right": "issue:43366", + "accept": false, + "reason": "Different model support/load issues with no shared concrete change." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary stays within the packet evidence and the soft-edge calls are conservative. The ZeRO-3/BERT/Gemma cluster is the clearest duplicate set, and the docs-only cluster is appropriately treated as weaker." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 2, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:36331", + "issue:39186", + "issue:39290", + "issue:39692", + "issue:40990", + "issue:41093", + "issue:41553", + "issue:41762", + "issue:42915", + "issue:43054", + "issue:43366", + "issue:43404", + "issue:43531", + "issue:43541", + "issue:43572", + "issue:43596", + "issue:43644", + "issue:43645", + "issue:43742", + "issue:43828", + "issue:43866", + "issue:43873", + "issue:43883", + "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:44560", + "issue:44589", + "issue:44661", + "issue:44863", + "issue:44918", + "issue:44928", + "issue:44960", + "issue:45005", + "issue:45070", + "issue:45161", + "issue:45399", + "issue:45464", + "issue:45507" + ], + "soft_pairs": [ + "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:43531|issue:45070", + "issue:44661|issue:45464", + "issue:39290|issue:43742", + "issue:43054|issue:43994", + "issue:43541|issue:44589", + "issue:41093|issue:43596", + "issue:42915|issue:43541", + "issue:40990|issue:44960", + "issue:39186|issue:44918", + "issue:43404|issue:45005", + "issue:43645|issue:45399", + "issue:44530|issue:45005", + "issue:44863|issue:45005", + "issue:43873|issue:45005", + "issue:44360|issue:44512", + "issue:42915|issue:45399", + "issue:44918|issue:45507", + "issue:44492|issue:44512", + "issue:43975|issue:44292", + "issue:43950|issue:44534", + "issue:43644|issue:43950", + "issue:44292|issue:45507", + "issue:43828|issue:44928", + "issue:39692|issue:43054", + "issue:41553|issue:43883", + "issue:43866|issue:44403", + "issue:36331|issue:41762", + "issue:44560|issue:45507" + ], + "prepared_review_unit_hash": "2af7e5185179a934c9888ce3cec0fd72d917bd15ea784d833f44aeacd9f4115b", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37571, + "estimated_input_tokens": 9393, + "estimated_eval_tokens": 19042 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is mostly unrelated issue reports; the only clear duplicates are the non-persistent buffer regression reports in Transformers 5.x. The rest differ by model, failure mode, or subsystem and should stay separate.", + "confidence": 0.84, + "canonical_issue_reason": "issue:43950 is the strongest canonical issue for the duplicate buffer regression because it states the exact regression (`from_pretrained()` corrupting `register_buffer(persistent=False)`) and is the most specific root-cause description.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43950 best represents the duplicate cluster because it precisely names the v5 non-persistent-buffer bug, making it the most useful anchor for triage and linking related reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43572", + "right": "issue:45070", + "accept": false, + "reason": "Both are v5/config-related regressions, but one is about `StableLmConfig.pad_token_idx` and the other is a pydantic `PretrainedConfig` field issue; different bugs." + }, + { + "left": "issue:44387", + "right": "issue:45005", + "accept": false, + "reason": "One reports int4 quantization memory/OOM behavior, the other tied-weights problems in translation models; different failure modes." + }, + { + "left": "issue:43541", + "right": "issue:45161", + "accept": false, + "reason": "Both involve MoE/generation paths, but one is a torch-dynamo `grouped_mm` tracing error and the other is a tensor-parallel support issue for GPT-OSS; not the same bug." + }, + { + "left": "issue:43828", + "right": "issue:45464", + "accept": false, + "reason": "Autocast dtype mismatch in Phi-tiny-MoE is unrelated to a streaming chat/completions failure on Qwen3.5-0.8B." + }, + { + "left": "issue:44291", + "right": "issue:45070", + "accept": false, + "reason": "`init_empty_weights` unexpectedly passing `_is_hf_initialized` is a different initialization bug than the pydantic config-field regression." + }, + { + "left": "issue:43366", + "right": "issue:45464", + "accept": false, + "reason": "GGUF support for gpt-oss and a streaming API failure are unrelated." + }, + { + "left": "issue:43531", + "right": "issue:45070", + "accept": false, + "reason": "A Qwen3-MoE `sliding_window` issue is not the same as the generic `PretrainedConfig` field regression." + }, + { + "left": "issue:44661", + "right": "issue:45464", + "accept": false, + "reason": "Tokenizer-mapping failure in `add-new-model-like` is unrelated to a Qwen3.5 streaming inference bug." + }, + { + "left": "issue:39290", + "right": "issue:43742", + "accept": false, + "reason": "Both are load-time errors, but one is a missing `sliding_window_pattern` attribute for Gemma3/vLLM and the other is a key error loading MobileLLM." + }, + { + "left": "issue:43054", + "right": "issue:43994", + "accept": false, + "reason": "Both mention SigLIP2, but one is about worse text embeddings while the other is about nonsensical outputs in AutoModel/pipeline; too different without stronger evidence." + }, + { + "left": "issue:43541", + "right": "issue:44589", + "accept": false, + "reason": "Torch-dynamo grouped_mm tracing and missing Float8 storage are distinct runtime errors." + }, + { + "left": "issue:41093", + "right": "issue:43596", + "accept": false, + "reason": "Both are indexing/shape errors, but one is a mask-length mismatch and the other is a DeepSpeed ZeRO-3 zero-size tensor index error." + }, + { + "left": "issue:42915", + "right": "issue:43541", + "accept": false, + "reason": "FineGrainedFP8Config failure for Qwen3-MoE is not the same as a Mixtral grouped_mm tracing error." + }, + { + "left": "issue:40990", + "right": "issue:44960", + "accept": false, + "reason": "High perplexity on GPT-OSS and a GLM5 issue are unrelated model-specific reports." + }, + { + "left": "issue:39186", + "right": "issue:44918", + "accept": false, + "reason": "An FSDP weight-shape runtime error is unrelated to TRL SFT input-embedding unpacking on Qwen3.5." + }, + { + "left": "issue:43404", + "right": "issue:45005", + "accept": false, + "reason": "Both involve tied weights, but one is a Mistral3 image-text model bug and the other is a broader v5 translation-model tied-weights regression; not enough to merge as the same bug." + }, + { + "left": "issue:43645", + "right": "issue:45399", + "accept": false, + "reason": "Custom-model initialization in notebooks and flash-attn2 fallback gating are different issues." + }, + { + "left": "issue:44530", + "right": "issue:45005", + "accept": false, + "reason": "PagedAttentionCache group-type errors on Qwen3.5 models are unrelated to tied-weight handling." + }, + { + "left": "issue:44863", + "right": "issue:45005", + "accept": false, + "reason": "NemotronH checkpoint loading is a model-compatibility problem, not the tied-weights regression." + }, + { + "left": "issue:43873", + "right": "issue:45005", + "accept": false, + "reason": "Quantization/offloading behavior is unrelated to tied weights." + }, + { + "left": "issue:44360", + "right": "issue:44512", + "accept": false, + "reason": "A DSA indexer activation request and a docs typo are unrelated." + }, + { + "left": "issue:44918", + "right": "issue:45507", + "accept": false, + "reason": "TRL SFT embedding unpacking and a GraniteMoEHybrid invalid-method call are different code paths." + }, + { + "left": "issue:44492", + "right": "issue:44512", + "accept": false, + "reason": "Cache-strategy typo and removed-run-command docs are unrelated documentation issues." + }, + { + "left": "issue:43975", + "right": "issue:44292", + "accept": false, + "reason": "Detokenization in v5 and a Qwen-3-8B-NVFP4 runtime error are different model/runtime problems." + }, + { + "left": "issue:43950", + "right": "issue:44534", + "accept": true, + "reason": "These describe the same v5 regression: non-persistent buffers being populated incorrectly during loading." + }, + { + "left": "issue:43644", + "right": "issue:43950", + "accept": true, + "reason": "Both report the same non-persistent-buffer corruption regression in Transformers 5.x." + }, + { + "left": "issue:44292", + "right": "issue:45507", + "accept": false, + "reason": "Qwen-3-8B-NVFP4 runtime failure is unrelated to GraniteMoEHybrid invalid-method calls." + }, + { + "left": "issue:43828", + "right": "issue:44928", + "accept": false, + "reason": "Autocast dtype mismatch and Qwen3.5 RLHF NaN explosion are different failures, even though both involve MoE/precision concerns." + }, + { + "left": "issue:39692", + "right": "issue:43054", + "accept": false, + "reason": "A broken SigLIP2 docs example is not the same as a separate report that SigLIP2 embeddings are worse than SigLIP." + }, + { + "left": "issue:41553", + "right": "issue:43883", + "accept": false, + "reason": "Bad AutoTokenizer error messaging for Voxtral is unrelated to missing `all_tied_weights_keys` on MolmoForCausalLM." + }, + { + "left": "issue:43866", + "right": "issue:44403", + "accept": false, + "reason": "A corrupted Ovis2 checkpoint and loading noise are not the same bug." + }, + { + "left": "issue:36331", + "right": "issue:41762", + "accept": false, + "reason": "A custom trainer signature mismatch is unrelated to a Gemma3 DeepSpeed ZeRO-3 indexing error." + }, + { + "left": "issue:44560", + "right": "issue:45507", + "accept": false, + "reason": "Qwen3-vl video StopIteration and GraniteMoEHybrid invalid-method are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The two accepted soft-edge pairs are well supported by near-identical issue titles and descriptions about the same non-persistent-buffer regression in Transformers 5.x, and the other rejections avoid overclaiming 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": 13, + "review_unit_index": 3, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:38175", + "issue:41553", + "issue:41762", + "issue:42491", + "issue:42915", + "issue:42947", + "issue:43054", + "issue:43257", + "issue:43278", + "issue:43404", + "issue:43493", + "issue:43643", + "issue:43742", + "issue:43782", + "issue:43792", + "issue:43824", + "issue:43827", + "issue:43854", + "issue:43856", + "issue:43866", + "issue:43872", + "issue:43881", + "issue:43883", + "issue:43940", + "issue:43950", + "issue:43975", + "issue:44220", + "issue:44291", + "issue:44368", + "issue:44387", + "issue:44403", + "issue:44451", + "issue:44488", + "issue:44509", + "issue:44589", + "issue:44661", + "issue:44863", + "issue:44928", + "issue:44960", + "issue:44991", + "issue:45020", + "issue:45081", + "issue:45305", + "issue:45313", + "issue:45356", + "issue:45399", + "issue:45520", + "issue:45588" + ], + "soft_pairs": [ + "issue:41553|issue:43881", + "issue:43872|issue:44589", + "issue:38175|issue:43054", + "issue:42947|issue:44387", + "issue:43054|issue:43493", + "issue:43881|issue:43883", + "issue:44403|issue:44451", + "issue:43975|issue:45520", + "issue:42947|issue:43856", + "issue:43643|issue:45020", + "issue:44403|issue:44488", + "issue:43782|issue:44960", + "issue:42491|issue:44368", + "issue:41762|issue:42915", + "issue:43975|issue:44451", + "issue:45020|issue:45356", + "issue:44661|issue:45020", + "issue:43054|issue:43278", + "issue:43824|issue:43872", + "issue:44991|issue:45399", + "issue:43827|issue:44509", + "issue:43792|issue:44220", + "issue:45081|issue:45399", + "issue:43404|issue:43950", + "issue:43257|issue:43866", + "issue:42915|issue:45020", + "issue:43742|issue:45399", + "issue:41553|issue:44991", + "issue:43742|issue:45020", + "issue:43940|issue:45313", + "issue:43872|issue:44291", + "issue:43854|issue:44863", + "issue:44928|issue:45588", + "issue:41553|issue:44488", + "issue:42915|issue:43872", + "issue:43257|issue:45305" + ], + "prepared_review_unit_hash": "d758c0340a6177fa2fdb80123af951978fefa5db6e53f3406086f833a67499e2", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 36, + "serialized_chars": 38600, + "estimated_input_tokens": 9650, + "estimated_eval_tokens": 19556 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a mix of unrelated reports with several tight duplicate clusters. The SigLIP2 group should be described more conservatively: 43493 is the best anchor for the HF-vs-JAX discrepancy, but 38175 looks only loosely related from the available evidence rather than a confirmed duplicate of 43054.", + "confidence": 0.63, + "canonical_issue_reason": "43493 is the strongest single anchor because it names the concrete SigLIP2 HF-vs-JAX implementation discrepancy; it is the cleanest root-cause-style report in the subgroup.", + "canonical_pr_reason": null, + "best_issue_reason": "43493 is the best overall issue representative because it captures a specific implementation mismatch rather than just a downstream symptom, and it is the clearest anchor for the SigLIP2 cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41553", + "right": "issue:43881", + "accept": false, + "reason": "Different models and different failures; both are loading issues but not the same bug." + }, + { + "left": "issue:43872", + "right": "issue:44589", + "accept": false, + "reason": "Both involve compatibility/loading problems, but the `_is_hf_initialized` kwarg bug is distinct from the Float8 storage error." + }, + { + "left": "issue:38175", + "right": "issue:43054", + "accept": false, + "reason": "They are both SigLIP2-related quality reports, but the packet only supports broad thematic similarity, not a confirmed shared underlying implementation bug." + }, + { + "left": "issue:42947", + "right": "issue:44387", + "accept": false, + "reason": "Different problems: LoRA gradient checkpointing vs int4 quantization memory/OOM." + }, + { + "left": "issue:43054", + "right": "issue:43493", + "accept": true, + "reason": "Same SigLIP2 discrepancy family; 43493 states the root HF-vs-JAX mismatch behind the degraded outputs." + }, + { + "left": "issue:43881", + "right": "issue:43883", + "accept": false, + "reason": "Different model families and different failure modes." + }, + { + "left": "issue:44403", + "right": "issue:44451", + "accept": false, + "reason": "Generic loading noise/warnings vs a specific model load failure." + }, + { + "left": "issue:43975", + "right": "issue:45520", + "accept": false, + "reason": "Unrelated subsystems: tokenizer detokenization vs flash-attn import/key errors." + }, + { + "left": "issue:42947", + "right": "issue:43856", + "accept": false, + "reason": "Both mention memory, but the training/checkpointing contexts and root causes differ." + }, + { + "left": "issue:43643", + "right": "issue:45020", + "accept": false, + "reason": "Both are remote_code-related, but one is a specific AutoConfig symptom and the other is a broad umbrella report; not enough to confirm the same bug." + }, + { + "left": "issue:44403", + "right": "issue:44488", + "accept": false, + "reason": "These are separate model-loading reports, not the same defect." + }, + { + "left": "issue:43782", + "right": "issue:44960", + "accept": false, + "reason": "Different model families and incompatible error types." + }, + { + "left": "issue:42491", + "right": "issue:44368", + "accept": false, + "reason": "LoRA hf4.x/hf5.x compatibility breakage is unrelated to a tie_word_embeddings warning." + }, + { + "left": "issue:41762", + "right": "issue:42915", + "accept": false, + "reason": "Different models and different DeepSpeed/config problems." + }, + { + "left": "issue:43975", + "right": "issue:44451", + "accept": false, + "reason": "Different issues: detokenization regression vs a model load failure." + }, + { + "left": "issue:45020", + "right": "issue:45356", + "accept": false, + "reason": "Both mention remote_code/tokenizer regressions, but the Kimi tokenizer codec bug is a different concrete problem." + }, + { + "left": "issue:44661", + "right": "issue:45020", + "accept": false, + "reason": "Tokenizer-mapping template generation bug is not the same as remote_code loading regressions." + }, + { + "left": "issue:43054", + "right": "issue:43278", + "accept": false, + "reason": "SigLIP2 embedding quality vs a dtype change during evaluate; not the same bug." + }, + { + "left": "issue:43824", + "right": "issue:43872", + "accept": false, + "reason": "Importing a missing VL class is unrelated to the bitsandbytes `_is_hf_initialized` incompatibility." + }, + { + "left": "issue:44991", + "right": "issue:45399", + "accept": false, + "reason": "Tokenizer loading failure and flash-attn fallback logic are different code paths." + }, + { + "left": "issue:43827", + "right": "issue:44509", + "accept": true, + "reason": "Same docs cleanup: both still reference pipeline tasks removed in v5." + }, + { + "left": "issue:43792", + "right": "issue:44220", + "accept": false, + "reason": "The Whisper report is too generic to confirm it is the same fbank helper bug." + }, + { + "left": "issue:45081", + "right": "issue:45399", + "accept": false, + "reason": "Tokenizer regex patch crash and flash-attn fallback gating are unrelated." + }, + { + "left": "issue:43404", + "right": "issue:43950", + "accept": false, + "reason": "Weight-tying in Mistral3 and non-persistent buffer corruption are distinct issues." + }, + { + "left": "issue:43257", + "right": "issue:43866", + "accept": false, + "reason": "Qwen3 MoE deepspeed conversion bug vs an Ovis2 checkpoint corruption report." + }, + { + "left": "issue:42915", + "right": "issue:45020", + "accept": false, + "reason": "Qwen3 MoE FP8 training/memory issue is unrelated to remote_code loading regressions." + }, + { + "left": "issue:43742", + "right": "issue:45399", + "accept": false, + "reason": "Different models and different failure mechanisms." + }, + { + "left": "issue:41553", + "right": "issue:44991", + "accept": false, + "reason": "Different model families and different tokenizer-loading errors." + }, + { + "left": "issue:43742", + "right": "issue:45020", + "accept": false, + "reason": "A specific model key error is not the same as the broader remote_code regression." + }, + { + "left": "issue:43940", + "right": "issue:45313", + "accept": true, + "reason": "Same DeepSpeed ZeRO-3 weight-loading failure class on Qwen3-family models." + }, + { + "left": "issue:43872", + "right": "issue:44291", + "accept": true, + "reason": "Exact same `_is_hf_initialized` / init_empty_weights incompatibility." + }, + { + "left": "issue:43854", + "right": "issue:44863", + "accept": false, + "reason": "Different model families and different checkpoint-loading failures." + }, + { + "left": "issue:44928", + "right": "issue:45588", + "accept": false, + "reason": "RLHF gradient explosion from position_ids/SDPA fallback is unrelated to flash_attention s_aux handling." + }, + { + "left": "issue:41553", + "right": "issue:44488", + "accept": false, + "reason": "Separate model-loading failures, not the same bug." + }, + { + "left": "issue:42915", + "right": "issue:43872", + "accept": false, + "reason": "Qwen3 MoE FP8 training memory issue is unrelated to the bitsandbytes `_is_hf_initialized` crash." + }, + { + "left": "issue:43257", + "right": "issue:45305", + "accept": false, + "reason": "Different Qwen3 training/load bugs with different symptoms and code paths." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "Mostly grounded, but one soft-edge verdict is too strong for the evidence available. The SigLIP2 pair (issue:38175 \u2194 issue:43054) is only supported by broad title similarity; from the packet alone it is safer to call them related symptoms, not the same underlying implementation mismatch. Because the cluster summary also presents SigLIP2 as a clear duplicate subgroup, the overall writeup is a bit overconfident and should be made more conservative." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 4, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:24643", + "issue:30064", + "issue:36010", + "issue:36331", + "issue:38175", + "issue:39692", + "issue:41093", + "issue:42491", + "issue:42617", + "issue:42915", + "issue:43317", + "issue:43366", + "issue:43531", + "issue:43550", + "issue:43596", + "issue:43638", + "issue:43644", + "issue:43645", + "issue:43646", + "issue:43720", + "issue:43824", + "issue:43828", + "issue:43872", + "issue:43950", + "issue:43957", + "issue:43994", + "issue:44155", + "issue:44479", + "issue:44530", + "issue:44534", + "issue:44560", + "issue:44589", + "issue:44661", + "issue:44756", + "issue:44805", + "issue:44863", + "issue:44877", + "issue:44910", + "issue:44918", + "issue:44960", + "issue:44977", + "issue:45030", + "issue:45313", + "issue:45325", + "issue:45357", + "issue:45538", + "issue:45584" + ], + "soft_pairs": [ + "issue:36331|issue:41093", + "issue:41093|issue:44805", + "issue:43872|issue:45538", + "issue:44479|issue:44560", + "issue:44530|issue:44863", + "issue:43366|issue:43828", + "issue:24643|issue:30064", + "issue:44155|issue:45584", + "issue:43366|issue:43531", + "issue:43550|issue:44910", + "issue:43645|issue:43646", + "issue:43950|issue:45325", + "issue:44560|issue:44918", + "issue:43366|issue:44589", + "issue:43824|issue:43957", + "issue:42915|issue:43957", + "issue:42617|issue:43366", + "issue:38175|issue:43994", + "issue:43646|issue:43950", + "issue:44560|issue:44805", + "issue:36010|issue:42915", + "issue:43638|issue:44661", + "issue:44877|issue:45030", + "issue:43596|issue:44661", + "issue:43317|issue:44756", + "issue:43644|issue:44534", + "issue:45313|issue:45357", + "issue:38175|issue:39692", + "issue:42491|issue:43720", + "issue:44960|issue:44977" + ], + "prepared_review_unit_hash": "4a0772e4c38cbdc509a62209740a10779b54923e621469b01c702cc07f6bfb33", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36151, + "estimated_input_tokens": 9038, + "estimated_eval_tokens": 18332 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a loose collection of mostly unrelated Transformers issue reports, with a few clear duplicate subclusters: non-persistent buffer corruption, custom model initialization failures, Qwen video-regression reports, and repeated mask-shape IndexErrors. No PRs are present.", + "confidence": 0.83, + "canonical_issue_reason": "issue:44534 is the cleanest representative of the strongest duplicate subcluster: it is the broader, clearer restatement of the non-persistent-buffer regression and subsumes issue:43644.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44534 is the best global issue representative because it is the most general and clearly phrased duplicate target among the issues in this cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36331", + "right": "issue:41093", + "accept": false, + "reason": "Different failures: custom trainer API mismatch vs tensor mask-shape IndexError." + }, + { + "left": "issue:41093", + "right": "issue:44805", + "accept": true, + "reason": "Same generic mask/tensor shape-mismatch error; titles indicate the same underlying IndexError regression." + }, + { + "left": "issue:43872", + "right": "issue:45538", + "accept": false, + "reason": "Unrelated bugs: bitsandbytes constructor incompatibility vs tokenizer max-length constant." + }, + { + "left": "issue:44479", + "right": "issue:44560", + "accept": true, + "reason": "Both report the same Qwen video-input regression in the 5.3.0 timeframe; same affected code path is likely." + }, + { + "left": "issue:44530", + "right": "issue:44863", + "accept": false, + "reason": "Different model/path failures: PagedAttentionCache linear_attention crash vs NemotronH checkpoint loading." + }, + { + "left": "issue:43366", + "right": "issue:43828", + "accept": false, + "reason": "Different areas and symptoms: GGUF/gpt-oss support vs autocast dtype mismatch in Phi-tiny-MoE." + }, + { + "left": "issue:24643", + "right": "issue:30064", + "accept": false, + "reason": "Completely different bugs: DeepSpeed training weight shape error vs void segmentation-map processing." + }, + { + "left": "issue:44155", + "right": "issue:45584", + "accept": false, + "reason": "Different audio/ASR issues with no shared code path evident." + }, + { + "left": "issue:43366", + "right": "issue:43531", + "accept": false, + "reason": "Different features/models: gpt-oss GGUF support vs Qwen3-MoE sliding_window handling." + }, + { + "left": "issue:43550", + "right": "issue:44910", + "accept": false, + "reason": "Different attention/compile failures in different models and code paths." + }, + { + "left": "issue:43645", + "right": "issue:43646", + "accept": true, + "reason": "Very close duplicate wording around custom model initialization breaking in Transformers 5.0." + }, + { + "left": "issue:43950", + "right": "issue:45325", + "accept": false, + "reason": "Different regressions: non-persistent buffer corruption vs Qwen2.5-VL rope/position-id scaling." + }, + { + "left": "issue:44560", + "right": "issue:44918", + "accept": false, + "reason": "Both are Qwen video/embedding related, but the concrete failures and code paths differ (video StopIteration vs TRL SFT unpacking)." + }, + { + "left": "issue:43366", + "right": "issue:44589", + "accept": false, + "reason": "Unrelated: GGUF architecture support vs float8 storage lookup failure." + }, + { + "left": "issue:43824", + "right": "issue:43957", + "accept": false, + "reason": "Different load/import regressions with different mechanisms and affected models." + }, + { + "left": "issue:42915", + "right": "issue:43957", + "accept": false, + "reason": "Different bugs: FineGrainedFP8Config failure vs meta-device loading failure." + }, + { + "left": "issue:42617", + "right": "issue:43366", + "accept": false, + "reason": "Different subjects: 3D parallel script failure vs GGUF gpt-oss support." + }, + { + "left": "issue:38175", + "right": "issue:43994", + "accept": false, + "reason": "Same model family, but the reports are too symptom-level and not clearly the same underlying bug." + }, + { + "left": "issue:43646", + "right": "issue:43950", + "accept": false, + "reason": "Different custom-model regression vs silent non-persistent-buffer corruption." + }, + { + "left": "issue:44560", + "right": "issue:44805", + "accept": false, + "reason": "Different code paths and symptoms: Qwen video StopIteration vs mask/tensor shape mismatch." + }, + { + "left": "issue:36010", + "right": "issue:42915", + "accept": false, + "reason": "Different failures: missing GenerationMixin import vs Qwen3-MoE FP8 config issue." + }, + { + "left": "issue:43638", + "right": "issue:44661", + "accept": false, + "reason": "Different bugs: DeepSpeed Zero-3/Bert index error vs add-new-model-like tokenizer mapping issue." + }, + { + "left": "issue:44877", + "right": "issue:45030", + "accept": false, + "reason": "Both are config-validation related, but the affected models and failure modes differ." + }, + { + "left": "issue:43596", + "right": "issue:44661", + "accept": false, + "reason": "Different code paths: Zero-3 Bert init error vs tokenizer-mapping registration failure." + }, + { + "left": "issue:43317", + "right": "issue:44756", + "accept": false, + "reason": "Different problems: dequantized-model offload loading vs mmap OOM on Strix Halo." + }, + { + "left": "issue:43644", + "right": "issue:44534", + "accept": true, + "reason": "Direct duplicates: same non-persistent-buffer regression, with 44534 being the broader rephrasing." + }, + { + "left": "issue:45313", + "right": "issue:45357", + "accept": false, + "reason": "Different Qwen3.5 load/save regressions affecting different components." + }, + { + "left": "issue:38175", + "right": "issue:39692", + "accept": false, + "reason": "SigLIP2 is the only shared context, but 39692 is a broader documentation-example issue with additional quantization/model-processor problems." + }, + { + "left": "issue:42491", + "right": "issue:43720", + "accept": false, + "reason": "Unrelated loading/compatibility problems in different quantization/accelerate paths." + }, + { + "left": "issue:44960", + "right": "issue:44977", + "accept": false, + "reason": "Different model families and failures: GLM5 vs Qwen3.5 flash-attention generation." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: it correctly reflects that the set is mostly a collection of issue reports, and the named duplicate subclusters are supported by the issue titles. The no-PR statement is also consistent with the packet. The soft-edge acceptances are generally conservative, with the strongest evidence on the non-persistent-buffer and mask-shape pairs. " + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 5, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:36010", + "issue:39404", + "issue:39692", + "issue:41720", + "issue:42491", + "issue:42915", + "issue:42947", + "issue:43257", + "issue:43381", + "issue:43404", + "issue:43425", + "issue:43454", + "issue:43644", + "issue:43645", + "issue:43646", + "issue:43708", + "issue:43854", + "issue:43856", + "issue:43873", + "issue:43931", + "issue:43957", + "issue:43994", + "issue:44075", + "issue:44155", + "issue:44164", + "issue:44291", + "issue:44292", + "issue:44387", + "issue:44402", + "issue:44451", + "issue:44488", + "issue:44661", + "issue:44683", + "issue:44743", + "issue:44756", + "issue:44910", + "issue:44912", + "issue:44928", + "issue:44960", + "issue:44991", + "issue:45216", + "issue:45276", + "issue:45292", + "issue:45335", + "issue:45362", + "issue:45406", + "issue:45588" + ], + "soft_pairs": [ + "issue:44451|issue:44488", + "issue:43708|issue:44075", + "issue:43854|issue:43931", + "issue:43856|issue:43873", + "issue:42491|issue:45276", + "issue:41720|issue:42915", + "issue:43257|issue:43854", + "issue:39692|issue:43994", + "issue:44488|issue:44991", + "issue:43856|issue:44387", + "issue:45362|issue:45406", + "issue:43644|issue:43645", + "issue:42915|issue:44756", + "issue:44661|issue:44683", + "issue:42491|issue:43931", + "issue:44910|issue:45588", + "issue:43404|issue:43454", + "issue:42491|issue:43856", + "issue:45276|issue:45335", + "issue:36010|issue:39404", + "issue:44164|issue:44291", + "issue:44402|issue:44488", + "issue:41720|issue:44155", + "issue:43873|issue:44387", + "issue:39692|issue:44960", + "issue:43425|issue:43957", + "issue:44387|issue:44756", + "issue:43854|issue:45216", + "issue:44292|issue:44912", + "issue:42947|issue:43381", + "issue:44291|issue:44756", + "issue:44743|issue:44960", + "issue:45276|issue:45292", + "issue:43381|issue:44928", + "issue:43957|issue:44756", + "issue:44164|issue:44756", + "issue:43646|issue:43708", + "issue:45292|issue:45335" + ], + "prepared_review_unit_hash": "f11c5d19c87a85f9fe938011bbc90b84a995dde28423c1230b7841abea208c04", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 38, + "serialized_chars": 38399, + "estimated_input_tokens": 9600, + "estimated_eval_tokens": 19456 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "There is one clear duplicate cluster around `resize_token_embeddings` not propagating to output/decoder embeddings (issues 45276, 45292, 45335). The rest of the soft pairs are mostly thematically similar but appear to be different bugs/models and should stay separate.", + "confidence": 0.89, + "canonical_issue_reason": "issue:45292 is the broadest, model-agnostic report of the shared `resize_token_embeddings` bug and best covers the narrower Gemma4/T5Gemma variants.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45292 is the best cluster anchor: open, general, and directly describes the common failure mode that the other two issues narrow to specific model components.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44451", + "right": "issue:44488", + "accept": false, + "reason": "Same general area (model loading) but different models and no clear shared code-path bug; likely related, not duplicate." + }, + { + "left": "issue:43708", + "right": "issue:44075", + "accept": false, + "reason": "Different trainer/optimizer problems; the titles do not describe the same underlying defect." + }, + { + "left": "issue:43854", + "right": "issue:43931", + "accept": false, + "reason": "Both are model-loading failures, but for different models and distinct symptoms (unit-test load vs weight-shape mismatch)." + }, + { + "left": "issue:43856", + "right": "issue:43873", + "accept": false, + "reason": "Both involve memory/quantization, but one is Qwen3 MoE training memory use and the other is offloading under quantization; not the same bug." + }, + { + "left": "issue:42491", + "right": "issue:45276", + "accept": false, + "reason": "Different models and different failures; one is a LoRA compatibility issue, the other is resize-token-embedding propagation." + }, + { + "left": "issue:41720", + "right": "issue:42915", + "accept": false, + "reason": "Both mention Qwen3 MoE, but one is a device-mapping crash and the other is a conversion/loading issue under accelerate+deepspeed." + }, + { + "left": "issue:43257", + "right": "issue:43854", + "accept": false, + "reason": "Unrelated model families and failure modes; no shared concrete bug." + }, + { + "left": "issue:39692", + "right": "issue:43994", + "accept": false, + "reason": "Both are SigLIP2-related, but one is a docs/example issue and the other is a model/pipeline behavior report; not enough evidence of one underlying bug." + }, + { + "left": "issue:44488", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer-loading regressions, but they concern different models and likely different configs/root causes." + }, + { + "left": "issue:43856", + "right": "issue:44387", + "accept": false, + "reason": "Both are memory-related, but one is training-memory inefficiency and the other is int4 reserved-memory OOM; not the same change." + }, + { + "left": "issue:45362", + "right": "issue:45406", + "accept": false, + "reason": "Different model classes and different processor/runtime failures; not a duplicate." + }, + { + "left": "issue:43644", + "right": "issue:43645", + "accept": false, + "reason": "Both are Transformers 5.0 regressions, but one is junk non-persistent buffers and the other is custom model init in notebooks; separate bugs." + }, + { + "left": "issue:42915", + "right": "issue:44756", + "accept": false, + "reason": "Unrelated issues: Qwen3 MoE conversion vs Strix Halo mmap/OOM." + }, + { + "left": "issue:44661", + "right": "issue:44683", + "accept": false, + "reason": "Completely different areas: tokenizer mapping helper vs compiled flex attention on new torch." + }, + { + "left": "issue:42491", + "right": "issue:43931", + "accept": false, + "reason": "Different Qwen3/VL problems with no shared underlying code path." + }, + { + "left": "issue:44910", + "right": "issue:45588", + "accept": false, + "reason": "Both touch flash attention, but one is a Qwen3.5 packed-sequence interpretation bug and the other is an AttributeError on sink-less models; not the same defect." + }, + { + "left": "issue:43404", + "right": "issue:43454", + "accept": false, + "reason": "Both are lm_head weight-tying complaints, but they target different model implementations and symptoms; too broad to merge." + }, + { + "left": "issue:42491", + "right": "issue:43856", + "accept": false, + "reason": "Different Qwen3 MoE issues: LoRA compatibility vs training memory usage." + }, + { + "left": "issue:45276", + "right": "issue:45335", + "accept": true, + "reason": "Same underlying `resize_token_embeddings` propagation bug; both report the embeddings not updating in different model wrappers." + }, + { + "left": "issue:36010", + "right": "issue:39404", + "accept": false, + "reason": "No shared code path: import error for GenerationMixin vs Whisper pipeline `return_language` regression." + }, + { + "left": "issue:44164", + "right": "issue:44291", + "accept": false, + "reason": "Both involve save/load behavior, but one is `extra_state` handling and the other is `init_empty_weights`/`_is_hf_initialized`; different bugs." + }, + { + "left": "issue:44402", + "right": "issue:44488", + "accept": false, + "reason": "Tokenizer vocab mismatch vs model loading failure for a different model; not the same issue." + }, + { + "left": "issue:41720", + "right": "issue:44155", + "accept": false, + "reason": "Distinct subsystems and symptoms: Qwen3 device mapping crash vs AudioFlamingo3 batched inference leakage." + }, + { + "left": "issue:43873", + "right": "issue:44387", + "accept": false, + "reason": "Related to memory pressure, but one is quantization offloading and the other is int4 CUDA reserved memory/OOM; not duplicate enough." + }, + { + "left": "issue:39692", + "right": "issue:44960", + "accept": false, + "reason": "Different models and problem types; one is SigLIP2 docs/model mismatch, the other is GLM5." + }, + { + "left": "issue:43425", + "right": "issue:43957", + "accept": false, + "reason": "Both are version-compatibility regressions, but one is torch 2.10 and the other is `torch.device(\"meta\")` model loading; separate causes." + }, + { + "left": "issue:44387", + "right": "issue:44756", + "accept": false, + "reason": "Both mention memory, but one is quantization OOM and the other is Strix Halo mmap behavior; unrelated." + }, + { + "left": "issue:43854", + "right": "issue:45216", + "accept": false, + "reason": "Different models and different failures: GLM-4.7-Flash test loading vs Qwen3.5 checkpoint saving." + }, + { + "left": "issue:44292", + "right": "issue:44912", + "accept": false, + "reason": "Both are quantization-related, but on different models and with different failure modes; not the same change." + }, + { + "left": "issue:42947", + "right": "issue:43381", + "accept": false, + "reason": "Both involve gradient checkpointing, but one is PEFT/LoRA effectiveness and the other is eval-mode usage; different bugs." + }, + { + "left": "issue:44291", + "right": "issue:44756", + "accept": false, + "reason": "No meaningful overlap beyond being regressions; `_is_hf_initialized` loading error is unrelated to mmap/OOM." + }, + { + "left": "issue:44743", + "right": "issue:44960", + "accept": false, + "reason": "Different model implementations and different runtime behavior bugs." + }, + { + "left": "issue:45276", + "right": "issue:45292", + "accept": true, + "reason": "Same `resize_token_embeddings` bug; 45292 is the general report and 45276 is a Gemma4-specific instance." + }, + { + "left": "issue:43381", + "right": "issue:44928", + "accept": false, + "reason": "Both concern checkpointing/sequence handling, but one is eval-mode checkpointing and the other is Qwen3.5 3D position_ids/SDPA behavior." + }, + { + "left": "issue:43957", + "right": "issue:44756", + "accept": false, + "reason": "Different loading path problems with no shared underlying defect." + }, + { + "left": "issue:44164", + "right": "issue:44756", + "accept": false, + "reason": "Save/from_pretrained extra_state handling is unrelated to mmap/OOM on Strix Halo." + }, + { + "left": "issue:43646", + "right": "issue:43708", + "accept": false, + "reason": "Different initialization/resume bugs; no shared code-path evidence." + }, + { + "left": "issue:45292", + "right": "issue:45335", + "accept": true, + "reason": "Same `resize_token_embeddings` propagation issue; 45335 is a t5gemma-specific manifestation." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The cluster summary is well grounded in the packet. The resize_token_embeddings group (45276, 45292, 45335) is supported by the titles and the chosen anchor/canonical issue is conservative. The other soft-pair rejections also stay on the cautious side and do not overclaim duplication from thematic similarity alone." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 6, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:32090", + "issue:36032", + "issue:39404", + "issue:40990", + "issue:42947", + "issue:43257", + "issue:43299", + "issue:43421", + "issue:43425", + "issue:43452", + "issue:43582", + "issue:43596", + "issue:43611", + "issue:43632", + "issue:43644", + "issue:43645", + "issue:43716", + "issue:43828", + "issue:43856", + "issue:43883", + "issue:43901", + "issue:43906", + "issue:43931", + "issue:43957", + "issue:43994", + "issue:44079", + "issue:44164", + "issue:44265", + "issue:44402", + "issue:44451", + "issue:44479", + "issue:44488", + "issue:44509", + "issue:44530", + "issue:44589", + "issue:44671", + "issue:44683", + "issue:44756", + "issue:44805", + "issue:44863", + "issue:44877", + "issue:44898", + "issue:44912", + "issue:44918", + "issue:44991", + "issue:45081", + "issue:45084", + "issue:45161" + ], + "soft_pairs": [ + "issue:44479|issue:44877", + "issue:44402|issue:44451", + "issue:43645|issue:44164", + "issue:43257|issue:44863", + "issue:43425|issue:43828", + "issue:43828|issue:43957", + "issue:44589|issue:44756", + "issue:43906|issue:44530", + "issue:43931|issue:44863", + "issue:43611|issue:43645", + "issue:39404|issue:44912", + "issue:43425|issue:43716", + "issue:44530|issue:45084", + "issue:43901|issue:44509", + "issue:43299|issue:43931", + "issue:44265|issue:44898", + "issue:44479|issue:44805", + "issue:43994|issue:44079", + "issue:44671|issue:44991", + "issue:43856|issue:44756", + "issue:43425|issue:44918", + "issue:39404|issue:44671", + "issue:40990|issue:42947", + "issue:43596|issue:44683", + "issue:44589|issue:45084", + "issue:36032|issue:43452", + "issue:43582|issue:43632", + "issue:44991|issue:45081", + "issue:32090|issue:39404", + "issue:43957|issue:44164", + "issue:40990|issue:43421", + "issue:43883|issue:44488", + "issue:44164|issue:44479", + "issue:44488|issue:45081", + "issue:43425|issue:45161", + "issue:43611|issue:43644" + ], + "prepared_review_unit_hash": "6c8a8cbe78b171370d188bf37d57edaee6e99a2441cc440a6490ebe9ec7989a3", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 36, + "serialized_chars": 38488, + "estimated_input_tokens": 9622, + "estimated_eval_tokens": 19500 + }, + "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 regressions, especially model/tokenizer loading problems, but the soft pairs are not the same concrete bugs. No soft merges are warranted.", + "confidence": 0.72, + "canonical_issue_reason": "issue:43611 is the broadest and most representative loading-regression report in the set: it describes a v5 break affecting model loading via `base_model_prefix`, which aligns with the overall theme of the cluster better than the narrower model-specific issues.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43611 is the best single issue to anchor this cluster because it is general, user-facing, and closest to the common failure mode across the nearby reports (loading regressions after v5).", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44479", + "right": "issue:44877", + "accept": false, + "reason": "Both are v5 regressions, but one is a video-input pipeline issue and the other is strict config handling; different code paths and failure modes." + }, + { + "left": "issue:44402", + "right": "issue:44451", + "accept": false, + "reason": "One is tokenizer vocab boundary metadata, the other is a model-load failure for a specific checkpoint; not the same bug." + }, + { + "left": "issue:43645", + "right": "issue:44164", + "accept": false, + "reason": "Custom model initialization in notebooks and `extra_state` save/load handling are unrelated." + }, + { + "left": "issue:43257", + "right": "issue:44863", + "accept": false, + "reason": "Both are loading failures, but for different model families and different mechanisms (`accelerate+deepspeed` conversion vs NemotronH checkpoint compatibility)." + }, + { + "left": "issue:43425", + "right": "issue:43828", + "accept": false, + "reason": "Torch version incompatibility and autocast dtype mismatch are distinct problems." + }, + { + "left": "issue:43828", + "right": "issue:43957", + "accept": false, + "reason": "Autocast dtype mismatch is not the same as meta-device loading breakage." + }, + { + "left": "issue:44589", + "right": "issue:44756", + "accept": false, + "reason": "Float8 storage lookup error and Apple Silicon mmap OOM are unrelated." + }, + { + "left": "issue:43906", + "right": "issue:44530", + "accept": false, + "reason": "An isolated reproduction of an old issue is not the same as the Qwen3.5 PagedAttentionCache crash." + }, + { + "left": "issue:43931", + "right": "issue:44863", + "accept": false, + "reason": "Different models and different failure signatures: Qwen3-VL shape mismatch vs NemotronH checkpoint loading." + }, + { + "left": "issue:43611", + "right": "issue:43645", + "accept": false, + "reason": "Both involve model loading, but one is a `base_model_prefix` regression and the other is notebook-defined custom model initialization; not one concrete bug." + }, + { + "left": "issue:39404", + "right": "issue:44912", + "accept": false, + "reason": "Whisper `return_language` pipeline regression and GPT-OSS MXFP4 quantization fallback are unrelated." + }, + { + "left": "issue:43425", + "right": "issue:43716", + "accept": false, + "reason": "General torch compatibility and Mistral image dtype mismatch are different bugs." + }, + { + "left": "issue:44530", + "right": "issue:45084", + "accept": false, + "reason": "`PagedAttentionCache` group-type crash and template compilation failure are separate code paths." + }, + { + "left": "issue:43901", + "right": "issue:44509", + "accept": false, + "reason": "Both are docs issues, but they cover different pipeline/task deprecations and are not duplicates." + }, + { + "left": "issue:43299", + "right": "issue:43931", + "accept": false, + "reason": "Both mention Qwen3-VL-related loading, but one is a general MoE loading breakage and the other is a checkpoint shape mismatch; too different to merge." + }, + { + "left": "issue:44265", + "right": "issue:44898", + "accept": false, + "reason": "Torch export with `torch_compilable_check` and Perceiver interpolation failure are unrelated." + }, + { + "left": "issue:44479", + "right": "issue:44805", + "accept": false, + "reason": "Video-input regression and mask shape mismatch are not the same underlying bug." + }, + { + "left": "issue:43994", + "right": "issue:44079", + "accept": false, + "reason": "Nonsensical model outputs and `ModelOutput` key assignment with `None` are unrelated." + }, + { + "left": "issue:44671", + "right": "issue:44991", + "accept": false, + "reason": "CamemBERT masked-LM prediction errors and tokenizer loading failure are different issues." + }, + { + "left": "issue:43856", + "right": "issue:44756", + "accept": false, + "reason": "Training memory inefficiency and Strix Halo mmap OOM are separate performance/memory problems." + }, + { + "left": "issue:43425", + "right": "issue:44918", + "accept": false, + "reason": "Torch version compatibility and Qwen3.5 embedding unpacking are different failure modes." + }, + { + "left": "issue:39404", + "right": "issue:44671", + "accept": false, + "reason": "Whisper pipeline behavior and CamemBERT MLM outputs are unrelated." + }, + { + "left": "issue:40990", + "right": "issue:42947", + "accept": false, + "reason": "High perplexity on a model and gradient checkpointing not taking effect are distinct issues." + }, + { + "left": "issue:43596", + "right": "issue:44683", + "accept": false, + "reason": "DeepSpeed zero3 init index error and compiled flex_attention failure on newer torch versions are unrelated." + }, + { + "left": "issue:44589", + "right": "issue:45084", + "accept": false, + "reason": "Missing Float8 storage and template-node compilation errors are different bugs." + }, + { + "left": "issue:36032", + "right": "issue:43452", + "accept": false, + "reason": "Tokenizer special-token method conflict and `gguf_file` loading breakage are not the same problem." + }, + { + "left": "issue:43582", + "right": "issue:43632", + "accept": false, + "reason": "Apple Silicon warmup TypeError and `_is_hf_initialized` flag breakage are different runtime issues." + }, + { + "left": "issue:44991", + "right": "issue:45081", + "accept": false, + "reason": "Tokenizer loading failure and `_patch_mistral_regex` backend-tokenizer crash are related to tokenizers, but they are different concrete failures." + }, + { + "left": "issue:32090", + "right": "issue:39404", + "accept": false, + "reason": "Trainer GPU broadcast `NoneType` error and Whisper `return_language` regression are unrelated." + }, + { + "left": "issue:43957", + "right": "issue:44164", + "accept": false, + "reason": "Meta-device loading and `extra_state` save/load are separate mechanisms." + }, + { + "left": "issue:40990", + "right": "issue:43421", + "accept": false, + "reason": "Perplexity regression and runtime special-token post-processor update are unrelated." + }, + { + "left": "issue:43883", + "right": "issue:44488", + "accept": false, + "reason": "Missing `all_tied_weights_keys` and inability to load a specific BERT checkpoint are different issues." + }, + { + "left": "issue:44164", + "right": "issue:44479", + "accept": false, + "reason": "`extra_state` serialization and video-input regression are unrelated." + }, + { + "left": "issue:44488", + "right": "issue:45081", + "accept": false, + "reason": "Both involve loading/tokenizer behavior, but one is a model-loading failure and the other is a tokenizer regex patch crash; not the same bug." + }, + { + "left": "issue:43425", + "right": "issue:45161", + "accept": false, + "reason": "Torch compatibility and GPT-OSS tensor-parallel loading are different problems." + }, + { + "left": "issue:43611", + "right": "issue:43644", + "accept": false, + "reason": "Both are v5 model-loading regressions, but they target different failures: `base_model_prefix` loading vs non-persistent buffer initialization." + } + ] + }, + "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": 13, + "review_unit_index": 7, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:34567", + "issue:36032", + "issue:39404", + "issue:40444", + "issue:41553", + "issue:42915", + "issue:42947", + "issue:43262", + "issue:43317", + "issue:43322", + "issue:43377", + "issue:43404", + "issue:43452", + "issue:43482", + "issue:43540", + "issue:43541", + "issue:43582", + "issue:43643", + "issue:43644", + "issue:43645", + "issue:43646", + "issue:43716", + "issue:43819", + "issue:43825", + "issue:43883", + "issue:43994", + "issue:44206", + "issue:44220", + "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:45216", + "issue:45325", + "issue:45357", + "issue:45507", + "issue:45584" + ], + "soft_pairs": [ + "issue:44811|issue:45584", + "issue:44206|issue:44220", + "issue:44488|issue:44987", + "issue:42947|issue:44756", + "issue:43716|issue:45084", + "issue:34567|issue:40444", + "issue:43883|issue:44991", + "issue:43644|issue:43646", + "issue:43643|issue:44530", + "issue:43452|issue:43482", + "issue:44451|issue:44987", + "issue:43317|issue:43482", + "issue:36032|issue:42915", + "issue:43541|issue:45084", + "issue:39404|issue:43825", + "issue:44849|issue:45325", + "issue:42915|issue:44530", + "issue:43404|issue:44466", + "issue:43262|issue:43377", + "issue:36032|issue:43645", + "issue:44987|issue:44991", + "issue:43646|issue:44534", + "issue:45084|issue:45507", + "issue:43994|issue:44610", + "issue:43645|issue:44534", + "issue:45216|issue:45357", + "issue:43322|issue:43540", + "issue:43377|issue:43819", + "issue:44403|issue:45081", + "issue:44451|issue:45081", + "issue:41553|issue:43582", + "issue:44220|issue:44683" + ], + "prepared_review_unit_hash": "f862802ba83fc25a8eb496eedd17212f4cf94f26fb57cef28ecbbfbc2e1ae789", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37202, + "estimated_input_tokens": 9301, + "estimated_eval_tokens": 18858 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a heterogeneous cluster of unrelated Transformers regressions; only a couple of pairs look like true duplicates, centered on GGUF loading and Qwen3.5 save_pretrained serialization.", + "confidence": 0.67, + "canonical_issue_reason": "Issue 45216 is the cleanest anchor: it states the Qwen3.5 save_pretrained regression directly, and 45357 reads like a follow-up/variant of the same checkpoint-serialization bug.", + "canonical_pr_reason": null, + "best_issue_reason": "45216 is the best representative issue because it is concrete, specific to the underlying regression, and has the clearest near-duplicate in 45357.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44811", + "right": "issue:45584", + "accept": false, + "reason": "Both are Whisper-related, but one is about batch_decode skip_special_tokens handling and the other about empty-transcription generation after align_special_tokens; different failure modes." + }, + { + "left": "issue:44206", + "right": "issue:44220", + "accept": false, + "reason": "Both touch audio feature extraction, but the titles point to different bugs: an unsupported center argument vs a separate _torch_extract_fbank_features() issue." + }, + { + "left": "issue:44488", + "right": "issue:44987", + "accept": false, + "reason": "Both are model-loading failures, but they affect different models and describe different regressions; too broad to be the same bug." + }, + { + "left": "issue:42947", + "right": "issue:44756", + "accept": false, + "reason": "Different areas entirely: LoRA/gradient checkpointing behavior vs Apple Silicon mmap/OOM handling." + }, + { + "left": "issue:43716", + "right": "issue:45084", + "accept": false, + "reason": "Mistral image dtype mismatch is unrelated to a template compilation TypeError." + }, + { + "left": "issue:34567", + "right": "issue:40444", + "accept": false, + "reason": "TrainerState token counting and Qwen2.5-VL multi-image IterableDataset failures are unrelated." + }, + { + "left": "issue:43883", + "right": "issue:44991", + "accept": false, + "reason": "Different model/tokenizer-loading regressions with different root symptoms; not the same concrete bug." + }, + { + "left": "issue:43644", + "right": "issue:43646", + "accept": false, + "reason": "Both are v5 regression reports, but one is about non-persistent buffers and the other about custom model initialization; too generic to merge." + }, + { + "left": "issue:43643", + "right": "issue:44530", + "accept": false, + "reason": "AutoConfig trust_remote_code field loss is unrelated to Qwen3.5 PagedAttentionCache crashes." + }, + { + "left": "issue:43452", + "right": "issue:43482", + "accept": true, + "reason": "Both point to the same GGUF/from_pretrained loading regression in the v5 loader path; one is the generic API break, the other a specific Qwen2.5-GGUF manifestation." + }, + { + "left": "issue:44451", + "right": "issue:44987", + "accept": false, + "reason": "Both are loading failures, but they are for different repositories/models and do not indicate the same code-path bug." + }, + { + "left": "issue:43317", + "right": "issue:43482", + "accept": false, + "reason": "Device-map offload/dequantized-model loading is a different failure mode from GGUF loading in v5." + }, + { + "left": "issue:36032", + "right": "issue:42915", + "accept": false, + "reason": "T5 tokenizer special-token method conflict and Qwen3Moe FineGrainedFP8Config failure are unrelated." + }, + { + "left": "issue:43541", + "right": "issue:45084", + "accept": false, + "reason": "Torch Dynamo grouped_mm tracing failure is unrelated to the template-node compilation error." + }, + { + "left": "issue:39404", + "right": "issue:43825", + "accept": false, + "reason": "Both involve pipeline behavior, but one is a Whisper return_language regression and the other is an error-message/docs issue about translation support." + }, + { + "left": "issue:44849", + "right": "issue:45325", + "accept": false, + "reason": "Different Qwen model families and different bugs: hidden-states output vs rope index scaling." + }, + { + "left": "issue:42915", + "right": "issue:44530", + "accept": false, + "reason": "Qwen3Moe FP8 configuration failure and Qwen3.5 PagedAttentionCache linear_attention crash are different issues." + }, + { + "left": "issue:43404", + "right": "issue:44466", + "accept": false, + "reason": "Both concern tied weights, but one is an untied lm_head bug in Mistral3ForConditionalGeneration and the other is a device-dependent save_pretrained serialization issue." + }, + { + "left": "issue:43262", + "right": "issue:43377", + "accept": false, + "reason": "Audio chat-template sampling-rate defaults and MIMI padding-mask batching differences are separate bugs." + }, + { + "left": "issue:36032", + "right": "issue:43645", + "accept": false, + "reason": "Tokenizer method conflict and custom model initialization in notebooks are not the same bug." + }, + { + "left": "issue:44987", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer/model loading regressions, but they affect different models and likely different loader paths." + }, + { + "left": "issue:43646", + "right": "issue:44534", + "accept": false, + "reason": "Custom model initialization and non-persistent buffer junk are related by theme, but the titles describe different concrete regressions." + }, + { + "left": "issue:45084", + "right": "issue:45507", + "accept": false, + "reason": "Template compilation failure and GraniteMoEHybrid invalid-method calls are unrelated." + }, + { + "left": "issue:43994", + "right": "issue:44610", + "accept": false, + "reason": "Both involve model/processor mismatch, but they are for different models and different preprocessing expectations." + }, + { + "left": "issue:43645", + "right": "issue:44534", + "accept": false, + "reason": "Custom notebook model initialization and v5 non-persistent buffer junk are not the same concrete bug." + }, + { + "left": "issue:45216", + "right": "issue:45357", + "accept": true, + "reason": "Same Qwen3.5 save_pretrained regression: both report incorrect checkpoint serialization, with 45357 narrowing it to visual encoder keys." + }, + { + "left": "issue:43322", + "right": "issue:43540", + "accept": false, + "reason": "Llava Next loading segfault and Qwen3OmniMoe video-input ValueError are different model-specific failures." + }, + { + "left": "issue:43377", + "right": "issue:43819", + "accept": false, + "reason": "MIMI batch-vs-single padding-mask discrepancy is unrelated to DAC.from_latents missing STE behavior." + }, + { + "left": "issue:44403", + "right": "issue:45081", + "accept": false, + "reason": "Generic loading noise and a Mistral regex patch AttributeError are different issues." + }, + { + "left": "issue:44451", + "right": "issue:45081", + "accept": false, + "reason": "Different model-loading failures with no shared concrete bug path." + }, + { + "left": "issue:41553", + "right": "issue:43582", + "accept": false, + "reason": "Bad AutoTokenizer error message for Voxtral and Apple Silicon caching_allocator_warmup TypeError are unrelated." + }, + { + "left": "issue:44220", + "right": "issue:44683", + "accept": false, + "reason": "Audio fbank feature extraction and compiled flex_attention on torch>=2.9 are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The cluster summary is grounded in the packet and stays conservative. The two accepted pairs are well supported by their titles alone: 43452/43482 both point to the same GGUF/v5 loading regression, and 45216/45357 both describe the same Qwen3.5 save_pretrained serialization bug. The remaining pairwise rejections avoid overclaiming and generally distinguish different models or failure modes appropriately." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 8, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:33666", + "issue:35707", + "issue:36032", + "issue:40444", + "issue:40990", + "issue:41720", + "issue:42175", + "issue:42915", + "issue:43296", + "issue:43317", + "issue:43404", + "issue:43421", + "issue:43425", + "issue:43482", + "issue:43531", + "issue:43611", + "issue:43632", + "issue:43742", + "issue:43792", + "issue:43818", + "issue:43856", + "issue:44062", + "issue:44079", + "issue:44265", + "issue:44291", + "issue:44403", + "issue:44479", + "issue:44534", + "issue:44568", + "issue:44589", + "issue:44610", + "issue:44683", + "issue:44756", + "issue:44811", + "issue:44829", + "issue:44877", + "issue:44987", + "issue:44991", + "issue:45020", + "issue:45081", + "issue:45084", + "issue:45127", + "issue:45325", + "issue:45357", + "issue:45479", + "issue:45538", + "issue:45542" + ], + "soft_pairs": [ + "issue:43632|issue:44756", + "issue:44265|issue:44610", + "issue:43404|issue:45127", + "issue:42915|issue:45084", + "issue:44987|issue:45081", + "issue:43296|issue:43531", + "issue:44479|issue:45325", + "issue:44062|issue:44987", + "issue:42915|issue:44291", + "issue:40990|issue:44811", + "issue:42175|issue:45542", + "issue:43317|issue:43856", + "issue:43611|issue:44534", + "issue:36032|issue:43742", + "issue:40444|issue:45325", + "issue:43632|issue:44534", + "issue:43421|issue:44568", + "issue:43818|issue:45357", + "issue:42915|issue:44589", + "issue:43531|issue:44877", + "issue:36032|issue:41720", + "issue:44683|issue:45020", + "issue:43425|issue:44403", + "issue:43482|issue:45538", + "issue:44829|issue:45479", + "issue:33666|issue:40444", + "issue:44403|issue:44991", + "issue:43792|issue:44589", + "issue:44079|issue:44534", + "issue:35707|issue:40444" + ], + "prepared_review_unit_hash": "d7ffc5c6c082c02c1c6e3fd7228f2baa7b9c0bb8dfe5b48c0d0dbe0f87802dba", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36158, + "estimated_input_tokens": 9040, + "estimated_eval_tokens": 18336 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is highly heterogeneous: the suggested pairs share at most broad subsystem vocabulary (tokenizers, Qwen, v5, FP8, etc.) but not the same concrete bug or code path. I don\u2019t see a true duplicate cluster here, so no canonical issue/PR stands out.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43632", + "right": "issue:44756", + "accept": false, + "reason": "Different problems: HF init flag regression vs Strix Halo mmap/OOM handling." + }, + { + "left": "issue:44265", + "right": "issue:44610", + "accept": false, + "reason": "torch.export/torch_compilable_check is unrelated to OmDet-Turbo input-size mismatch." + }, + { + "left": "issue:43404", + "right": "issue:45127", + "accept": false, + "reason": "Both mention weight tying, but one is missing tie in Mistral3 and the other is LoRA merge collapse; different bugs." + }, + { + "left": "issue:42915", + "right": "issue:45084", + "accept": false, + "reason": "Qwen3Moe FP8 config failure and template-node compilation error are unrelated failure modes." + }, + { + "left": "issue:44987", + "right": "issue:45081", + "accept": false, + "reason": "Different models and code paths: physical-intelligence/fast loading vs Mistral regex patch tokenizer crash." + }, + { + "left": "issue:43296", + "right": "issue:43531", + "accept": false, + "reason": "PaddleOCR-VL load failure and Qwen3-MoE sliding_window bug are unrelated." + }, + { + "left": "issue:44479", + "right": "issue:45325", + "accept": false, + "reason": "Both are Qwen VL regressions, but one is a broad video-input regression and the other is a specific still-image RoPE scaling bug." + }, + { + "left": "issue:44062", + "right": "issue:44987", + "accept": false, + "reason": "AddedToken special-argument conflict is a tokenizer API bug, not the same as the physical-intelligence/fast loading failure." + }, + { + "left": "issue:42915", + "right": "issue:44291", + "accept": false, + "reason": "Both involve loading in v5, but FP8 config failure and _is_hf_initialized/init_empty_weights TypeError are distinct issues." + }, + { + "left": "issue:40990", + "right": "issue:44811", + "accept": false, + "reason": "Perplexity evaluation issue is unrelated to Whisper batch_decode skip_special_tokens behavior." + }, + { + "left": "issue:42175", + "right": "issue:45542", + "accept": false, + "reason": "Both concern TensorFlow packaging, but one is missing tf backend in torch extra and the other is a tensorboard-only backend error." + }, + { + "left": "issue:43317", + "right": "issue:43856", + "accept": false, + "reason": "GPU/CPU offload loading failure and Qwen3 MoE memory inefficiency are different problems." + }, + { + "left": "issue:43611", + "right": "issue:44534", + "accept": false, + "reason": "Both are v5 regressions, but base_model_prefix loading and non-persistent buffer corruption are separate code paths." + }, + { + "left": "issue:36032", + "right": "issue:43742", + "accept": false, + "reason": "Tokenizer special-token conflict and MobileLLM-125M key error are unrelated load failures." + }, + { + "left": "issue:40444", + "right": "issue:45325", + "accept": false, + "reason": "Different Qwen2.5-VL bugs: multi-image iterable finetuning vs RoPE temporal-position scaling." + }, + { + "left": "issue:43632", + "right": "issue:44534", + "accept": false, + "reason": "HF initialization flag regression is not the same as junk-filled non-persistent buffers." + }, + { + "left": "issue:43421", + "right": "issue:44568", + "accept": false, + "reason": "Special-token runtime update bug and mdeberta-v3 BOS/EOS insertion bug are related only superficially." + }, + { + "left": "issue:43818", + "right": "issue:45357", + "accept": false, + "reason": "Video-LLaVA weight/temporal-attention issue is unrelated to Qwen3.5 save_pretrained key mismatch." + }, + { + "left": "issue:42915", + "right": "issue:44589", + "accept": false, + "reason": "FP8 config failure and missing Float8 storage type are different FP8-related bugs, not the same defect." + }, + { + "left": "issue:43531", + "right": "issue:44877", + "accept": false, + "reason": "Qwen3-MoE sliding_window bug and granite_speech strict-config loading are unrelated." + }, + { + "left": "issue:36032", + "right": "issue:41720", + "accept": false, + "reason": "Tokenizer load conflict and Qwen3 auto device-map cuda assert are unrelated." + }, + { + "left": "issue:44683", + "right": "issue:45020", + "accept": false, + "reason": "Compiled flex_attention on torch>=2.9 and remote_code loading regressions are different areas." + }, + { + "left": "issue:43425", + "right": "issue:44403", + "accept": false, + "reason": "Torch version incompatibility is not the same as noisy transformer loading." + }, + { + "left": "issue:43482", + "right": "issue:45538", + "accept": false, + "reason": "Qwen2.5-GGUF/v5 loading failure and CLIPTokenizer max_length bug are unrelated." + }, + { + "left": "issue:44829", + "right": "issue:45479", + "accept": false, + "reason": "Both involve bad training behavior, but flash_attention_3 degeneration and single-label/num_labels=1 zero-loss are distinct causes." + }, + { + "left": "issue:33666", + "right": "issue:40444", + "accept": false, + "reason": "Same broad family (Qwen VL training), but multi-GPU training and multi-image iterable finetuning are not the same bug." + }, + { + "left": "issue:44403", + "right": "issue:44991", + "accept": false, + "reason": "Unnecessary load noise and tokenizer load failure for est-roberta are different issues." + }, + { + "left": "issue:43792", + "right": "issue:44589", + "accept": false, + "reason": "Whisper runtime failure and missing Float8 storage object are unrelated." + }, + { + "left": "issue:44079", + "right": "issue:44534", + "accept": false, + "reason": "ModelOutput key assignment and non-persistent buffer corruption are different internal bugs." + }, + { + "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 dataset finetuning." + } + ] + }, + "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": 13, + "review_unit_index": 9, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:34634", + "issue:35707", + "issue:40444", + "issue:40990", + "issue:41720", + "issue:42175", + "issue:42915", + "issue:43262", + "issue:43296", + "issue:43317", + "issue:43377", + "issue:43454", + "issue:43482", + "issue:43525", + "issue:43526", + "issue:43531", + "issue:43611", + "issue:43632", + "issue:43644", + "issue:43646", + "issue:43701", + "issue:43746", + "issue:43749", + "issue:43792", + "issue:43828", + "issue:43873", + "issue:43881", + "issue:43883", + "issue:43957", + "issue:43994", + "issue:44079", + "issue:44265", + "issue:44291", + "issue:44387", + "issue:44466", + "issue:44488", + "issue:44589", + "issue:44617", + "issue:44683", + "issue:44898", + "issue:44991", + "issue:45072", + "issue:45081", + "issue:45325", + "issue:45381", + "issue:45491", + "issue:45563", + "issue:45584" + ], + "soft_pairs": [ + "issue:43377|issue:45491", + "issue:43482|issue:43525", + "issue:44291|issue:44589", + "issue:43749|issue:44079", + "issue:44079|issue:45072", + "issue:43644|issue:44079", + "issue:43632|issue:45072", + "issue:40444|issue:45381", + "issue:44265|issue:45072", + "issue:43881|issue:44488", + "issue:45325|issue:45381", + "issue:43531|issue:44291", + "issue:43611|issue:43646", + "issue:41720|issue:45081", + "issue:42175|issue:43296", + "issue:43454|issue:44466", + "issue:43994|issue:44898", + "issue:44387|issue:44617", + "issue:43828|issue:44683", + "issue:42915|issue:43482", + "issue:43526|issue:43883", + "issue:43792|issue:43957", + "issue:43701|issue:45325", + "issue:43262|issue:43746", + "issue:43632|issue:45563", + "issue:43881|issue:44991", + "issue:43317|issue:43873", + "issue:40990|issue:45584", + "issue:34634|issue:35707" + ], + "prepared_review_unit_hash": "c22d20c078767bf7e4f2a00609c0508fbdd893e92cef0217ed7a6050c50b69b5", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36393, + "estimated_input_tokens": 9099, + "estimated_eval_tokens": 18454 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a loose thematic group of transformer-regression reports, not a set of true duplicates. The strongest center is around Transformers v5 loading/initialization regressions, but the paired items usually hit different code paths or model families.", + "confidence": 0.74, + "canonical_issue_reason": "Issue 43632 is the best representative because it captures a broad, core v5 initialization regression that can plausibly underlie several nearby loading bugs, while still being concrete and well-scoped.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43632 is the best issue to keep as the cluster anchor: it is broad enough to represent the v5 loading/init breakage theme, but specific enough to remain actionable.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43377", + "right": "issue:45491", + "accept": false, + "reason": "Both mention sequence/batching behavior, but one is MIMI encoder padding-mask inconsistency and the other is Gemma3 sliding-window NaNs; different models and different failure mechanisms." + }, + { + "left": "issue:43482", + "right": "issue:43525", + "accept": false, + "reason": "Both are Transformers v5 load regressions, but one is GGUF loading and the other is a missing pad_token_id attribute on Llama4Config; distinct bugs." + }, + { + "left": "issue:44291", + "right": "issue:44589", + "accept": false, + "reason": "Both involve v5/init-loading breakage, but one is an unexpected _is_hf_initialized argument with init_empty_weights and the other is a missing Float8 storage type; not the same code path." + }, + { + "left": "issue:43749", + "right": "issue:44079", + "accept": false, + "reason": "FSDP CPU RAM efficient loading and ModelOutput key assignment are unrelated behaviors; only a broad v5 context overlaps." + }, + { + "left": "issue:44079", + "right": "issue:45072", + "accept": false, + "reason": "ModelOutput key handling and CI dtype mismatches in SwitchTransformers/TimmWrapperModel are different bugs with different symptoms." + }, + { + "left": "issue:43644", + "right": "issue:44079", + "accept": false, + "reason": "Non-persistent buffer serialization corruption is a separate state-dict/load issue from ModelOutput key assignment." + }, + { + "left": "issue:43632", + "right": "issue:45072", + "accept": false, + "reason": "The _is_hf_initialized regression and bfloat16 dtype mismatches are different failures; they may both surface in v5 but not the same underlying bug." + }, + { + "left": "issue:40444", + "right": "issue:45381", + "accept": false, + "reason": "One is multi-image iterable dataset finetuning for Qwen2.5-VL, the other is video vision_position_ids in Qwen2.5-VL; related model family but different input modality bug." + }, + { + "left": "issue:44265", + "right": "issue:45072", + "accept": false, + "reason": "torch.export.export with torch_compilable_check and inference dtype mismatches are unrelated issues." + }, + { + "left": "issue:43881", + "right": "issue:44488", + "accept": false, + "reason": "GLM-4V load failure and cjvt/sleng-bert tokenizer/model load failure are unrelated model-specific loading problems." + }, + { + "left": "issue:45325", + "right": "issue:45381", + "accept": false, + "reason": "Both are Qwen2.5-VL position-id bugs, but one is still-image temporal scaling and the other is video input vision_position_ids; related but distinct paths." + }, + { + "left": "issue:43531", + "right": "issue:44291", + "accept": false, + "reason": "Sliding_window behavior in Qwen3-MoE and init_empty_weights/_is_hf_initialized are different regression classes." + }, + { + "left": "issue:43611", + "right": "issue:43646", + "accept": false, + "reason": "Base_model_prefix loading and custom model initialization are both v5 load/init regressions, but they are different concrete breakages." + }, + { + "left": "issue:41720", + "right": "issue:45081", + "accept": false, + "reason": "Qwen3 auto device mapping cudaErrorAssert and Mistral tokenizer regex patch crash are unrelated." + }, + { + "left": "issue:42175", + "right": "issue:43296", + "accept": false, + "reason": "TensorFlow backend packaging and PaddleOCR-VL model loading are different issues with no shared failure path." + }, + { + "left": "issue:43454", + "right": "issue:44466", + "accept": false, + "reason": "AyaVision lm_head weight tying and inconsistent lm_head.weight serialization are both weight-tying related, but one is a missing tie and the other is device-dependent serialization behavior." + }, + { + "left": "issue:43994", + "right": "issue:44898", + "accept": false, + "reason": "SigLIP2 nonsensical pipeline output and Perceiver non-default resolution failure are different model-specific inference issues." + }, + { + "left": "issue:44387", + "right": "issue:44617", + "accept": false, + "reason": "Int4 quantization memory regression and Sam3Video OOM are both memory-related, but the causes and affected code paths differ." + }, + { + "left": "issue:43828", + "right": "issue:44683", + "accept": false, + "reason": "torch.autocast dtype mismatch in Phi-tiny-MoE is unrelated to compiled flex_attention failures on torch >= 2.9." + }, + { + "left": "issue:42915", + "right": "issue:43482", + "accept": false, + "reason": "Qwen3Moe FP8 config failure and Qwen2.5-GGUF loading failure are different model/loading paths." + }, + { + "left": "issue:43526", + "right": "issue:43883", + "accept": false, + "reason": "BeitImageProcessorFast label reduction and Molmo all_tied_weights_keys are unrelated issues." + }, + { + "left": "issue:43792", + "right": "issue:43957", + "accept": false, + "reason": "Whisper large-v2 runtime failure and meta-device loading regressions on transformers 5 are separate problems." + }, + { + "left": "issue:43701", + "right": "issue:45325", + "accept": false, + "reason": "Checkpoint key mismatch during resume and Qwen2.5-VL rope-index scaling are unrelated bugs." + }, + { + "left": "issue:43262", + "right": "issue:43746", + "accept": false, + "reason": "Audio chat-template sample-rate defaulting and GraniteSpeech PEFT local checkpoint loading are different audio/model-loading issues." + }, + { + "left": "issue:43632", + "right": "issue:45563", + "accept": false, + "reason": "_is_hf_initialized regression and stale paged generate warning are not the same bug." + }, + { + "left": "issue:43881", + "right": "issue:44991", + "accept": false, + "reason": "GLM-4V loading failure and tokenizer loading failure for EMBEDDIA/est-roberta are distinct model/tokenizer regressions." + }, + { + "left": "issue:43317", + "right": "issue:43873", + "accept": false, + "reason": "gpu+cpu offload failing for dequantized models and offloading with quantization not working are related only at a high level; the concrete failure modes differ." + }, + { + "left": "issue:40990", + "right": "issue:45584", + "accept": false, + "reason": "High perplexity on gpt-oss-20b and Whisper empty transcription failure are unrelated generation/evaluation issues." + }, + { + "left": "issue:34634", + "right": "issue:35707", + "accept": false, + "reason": "BarkProcessor voice_preset and progressive generation with inputs_embeds/past_key_values are completely 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": 13, + "review_unit_index": 10, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:35707", + "issue:36331", + "issue:39692", + "issue:40444", + "issue:41720", + "issue:42617", + "issue:42915", + "issue:43296", + "issue:43316", + "issue:43317", + "issue:43322", + "issue:43377", + "issue:43404", + "issue:43454", + "issue:43526", + "issue:43550", + "issue:43577", + "issue:43606", + "issue:43708", + "issue:43720", + "issue:43749", + "issue:43792", + "issue:43819", + "issue:43873", + "issue:43881", + "issue:44186", + "issue:44265", + "issue:44291", + "issue:44292", + "issue:44423", + "issue:44466", + "issue:44479", + "issue:44534", + "issue:44610", + "issue:44671", + "issue:44683", + "issue:44743", + "issue:44756", + "issue:44877", + "issue:44898", + "issue:44913", + "issue:44918", + "issue:44977", + "issue:44991", + "issue:45072", + "issue:45325", + "issue:45357", + "issue:45406" + ], + "soft_pairs": [ + "issue:43606|issue:44265", + "issue:44291|issue:44877", + "issue:44186|issue:44265", + "issue:43606|issue:43819", + "issue:44610|issue:45325", + "issue:43377|issue:44898", + "issue:35707|issue:41720", + "issue:43454|issue:43550", + "issue:43454|issue:45072", + "issue:43377|issue:44610", + "issue:44466|issue:45357", + "issue:39692|issue:40444", + "issue:43749|issue:44534", + "issue:43296|issue:44991", + "issue:43296|issue:44877", + "issue:43792|issue:44683", + "issue:41720|issue:43322", + "issue:43454|issue:43720", + "issue:43404|issue:45357", + "issue:41720|issue:44977", + "issue:44423|issue:45406", + "issue:43526|issue:43881", + "issue:44186|issue:45072", + "issue:43577|issue:43708", + "issue:43873|issue:44756", + "issue:42617|issue:42915", + "issue:44610|issue:44898", + "issue:44877|issue:44991", + "issue:43550|issue:43720", + "issue:44479|issue:44918", + "issue:44186|issue:44610", + "issue:36331|issue:42915", + "issue:36331|issue:42617", + "issue:43316|issue:44913", + "issue:44671|issue:44743", + "issue:42915|issue:43317", + "issue:43550|issue:43606", + "issue:41720|issue:42617", + "issue:44292|issue:44479" + ], + "prepared_review_unit_hash": "af40a5c109f29ff6676b5131695b1388f8c0cea334d0bbd463cecab90012a688", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 39, + "serialized_chars": 39466, + "estimated_input_tokens": 9867, + "estimated_eval_tokens": 19990 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is highly heterogeneous: the titles point to many different bugs across loading, multimodal, tokenizer, and training paths. I do not see any soft pair that is clearly the same underlying issue, so I would keep them separate.", + "confidence": 0.16, + "canonical_issue_reason": "issue:43749 is the broadest, most infrastructure-level report here: a concrete loading regression with cross-references, making it the best representative issue in this otherwise mixed set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43749 is the strongest single issue to anchor on because it describes a clear, central failure mode in model loading rather than a narrow model-specific symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43606", + "right": "issue:44265", + "accept": false, + "reason": "Different failures: CPU offload device mismatch vs torch.export failing on torch_compilable_check." + }, + { + "left": "issue:44291", + "right": "issue:44877", + "accept": false, + "reason": "Unexpected init argument vs strict config loading; different code paths and fixes." + }, + { + "left": "issue:44186", + "right": "issue:44265", + "accept": false, + "reason": "Tokenizer crash on NER/padding vs export failure in compiled-check models." + }, + { + "left": "issue:43606", + "right": "issue:43819", + "accept": false, + "reason": "Offload device mismatch is unrelated to DAC.from_latents missing STE behavior." + }, + { + "left": "issue:44610", + "right": "issue:45325", + "accept": false, + "reason": "Processor/model image-size mismatch vs Qwen2.5-VL temporal position scaling bug." + }, + { + "left": "issue:43377", + "right": "issue:44898", + "accept": false, + "reason": "Batched-vs-single padding mask bug vs Perceiver non-default resolution failure." + }, + { + "left": "issue:35707", + "right": "issue:41720", + "accept": false, + "reason": "Generation with inputs_embeds/past_key_values is unrelated to Qwen3 auto device map cudaErrorAssert." + }, + { + "left": "issue:43454", + "right": "issue:43550", + "accept": false, + "reason": "lm_head weight tying bug vs Bamba torch.compile/SDPA failure." + }, + { + "left": "issue:43454", + "right": "issue:45072", + "accept": false, + "reason": "Weight-tying serialization issue vs dtype mismatch in SwitchTransformers/TimmWrapperModel." + }, + { + "left": "issue:43377", + "right": "issue:44610", + "accept": false, + "reason": "Different multimodal issues: MIMI padding masks vs OmDet-Turbo processor resolution mismatch." + }, + { + "left": "issue:44466", + "right": "issue:45357", + "accept": false, + "reason": "Device-dependent lm_head serialization vs Qwen3.5 visual encoder key saving regression." + }, + { + "left": "issue:39692", + "right": "issue:40444", + "accept": false, + "reason": "SigLIP2 doc example errors are unrelated to Qwen2.5-VL IterableDataset finetuning failure." + }, + { + "left": "issue:43749", + "right": "issue:44534", + "accept": false, + "reason": "FSDP CPU-efficient loading broken is different from v5 non-persistent buffer junk filling." + }, + { + "left": "issue:43296", + "right": "issue:44991", + "accept": false, + "reason": "PaddleOCR-VL loading in vLLM differs from tokenizer loading failure for est-roberta." + }, + { + "left": "issue:43296", + "right": "issue:44877", + "accept": false, + "reason": "PaddleOCR-VL/vLLM loading issue is not the same as granite_speech strict-config rejection." + }, + { + "left": "issue:43792", + "right": "issue:44683", + "accept": false, + "reason": "Whisper model load failure is unrelated to compiled flex_attention on torch >= 2.9." + }, + { + "left": "issue:41720", + "right": "issue:43322", + "accept": false, + "reason": "Qwen3 auto device-map assert differs from Llava Next segmentation fault on load." + }, + { + "left": "issue:43454", + "right": "issue:43720", + "accept": false, + "reason": "Different loading/serialization bugs: lm_head tying vs unpacking packed weights during accelerate load." + }, + { + "left": "issue:43404", + "right": "issue:45357", + "accept": false, + "reason": "Mistral3 lm_head tying bug is different from Qwen3.5 visual encoder key regression." + }, + { + "left": "issue:41720", + "right": "issue:44977", + "accept": false, + "reason": "cudaErrorAssert on A800 is not the same as Qwen3.5 flash-attention generation regression." + }, + { + "left": "issue:44423", + "right": "issue:45406", + "accept": false, + "reason": "Continuous-batching multimodal crash vs Gemma4Processor missing _tokenizer; different processors and failures." + }, + { + "left": "issue:43526", + "right": "issue:43881", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug is unrelated to glm-4v-9b loading failure." + }, + { + "left": "issue:44186", + "right": "issue:45072", + "accept": false, + "reason": "LayoutLMv2 tokenizer crash differs from dtype mismatch in SwitchTransformers/TimmWrapperModel." + }, + { + "left": "issue:43577", + "right": "issue:43708", + "accept": false, + "reason": "Blip2 dtype not propagated is unrelated to Trainer resume/max_steps recalculation." + }, + { + "left": "issue:43873", + "right": "issue:44756", + "accept": false, + "reason": "Quantization/offloading behavior issue vs mmap OOM on Strix Halo; not the same bug." + }, + { + "left": "issue:42617", + "right": "issue:42915", + "accept": false, + "reason": "3d_parallel.py failure and Qwen3Moe FineGrainedFP8Config failure are different runtime issues." + }, + { + "left": "issue:44610", + "right": "issue:44898", + "accept": false, + "reason": "OmDet-Turbo processor output size mismatch is not the same as Perceiver interpolation failure." + }, + { + "left": "issue:44877", + "right": "issue:44991", + "accept": false, + "reason": "Strict config loading for granite_speech is unrelated to tokenizer loading for est-roberta." + }, + { + "left": "issue:43550", + "right": "issue:43720", + "accept": false, + "reason": "torch.compile SDPA failure and packed-weight unpacking during load are different code paths." + }, + { + "left": "issue:44479", + "right": "issue:44918", + "accept": false, + "reason": "Video-input regression in v5.3.0 is distinct from input-embedding unpacking in trl SFT trainer." + }, + { + "left": "issue:44186", + "right": "issue:44610", + "accept": false, + "reason": "Tokenizer crash on NER inputs differs from OmDet-Turbo processor/model resolution mismatch." + }, + { + "left": "issue:36331", + "right": "issue:42915", + "accept": false, + "reason": "Trainer custom compute_loss signature error is unrelated to Qwen3Moe FP8 loading." + }, + { + "left": "issue:36331", + "right": "issue:42617", + "accept": false, + "reason": "Unexpected Trainer keyword arg and 3d_parallel.py failure are different training/runtime problems." + }, + { + "left": "issue:43316", + "right": "issue:44913", + "accept": false, + "reason": "Gemma3TextConfig API discrepancy is unrelated to GPTNeoX rotary_pct reload behavior." + }, + { + "left": "issue:44671", + "right": "issue:44743", + "accept": false, + "reason": "CamemBERT MLM prediction regression and Qwen3.5 recurrent-state reset are different model bugs." + }, + { + "left": "issue:42915", + "right": "issue:43317", + "accept": false, + "reason": "Qwen3Moe FineGrainedFP8Config failure is not the same as dequantized model offload loading failure." + }, + { + "left": "issue:43550", + "right": "issue:43606", + "accept": false, + "reason": "Bamba SDPA compile bug and Bark CPU offload mismatch are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:42617", + "accept": false, + "reason": "Qwen3 device-map assert differs from 3d_parallel.py execution failure." + }, + { + "left": "issue:44292", + "right": "issue:44479", + "accept": false, + "reason": "Qwen-3-8B-NVFP4 running error is not the same as Qwen v5.3.0 video-input 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": 13, + "review_unit_index": 11, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:30064", + "issue:33357", + "issue:34567", + "issue:34634", + "issue:35707", + "issue:36010", + "issue:36331", + "issue:41720", + "issue:42617", + "issue:42886", + "issue:42915", + "issue:43322", + "issue:43381", + "issue:43388", + "issue:43421", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43572", + "issue:43606", + "issue:43653", + "issue:43720", + "issue:43746", + "issue:43782", + "issue:43844", + "issue:43873", + "issue:43927", + "issue:44062", + "issue:44186", + "issue:44361", + "issue:44368", + "issue:44451", + "issue:44492", + "issue:44509", + "issue:44514", + "issue:44545", + "issue:44625", + "issue:44843", + "issue:44898", + "issue:44991", + "issue:45059", + "issue:45072", + "issue:45161", + "issue:45357", + "issue:45381", + "issue:45406", + "issue:45464", + "issue:45479" + ], + "soft_pairs": [ + "issue:43531|issue:43572", + "issue:41720|issue:45161", + "issue:43540|issue:43782", + "issue:43388|issue:45059", + "issue:44186|issue:44361", + "issue:41720|issue:43873", + "issue:42915|issue:43322", + "issue:36010|issue:42617", + "issue:45406|issue:45464", + "issue:44514|issue:44545", + "issue:36331|issue:41720", + "issue:33357|issue:35707", + "issue:41720|issue:43746", + "issue:43606|issue:43720", + "issue:30064|issue:34634", + "issue:44492|issue:44509", + "issue:43550|issue:43653", + "issue:44368|issue:45357", + "issue:44625|issue:45479", + "issue:43421|issue:43927", + "issue:43606|issue:43653", + "issue:43782|issue:45381", + "issue:34567|issue:35707", + "issue:34634|issue:41720", + "issue:44898|issue:45072", + "issue:42886|issue:44843", + "issue:43421|issue:43653", + "issue:44451|issue:44991", + "issue:44062|issue:44451", + "issue:43381|issue:43844" + ], + "prepared_review_unit_hash": "3e9eeddf8eb4d697a4ed643f0ba42b83f879698a66e2594a3f67e1fc118f1fc9", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36765, + "estimated_input_tokens": 9192, + "estimated_eval_tokens": 18640 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most pairs are unrelated superficial similarities. Two soft duplicate candidates stand out: the Qwen2_5_VLProcessor batched padding=False crash, and the HF_HUB_OFFLINE tokenizer-loading regression.", + "confidence": 0.78, + "canonical_issue_reason": "Issue 44514 is the best canonical issue: it has the fuller repro for the `Qwen2_5_VLProcessor.apply_chat_template` crash with `padding=False`, and 44545 appears to be the same bug with less detail.", + "canonical_pr_reason": null, + "best_issue_reason": "44514 is the strongest issue to anchor this cluster because it is a precise, reproducible report and the clearest representative of an actual duplicate pair.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43531", + "right": "issue:43572", + "accept": false, + "reason": "Different models and failure modes: Qwen3-MoE sliding-window behavior vs StableLmConfig pad token metadata." + }, + { + "left": "issue:41720", + "right": "issue:45161", + "accept": false, + "reason": "Both involve model execution, but the reported problems are different: A800 cudaErrorAssert vs GPT-OSS MoE tensor-parallel behavior." + }, + { + "left": "issue:43540", + "right": "issue:43782", + "accept": false, + "reason": "Different code paths: video input processing in Qwen3OmniMoe vs Qwen3VL `from_pretrained(weight_only=True)` loading error." + }, + { + "left": "issue:43388", + "right": "issue:45059", + "accept": false, + "reason": "Unrelated bugs in evaluation metric gathering vs SAM3 text/bounding-box prompting behavior." + }, + { + "left": "issue:44186", + "right": "issue:44361", + "accept": false, + "reason": "Both are tokenizer/task failures, but they affect different tokenizer families and different underlying errors." + }, + { + "left": "issue:41720", + "right": "issue:43873", + "accept": false, + "reason": "Different issues: device-map assertion on Qwen3 vs offloading/quantization behavior." + }, + { + "left": "issue:42915", + "right": "issue:43322", + "accept": false, + "reason": "Different failures in different model stacks: FineGrainedFP8 on Qwen3Moe vs Llava Next load-time segfault." + }, + { + "left": "issue:36010", + "right": "issue:42617", + "accept": false, + "reason": "No shared underlying bug; import-path regression is unrelated to running `3d_parallel.py`." + }, + { + "left": "issue:45406", + "right": "issue:45464", + "accept": false, + "reason": "Different surfaces and symptoms: transformers-serve processor init crash vs chat/completions streaming failure." + }, + { + "left": "issue:44514", + "right": "issue:44545", + "accept": true, + "reason": "Same exact `Qwen2_5_VLProcessor.apply_chat_template` crash on batched input with `padding=False`; 44545 is a duplicate report." + }, + { + "left": "issue:36331", + "right": "issue:41720", + "accept": false, + "reason": "Different bugs: custom trainer signature mismatch vs model device-mapping assertion." + }, + { + "left": "issue:33357", + "right": "issue:35707", + "accept": false, + "reason": "No common code path; MacOS bus error in CLIP loading is unrelated to progressive generation with `inputs_embeds` and `past_key_values`." + }, + { + "left": "issue:41720", + "right": "issue:43746", + "accept": false, + "reason": "Different problems: Qwen3 device-map failure vs PEFT-adapter checkpoint loading for GraniteSpeech." + }, + { + "left": "issue:43606", + "right": "issue:43720", + "accept": false, + "reason": "Both touch loading/offload, but one is a CPU-offload device mismatch and the other is BitNet packed-weight unpacking during accelerate loading." + }, + { + "left": "issue:30064", + "right": "issue:34634", + "accept": false, + "reason": "Unrelated processor bugs: segmentation-map handling vs Bark voice preset parsing." + }, + { + "left": "issue:44492", + "right": "issue:44509", + "accept": false, + "reason": "A documentation typo is not the same as stale pipeline-task docs in v5; different scope and fix." + }, + { + "left": "issue:43550", + "right": "issue:43653", + "accept": false, + "reason": "Different tokenizer/model issues: torch.compile + SDPA vs mask-token registration and empty decode output." + }, + { + "left": "issue:44368", + "right": "issue:45357", + "accept": false, + "reason": "Different regressions affecting different parts of model config/save behavior." + }, + { + "left": "issue:44625", + "right": "issue:45479", + "accept": false, + "reason": "Related to classification config, but not the same bug: one is `num_labels` propagation in Qwen3.5, the other is degenerate zero loss for single-label classification across models." + }, + { + "left": "issue:43421", + "right": "issue:43927", + "accept": false, + "reason": "Different tokenizer-state bugs: runtime post-processor updates vs saved config losing custom token IDs." + }, + { + "left": "issue:43606", + "right": "issue:43653", + "accept": false, + "reason": "Different bugs in different models: device mismatch during offload vs tokenizer special-token registration." + }, + { + "left": "issue:43782", + "right": "issue:45381", + "accept": false, + "reason": "Different Qwen vision-language failures: `weight_only=True` load error vs incorrect video `vision_position_ids`." + }, + { + "left": "issue:34567", + "right": "issue:35707", + "accept": false, + "reason": "No shared underlying issue; trainer token counting is unrelated to generation with cached past key values." + }, + { + "left": "issue:34634", + "right": "issue:41720", + "accept": false, + "reason": "Bark processor voice preset handling is unrelated to Qwen3 device-mapping crashes." + }, + { + "left": "issue:44898", + "right": "issue:45072", + "accept": false, + "reason": "Different models and failure modes: Perceiver image resolution handling vs dtype mismatches in inference." + }, + { + "left": "issue:42886", + "right": "issue:44843", + "accept": true, + "reason": "Both describe tokenizer loading breaking in HF_HUB_OFFLINE mode due to an unconditional hub metadata call in the tokenizer-loading path." + }, + { + "left": "issue:43421", + "right": "issue:43653", + "accept": false, + "reason": "Different tokenizer bugs: post-processor not refreshed at runtime vs mask token not registered as special." + }, + { + "left": "issue:44451", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer load failures after newer versions, but they hit different models and the root cause is not established as the same." + }, + { + "left": "issue:44062", + "right": "issue:44451", + "accept": false, + "reason": "The AddedToken keyword-argument error is a specific tokenizer construction bug, while ScandiBERT loading failure is a separate model-specific report." + }, + { + "left": "issue:43381", + "right": "issue:43844", + "accept": false, + "reason": "Unrelated training/gradient issues: eval-mode gradient checkpointing vs ZeRO-3 gradient explosion." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The cluster summary is grounded in the packet, and the two accepted soft edges are conservative enough: 44514/44545 are near-identical reports of the same Qwen2_5_VLProcessor padding=False crash, and 42886/44843 both point to the same HF_HUB_OFFLINE tokenizer-loading regression. The rejected pairs are also framed cautiously and do not overclaim duplicates." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 12, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:30064", + "issue:36010", + "issue:39692", + "issue:40444", + "issue:43335", + "issue:43421", + "issue:43525", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43577", + "issue:43596", + "issue:43618", + "issue:43653", + "issue:43697", + "issue:43716", + "issue:43720", + "issue:43746", + "issue:43756", + "issue:43818", + "issue:43819", + "issue:43873", + "issue:43927", + "issue:43994", + "issue:44008", + "issue:44062", + "issue:44077", + "issue:44186", + "issue:44220", + "issue:44488", + "issue:44589", + "issue:44610", + "issue:44625", + "issue:44661", + "issue:44671", + "issue:44811", + "issue:44843", + "issue:44898", + "issue:44918", + "issue:44936", + "issue:44987", + "issue:45042", + "issue:45072", + "issue:45081", + "issue:45183", + "issue:45356", + "issue:45381", + "issue:45479" + ], + "soft_pairs": [ + "issue:44918|issue:44936", + "issue:44077|issue:44625", + "issue:44987|issue:45042", + "issue:43531|issue:44589", + "issue:43994|issue:44671", + "issue:39692|issue:44610", + "issue:43421|issue:44186", + "issue:45081|issue:45356", + "issue:43525|issue:43531", + "issue:43596|issue:44220", + "issue:45183|issue:45479", + "issue:43746|issue:45381", + "issue:39692|issue:43873", + "issue:43618|issue:43697", + "issue:43540|issue:44008", + "issue:43746|issue:43873", + "issue:40444|issue:43746", + "issue:44220|issue:44661", + "issue:43716|issue:44008", + "issue:43335|issue:43756", + "issue:43720|issue:43819", + "issue:43653|issue:43720", + "issue:44843|issue:45081", + "issue:43421|issue:44811", + "issue:30064|issue:36010", + "issue:44062|issue:44488", + "issue:44186|issue:44898", + "issue:43540|issue:45381", + "issue:43550|issue:45072", + "issue:43577|issue:43818", + "issue:43550|issue:43927" + ], + "prepared_review_unit_hash": "68eda53b31bae9b20c6a5ed8e508c5f6db13830f46cc2ced5cff3abba4766f85", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37390, + "estimated_input_tokens": 9348, + "estimated_eval_tokens": 18952 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is not a duplicate cluster: the items span many unrelated bugs across tokenizers, vision/video processors, quantization, training, and model config. All soft edges should be rejected.", + "confidence": 0.97, + "canonical_issue_reason": "No canonical issue: the collection is heterogeneous and does not center on one underlying bug or change.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43873 is the closest loose representative because it is open and has the most active discussion/inbound references, but it is still not a duplicate target for the rest of the set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44918", + "right": "issue:44936", + "accept": false, + "reason": "Different failures: Qwen3.5 embedding unpacking in TRL SFT vs trainer.evaluate() after train()." + }, + { + "left": "issue:44077", + "right": "issue:44625", + "accept": false, + "reason": "Unrelated: patchtsmixer post_init policy vs Qwen3.5 num_labels propagation." + }, + { + "left": "issue:44987", + "right": "issue:45042", + "accept": false, + "reason": "Different subsystems: loading a physical-intelligence model vs PIL image processors wrongly requiring torchvision." + }, + { + "left": "issue:43531", + "right": "issue:44589", + "accept": false, + "reason": "Different bugs: Qwen3-MoE sliding_window vs Float8 storage lookup failure." + }, + { + "left": "issue:43994", + "right": "issue:44671", + "accept": false, + "reason": "Different models and symptoms: SigLIP2 inference issues vs CamemBERT masked LM regression." + }, + { + "left": "issue:39692", + "right": "issue:44610", + "accept": false, + "reason": "Doc/example mistakes for SigLIP2 are unrelated to OmDet-Turbo processor size mismatch." + }, + { + "left": "issue:43421", + "right": "issue:44186", + "accept": false, + "reason": "Both are tokenizer-related, but they are distinct code paths and failures." + }, + { + "left": "issue:45081", + "right": "issue:45356", + "accept": false, + "reason": "Both touch mistral regex handling, but one is a crash and the other is a tokenizer regression/codec warning; not the same concrete bug." + }, + { + "left": "issue:43525", + "right": "issue:43531", + "accept": false, + "reason": "Llama4 pad_token_id attribute error is unrelated to Qwen3-MoE sliding_window behavior." + }, + { + "left": "issue:43596", + "right": "issue:44220", + "accept": false, + "reason": "Deepspeed zero3/BertModel initialization error is unrelated to fbank feature extraction." + }, + { + "left": "issue:45183", + "right": "issue:45479", + "accept": false, + "reason": "Input validation error messaging is unrelated to the zero-loss sequence-classification bug." + }, + { + "left": "issue:43746", + "right": "issue:45381", + "accept": false, + "reason": "GraniteSpeech PEFT checkpoint loading is unrelated to Qwen2.5-VL video position ids." + }, + { + "left": "issue:39692", + "right": "issue:43873", + "accept": false, + "reason": "SigLIP2 documentation/example errors are unrelated to quantization offloading behavior." + }, + { + "left": "issue:43618", + "right": "issue:43697", + "accept": false, + "reason": "CLIPOutput attentions regression is unrelated to RTDetrV2 output differences." + }, + { + "left": "issue:43540", + "right": "issue:44008", + "accept": false, + "reason": "Qwen3OmniMoe video processing failure is unrelated to Gemma3n audio mask name collision." + }, + { + "left": "issue:43746", + "right": "issue:43873", + "accept": false, + "reason": "PEFT adapter loading and quantized offloading are separate bugs." + }, + { + "left": "issue:40444", + "right": "issue:43746", + "accept": false, + "reason": "Qwen2.5-VL iterable dataset multi-image training failure is unrelated to GraniteSpeech local checkpoint loading." + }, + { + "left": "issue:44220", + "right": "issue:44661", + "accept": false, + "reason": "Audio feature extraction bug is unrelated to add-new-model-like failing in tokenizer mapping." + }, + { + "left": "issue:43716", + "right": "issue:44008", + "accept": false, + "reason": "Mistral image preprocessor dtype mismatch is unrelated to Gemma3n variable collision." + }, + { + "left": "issue:43335", + "right": "issue:43756", + "accept": false, + "reason": "SwitchTransformers sparse-layer config bug is unrelated to Smollm3 RoPE layer dropping." + }, + { + "left": "issue:43720", + "right": "issue:43819", + "accept": false, + "reason": "BitNet loading/unpacking issue is unrelated to DAC forward/from_latents mismatch." + }, + { + "left": "issue:43653", + "right": "issue:43720", + "accept": false, + "reason": "BigBirdTokenizer special-token decode bug is unrelated to BitNet accelerate-loading bug." + }, + { + "left": "issue:44843", + "right": "issue:45081", + "accept": false, + "reason": "Both involve mistral-regex code, but one breaks offline model_info calls while the other crashes on a missing backend_tokenizer attribute." + }, + { + "left": "issue:43421", + "right": "issue:44811", + "accept": false, + "reason": "Runtime special-token post-processing and Whisper batch_decode skip_special_tokens are different behaviors." + }, + { + "left": "issue:30064", + "right": "issue:36010", + "accept": false, + "reason": "Void segmentation map processing is unrelated to GenerationMixin import failure." + }, + { + "left": "issue:44062", + "right": "issue:44488", + "accept": false, + "reason": "AddedToken special-argument TypeError is not the same bug as loading cjvt/sleng-bert." + }, + { + "left": "issue:44186", + "right": "issue:44898", + "accept": false, + "reason": "LayoutLMv2 tokenizer crashes are unrelated to Perceiver image classification at non-default resolution." + }, + { + "left": "issue:43540", + "right": "issue:45381", + "accept": false, + "reason": "Both mention video inputs, but they are different model families and different failure modes." + }, + { + "left": "issue:43550", + "right": "issue:45072", + "accept": false, + "reason": "torch.compile/SDPA failure in Bamba is unrelated to bf16 dtype mismatches in SwitchTransformers/TimmWrapperModel." + }, + { + "left": "issue:43577", + "right": "issue:43818", + "accept": false, + "reason": "Blip2 dtype handling is unrelated to Video-LLaVA temporal-attention/weight-sharing problems." + }, + { + "left": "issue:43550", + "right": "issue:43927", + "accept": false, + "reason": "Bamba torch.compile SDPA regression is unrelated to DiaConfig custom token ID loss." + } + ] + }, + "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": 13, + "review_unit_index": 13, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:30064", + "issue:34634", + "issue:36010", + "issue:36331", + "issue:41720", + "issue:42175", + "issue:43262", + "issue:43531", + "issue:43550", + "issue:43577", + "issue:43582", + "issue:43606", + "issue:43643", + "issue:43644", + "issue:43650", + "issue:43653", + "issue:43720", + "issue:43749", + "issue:43782", + "issue:43819", + "issue:43825", + "issue:43827", + "issue:43906", + "issue:43994", + "issue:44060", + "issue:44186", + "issue:44291", + "issue:44368", + "issue:44442", + "issue:44448", + "issue:44485", + "issue:44509", + "issue:44561", + "issue:44610", + "issue:44671", + "issue:44805", + "issue:44821", + "issue:44857", + "issue:44877", + "issue:44936", + "issue:44977", + "issue:44991", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45084", + "issue:45325", + "issue:45406" + ], + "soft_pairs": [ + "issue:43643|issue:44877", + "issue:43577|issue:43582", + "issue:43782|issue:44977", + "issue:43531|issue:43643", + "issue:44448|issue:44671", + "issue:43644|issue:43749", + "issue:43653|issue:43819", + "issue:44561|issue:45020", + "issue:43825|issue:43994", + "issue:43550|issue:43819", + "issue:43825|issue:43827", + "issue:44186|issue:44442", + "issue:44821|issue:45084", + "issue:43650|issue:43906", + "issue:41720|issue:44991", + "issue:44805|issue:44936", + "issue:30064|issue:36331", + "issue:43606|issue:45072", + "issue:44485|issue:44509", + "issue:42175|issue:45081", + "issue:43782|issue:45325", + "issue:44610|issue:45072", + "issue:34634|issue:36010", + "issue:44060|issue:44368", + "issue:45081|issue:45406", + "issue:43720|issue:45072", + "issue:43262|issue:43819", + "issue:43653|issue:44671", + "issue:43582|issue:44857", + "issue:43749|issue:44291" + ], + "prepared_review_unit_hash": "b36fa89192bc3b82a60d484e384712abcbc234fbcf89edf0b1a4a0e2dd7cc3ec", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36840, + "estimated_input_tokens": 9210, + "estimated_eval_tokens": 18676 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a heterogeneous set of unrelated transformer issues with only a few loose theme overlaps (v5 regressions, remote_code, tokenizer/processor loading). No PRs are present. I would not merge any of the soft pairs as duplicates.", + "confidence": 0.95, + "canonical_issue_reason": "No single canonical duplicate stands out; the cluster is too heterogeneous. If an umbrella is needed, 45020 is the broadest remote_code-regression report.", + "canonical_pr_reason": null, + "best_issue_reason": "45020 is the closest thing to an umbrella issue because it captures the broad 'recent versions break remote_code' theme seen in a few nearby reports, though it still does not unify the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43643", + "right": "issue:44877", + "accept": false, + "reason": "Both involve config/model loading, but one is missing fields with trust_remote_code and the other is strict config rejection for granite_speech; different bugs." + }, + { + "left": "issue:43577", + "right": "issue:43582", + "accept": false, + "reason": "BLIP2 dtype propagation and Apple Silicon allocator warmup TypeError are unrelated code paths." + }, + { + "left": "issue:43782", + "right": "issue:44977", + "accept": false, + "reason": "Different models and failures: Qwen3VL weight_only loading error vs Qwen3.5 flash-attention generation issue." + }, + { + "left": "issue:43531", + "right": "issue:43643", + "accept": false, + "reason": "Sliding-window behavior in Qwen3-MoE is unrelated to trust_remote_code config field loss." + }, + { + "left": "issue:44448", + "right": "issue:44671", + "accept": false, + "reason": "Both are v5 regressions, but Pegasus generation output changes and CamemBERT masked LM predictions are distinct model/code paths." + }, + { + "left": "issue:43644", + "right": "issue:43749", + "accept": false, + "reason": "Non-persistent buffer junk and FSDP RAM-efficient loading are separate loading/initialization problems." + }, + { + "left": "issue:43653", + "right": "issue:43819", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and DAC from_latents/STE mismatch are unrelated." + }, + { + "left": "issue:44561", + "right": "issue:45020", + "accept": false, + "reason": "45020 is a broad umbrella for remote_code breakage, while 44561 is a specific is_torch_fx_available removal regression; not the same concrete bug." + }, + { + "left": "issue:43825", + "right": "issue:43994", + "accept": false, + "reason": "Pipeline error-message text and SigLIP nonsensical outputs are unrelated." + }, + { + "left": "issue:43550", + "right": "issue:43819", + "accept": false, + "reason": "torch.compile + SDPA failure in Bamba is unrelated to DAC latent decoding mismatch." + }, + { + "left": "issue:43825", + "right": "issue:43827", + "accept": false, + "reason": "One is a runtime error message, the other is stale docs; related topic but not the same bug." + }, + { + "left": "issue:44186", + "right": "issue:44442", + "accept": false, + "reason": "LayoutLMv2 NER padding/truncation crash and FastSpeech2Conformer tokenizer loading are different tokenizer issues." + }, + { + "left": "issue:44821", + "right": "issue:45084", + "accept": false, + "reason": "AutoImageProcessor URL loading and template compilation errors are unrelated." + }, + { + "left": "issue:43650", + "right": "issue:43906", + "accept": false, + "reason": "Too little concrete overlap; one is a vague 'ADD THE DATA' issue and the other is a reproduction of a different linked report." + }, + { + "left": "issue:41720", + "right": "issue:44991", + "accept": false, + "reason": "Qwen3 auto device mapping CUDA assert and est-roberta tokenizer loading are unrelated." + }, + { + "left": "issue:44805", + "right": "issue:44936", + "accept": false, + "reason": "Mask-shape IndexError and trainer.evaluate-after-train failure are distinct issues." + }, + { + "left": "issue:30064", + "right": "issue:36331", + "accept": false, + "reason": "Void segmentation map processing and CustomTrainer compute_loss kwargs are unrelated." + }, + { + "left": "issue:43606", + "right": "issue:45072", + "accept": false, + "reason": "CPU offload device mismatch in Bark-small and bf16 dtype mismatches in wrappers are different bugs." + }, + { + "left": "issue:44485", + "right": "issue:44509", + "accept": false, + "reason": "GLM-5 RoPE discussion and docs still mentioning removed pipeline tasks are unrelated." + }, + { + "left": "issue:42175", + "right": "issue:45081", + "accept": false, + "reason": "TensorFlow backend installation and Mistral regex patch crash are unrelated." + }, + { + "left": "issue:43782", + "right": "issue:45325", + "accept": false, + "reason": "Different Qwen model families and different bugs: weight_only loading vs still-image RoPE scaling." + }, + { + "left": "issue:44610", + "right": "issue:45072", + "accept": false, + "reason": "Processor image-size mismatch and bf16 dtype mismatch are not the same code-path problem." + }, + { + "left": "issue:34634", + "right": "issue:36010", + "accept": false, + "reason": "BarkProcessor voice_preset and GenerationMixin import failure are unrelated." + }, + { + "left": "issue:44060", + "right": "issue:44368", + "accept": false, + "reason": "Both mention tied-weights warnings, but they involve different Qwen variants and different triggering conditions; not clearly the same concrete bug." + }, + { + "left": "issue:45081", + "right": "issue:45406", + "accept": false, + "reason": "Both are processor/tokenizer attribute errors, but on different processors and different missing attributes; not mergeable as one fix." + }, + { + "left": "issue:43720", + "right": "issue:45072", + "accept": false, + "reason": "Packed-weight unpacking in BitNet and dtype mismatches in other models are unrelated." + }, + { + "left": "issue:43262", + "right": "issue:43819", + "accept": false, + "reason": "Audio chat-template sampling-rate defaulting and DAC latent mismatch are unrelated." + }, + { + "left": "issue:43653", + "right": "issue:44671", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and CamemBERT masked LM output regression are different model/tokenizer bugs." + }, + { + "left": "issue:43582", + "right": "issue:44857", + "accept": false, + "reason": "Apple Silicon caching_allocator_warmup TypeError and LwDetrImageLoss AMP crash are unrelated." + }, + { + "left": "issue:43749", + "right": "issue:44291", + "accept": false, + "reason": "Both concern loading, but FSDP CPU RAM efficient loading and init_empty_weights with unexpected _is_hf_initialized are distinct 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": 13, + "review_unit_index": 14, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:34567", + "issue:34634", + "issue:36010", + "issue:36331", + "issue:38175", + "issue:39692", + "issue:40990", + "issue:43257", + "issue:43262", + "issue:43329", + "issue:43452", + "issue:43454", + "issue:43526", + "issue:43531", + "issue:43550", + "issue:43577", + "issue:43638", + "issue:43645", + "issue:43653", + "issue:43696", + "issue:43697", + "issue:43720", + "issue:43746", + "issue:43749", + "issue:43756", + "issue:43819", + "issue:43854", + "issue:43927", + "issue:43931", + "issue:44479", + "issue:44554", + "issue:44568", + "issue:44589", + "issue:44610", + "issue:44756", + "issue:44811", + "issue:44912", + "issue:44936", + "issue:44977", + "issue:44991", + "issue:45042", + "issue:45072", + "issue:45084", + "issue:45356", + "issue:45357", + "issue:45488", + "issue:45538", + "issue:45600" + ], + "soft_pairs": [ + "issue:43526|issue:43697", + "issue:43526|issue:44554", + "issue:43329|issue:45600", + "issue:45084|issue:45538", + "issue:43653|issue:44912", + "issue:43454|issue:43577", + "issue:44568|issue:45488", + "issue:34634|issue:36331", + "issue:43638|issue:44936", + "issue:43452|issue:44991", + "issue:43257|issue:43329", + "issue:43746|issue:44811", + "issue:43854|issue:44977", + "issue:38175|issue:44610", + "issue:44589|issue:45042", + "issue:43257|issue:43696", + "issue:39692|issue:44912", + "issue:44568|issue:45356", + "issue:43819|issue:43927", + "issue:36010|issue:43645", + "issue:43720|issue:44610", + "issue:43262|issue:44811", + "issue:43550|issue:44912", + "issue:43749|issue:44756", + "issue:43531|issue:45042", + "issue:43329|issue:44479", + "issue:43257|issue:43931", + "issue:43257|issue:43756", + "issue:36010|issue:36331", + "issue:34567|issue:40990", + "issue:43697|issue:45357", + "issue:43577|issue:45072" + ], + "prepared_review_unit_hash": "ef7779cfb1cd1971437635f94a1811ef8055961ae7b6f7c8bb412c2ebf9f55eb", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37525, + "estimated_input_tokens": 9382, + "estimated_eval_tokens": 19020 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a broad grab-bag of mostly unrelated closed issues across training, tokenizers, multimodal processing, loading, and model-specific regressions. I only see one plausible duplicate-style soft edge: the two video-regression reports around Qwen/VLM multimodal token counting. Everything else looks like distinct bugs.", + "confidence": 0.79, + "canonical_issue_reason": "No single canonical issue stands out because the cluster is heterogeneous; only issue:43329 has a clear duplicate-like counterpart in the soft pairs.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43329 is the strongest representative because it describes a concrete, reproducible multimodal video-path bug and is the only item that plausibly matches another report in the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43526", + "right": "issue:43697", + "accept": false, + "reason": "Different subsystems and failure modes: Beit image label reduction vs RTDetrV2 output drift." + }, + { + "left": "issue:43526", + "right": "issue:44554", + "accept": false, + "reason": "Unrelated bugs: image processor label handling vs an attention correctness issue on MPS." + }, + { + "left": "issue:43329", + "right": "issue:45600", + "accept": false, + "reason": "Different code paths: multimodal video token counting vs auto-mapping references to removed configs." + }, + { + "left": "issue:45084", + "right": "issue:45538", + "accept": false, + "reason": "No overlap in underlying bug: compilation error vs tokenizer max_length default behavior." + }, + { + "left": "issue:43653", + "right": "issue:44912", + "accept": false, + "reason": "Tokenizer special-token registration is unrelated to MXFP4 quantization loading." + }, + { + "left": "issue:43454", + "right": "issue:43577", + "accept": false, + "reason": "Different model families and issues: lm_head tying vs dtype propagation in BLIP2." + }, + { + "left": "issue:44568", + "right": "issue:45488", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different models and different mechanisms." + }, + { + "left": "issue:34634", + "right": "issue:36331", + "accept": false, + "reason": "BarkProcessor voice_preset failure is unrelated to CustomTrainer compute_loss keyword handling." + }, + { + "left": "issue:43638", + "right": "issue:44936", + "accept": false, + "reason": "Different trainer failures: ZeRO-3/non-pretrained BERT indexing vs evaluate-after-train behavior." + }, + { + "left": "issue:43452", + "right": "issue:44991", + "accept": false, + "reason": "Both involve loading/tokenizers, but one is gguf_file + auto classes and the other is a specific tokenizer regression; not the same bug." + }, + { + "left": "issue:43257", + "right": "issue:43329", + "accept": false, + "reason": "Qwen3 MOE weight conversion/load issue is unrelated to multimodal video token counting." + }, + { + "left": "issue:43746", + "right": "issue:44811", + "accept": false, + "reason": "PEFT checkpoint loading for GraniteSpeech is unrelated to Whisper batch_decode special-token handling." + }, + { + "left": "issue:43854", + "right": "issue:44977", + "accept": false, + "reason": "Different model-specific inference/load problems: GLM-4.7-Flash loading vs Qwen3.5 flash-attention generation." + }, + { + "left": "issue:38175", + "right": "issue:44610", + "accept": false, + "reason": "SigLIP2 zero probabilities and OmDet-Turbo input-size mismatch are distinct vision bugs." + }, + { + "left": "issue:44589", + "right": "issue:45042", + "accept": false, + "reason": "Float8 storage lookup error is unrelated to PIL backend requiring torchvision." + }, + { + "left": "issue:43257", + "right": "issue:43696", + "accept": false, + "reason": "Qwen3 MOE conversion/loading differs from a CUDA OOM on GPT-oss-20b." + }, + { + "left": "issue:39692", + "right": "issue:44912", + "accept": false, + "reason": "Documentation example errors are unrelated to MXFP4 quantization loading." + }, + { + "left": "issue:44568", + "right": "issue:45356", + "accept": false, + "reason": "Both are tokenizer-related, but they concern different tokenizers and different regression mechanisms." + }, + { + "left": "issue:43819", + "right": "issue:43927", + "accept": false, + "reason": "DAC forward/from_latents mismatch is unrelated to DiaConfig save/load token ID loss." + }, + { + "left": "issue:36010", + "right": "issue:43645", + "accept": false, + "reason": "GenerationMixin import failure and Jupyter custom-model init issues are distinct API breakages." + }, + { + "left": "issue:43720", + "right": "issue:44610", + "accept": false, + "reason": "BitNet packed-weight loading is unrelated to OmDet-Turbo processor size mismatch." + }, + { + "left": "issue:43262", + "right": "issue:44811", + "accept": false, + "reason": "Audio chat-template sampling-rate default is unrelated to Whisper batch_decode skipping special tokens." + }, + { + "left": "issue:43550", + "right": "issue:44912", + "accept": false, + "reason": "torch.compile/SDPA failure is unrelated to MXFP4 quantization fallback." + }, + { + "left": "issue:43749", + "right": "issue:44756", + "accept": false, + "reason": "FSDP CPU RAM-efficient loading and Strix Halo mmap/OOM are separate memory-loading issues." + }, + { + "left": "issue:43531", + "right": "issue:45042", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior is unrelated to PIL backend torchvision requirements." + }, + { + "left": "issue:43329", + "right": "issue:44479", + "accept": true, + "reason": "These both point to the same video-input/multimodal regression path in Qwen/VLM processing, with 43329 naming the broken video branch directly." + }, + { + "left": "issue:43257", + "right": "issue:43931", + "accept": false, + "reason": "Qwen3 MOE loading/weight conversion is unrelated to Qwen3-VL shape mismatch." + }, + { + "left": "issue:43257", + "right": "issue:43756", + "accept": false, + "reason": "Different model families and bugs: MOE loading vs Smollm3 RoPE-layer configuration." + }, + { + "left": "issue:36010", + "right": "issue:36331", + "accept": false, + "reason": "Importing GenerationMixin and CustomTrainer.compute_loss keyword mismatch are unrelated failures." + }, + { + "left": "issue:34567", + "right": "issue:40990", + "accept": false, + "reason": "Trainer input-token counter bug is unrelated to GPT-oss perplexity behavior." + }, + { + "left": "issue:43697", + "right": "issue:45357", + "accept": false, + "reason": "RTDetrV2 output drift and Qwen3.5 visual-encoder save_pretrained regression are separate model-specific bugs." + }, + { + "left": "issue:43577", + "right": "issue:45072", + "accept": false, + "reason": "BLIP2 dtype propagation and SwitchTransformers/TimmWrapperModel bfloat16 mismatches are different loading/inference bugs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: it stays conservative about the cluster being heterogeneous, and it only endorses one soft pair that is plausibly the same multimodal video-path regression. No soft-edge verdict overstates the evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 15, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:28282", + "issue:33357", + "issue:34567", + "issue:34689", + "issue:36010", + "issue:38175", + "issue:41720", + "issue:42175", + "issue:42915", + "issue:43317", + "issue:43329", + "issue:43450", + "issue:43452", + "issue:43493", + "issue:43526", + "issue:43540", + "issue:43582", + "issue:43643", + "issue:43646", + "issue:43742", + "issue:43749", + "issue:43756", + "issue:43782", + "issue:43824", + "issue:43906", + "issue:43927", + "issue:43994", + "issue:44062", + "issue:44291", + "issue:44479", + "issue:44488", + "issue:44560", + "issue:44737", + "issue:44821", + "issue:44898", + "issue:44912", + "issue:44938", + "issue:44987", + "issue:44991", + "issue:45042", + "issue:45137", + "issue:45325", + "issue:45375", + "issue:45381", + "issue:45405", + "issue:45479", + "issue:45538", + "issue:45588" + ], + "soft_pairs": [ + "issue:43329|issue:43450", + "issue:43452|issue:43582", + "issue:41720|issue:43540", + "issue:44479|issue:45381", + "issue:42175|issue:44938", + "issue:44987|issue:45538", + "issue:43317|issue:45538", + "issue:43927|issue:44912", + "issue:43540|issue:44560", + "issue:44291|issue:45042", + "issue:33357|issue:34567", + "issue:43906|issue:45381", + "issue:43540|issue:44479", + "issue:42915|issue:45538", + "issue:42915|issue:43742", + "issue:42175|issue:43824", + "issue:44737|issue:45588", + "issue:43526|issue:45479", + "issue:42915|issue:44821", + "issue:42175|issue:44488", + "issue:44062|issue:44991", + "issue:45137|issue:45405", + "issue:38175|issue:44898", + "issue:43582|issue:43782", + "issue:43646|issue:43749", + "issue:28282|issue:34689", + "issue:36010|issue:42175", + "issue:43643|issue:45375", + "issue:43756|issue:45325", + "issue:43742|issue:44291", + "issue:43493|issue:43994" + ], + "prepared_review_unit_hash": "0df656a80f63ba86672f02b6dfe8e0bfbe247e97fcac64ac5c0af9ed87387132", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37106, + "estimated_input_tokens": 9277, + "estimated_eval_tokens": 18810 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The packet is mostly heterogeneous, but there are two solid duplicate subclusters: the Qwen video-input regression and the SigLIP2 discrepancy reports. The tokenizer pair `issue:44062` / `issue:44991` is not strong enough to merge on the evidence shown and is rejected conservatively.", + "confidence": 0.64, + "canonical_issue_reason": "Issue 44479 is the broadest, most explicit representative of the Qwen video-input regression subcluster, covering multiple affected Qwen VL variants and serving as the best anchor among the candidate issues.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44479 is the strongest global issue candidate because it is the most central and broadly scoped duplicate target in the packet; the other items are either narrower repros or unrelated bugs.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43329", + "right": "issue:43450", + "accept": false, + "reason": "Both are video-related, but one is an undefined-variable bug in multimodal token counting and the other is a batched-shape bug in video processors." + }, + { + "left": "issue:43452", + "right": "issue:43582", + "accept": false, + "reason": "Completely different areas: gguf/tokenizer loading vs Apple Silicon allocator warmup." + }, + { + "left": "issue:41720", + "right": "issue:43540", + "accept": false, + "reason": "Different failure modes and code paths: auto device-mapping CUDA assert vs Qwen3OmniMoe video-input validation." + }, + { + "left": "issue:44479", + "right": "issue:45381", + "accept": true, + "reason": "Same underlying Qwen VL video-position-id regression; 45381 is a narrower repro of the broader 44479 video-input breakage." + }, + { + "left": "issue:42175", + "right": "issue:44938", + "accept": false, + "reason": "Unrelated packaging/backend issue vs Python 3.14 load failure." + }, + { + "left": "issue:44987", + "right": "issue:45538", + "accept": false, + "reason": "Tokenizer/model loading failure and CLIP max-length constant issue are different bugs." + }, + { + "left": "issue:43317", + "right": "issue:45538", + "accept": false, + "reason": "Unrelated device-map/offload bug vs tokenizer configuration bug." + }, + { + "left": "issue:43927", + "right": "issue:44912", + "accept": false, + "reason": "Different code paths: config save/load losing token IDs vs quantization fallback to bf16." + }, + { + "left": "issue:43540", + "right": "issue:44560", + "accept": false, + "reason": "Both concern Qwen video inputs, but the model variants and concrete errors differ too much to treat as the same bug." + }, + { + "left": "issue:44291", + "right": "issue:45042", + "accept": false, + "reason": "Unrelated issues: init_empty_weights argument handling vs PIL backend torchvision dependency." + }, + { + "left": "issue:33357", + "right": "issue:34567", + "accept": false, + "reason": "MacOS bus error on CLIP vs TrainerState token-count tracking are unrelated." + }, + { + "left": "issue:43906", + "right": "issue:45381", + "accept": false, + "reason": "No clear evidence these are the same bug; one is an isolated reproduction of a different issue." + }, + { + "left": "issue:43540", + "right": "issue:44479", + "accept": false, + "reason": "Related theme, but not the same concrete bug: different Qwen video code paths and different symptoms." + }, + { + "left": "issue:42915", + "right": "issue:45538", + "accept": false, + "reason": "FP8 config failure and CLIP tokenizer max-length bug are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:43742", + "accept": false, + "reason": "Different problems: FineGrainedFP8Config loading vs MobileLLM key error." + }, + { + "left": "issue:42175", + "right": "issue:43824", + "accept": false, + "reason": "Packaging/backend installation issue vs missing Qwen class import." + }, + { + "left": "issue:44737", + "right": "issue:45588", + "accept": false, + "reason": "XLNet CPU allocation bug and flash-attention null-aux crash are unrelated." + }, + { + "left": "issue:43526", + "right": "issue:45479", + "accept": false, + "reason": "Different model families and failure modes: BEiT label reduction vs degenerate zero loss in sequence classification." + }, + { + "left": "issue:42915", + "right": "issue:44821", + "accept": false, + "reason": "FP8 config bug and AutoImageProcessor URL loading are unrelated." + }, + { + "left": "issue:42175", + "right": "issue:44488", + "accept": false, + "reason": "Backend installation issue vs model/tokenizer loading failure." + }, + { + "left": "issue:44062", + "right": "issue:44991", + "accept": false, + "reason": "One side is a specific AddedToken TypeError and the other is a generic tokenizer-loading failure; the available evidence does not show the same underlying regression." + }, + { + "left": "issue:45137", + "right": "issue:45405", + "accept": false, + "reason": "DeepSpeed ZeRO3 deque error and PEFT version pin issue are unrelated." + }, + { + "left": "issue:38175", + "right": "issue:44898", + "accept": false, + "reason": "Different model/feature areas: SigLIP2 output anomaly vs Perceiver positional-encoding interpolation." + }, + { + "left": "issue:43582", + "right": "issue:43782", + "accept": false, + "reason": "Apple Silicon TypeError and Qwen3VL weight_only loading error are different bugs." + }, + { + "left": "issue:43646", + "right": "issue:43749", + "accept": false, + "reason": "General custom model init breakage vs FSDP CPU RAM efficient loading are not the same concrete failure." + }, + { + "left": "issue:28282", + "right": "issue:34689", + "accept": false, + "reason": "Missing PyTorch import and Llama 3.2 Vision loading regression are unrelated." + }, + { + "left": "issue:36010", + "right": "issue:42175", + "accept": false, + "reason": "GenerationMixin import failure and TensorFlow backend packaging are unrelated." + }, + { + "left": "issue:43643", + "right": "issue:45375", + "accept": false, + "reason": "Both involve config fields, but the titles indicate different mechanisms and no clear same-bug evidence." + }, + { + "left": "issue:43756", + "right": "issue:45325", + "accept": false, + "reason": "RoPE-layer omission and temporal position-id scaling are different bugs." + }, + { + "left": "issue:43742", + "right": "issue:44291", + "accept": false, + "reason": "MobileLLM key error and init_empty_weights argument mismatch are unrelated." + }, + { + "left": "issue:43493", + "right": "issue:43994", + "accept": true, + "reason": "Same SigLIP2 model family and same underlying incorrect-output discrepancy; 43994 is a user-facing repro of the HF-vs-JAX mismatch." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The cluster summary is mostly grounded, but one soft-edge accept is too strong for the packet: `issue:44062` / `issue:44991` only shows a specific AddedToken TypeError on one side and a generic tokenizer-loading failure on the other, so calling them the same underlying regression goes beyond the evidence available here. The Qwen video and SigLIP2 overlaps are plausible, but that pair makes the verdict non-conservative." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 16, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:28282", + "issue:29127", + "issue:34567", + "issue:36331", + "issue:41762", + "issue:43295", + "issue:43452", + "issue:43531", + "issue:43577", + "issue:43643", + "issue:43653", + "issue:43688", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43749", + "issue:43819", + "issue:44062", + "issue:44291", + "issue:44464", + "issue:44466", + "issue:44484", + "issue:44488", + "issue:44514", + "issue:44561", + "issue:44568", + "issue:44589", + "issue:44625", + "issue:44704", + "issue:44743", + "issue:44792", + "issue:44811", + "issue:44821", + "issue:44843", + "issue:44877", + "issue:44898", + "issue:44936", + "issue:44964", + "issue:45005", + "issue:45042", + "issue:45081", + "issue:45216", + "issue:45290", + "issue:45356", + "issue:45381", + "issue:45405", + "issue:45440", + "issue:45600" + ], + "soft_pairs": [ + "issue:28282|issue:29127", + "issue:44484|issue:44704", + "issue:34567|issue:36331", + "issue:44062|issue:45081", + "issue:44291|issue:44821", + "issue:43452|issue:44488", + "issue:44792|issue:44964", + "issue:44514|issue:45290", + "issue:45405|issue:45600", + "issue:43688|issue:43749", + "issue:43643|issue:44561", + "issue:44514|issue:45381", + "issue:43452|issue:43577", + "issue:43697|issue:45216", + "issue:43742|issue:44589", + "issue:45042|issue:45081", + "issue:43531|issue:44821", + "issue:43688|issue:45440", + "issue:43452|issue:44843", + "issue:44625|issue:44877", + "issue:43653|issue:44568", + "issue:43720|issue:44898", + "issue:43819|issue:44811", + "issue:41762|issue:44936", + "issue:43295|issue:45356", + "issue:44466|issue:45005", + "issue:44464|issue:44743" + ], + "prepared_review_unit_hash": "1900b5e6f3f8b4004d3f6d8d01e5d6234391e7e6efaff901060e88c7b1c4381a", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "serialized_chars": 36193, + "estimated_input_tokens": 9049, + "estimated_eval_tokens": 18354 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most pairs are unrelated bug reports touching different code paths. The only plausible duplicate is the v5 tied-weights serialization/saving regression pair.", + "confidence": 0.62, + "canonical_issue_reason": "issue:45005 is the broader, more canonical description of the v5 tied-weights save/serialization regression; issue:44466 reads like a specific manifestation depending on model device.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45005 is the best global issue candidate because it captures the underlying tied-weights problem more generally and is easier to map to related symptoms.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:28282", + "right": "issue:29127", + "accept": false, + "reason": "Different failures: missing PyTorch dependency vs clearer LayoutLMv3 error messaging." + }, + { + "left": "issue:44484", + "right": "issue:44704", + "accept": false, + "reason": "One is about max shard size defaults; the other is AutoProcessor failing to forward kwargs to cached_file." + }, + { + "left": "issue:34567", + "right": "issue:36331", + "accept": false, + "reason": "TrainerState token counting and CustomTrainer.compute_loss keyword incompatibility are separate trainer issues." + }, + { + "left": "issue:44062", + "right": "issue:45081", + "accept": false, + "reason": "AddedToken special-argument duplication is unrelated to the Mistral regex backend_tokenizer crash." + }, + { + "left": "issue:44291", + "right": "issue:44821", + "accept": false, + "reason": "init_empty_weights/_is_hf_initialized and loading AutoImageProcessor from URL are different loading failures." + }, + { + "left": "issue:43452", + "right": "issue:44488", + "accept": false, + "reason": "Both are model loading problems, but the affected APIs and failure modes are not the same." + }, + { + "left": "issue:44792", + "right": "issue:44964", + "accept": false, + "reason": "A failed Janus image-generation test is not the same bug as failing to load Phi-4 multimodal." + }, + { + "left": "issue:44514", + "right": "issue:45290", + "accept": false, + "reason": "Both involve apply_chat_template, but one is batched padding behavior and the other is tool-call assistant message handling." + }, + { + "left": "issue:45405", + "right": "issue:45600", + "accept": false, + "reason": "Unreleased PEFT minimum version and removed Sam3LiteText config references are unrelated CI/versioning issues." + }, + { + "left": "issue:43688", + "right": "issue:43749", + "accept": false, + "reason": "Auxiliary-loss normalization in MoE models is unrelated to broken FSDP CPU RAM-efficient loading." + }, + { + "left": "issue:43643", + "right": "issue:44561", + "accept": false, + "reason": "Missing fields from trust_remote_code AutoConfig and removal of is_torch_fx_available are different regressions." + }, + { + "left": "issue:44514", + "right": "issue:45381", + "accept": false, + "reason": "Different Qwen2.5-VL bugs: chat templating on batches vs wrong video vision_position_ids." + }, + { + "left": "issue:43452", + "right": "issue:43577", + "accept": false, + "reason": "gguf_file loading breakage is unrelated to BLIP2 dtype propagation staying float32." + }, + { + "left": "issue:43697", + "right": "issue:45216", + "accept": false, + "reason": "RTDetrV2 output divergence and Qwen3.5 save_pretrained checkpoint correctness are different problems." + }, + { + "left": "issue:43742", + "right": "issue:44589", + "accept": false, + "reason": "MobileLLM key error and missing Float8 storage type are separate loading/storage issues." + }, + { + "left": "issue:45042", + "right": "issue:45081", + "accept": false, + "reason": "PIL/torchvision dependency regression is not the same as the Mistral regex tokenizer crash." + }, + { + "left": "issue:43531", + "right": "issue:44821", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior and AutoImageProcessor URL loading are unrelated." + }, + { + "left": "issue:43688", + "right": "issue:45440", + "accept": false, + "reason": "Both are MoE-related, but auxiliary-loss normalization and DeepSeekV3 implementation divergence are different bugs." + }, + { + "left": "issue:43452", + "right": "issue:44843", + "accept": false, + "reason": "gguf_file loading failure is unrelated to model_info being called in offline mode." + }, + { + "left": "issue:44625", + "right": "issue:44877", + "accept": false, + "reason": "num_labels propagation and strict granite_speech config loading are separate config issues." + }, + { + "left": "issue:43653", + "right": "issue:44568", + "accept": false, + "reason": "BigBird mask-token special registration and mdeberta BOS/EOS insertion are different tokenizer bugs." + }, + { + "left": "issue:43720", + "right": "issue:44898", + "accept": false, + "reason": "BitNet packed-weight loading and Perceiver non-default resolution handling are unrelated." + }, + { + "left": "issue:43819", + "right": "issue:44811", + "accept": false, + "reason": "DAC latent reconstruction mismatch and Whisper batch_decode skip_special_tokens behavior are different code paths." + }, + { + "left": "issue:41762", + "right": "issue:44936", + "accept": false, + "reason": "Gemma3 ZeRO-3 load failure and trainer.evaluate after train are not the same issue." + }, + { + "left": "issue:43295", + "right": "issue:45356", + "accept": false, + "reason": "Custom processor/tokenizer regression and Kimi-K2.5 codec/fix_mistral_regex regression are different tokenizer issues." + }, + { + "left": "issue:44466", + "right": "issue:45005", + "accept": true, + "reason": "Both describe the same v5 tied-weights/save_pretrained serialization regression; 45005 is the broader translation-model manifestation and 44466 is a device-dependent symptom." + }, + { + "left": "issue:44464", + "right": "issue:44743", + "accept": false, + "reason": "Chunked generation with compiled forward and Qwen3.5 recurrent state reset are distinct generation/runtime bugs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet and stays mostly conservative. The soft-edge verdicts generally separate clearly different issue titles/code paths, and the lone accepted pair is a plausible duplicate based on the shared tied-weights/v5 serialization theme. No obvious overstatement beyond the evidence in the titles." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 17, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:24643", + "issue:28282", + "issue:29127", + "issue:30064", + "issue:32090", + "issue:33357", + "issue:33666", + "issue:34567", + "issue:35141", + "issue:38175", + "issue:41720", + "issue:43122", + "issue:43262", + "issue:43278", + "issue:43295", + "issue:43329", + "issue:43452", + "issue:43504", + "issue:43525", + "issue:43531", + "issue:43550", + "issue:43577", + "issue:43643", + "issue:43653", + "issue:43688", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43906", + "issue:43927", + "issue:44361", + "issue:44442", + "issue:44451", + "issue:44464", + "issue:44479", + "issue:44554", + "issue:44610", + "issue:44625", + "issue:44843", + "issue:44849", + "issue:44936", + "issue:44977", + "issue:44991", + "issue:45084", + "issue:45325", + "issue:45356", + "issue:45357", + "issue:45588" + ], + "soft_pairs": [ + "issue:41720|issue:43906", + "issue:24643|issue:29127", + "issue:43525|issue:43643", + "issue:43577|issue:43697", + "issue:38175|issue:43295", + "issue:44361|issue:44442", + "issue:44843|issue:44991", + "issue:43653|issue:44361", + "issue:44479|issue:44936", + "issue:43122|issue:43906", + "issue:44977|issue:45356", + "issue:28282|issue:32090", + "issue:28282|issue:33357", + "issue:28282|issue:35141", + "issue:43577|issue:45588", + "issue:30064|issue:33666", + "issue:43577|issue:44554", + "issue:44464|issue:44977", + "issue:43653|issue:43927", + "issue:43531|issue:43742", + "issue:43329|issue:45325", + "issue:44479|issue:44625", + "issue:43550|issue:44361", + "issue:41720|issue:44464", + "issue:43452|issue:44451", + "issue:43504|issue:43720", + "issue:43504|issue:43550", + "issue:44849|issue:45357", + "issue:43262|issue:45084", + "issue:32090|issue:34567", + "issue:32090|issue:33666", + "issue:43504|issue:44610", + "issue:43278|issue:43688" + ], + "prepared_review_unit_hash": "c7aadc8dc6bb4a8d4f8e3ad1b7007cb8775c8bdd11fefbdfe90ec8604c976f36", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37812, + "estimated_input_tokens": 9453, + "estimated_eval_tokens": 19162 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a heterogeneous mix of unrelated Transformers issues: model loading, tokenizers, multimodal processors, training/TrainerState, dtype drift, and a few Qwen/BLIP/BEiT-specific regressions. The soft edges are mostly superficial text similarity, not true duplicates.", + "confidence": 0.96, + "canonical_issue_reason": "Issue 43504 is the closest thing to a hub because it is a concrete model-loading failure and sits near several other load-time regressions by wording, but the cluster is still too mixed to have a real duplicate canonical issue.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43504 is the least bad representative of the cluster\u2019s broad loading-regression theme, but it is not a safe global canonical because the linked issues span different models and code paths.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41720", + "right": "issue:43906", + "accept": false, + "reason": "Different bugs: Qwen3 auto device mapping CUDA assert vs an isolated reproduction of another issue." + }, + { + "left": "issue:24643", + "right": "issue:29127", + "accept": false, + "reason": "Unrelated symptoms and code paths: DeepSpeed weight shape error vs LayoutLMv3 box validation/message clarity." + }, + { + "left": "issue:43525", + "right": "issue:43643", + "accept": false, + "reason": "Both are config-related, but one is a missing pad_token_id on Llama4 and the other is trust_remote_code dropping fields; not the same bug." + }, + { + "left": "issue:43577", + "right": "issue:43697", + "accept": false, + "reason": "Different models and failures: BLIP2 dtype preservation vs RTDetrV2 output drift." + }, + { + "left": "issue:38175", + "right": "issue:43295", + "accept": false, + "reason": "SigLIP2 zero-probability issue and processor.tokenizer/images regression are different problems." + }, + { + "left": "issue:44361", + "right": "issue:44442", + "accept": false, + "reason": "Different tokenizer failures: MLukeTokenizer task error vs FastSpeech2ConformerTokenizer load failure." + }, + { + "left": "issue:44843", + "right": "issue:44991", + "accept": false, + "reason": "Offline model_info() call in tokenizer patch vs EMBEDDIA/est-roberta loading regression; different causes." + }, + { + "left": "issue:43653", + "right": "issue:44361", + "accept": false, + "reason": "BigBird special-token decode bug is not the same as MLukeTokenizer task AttributeError." + }, + { + "left": "issue:44479", + "right": "issue:44936", + "accept": false, + "reason": "Qwen video-input regression vs trainer.evaluate() failing after train(); unrelated." + }, + { + "left": "issue:43122", + "right": "issue:43906", + "accept": false, + "reason": "Version-to-version tokenization change is not the same as the isolated reproduction of another bug." + }, + { + "left": "issue:44977", + "right": "issue:45356", + "accept": false, + "reason": "Different surfaces: flash-attention generation failure in Qwen3.5 vs tokenizer codec handling regression in Kimi-K2.5." + }, + { + "left": "issue:28282", + "right": "issue:32090", + "accept": false, + "reason": "Missing PyTorch import error vs NoneType passed to _gpu_broadcast_one; unrelated." + }, + { + "left": "issue:28282", + "right": "issue:33357", + "accept": false, + "reason": "Environment import failure vs MacOS bus error in CLIP model loading; not the same issue." + }, + { + "left": "issue:28282", + "right": "issue:35141", + "accept": false, + "reason": "No shared bug path: PyTorch missing import vs embedding reinitialization after resize." + }, + { + "left": "issue:43577", + "right": "issue:45588", + "accept": false, + "reason": "BLIP2 dtype mismatch and flash_attention.py crashing on s_aux=None are different code paths." + }, + { + "left": "issue:30064", + "right": "issue:33666", + "accept": false, + "reason": "Void segmentation-map processing and Qwen2-VL multi-GPU training are unrelated." + }, + { + "left": "issue:43577", + "right": "issue:44554", + "accept": false, + "reason": "BLIP2 dtype bug is not the same as the MPS attention correctness issue." + }, + { + "left": "issue:44464", + "right": "issue:44977", + "accept": false, + "reason": "Chunked generation compiled-forward inconsistency vs Qwen3.5 flash-attention generation failure; different bugs." + }, + { + "left": "issue:43653", + "right": "issue:43927", + "accept": false, + "reason": "BigBird mask-token registration issue and DiaConfig custom-token-ID loss are different tokenizer/config bugs." + }, + { + "left": "issue:43531", + "right": "issue:43742", + "accept": false, + "reason": "Qwen3-MoE sliding_window bug vs MobileLLM loading key error; unrelated." + }, + { + "left": "issue:43329", + "right": "issue:45325", + "accept": false, + "reason": "Both touch multimodal/video logic, but one is undefined helpers in token counting and the other is rope-index scaling for still images." + }, + { + "left": "issue:44479", + "right": "issue:44625", + "accept": false, + "reason": "Video-input regression vs num_labels propagation bug; different model parts." + }, + { + "left": "issue:43550", + "right": "issue:44361", + "accept": false, + "reason": "torch.compile/SDPA failure in Bamba is unrelated to MLukeTokenizer AttributeError." + }, + { + "left": "issue:41720", + "right": "issue:44464", + "accept": false, + "reason": "CUDA assert in Qwen3 auto device mapping and chunked generation inconsistency are separate failures." + }, + { + "left": "issue:43452", + "right": "issue:44451", + "accept": false, + "reason": "gguf_file breaks tokenizer/model loading APIs, but ScandiBERT load failure is a different model-specific issue." + }, + { + "left": "issue:43504", + "right": "issue:43720", + "accept": false, + "reason": "BEiT legacy-field load bug and BitNet packed-weight unpacking bug are both loading-related but not the same code path." + }, + { + "left": "issue:43504", + "right": "issue:43550", + "accept": false, + "reason": "BEiT pretrained-load legacy field issue vs Bamba torch.compile SDPA bug; unrelated." + }, + { + "left": "issue:44849", + "right": "issue:45357", + "accept": false, + "reason": "Qwen3.5 output_hidden_states bug and save_pretrained visual-key regression are different regressions." + }, + { + "left": "issue:43262", + "right": "issue:45084", + "accept": false, + "reason": "Audio processor sampling-rate default bug vs chat template compilation error; different subsystems." + }, + { + "left": "issue:32090", + "right": "issue:34567", + "accept": false, + "reason": "NoneType broadcast error in trainer vs TrainerState num_input_tokens_seen not updating; unrelated." + }, + { + "left": "issue:32090", + "right": "issue:33666", + "accept": false, + "reason": "Trainer broadcast failure and Qwen2-VL multi-GPU training issue are not the same bug." + }, + { + "left": "issue:43504", + "right": "issue:44610", + "accept": false, + "reason": "BEiT legacy-field loading issue vs OmDet-Turbo processor/model input-size mismatch; different failures." + }, + { + "left": "issue:43278", + "right": "issue:43688", + "accept": false, + "reason": "Embedding dtype drift during eval vs auxiliary-loss normalization bug; unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 18, + "review_unit_count": 43, + "status": "error", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:33357", + "issue:33666", + "issue:36010", + "issue:36331", + "issue:39692", + "issue:43257", + "issue:43278", + "issue:43295", + "issue:43299", + "issue:43334", + "issue:43493", + "issue:43525", + "issue:43540", + "issue:43572", + "issue:43606", + "issue:43646", + "issue:43688", + "issue:43716", + "issue:43720", + "issue:43742", + "issue:43746", + "issue:43756", + "issue:43824", + "issue:43825", + "issue:43844", + "issue:43873", + "issue:43927", + "issue:44060", + "issue:44291", + "issue:44361", + "issue:44423", + "issue:44466", + "issue:44488", + "issue:44521", + "issue:44589", + "issue:44625", + "issue:44734", + "issue:44821", + "issue:44843", + "issue:44913", + "issue:44964", + "issue:44977", + "issue:45200", + "issue:45229", + "issue:45290", + "issue:45405", + "issue:45520", + "issue:45584" + ], + "soft_pairs": [ + "issue:43334|issue:43572", + "issue:43756|issue:44913", + "issue:43540|issue:43716", + "issue:43525|issue:43572", + "issue:43493|issue:43825", + "issue:43742|issue:44821", + "issue:45200|issue:45229", + "issue:33666|issue:36010", + "issue:43688|issue:43873", + "issue:43720|issue:43927", + "issue:43606|issue:43927", + "issue:43257|issue:43299", + "issue:43278|issue:43844", + "issue:43540|issue:44977", + "issue:44488|issue:44843", + "issue:43720|issue:44361", + "issue:39692|issue:43493", + "issue:44964|issue:45405", + "issue:43493|issue:43844", + "issue:33666|issue:36331", + "issue:43756|issue:44060", + "issue:44589|issue:45520", + "issue:44625|issue:45584", + "issue:44521|issue:45290", + "issue:43646|issue:44466", + "issue:44423|issue:44734", + "issue:43824|issue:44589", + "issue:43688|issue:43746", + "issue:39692|issue:43295", + "issue:33357|issue:33666", + "issue:43572|issue:44291" + ], + "prepared_review_unit_hash": "e265358a354d294653517b540cb753ff3377f748df229c2bcc92d3579e5bc800", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37175, + "estimated_input_tokens": 9294, + "estimated_eval_tokens": 18844 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": null, + "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": 13, + "review_unit_index": 19, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:15354", + "issue:29942", + "issue:30333", + "issue:37428", + "issue:38175", + "issue:39401", + "issue:43232", + "issue:43278", + "issue:43295", + "issue:43334", + "issue:43504", + "issue:43525", + "issue:43540", + "issue:43575", + "issue:43582", + "issue:43606", + "issue:43653", + "issue:43701", + "issue:43844", + "issue:43927", + "issue:43957", + "issue:43994", + "issue:44112", + "issue:44315", + "issue:44361", + "issue:44464", + "issue:44466", + "issue:44493", + "issue:44554", + "issue:44568", + "issue:44610", + "issue:44792", + "issue:44849", + "issue:44898", + "issue:44964", + "issue:44977", + "issue:45072", + "issue:45084", + "issue:45127", + "issue:45198", + "issue:45200", + "issue:45325", + "issue:45356", + "issue:45405", + "issue:45412", + "issue:45446", + "issue:45520", + "issue:45584" + ], + "soft_pairs": [ + "issue:43994|issue:44493", + "issue:43504|issue:43606", + "issue:44464|issue:45584", + "issue:43504|issue:43653", + "issue:43927|issue:44361", + "issue:43575|issue:45405", + "issue:43278|issue:43701", + "issue:44792|issue:45405", + "issue:29942|issue:30333", + "issue:43606|issue:44112", + "issue:15354|issue:38175", + "issue:44554|issue:45446", + "issue:43540|issue:45200", + "issue:45084|issue:45520", + "issue:43232|issue:44849", + "issue:43844|issue:44964", + "issue:39401|issue:44568", + "issue:43582|issue:44977", + "issue:45072|issue:45198", + "issue:44315|issue:44849", + "issue:37428|issue:43957", + "issue:44554|issue:45356", + "issue:43334|issue:43525", + "issue:43295|issue:44610", + "issue:45200|issue:45325", + "issue:44466|issue:45127", + "issue:44898|issue:45412" + ], + "prepared_review_unit_hash": "4ceb043023b5768f38f363880e5d1d6f174d9929acc5d68404d323b678a6fce8", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "serialized_chars": 35999, + "estimated_input_tokens": 9000, + "estimated_eval_tokens": 18256 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: the items span unrelated bugs in tokenizers, generation, model loading, dtype/device behavior, CI, and versioning. The soft links are mostly superficial keyword overlap, so none of the candidate pairs look like true duplicates.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "No single issue is a safe global representative; the cluster mixes unrelated failure modes across different models and subsystems, so there is no clear canonical issue to anchor on.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43994", + "right": "issue:44493", + "accept": false, + "reason": "Different bugs: SigLIP2 bad outputs vs a position-id warning affecting many models; not the same failing code path." + }, + { + "left": "issue:43504", + "right": "issue:43606", + "accept": false, + "reason": "Legacy-field model loading bug vs CPU offload device mismatch; unrelated symptoms and fixes." + }, + { + "left": "issue:44464", + "right": "issue:45584", + "accept": false, + "reason": "Compiled-forward chunked generation issue vs empty-transcription token alignment bug; distinct generation paths." + }, + { + "left": "issue:43504", + "right": "issue:43653", + "accept": false, + "reason": "Pretrained model preset loading vs BigBirdTokenizer special-token decode behavior; different subsystems." + }, + { + "left": "issue:43927", + "right": "issue:44361", + "accept": false, + "reason": "Save/load custom token IDs causing IndexError vs tokenizer AttributeError on tasks; not the same bug." + }, + { + "left": "issue:43575", + "right": "issue:45405", + "accept": false, + "reason": "TP-related OOM vs a release/version-constant problem; no shared underlying change." + }, + { + "left": "issue:43278", + "right": "issue:43701", + "accept": false, + "reason": "BF16-to-FP32 eval dtype drift vs resume checkpoint key mismatch; unrelated failure modes." + }, + { + "left": "issue:44792", + "right": "issue:45405", + "accept": false, + "reason": "Janus image-generation test failure vs PEFT minimum-version bump; no common code path." + }, + { + "left": "issue:29942", + "right": "issue:30333", + "accept": false, + "reason": "Flash Attention 2 test failures vs MLFlow reporting after failed training; unrelated concerns." + }, + { + "left": "issue:43606", + "right": "issue:44112", + "accept": false, + "reason": "Both mention devices, but one is a real CPU-offload mismatch and the other is a stale CI test; not the same bug." + }, + { + "left": "issue:15354", + "right": "issue:38175", + "accept": false, + "reason": "TorchScript GeneratorExp limitation vs zero probabilities in SigLIP2; completely different issues." + }, + { + "left": "issue:44554", + "right": "issue:45446", + "accept": false, + "reason": "MPS attention correctness on mismatched heads vs flex_attention import version check; different code paths." + }, + { + "left": "issue:43540", + "right": "issue:45200", + "accept": false, + "reason": "Qwen3OmniMoe video-input processing vs Gemma 4 mm_token_type_ids handling; both multimodal, but not the same defect." + }, + { + "left": "issue:45084", + "right": "issue:45520", + "accept": false, + "reason": "Compiler template-node error vs flash_attn import failure on Python 3.13; unrelated." + }, + { + "left": "issue:43232", + "right": "issue:44849", + "accept": false, + "reason": "Generation kwargs update after sync_gpus vs Qwen3.5 hidden-states bug; same broad area, different bug." + }, + { + "left": "issue:43844", + "right": "issue:44964", + "accept": false, + "reason": "ZeRO-3 gradient inflation vs Phi-4 multimodal loading failure; no shared underlying problem." + }, + { + "left": "issue:39401", + "right": "issue:44568", + "accept": false, + "reason": "Qwen3 offset_mapping regression vs mdeberta special-token insertion; both tokenizer bugs, but distinct." + }, + { + "left": "issue:43582", + "right": "issue:44977", + "accept": false, + "reason": "Apple Silicon allocator TypeError vs Qwen3.5 flash-attention generation bug; unrelated." + }, + { + "left": "issue:45072", + "right": "issue:45198", + "accept": false, + "reason": "bfloat16 dtype mismatches in inference vs Wav2Vec2 save/tokenization failure; different subsystems." + }, + { + "left": "issue:44315", + "right": "issue:44849", + "accept": false, + "reason": "Liger Kernel not applied with model_init vs Qwen3.5 hidden-states issue; not the same fix." + }, + { + "left": "issue:37428", + "right": "issue:43957", + "accept": false, + "reason": "Flash-support import failure vs meta-device model loading breakage; separate problems." + }, + { + "left": "issue:44554", + "right": "issue:45356", + "accept": false, + "reason": "MPS attention correctness vs Kimi-K2.5 tokenizer codec regression; unrelated." + }, + { + "left": "issue:43334", + "right": "issue:43525", + "accept": false, + "reason": "Both mention missing pad_token_id, but they affect different model/config classes and load paths." + }, + { + "left": "issue:43295", + "right": "issue:44610", + "accept": false, + "reason": "Processor.tokenizer regression vs OmDet-Turbo input-size mismatch; different processor/model contracts." + }, + { + "left": "issue:45200", + "right": "issue:45325", + "accept": false, + "reason": "Gemma 4 token-type handling vs Qwen2.5-VL rope-index scaling; distinct multimodal bugs." + }, + { + "left": "issue:44466", + "right": "issue:45127", + "accept": false, + "reason": "lm_head.weight serialization inconsistency vs LoRA merge collapse with extended vocab; related theme but different concrete failures." + }, + { + "left": "issue:44898", + "right": "issue:45412", + "accept": false, + "reason": "Perceiver resize/interpolate failure vs RT-DETR memory leak on deletion; no common underlying issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 20, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:37428", + "issue:38175", + "issue:42915", + "issue:43122", + "issue:43278", + "issue:43295", + "issue:43388", + "issue:43450", + "issue:43493", + "issue:43526", + "issue:43572", + "issue:43653", + "issue:43701", + "issue:43819", + "issue:43824", + "issue:43827", + "issue:43844", + "issue:43856", + "issue:43873", + "issue:43901", + "issue:43975", + "issue:43994", + "issue:44112", + "issue:44206", + "issue:44360", + "issue:44442", + "issue:44462", + "issue:44464", + "issue:44514", + "issue:44521", + "issue:44561", + "issue:44568", + "issue:44589", + "issue:44779", + "issue:44792", + "issue:44849", + "issue:44936", + "issue:44987", + "issue:44991", + "issue:45083", + "issue:45127", + "issue:45198", + "issue:45245", + "issue:45290", + "issue:45381", + "issue:45412", + "issue:45563", + "issue:45584" + ], + "soft_pairs": [ + "issue:43493|issue:43701", + "issue:43873|issue:44464", + "issue:44792|issue:45563", + "issue:44514|issue:44521", + "issue:37428|issue:43824", + "issue:43388|issue:43526", + "issue:43572|issue:44987", + "issue:43844|issue:44936", + "issue:43572|issue:44589", + "issue:43824|issue:43975", + "issue:43295|issue:43450", + "issue:43295|issue:43873", + "issue:44360|issue:44561", + "issue:38175|issue:45412", + "issue:44442|issue:45198", + "issue:43295|issue:43994", + "issue:43122|issue:44849", + "issue:44206|issue:45584", + "issue:42915|issue:43824", + "issue:43278|issue:43856", + "issue:38175|issue:43493", + "issue:43827|issue:43901", + "issue:44568|issue:44991", + "issue:43653|issue:44112", + "issue:43450|issue:43493", + "issue:45290|issue:45381", + "issue:45127|issue:45245", + "issue:43819|issue:45083", + "issue:44462|issue:44561", + "issue:44561|issue:44779" + ], + "prepared_review_unit_hash": "2e2c5cadd241920eda5e9d6ea375f9ab1e604685fa0abc24204edfc0d42d2627", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36650, + "estimated_input_tokens": 9163, + "estimated_eval_tokens": 18582 + }, + "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 regressions/docs issues. The closest overlap is around multimodal chat-template handling, but none of the soft pairs are strong enough to treat as duplicates.", + "confidence": 0.66, + "canonical_issue_reason": "issue:44521 is the most active, well-referenced open issue and the best umbrella candidate among the multimodal/chat-template regressions here, though the overall cluster is heterogeneous.", + "canonical_pr_reason": null, + "best_issue_reason": "If a single issue must anchor the set, issue:44521 is the strongest choice because it has the most ongoing discussion and inbound references while describing a concrete, user-facing bug.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43493", + "right": "issue:43701", + "accept": false, + "reason": "Different bugs: SigLIP2 model discrepancy vs checkpoint resume key mismatch." + }, + { + "left": "issue:43873", + "right": "issue:44464", + "accept": false, + "reason": "Unrelated areas: quantization/offloading vs chunked generation with compiled forward." + }, + { + "left": "issue:44792", + "right": "issue:45563", + "accept": false, + "reason": "Different failures: janus image-generation test vs stale generation warning." + }, + { + "left": "issue:44514", + "right": "issue:44521", + "accept": false, + "reason": "Same API family, but different concrete defects: batched padding crash vs zero assistant masks in multimodal inputs." + }, + { + "left": "issue:37428", + "right": "issue:43824", + "accept": false, + "reason": "Both are ImportErrors, but they involve different missing symbols and different model families." + }, + { + "left": "issue:43388", + "right": "issue:43526", + "accept": false, + "reason": "Both involve labels, but one drops tuple elements in gather_for_metrics and the other collapses labels in a fast image processor." + }, + { + "left": "issue:43572", + "right": "issue:44987", + "accept": false, + "reason": "Different problems: missing StableLmConfig field vs model loading failure for a specific checkpoint." + }, + { + "left": "issue:43844", + "right": "issue:44936", + "accept": false, + "reason": "Training instability with ZeRO-3 is unrelated to trainer.evaluate() failing after train()." + }, + { + "left": "issue:43572", + "right": "issue:44589", + "accept": false, + "reason": "No overlap: config field regression vs Float8 storage lookup error." + }, + { + "left": "issue:43824", + "right": "issue:43975", + "accept": false, + "reason": "ImportError for a missing class is not the same as DeepSeek detokenization corruption." + }, + { + "left": "issue:43295", + "right": "issue:43450", + "accept": false, + "reason": "Processor/tokenizer regression and batched video shape bug are different code paths and symptoms." + }, + { + "left": "issue:43295", + "right": "issue:43873", + "accept": false, + "reason": "Custom processor regression is unrelated to quantization/offloading behavior." + }, + { + "left": "issue:44360", + "right": "issue:44561", + "accept": false, + "reason": "DSA indexer ReLU discussion is unrelated to removing is_torch_fx_available." + }, + { + "left": "issue:38175", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 zero-probabilities bug is unrelated to RT-DETR memory release." + }, + { + "left": "issue:44442", + "right": "issue:45198", + "accept": false, + "reason": "Different tokenizer/model-loading failures in different architectures." + }, + { + "left": "issue:43295", + "right": "issue:43994", + "accept": false, + "reason": "Processor/tokenizer regression and SigLIP2 inference nonsense are not the same bug." + }, + { + "left": "issue:43122", + "right": "issue:44849", + "accept": false, + "reason": "Tokenization drift across versions is unrelated to Qwen3.5 hidden-state output behavior." + }, + { + "left": "issue:44206", + "right": "issue:45584", + "accept": false, + "reason": "Feature-extractor center-arg crash and Whisper empty-transcription failure are different issues." + }, + { + "left": "issue:42915", + "right": "issue:43824", + "accept": false, + "reason": "Qwen3Moe FP8 config failure and Qwen2.5-VL import error are unrelated." + }, + { + "left": "issue:43278", + "right": "issue:43856", + "accept": false, + "reason": "Embedding dtype mismatch and MoE memory usage are different training issues." + }, + { + "left": "issue:38175", + "right": "issue:43493", + "accept": false, + "reason": "Same general SigLIP2 area, but one is zero probabilities and the other is HF-vs-JAX discrepancy." + }, + { + "left": "issue:43827", + "right": "issue:43901", + "accept": false, + "reason": "Both are docs issues, but they refer to different pages and different deprecated pipeline APIs." + }, + { + "left": "issue:44568", + "right": "issue:44991", + "accept": false, + "reason": "Different tokenizer regressions affecting different models and failure modes." + }, + { + "left": "issue:43653", + "right": "issue:44112", + "accept": false, + "reason": "Tokenizer special-token bug and GraniteSpeech CI test flake are unrelated." + }, + { + "left": "issue:43450", + "right": "issue:43493", + "accept": false, + "reason": "Video batching shape bug and SigLIP2 implementation discrepancy do not share the same code path." + }, + { + "left": "issue:45290", + "right": "issue:45381", + "accept": false, + "reason": "Assistant-message/tool-call chat-template crash is not the same as Qwen2.5-VL video position-id issue." + }, + { + "left": "issue:45127", + "right": "issue:45245", + "accept": false, + "reason": "LoRA/tied-embedding collapse and category-cardinality RuntimeError are unrelated." + }, + { + "left": "issue:43819", + "right": "issue:45083", + "accept": false, + "reason": "DAC latent decoding mismatch and qwen3_omni_moe feature-length helper behavior are different bugs." + }, + { + "left": "issue:44462", + "right": "issue:44561", + "accept": false, + "reason": "Tokenizer JSON loading and removal of is_torch_fx_available affect different layers of the stack." + }, + { + "left": "issue:44561", + "right": "issue:44779", + "accept": false, + "reason": "Remote-code compatibility break and DeepSeek detokenization regression are different issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 21, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:29127", + "issue:29942", + "issue:32090", + "issue:37428", + "issue:38175", + "issue:39692", + "issue:40444", + "issue:43262", + "issue:43278", + "issue:43335", + "issue:43425", + "issue:43450", + "issue:43504", + "issue:43526", + "issue:43550", + "issue:43575", + "issue:43606", + "issue:43611", + "issue:43653", + "issue:43720", + "issue:43723", + "issue:43819", + "issue:43825", + "issue:43931", + "issue:44112", + "issue:44292", + "issue:44351", + "issue:44448", + "issue:44493", + "issue:44554", + "issue:44568", + "issue:44610", + "issue:44743", + "issue:44779", + "issue:44855", + "issue:44857", + "issue:44977", + "issue:45072", + "issue:45083", + "issue:45200", + "issue:45229", + "issue:45310", + "issue:45381", + "issue:45478", + "issue:45491", + "issue:45520", + "issue:45588", + "issue:45593" + ], + "soft_pairs": [ + "issue:45200|issue:45588", + "issue:43450|issue:43575", + "issue:44610|issue:44857", + "issue:44857|issue:45593", + "issue:37428|issue:43425", + "issue:43262|issue:43450", + "issue:43819|issue:44112", + "issue:44448|issue:44743", + "issue:45310|issue:45478", + "issue:43606|issue:45083", + "issue:43278|issue:43825", + "issue:29942|issue:32090", + "issue:37428|issue:44351", + "issue:39692|issue:43526", + "issue:43611|issue:43931", + "issue:43819|issue:44493", + "issue:43335|issue:43550", + "issue:45200|issue:45381", + "issue:43450|issue:43526", + "issue:39692|issue:44493", + "issue:44855|issue:45083", + "issue:29127|issue:32090", + "issue:44448|issue:44779", + "issue:38175|issue:44493", + "issue:43335|issue:43653", + "issue:44292|issue:45520", + "issue:44977|issue:45229", + "issue:43335|issue:45083", + "issue:43335|issue:43504", + "issue:43550|issue:44112", + "issue:44568|issue:45491", + "issue:43335|issue:45072", + "issue:43723|issue:44554", + "issue:40444|issue:43526", + "issue:44448|issue:44977", + "issue:43335|issue:45593", + "issue:43720|issue:44112" + ], + "prepared_review_unit_hash": "7d408e6d01071dc1cada7bdb13614bae5b33d50bcab3099ae5721b76b010fae6", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 37, + "serialized_chars": 38895, + "estimated_input_tokens": 9724, + "estimated_eval_tokens": 19704 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a set of unrelated transformer bug reports. The only clear duplicate pair is the repeated Qwen3.5 MoE `from_pretrained` error; the rest are similar only at a broad subsystem level and should stay separate.", + "confidence": 0.98, + "canonical_issue_reason": "issue:45310 is the earlier report with the same title and the same Qwen3.5 MoE `from_pretrained` failure; it is the better canonical target for the duplicate pair with issue:45478.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45310 is the clearest representative issue in the cluster because it is a precise, reproducible bug report and has a direct duplicate.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45200", + "right": "issue:45588", + "accept": false, + "reason": "Both involve model/integration behavior, but one is Gemma 4 multimodal token ids and the other is a flash-attention sink-less crash; different code paths and bugs." + }, + { + "left": "issue:43450", + "right": "issue:43575", + "accept": false, + "reason": "Video processor shape handling and Qwen2.5-VL tensor-parallel OOM are unrelated failures." + }, + { + "left": "issue:44610", + "right": "issue:44857", + "accept": false, + "reason": "Processor input-size mismatch and AMP/CUDA loss crash are different bugs in different components." + }, + { + "left": "issue:44857", + "right": "issue:45593", + "accept": false, + "reason": "Both are training-time issues, but one is a float16/CUDA crash and the other is missing auxiliary losses; not the same defect." + }, + { + "left": "issue:37428", + "right": "issue:43425", + "accept": false, + "reason": "An import error for a missing flash-attention symbol and a Torch 2.10 incompatibility are separate compatibility problems." + }, + { + "left": "issue:43262", + "right": "issue:43450", + "accept": false, + "reason": "Audio chat-template sampling rate default and batched video processor shape are unrelated multimodal bugs." + }, + { + "left": "issue:43819", + "right": "issue:44112", + "accept": false, + "reason": "DAC forward/from_latents mismatch and GraniteSpeech stale device-override CI failure are different issues." + }, + { + "left": "issue:44448", + "right": "issue:44743", + "accept": false, + "reason": "Pegasus v4/v5 output differences and Qwen3.5 recurrent-state reset are different model behaviors and code paths." + }, + { + "left": "issue:45310", + "right": "issue:45478", + "accept": true, + "reason": "Exact same Qwen3.5 MoE `from_pretrained` error title and same underlying loading bug; clearly duplicates." + }, + { + "left": "issue:43606", + "right": "issue:45083", + "accept": false, + "reason": "CPU offload device mismatch for bark-small and `_get_feat_extract_output_lengths` behavior in qwen3_omni_moe are unrelated." + }, + { + "left": "issue:43278", + "right": "issue:43825", + "accept": false, + "reason": "BF16/FP32 embedding dtype drift and pipeline translation-task messaging are different concerns." + }, + { + "left": "issue:29942", + "right": "issue:32090", + "accept": false, + "reason": "Flash Attention 2 test failures and `_gpu_broadcast_one` rejecting NoneType are distinct failures." + }, + { + "left": "issue:37428", + "right": "issue:44351", + "accept": false, + "reason": "Missing `_flash_supports_window_size` and missing `HybridCache` imports are both import errors but for different symbols and fixes." + }, + { + "left": "issue:39692", + "right": "issue:43526", + "accept": false, + "reason": "SigLIP2 doc example issues and BeitImageProcessorFast `reduce_labels` behavior are unrelated." + }, + { + "left": "issue:43611", + "right": "issue:43931", + "accept": false, + "reason": "`base_model_prefix` loading breakage and Qwen3-VL weight-shape mismatch are different model-loading problems." + }, + { + "left": "issue:43819", + "right": "issue:44493", + "accept": false, + "reason": "DAC latent conversion mismatch and unexpected position-id keys are unrelated bugs." + }, + { + "left": "issue:43335", + "right": "issue:43550", + "accept": false, + "reason": "SwitchTransformers sparse-layer config and Bamba torch.compile/SDPA failure are different model-specific problems." + }, + { + "left": "issue:45200", + "right": "issue:45381", + "accept": false, + "reason": "Gemma 4 text-only fine-tuning defaults and Qwen2.5-VL video position ids are different multimodal issues." + }, + { + "left": "issue:43450", + "right": "issue:43526", + "accept": false, + "reason": "Both touch Beit-related processors, but one is batched video shape handling and the other is image-label reduction; not the same bug." + }, + { + "left": "issue:39692", + "right": "issue:44493", + "accept": false, + "reason": "Documentation example errors and position-id warnings in many models are not the same underlying defect." + }, + { + "left": "issue:44855", + "right": "issue:45083", + "accept": false, + "reason": "Python 3.13 `IndentationError` in DebertaV2 import and qwen3_omni_moe feature-length helper behavior are unrelated." + }, + { + "left": "issue:29127", + "right": "issue:32090", + "accept": false, + "reason": "LayoutLMv3 box-clarity error messaging and trainer broadcast NoneType are unrelated failures." + }, + { + "left": "issue:44448", + "right": "issue:44779", + "accept": false, + "reason": "Pegasus output differences and DeepSeek tokenizer regressions are separate model/tokenizer issues." + }, + { + "left": "issue:38175", + "right": "issue:44493", + "accept": false, + "reason": "SigLIP2 zero probabilities and position-id key warnings are not the same bug." + }, + { + "left": "issue:43335", + "right": "issue:43653", + "accept": false, + "reason": "SwitchTransformers sparse-layer config and BigBirdTokenizer special-token decode issue are unrelated." + }, + { + "left": "issue:44292", + "right": "issue:45520", + "accept": false, + "reason": "Qwen-3-8B-NVFP4 runtime error and Python 3.13 flash_attn import KeyError are different failures." + }, + { + "left": "issue:44977", + "right": "issue:45229", + "accept": false, + "reason": "Qwen3.5 flash-attention generation bug and Gemma4 multi-GPU CUDA OOM are unrelated." + }, + { + "left": "issue:43335", + "right": "issue:45083", + "accept": false, + "reason": "SwitchTransformers config bug and qwen3_omni_moe feature-length helper behavior are unrelated." + }, + { + "left": "issue:43335", + "right": "issue:43504", + "accept": false, + "reason": "SwitchTransformers sparse-layer creation and Beit semantic-segmentation legacy-field loading are different issues." + }, + { + "left": "issue:43550", + "right": "issue:44112", + "accept": false, + "reason": "Bamba SDPA/torch.compile failure and GraniteSpeech CI device override failure are unrelated." + }, + { + "left": "issue:44568", + "right": "issue:45491", + "accept": false, + "reason": "mDeBERTa special-token addition regression and Gemma3 NaN embeddings are different tokenizer/model problems." + }, + { + "left": "issue:43335", + "right": "issue:45072", + "accept": false, + "reason": "SwitchTransformers config bug and bfloat16 dtype mismatches in inference are not the same underlying issue." + }, + { + "left": "issue:43723", + "right": "issue:44554", + "accept": false, + "reason": "AutoTokenizer loading regression and MPS attention correctness issue are unrelated." + }, + { + "left": "issue:40444", + "right": "issue:43526", + "accept": false, + "reason": "Qwen2.5-VL iterable dataset multi-image finetuning failure and BeitImageProcessorFast label reduction are different areas." + }, + { + "left": "issue:44448", + "right": "issue:44977", + "accept": false, + "reason": "Pegasus output drift and Qwen3.5 flash-attention generation failure are separate model-specific bugs." + }, + { + "left": "issue:43335", + "right": "issue:45593", + "accept": false, + "reason": "SwitchTransformers sparse-layer config and D-FINE auxiliary-loss behavior are unrelated training/model issues." + }, + { + "left": "issue:43720", + "right": "issue:44112", + "accept": false, + "reason": "BitNet packed-weight unpacking during accelerate loading and GraniteSpeech CI stale device override are different failures." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Accepted. The canonical pair is well grounded by the packet: issue:45310 and issue:45478 have identical titles and clearly match. The remaining soft-edge rejections stay conservative at the title/body-summary level, and the cluster summary does not overstate the evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 22, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:25251", + "issue:29942", + "issue:32090", + "issue:33357", + "issue:34689", + "issue:35141", + "issue:37428", + "issue:41720", + "issue:43065", + "issue:43066", + "issue:43278", + "issue:43329", + "issue:43381", + "issue:43412", + "issue:43421", + "issue:43550", + "issue:43606", + "issue:43653", + "issue:43701", + "issue:43873", + "issue:43976", + "issue:43994", + "issue:44186", + "issue:44265", + "issue:44448", + "issue:44451", + "issue:44462", + "issue:44466", + "issue:44493", + "issue:44743", + "issue:44857", + "issue:44977", + "issue:44987", + "issue:45072", + "issue:45083", + "issue:45198", + "issue:45229", + "issue:45245", + "issue:45372", + "issue:45406", + "issue:45412", + "issue:45440", + "issue:45459", + "issue:45491", + "issue:45520", + "issue:45563", + "issue:45588" + ], + "soft_pairs": [ + "issue:45372|issue:45588", + "issue:43066|issue:44462", + "issue:34689|issue:35141", + "issue:44977|issue:45563", + "issue:44857|issue:45072", + "issue:43606|issue:44857", + "issue:43412|issue:45588", + "issue:43873|issue:45229", + "issue:45372|issue:45406", + "issue:43873|issue:44493", + "issue:37428|issue:44987", + "issue:43701|issue:45083", + "issue:29942|issue:35141", + "issue:43976|issue:45440", + "issue:45245|issue:45563", + "issue:43550|issue:45083", + "issue:41720|issue:45229", + "issue:43278|issue:43329", + "issue:32090|issue:33357", + "issue:45372|issue:45459", + "issue:44451|issue:45520", + "issue:44448|issue:44466", + "issue:43065|issue:43994", + "issue:43065|issue:45412", + "issue:25251|issue:32090", + "issue:43653|issue:44743", + "issue:44857|issue:45588", + "issue:44186|issue:45198", + "issue:43421|issue:45491", + "issue:43278|issue:43381", + "issue:43994|issue:45412", + "issue:44265|issue:45198" + ], + "prepared_review_unit_hash": "b3e62fc6f83b2d19584561cf0791db84f72df75daaca74d11c982c2c96df9382", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 32, + "serialized_chars": 36797, + "estimated_input_tokens": 9200, + "estimated_eval_tokens": 18656 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set looks like a loose collection of Transformers issues with superficial thematic overlap (tokenizers, Gemma/Qwen, flash-attn, offloading, dtype, export), but the soft pairs mostly describe different root causes and should not be deduplicated. No PRs are present. Issue 45372 is the best cluster anchor only because it is the most connected item in the candidate graph, not because it matches the others exactly.", + "confidence": 0.56, + "canonical_issue_reason": "Issue 45372 is the most central node among the soft links, with multiple nearby tokenizer/processor-loading references, so it is the best available anchor for this set.", + "canonical_pr_reason": null, + "best_issue_reason": "45372 has the broadest apparent overlap with other candidates in the provided similarity graph; it is the best representative issue, though still not a clear duplicate hub.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45372", + "right": "issue:45588", + "accept": false, + "reason": "Both involve tokenizer/processor-related failures, but one is a missing import for Gemma 4 loading and the other is a flash-attention runtime crash on `s_aux=None`; different code paths." + }, + { + "left": "issue:43066", + "right": "issue:44462", + "accept": false, + "reason": "Both touch tokenizer loading/serialization, but one is a wrong decoder type in v5 and the other is AutoTokenizer ignoring `tokenizer.json`; not the same bug." + }, + { + "left": "issue:34689", + "right": "issue:35141", + "accept": false, + "reason": "Model loading failure for Llama 3.2 Vision is unrelated to the embedding reinitialization bug in `post_init`." + }, + { + "left": "issue:44977", + "right": "issue:45563", + "accept": false, + "reason": "Flash-attention generation failure and a stale `num_return_sequences` warning are unrelated behavior." + }, + { + "left": "issue:44857", + "right": "issue:45072", + "accept": false, + "reason": "Both are dtype/device-related inference issues, but they affect different models and failure modes." + }, + { + "left": "issue:43606", + "right": "issue:44857", + "accept": false, + "reason": "CPU offload device mismatch and float16 AMP CUDA crash are separate bugs." + }, + { + "left": "issue:43412", + "right": "issue:45588", + "accept": false, + "reason": "Executorch export / unsupported op failure is unrelated to the flash_attention `s_aux=None` crash." + }, + { + "left": "issue:43873", + "right": "issue:45229", + "accept": false, + "reason": "Both mention offload/memory behavior, but one is quantization offloading and the other is multi-GPU OOM on Gemma4." + }, + { + "left": "issue:45372", + "right": "issue:45406", + "accept": false, + "reason": "Both are Gemma 4 loading/serving issues, but one is a missing `ReasoningEffort` import and the other is a missing `_tokenizer` attribute." + }, + { + "left": "issue:43873", + "right": "issue:44493", + "accept": false, + "reason": "Quantized offloading problems and unexpected position-id keys are different issues." + }, + { + "left": "issue:37428", + "right": "issue:44987", + "accept": false, + "reason": "Import error for `_flash_supports_window_size` and Qwen3.5 flash-attention generation failure are distinct failures." + }, + { + "left": "issue:43701", + "right": "issue:45083", + "accept": false, + "reason": "Checkpoint resume key mismatch is unrelated to the qwen3_omni_moe feature-extraction helper behavior." + }, + { + "left": "issue:29942", + "right": "issue:35141", + "accept": false, + "reason": "Flash Attention 2 test failures do not match the embedding reinitialization bug." + }, + { + "left": "issue:43976", + "right": "issue:45440", + "accept": false, + "reason": "Python version incompatibility and DeepSeekV3MoE divergence are unrelated." + }, + { + "left": "issue:45245", + "right": "issue:45563", + "accept": false, + "reason": "Category-count limit error is unrelated to the stale generation warning." + }, + { + "left": "issue:43550", + "right": "issue:45083", + "accept": false, + "reason": "torch.compile/SDPA failure and feature-length helper behavior are different code paths." + }, + { + "left": "issue:41720", + "right": "issue:45229", + "accept": false, + "reason": "Qwen3 auto device mapping CUDA assert and Gemma4 multi-GPU OOM are different model/runtime problems." + }, + { + "left": "issue:43278", + "right": "issue:43329", + "accept": false, + "reason": "Embedding dtype drift between train/eval is unrelated to the undefined video-branch helper variables." + }, + { + "left": "issue:32090", + "right": "issue:33357", + "accept": false, + "reason": "Trainer `_gpu_broadcast_one` NoneType error and MacOS bus error on CLIP are unrelated." + }, + { + "left": "issue:45372", + "right": "issue:45459", + "accept": false, + "reason": "Tokenizer import failure and protobuf-related error masking are different tokenizer-loading bugs." + }, + { + "left": "issue:44451", + "right": "issue:45520", + "accept": false, + "reason": "ScandiBERT load failure and Python 3.13 `flash_attn` import-key error are unrelated." + }, + { + "left": "issue:44448", + "right": "issue:44466", + "accept": false, + "reason": "Both involve v4/v5 behavior changes, but one is output divergence and the other is serialization/tied-weight inconsistency; not the same concrete bug." + }, + { + "left": "issue:43065", + "right": "issue:43994", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder and SigLIP2 nonsensical AutoModel/pipeline outputs are different model issues." + }, + { + "left": "issue:43065", + "right": "issue:45412", + "accept": false, + "reason": "Dummy layer in Sam3PixelDecoder and RT-DETR memory release issue are unrelated." + }, + { + "left": "issue:25251", + "right": "issue:32090", + "accept": false, + "reason": "Pipeline `top_k` output shape change and `_gpu_broadcast_one` NoneType error are unrelated." + }, + { + "left": "issue:43653", + "right": "issue:44743", + "accept": false, + "reason": "BigBirdTokenizer special-token decode bug and Qwen3.5 recurrent-state reset bug are unrelated." + }, + { + "left": "issue:44857", + "right": "issue:45588", + "accept": false, + "reason": "AMP/CUDA loss crash and flash_attention `s_aux=None` crash are separate inference failures." + }, + { + "left": "issue:44186", + "right": "issue:45198", + "accept": false, + "reason": "LayoutLMv2 NER/padding crash and Wav2Vec2 save/tokenization failure are different tokenizer bugs." + }, + { + "left": "issue:43421", + "right": "issue:45491", + "accept": false, + "reason": "Runtime special-token post-processor update feature and Gemma3 NaN embeddings are unrelated." + }, + { + "left": "issue:43278", + "right": "issue:43381", + "accept": false, + "reason": "Train/eval embedding dtype mismatch is unrelated to gradient checkpointing in eval mode." + }, + { + "left": "issue:43994", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 output issue and RT-DETR memory release problem are unrelated." + }, + { + "left": "issue:44265", + "right": "issue:45198", + "accept": false, + "reason": "torch.export failure with `torch_compilable_check` and Wav2Vec2 save/tokenization 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": 13, + "review_unit_index": 23, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:29127", + "issue:29942", + "issue:30064", + "issue:32090", + "issue:33290", + "issue:33357", + "issue:34567", + "issue:35141", + "issue:36010", + "issue:39692", + "issue:42915", + "issue:42994", + "issue:43257", + "issue:43262", + "issue:43278", + "issue:43334", + "issue:43381", + "issue:43441", + "issue:43526", + "issue:43531", + "issue:43653", + "issue:43701", + "issue:43756", + "issue:43761", + "issue:43824", + "issue:43931", + "issue:44079", + "issue:44186", + "issue:44206", + "issue:44279", + "issue:44361", + "issue:44442", + "issue:44464", + "issue:44479", + "issue:44610", + "issue:44871", + "issue:44977", + "issue:45072", + "issue:45103", + "issue:45198", + "issue:45229", + "issue:45245", + "issue:45372", + "issue:45412", + "issue:45440", + "issue:45491", + "issue:45588", + "issue:45593" + ], + "soft_pairs": [ + "issue:42915|issue:42994", + "issue:44361|issue:45198", + "issue:44206|issue:44479", + "issue:44871|issue:44977", + "issue:43257|issue:43278", + "issue:43756|issue:45440", + "issue:29942|issue:30064", + "issue:44610|issue:45412", + "issue:45103|issue:45372", + "issue:43824|issue:44279", + "issue:33357|issue:39692", + "issue:45440|issue:45593", + "issue:29127|issue:34567", + "issue:32090|issue:33290", + "issue:45072|issue:45229", + "issue:43653|issue:44442", + "issue:43381|issue:43701", + "issue:43526|issue:44186", + "issue:43334|issue:43531", + "issue:44464|issue:45491", + "issue:44977|issue:45245", + "issue:29942|issue:36010", + "issue:43262|issue:44206", + "issue:29127|issue:33357", + "issue:43761|issue:44079", + "issue:29127|issue:35141", + "issue:42915|issue:43931", + "issue:43441|issue:45588" + ], + "prepared_review_unit_hash": "4ed09d18c624dafd247c92e9d6e459a5b0bb6bf2f002b8c520c1b00fac56b5db", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36120, + "estimated_input_tokens": 9030, + "estimated_eval_tokens": 18316 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: the soft-linked pairs mostly share a broad subsystem or surface-level symptom, but not the same concrete bug/change. I would not merge any of the soft edges. The most representative issue is the CLIPVisionModel hidden-states regression because it is a precise, reproducible code-path bug.", + "confidence": 0.84, + "canonical_issue_reason": "No clear duplicate theme across the cluster; issue 43761 is the most concrete, reproducible regression among the set, so it is the best representative issue.", + "canonical_pr_reason": null, + "best_issue_reason": "43761 has a narrow failure mode, a specific model path, and a straightforward regression signature, making it the most actionable issue in this mixed cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42915", + "right": "issue:42994", + "accept": false, + "reason": "Both involve Qwen3-MoE/quantization, but one is an FP8 config failure and the other is a quantized saving problem; different stages and likely different bugs." + }, + { + "left": "issue:44361", + "right": "issue:45198", + "accept": false, + "reason": "Different models and different failure surfaces: MLukeTokenizer task errors vs Wav2Vec2 save/tokenization failure." + }, + { + "left": "issue:44206", + "right": "issue:44479", + "accept": false, + "reason": "Unsupported feature-extractor arg vs video-input regression; same broad area, not the same code-path bug." + }, + { + "left": "issue:44871", + "right": "issue:44977", + "accept": false, + "reason": "Tokenizer/model EOS config mismatch is unrelated to the flash-attention generation failure." + }, + { + "left": "issue:43257", + "right": "issue:43278", + "accept": false, + "reason": "Loading/conversion of Qwen3-MoE weights is distinct from BF16-to-FP32 dtype drift during evaluate." + }, + { + "left": "issue:43756", + "right": "issue:45440", + "accept": false, + "reason": "RoPE layer dropping and DeepSeek implementation divergence are different model discrepancies." + }, + { + "left": "issue:29942", + "right": "issue:30064", + "accept": false, + "reason": "Failing Flash Attention 2 tests and void segmentation map processing are unrelated issues." + }, + { + "left": "issue:44610", + "right": "issue:45412", + "accept": false, + "reason": "Processor output-size mismatch and RT-DETR memory leaks are not the same underlying bug." + }, + { + "left": "issue:45103", + "right": "issue:45372", + "accept": false, + "reason": "auto_docstring annotation parsing crash is unrelated to the mistral_common import dependency break." + }, + { + "left": "issue:43824", + "right": "issue:44279", + "accept": false, + "reason": "A specific missing import and a generic dependency issue do not indicate the same fix." + }, + { + "left": "issue:33357", + "right": "issue:39692", + "accept": false, + "reason": "MacOS CLIP bus error and SigLIP2 doc example errors are different problems." + }, + { + "left": "issue:45440", + "right": "issue:45593", + "accept": false, + "reason": "Native model divergence and missing auxiliary losses are separate model-behavior bugs." + }, + { + "left": "issue:29127", + "right": "issue:34567", + "accept": false, + "reason": "Error-message clarity for LayoutLMv3 is unrelated to TrainerState token-count tracking." + }, + { + "left": "issue:32090", + "right": "issue:33290", + "accept": false, + "reason": "NoneType broadcast error and Adafactor/deepspeed OOM are different Trainer/deepspeed failures." + }, + { + "left": "issue:45072", + "right": "issue:45229", + "accept": false, + "reason": "Bfloat16 dtype mismatches are not the same as multi-GPU CUDA OOM." + }, + { + "left": "issue:43653", + "right": "issue:44442", + "accept": false, + "reason": "BigBird special-token registration and AutoTokenizer loading a FastSpeech2Conformer tokenizer are unrelated." + }, + { + "left": "issue:43381", + "right": "issue:43701", + "accept": false, + "reason": "Eval-mode gradient-checkpointing restriction and resume checkpoint key mismatch are separate training-state bugs." + }, + { + "left": "issue:43526", + "right": "issue:44186", + "accept": false, + "reason": "reduce_labels returning one label and LayoutLMv2Tokenizer padding/truncation crashes are different tokenizer issues." + }, + { + "left": "issue:43334", + "right": "issue:43531", + "accept": false, + "reason": "Missing pad_token_id in Qwen3-VL and a Qwen3-MoE sliding_window issue are distinct model/config regressions." + }, + { + "left": "issue:44464", + "right": "issue:45491", + "accept": false, + "reason": "Compiled-forward chunked generation inconsistency and Gemma3 NaNs from all-padding windows are not the same bug." + }, + { + "left": "issue:44977", + "right": "issue:45245", + "accept": false, + "reason": "Flash-attention generation failure and category-count runtime limit are unrelated." + }, + { + "left": "issue:29942", + "right": "issue:36010", + "accept": false, + "reason": "Flash Attention 2 test failures and GenerationMixin import error are different failure modes." + }, + { + "left": "issue:43262", + "right": "issue:44206", + "accept": false, + "reason": "Audio chat-template sampling-rate defaulting and unsupported center arg in a feature extractor are unrelated." + }, + { + "left": "issue:29127", + "right": "issue:33357", + "accept": false, + "reason": "LayoutLMv3 error messaging and a CLIP MacOS bus error do not share a concrete fix." + }, + { + "left": "issue:43761", + "right": "issue:44079", + "accept": false, + "reason": "The CLIPVisionModel hidden-states regression may involve ModelOutput handling, but this is not clearly the same concrete bug as generic key assignment when a key was previously None." + }, + { + "left": "issue:29127", + "right": "issue:35141", + "accept": false, + "reason": "LayoutLMv3 error handling and embedding reinitialization in post_init are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:43931", + "accept": false, + "reason": "Qwen3-MoE FP8 failure and Qwen3-VL weight-shape mismatch are different loading issues." + }, + { + "left": "issue:43441", + "right": "issue:45588", + "accept": false, + "reason": "Ministral FlashAttention failure and sink-less flash_attention.py s_aux=None crash are different attention-path 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": 13, + "review_unit_index": 24, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:33290", + "issue:34567", + "issue:34689", + "issue:35141", + "issue:39692", + "issue:41628", + "issue:43232", + "issue:43316", + "issue:43381", + "issue:43388", + "issue:43452", + "issue:43493", + "issue:43525", + "issue:43526", + "issue:43575", + "issue:43611", + "issue:43646", + "issue:43673", + "issue:43701", + "issue:43723", + "issue:43761", + "issue:43827", + "issue:43873", + "issue:43931", + "issue:43994", + "issue:44077", + "issue:44188", + "issue:44206", + "issue:44387", + "issue:44442", + "issue:44479", + "issue:44610", + "issue:44743", + "issue:44811", + "issue:44857", + "issue:44898", + "issue:44977", + "issue:45003", + "issue:45072", + "issue:45216", + "issue:45290", + "issue:45372", + "issue:45440", + "issue:45479", + "issue:45491", + "issue:45584", + "issue:45588", + "issue:45600" + ], + "soft_pairs": [ + "issue:43232|issue:43388", + "issue:43526|issue:44857", + "issue:44442|issue:45072", + "issue:43723|issue:45479", + "issue:44479|issue:45290", + "issue:43526|issue:44610", + "issue:45003|issue:45440", + "issue:44743|issue:44811", + "issue:43452|issue:45588", + "issue:43931|issue:45216", + "issue:45588|issue:45600", + "issue:44977|issue:45584", + "issue:43761|issue:44188", + "issue:43316|issue:43525", + "issue:43575|issue:43701", + "issue:43646|issue:44077", + "issue:43994|issue:44206", + "issue:39692|issue:45491", + "issue:43575|issue:44387", + "issue:43873|issue:45588", + "issue:43673|issue:44743", + "issue:33290|issue:34567", + "issue:44442|issue:44898", + "issue:34689|issue:43611", + "issue:41628|issue:45372", + "issue:43493|issue:43827", + "issue:43381|issue:43873", + "issue:33290|issue:34689", + "issue:33290|issue:35141", + "issue:44077|issue:44479" + ], + "prepared_review_unit_hash": "bf2ed62e00b36489b5e3fa679536890ee45cfc5f7d3ad9909c0c4f7f50d6ac3d", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36854, + "estimated_input_tokens": 9214, + "estimated_eval_tokens": 18684 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is highly heterogeneous: it mixes unrelated tokenizer/loading, generation/cache, vision processor, quantization/offloading, documentation, and model-specific regression issues. None of the proposed soft pairs look like the same underlying bug or change, so all soft edges should be rejected.", + "confidence": 0.88, + "canonical_issue_reason": "Issue 43873 is the broadest and most active item here (open, with multiple inbound references) and is the closest thing to a cluster anchor, but the surrounding issues are too unrelated for it to be a true duplicate hub.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43873 is the best administrative representative because it has the most activity and references, but it still does not meaningfully cover the rest of the set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43232", + "right": "issue:43388", + "accept": false, + "reason": "Generation kwargs update logic and metric label gathering are unrelated code paths." + }, + { + "left": "issue:43526", + "right": "issue:44857", + "accept": false, + "reason": "ImageProcessor label reduction and AMP/CUDA loss crashes are different bugs." + }, + { + "left": "issue:44442", + "right": "issue:45072", + "accept": false, + "reason": "Tokenizer loading failure and bfloat16 dtype mismatch are unrelated issues." + }, + { + "left": "issue:43723", + "right": "issue:45479", + "accept": false, + "reason": "Tokenizer loading regression and sequence-classification zero-loss bug do not share the same fix." + }, + { + "left": "issue:44479", + "right": "issue:45290", + "accept": false, + "reason": "Video-input regression and chat template tool-call crash affect different subsystems." + }, + { + "left": "issue:43526", + "right": "issue:44610", + "accept": false, + "reason": "Label reduction in an image processor is unrelated to OmDet input-size mismatch." + }, + { + "left": "issue:45003", + "right": "issue:45440", + "accept": false, + "reason": "Unsafe sys.modules access and DeepSeekV3MoE divergence are distinct problems." + }, + { + "left": "issue:44743", + "right": "issue:44811", + "accept": false, + "reason": "Qwen recurrent-state reset and Whisper batch_decode token handling are not the same bug." + }, + { + "left": "issue:43452", + "right": "issue:45588", + "accept": false, + "reason": "GGUF loading breakage and flash-attention sink handling are different code paths." + }, + { + "left": "issue:43931", + "right": "issue:45216", + "accept": false, + "reason": "Shape-mismatch loading and save_pretrained checkpoint corruption are related to the model family but not the same concrete defect." + }, + { + "left": "issue:45588", + "right": "issue:45600", + "accept": false, + "reason": "Flash-attention AttributeError and removed Sam3LiteText auto-mapping references are unrelated." + }, + { + "left": "issue:44977", + "right": "issue:45584", + "accept": false, + "reason": "Qwen flash-attention generation and Whisper empty-transcription generation failures are different bugs." + }, + { + "left": "issue:43761", + "right": "issue:44188", + "accept": false, + "reason": "CLIP hidden_states regression and attention-kernel divergence are separate failures." + }, + { + "left": "issue:43316", + "right": "issue:43525", + "accept": false, + "reason": "Gemma3TextConfig API mismatch and missing Llama4 pad_token_id are not the same issue." + }, + { + "left": "issue:43575", + "right": "issue:43701", + "accept": false, + "reason": "OOM during large-model TP loading and resume_from_checkpoint key mismatch are unrelated." + }, + { + "left": "issue:43646", + "right": "issue:44077", + "accept": false, + "reason": "Generic custom model initialization breakage and patchtsmixer post_init validation are not the same concrete bug." + }, + { + "left": "issue:43994", + "right": "issue:44206", + "accept": false, + "reason": "SigLIP2 bad outputs and LasrFeatureExtractor center-arg crash are different problems." + }, + { + "left": "issue:39692", + "right": "issue:45491", + "accept": false, + "reason": "Documentation example errors and Gemma3 NaN embeddings are unrelated." + }, + { + "left": "issue:43575", + "right": "issue:44387", + "accept": false, + "reason": "Tensor-parallel load OOM and int4 reserved-memory OOM have different causes and fixes." + }, + { + "left": "issue:43873", + "right": "issue:45588", + "accept": false, + "reason": "Quantization offloading issues and flash-attention sink-less crashes are unrelated." + }, + { + "left": "issue:43673", + "right": "issue:44743", + "accept": false, + "reason": "Missing generation cache in v5.0.0 and Qwen recurrent-state reset are not the same bug." + }, + { + "left": "issue:33290", + "right": "issue:34567", + "accept": false, + "reason": "Adafactor/deepspeed OOM and TrainerState token-count tracking are unrelated." + }, + { + "left": "issue:44442", + "right": "issue:44898", + "accept": false, + "reason": "Tokenizer loading failure and Perceiver image-resolution failure are different areas." + }, + { + "left": "issue:34689", + "right": "issue:43611", + "accept": false, + "reason": "Both involve loading, but they target different model families and different root causes." + }, + { + "left": "issue:41628", + "right": "issue:45372", + "accept": false, + "reason": "Different missing imports in different processor-loading paths; not the same defect." + }, + { + "left": "issue:43493", + "right": "issue:43827", + "accept": false, + "reason": "SigLIP2 implementation mismatch and stale docs after pipeline removal are unrelated." + }, + { + "left": "issue:43381", + "right": "issue:43873", + "accept": false, + "reason": "Gradient-checkpointing eval-mode restriction and quantization offloading are separate issues." + }, + { + "left": "issue:33290", + "right": "issue:34689", + "accept": false, + "reason": "Optimizer OOM and model-loading regression do not share a code fix." + }, + { + "left": "issue:33290", + "right": "issue:35141", + "accept": false, + "reason": "OOM in training and embedding reinitialization during post_init are unrelated." + }, + { + "left": "issue:44077", + "right": "issue:44479", + "accept": false, + "reason": "PatchTSMixer post_init policy and Qwen video-input regression are different 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": 13, + "review_unit_index": 25, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:16998", + "issue:22355", + "issue:25251", + "issue:28282", + "issue:33290", + "issue:34689", + "issue:36010", + "issue:36331", + "issue:41950", + "issue:42175", + "issue:43065", + "issue:43295", + "issue:43316", + "issue:43381", + "issue:43388", + "issue:43404", + "issue:43441", + "issue:43475", + "issue:43540", + "issue:43643", + "issue:43688", + "issue:43716", + "issue:43720", + "issue:43749", + "issue:43761", + "issue:43825", + "issue:43856", + "issue:43873", + "issue:43931", + "issue:44162", + "issue:44190", + "issue:44442", + "issue:44479", + "issue:44496", + "issue:44514", + "issue:44617", + "issue:44734", + "issue:44792", + "issue:44855", + "issue:44871", + "issue:44877", + "issue:44913", + "issue:45127", + "issue:45137", + "issue:45200", + "issue:45406", + "issue:45584" + ], + "soft_pairs": [ + "issue:43720|issue:44442", + "issue:43643|issue:44913", + "issue:43749|issue:43931", + "issue:44190|issue:44496", + "issue:43873|issue:44871", + "issue:43540|issue:44514", + "issue:44162|issue:44792", + "issue:43316|issue:44877", + "issue:43381|issue:43856", + "issue:33290|issue:36331", + "issue:34689|issue:36010", + "issue:44855|issue:45137", + "issue:42175|issue:43316", + "issue:43404|issue:43441", + "issue:43388|issue:43688", + "issue:43065|issue:44617", + "issue:16998|issue:22355", + "issue:41950|issue:43475", + "issue:43316|issue:43716", + "issue:25251|issue:28282", + "issue:45127|issue:45200", + "issue:43761|issue:44479", + "issue:43295|issue:43825", + "issue:44871|issue:45584", + "issue:44734|issue:45406" + ], + "prepared_review_unit_hash": "f3cd8ef27bb3f3e6858aeccfe903a6e10359cc207d03e568c2a9644e47d0a4aa", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 25, + "serialized_chars": 34627, + "estimated_input_tokens": 8657, + "estimated_eval_tokens": 17570 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: the items cover unrelated bugs across loading, configs, pipelines, training, and multimodal models. None of the soft-similarity pairs look like the same underlying issue, so all should remain separate.", + "confidence": 0.94, + "canonical_issue_reason": "No single canonical issue stands out; the issues span distinct code paths and models, and the pairwise similarities are mostly superficial title overlap.", + "canonical_pr_reason": null, + "best_issue_reason": "If one issue must represent the cluster, issue 43761 is the clearest self-contained regression report, but it is not a true duplicate anchor for the rest of the set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43720", + "right": "issue:44442", + "accept": false, + "reason": "BitNet packed-weight loading vs AutoTokenizer/FastSpeech2 tokenizer loading; unrelated failure modes." + }, + { + "left": "issue:43643", + "right": "issue:44913", + "accept": false, + "reason": "trust_remote_code config field loss vs GPTNeoX rotary_pct reset on reload; different config bugs." + }, + { + "left": "issue:43749", + "right": "issue:43931", + "accept": false, + "reason": "FSDP CPU RAM-efficient loading breakage vs Qwen3-VL weight-shape mismatch; different loading paths." + }, + { + "left": "issue:44190", + "right": "issue:44496", + "accept": false, + "reason": "local dataset script issue vs unrecognized model/config.json error; unrelated subsystems." + }, + { + "left": "issue:43873", + "right": "issue:44871", + "accept": false, + "reason": "quantization/offloading behavior vs Gemma eos_token_id mismatch; not the same bug." + }, + { + "left": "issue:43540", + "right": "issue:44514", + "accept": false, + "reason": "Qwen3OmniMoe video-input processing vs Qwen2_5_VL batched chat-template padding crash; distinct code paths." + }, + { + "left": "issue:44162", + "right": "issue:44792", + "accept": false, + "reason": "ESM2 model breakage vs janus image-generation test failure; unrelated models and symptoms." + }, + { + "left": "issue:43316", + "right": "issue:44877", + "accept": false, + "reason": "Gemma3TextConfig API discrepancy vs strict granite_speech config loading; different config issues." + }, + { + "left": "issue:43381", + "right": "issue:43856", + "accept": false, + "reason": "gradient checkpointing in eval mode vs Qwen3 MoE training memory usage; different problems." + }, + { + "left": "issue:33290", + "right": "issue:36331", + "accept": false, + "reason": "Adafactor OOM in deepspeed vs CustomTrainer signature mismatch; unrelated training bugs." + }, + { + "left": "issue:34689", + "right": "issue:36010", + "accept": false, + "reason": "Llama 3.2 vision model loading regression vs GenerationMixin import error; different code paths." + }, + { + "left": "issue:44855", + "right": "issue:45137", + "accept": false, + "reason": "Python 3.13 IndentationError in torch.jit parsing vs DeepSpeed ZeRO3 deque underflow; unrelated." + }, + { + "left": "issue:42175", + "right": "issue:43316", + "accept": false, + "reason": "packaging/backends installation issue vs Gemma3TextConfig API discrepancy; not a duplicate." + }, + { + "left": "issue:43404", + "right": "issue:43441", + "accept": false, + "reason": "Mistral3 lm_head tying bug vs Ministral-3 FlashAttention failure; same family but different concrete problems." + }, + { + "left": "issue:43388", + "right": "issue:43688", + "accept": false, + "reason": "metrics batch-label truncation vs auxiliary-loss normalization; distinct training/eval logic." + }, + { + "left": "issue:43065", + "right": "issue:44617", + "accept": false, + "reason": "dummy Conv2d implementation question vs Sam3Video CUDA OOM; different issues." + }, + { + "left": "issue:16998", + "right": "issue:22355", + "accept": false, + "reason": "model_max_length question vs missing transformers.onnx module; unrelated topics." + }, + { + "left": "issue:41950", + "right": "issue:43475", + "accept": false, + "reason": "video-classification pipeline processor lookup vs Sam3VisionEncoderOutput missing attribute; different bugs." + }, + { + "left": "issue:43316", + "right": "issue:43716", + "accept": false, + "reason": "Gemma3TextConfig API mismatch vs Mistral-3 image-preprocessor dtype mismatch; unrelated models." + }, + { + "left": "issue:25251", + "right": "issue:28282", + "accept": false, + "reason": "pipeline top_k output-shape change vs AutoModel PyTorch import error; not the same bug." + }, + { + "left": "issue:45127", + "right": "issue:45200", + "accept": false, + "reason": "LoRA merge with extended vocabulary/tied embeddings vs Gemma 4 mm_token_type_ids defaulting; different mechanisms." + }, + { + "left": "issue:43761", + "right": "issue:44479", + "accept": false, + "reason": "CLIPVisionModel hidden_states regression vs broad v5 video-input regression across Qwen models; different subsystems." + }, + { + "left": "issue:43295", + "right": "issue:43825", + "accept": false, + "reason": "processor.tokenizer/images-to-tokenizer regression vs translation-task error message; one API break, one messaging bug." + }, + { + "left": "issue:44871", + "right": "issue:45584", + "accept": false, + "reason": "Gemma eos_token_id config mismatch vs Whisper empty transcription after align_special_tokens; different models and code paths." + }, + { + "left": "issue:44734", + "right": "issue:45406", + "accept": false, + "reason": "serve KV-cache continuation indexing bug vs Gemma4Processor missing _tokenizer; unrelated 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": 13, + "review_unit_index": 26, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:32090", + "issue:35141", + "issue:41720", + "issue:42617", + "issue:43065", + "issue:43295", + "issue:43452", + "issue:43550", + "issue:43575", + "issue:43606", + "issue:43646", + "issue:43701", + "issue:43742", + "issue:43761", + "issue:43827", + "issue:43906", + "issue:43931", + "issue:43994", + "issue:44060", + "issue:44077", + "issue:44190", + "issue:44242", + "issue:44464", + "issue:44479", + "issue:44496", + "issue:44521", + "issue:44534", + "issue:44610", + "issue:44617", + "issue:44734", + "issue:44792", + "issue:44871", + "issue:44913", + "issue:44933", + "issue:44938", + "issue:44964", + "issue:44977", + "issue:45127", + "issue:45245", + "issue:45290", + "issue:45357", + "issue:45362", + "issue:45381", + "issue:45542", + "issue:45563", + "issue:45584", + "issue:45600" + ], + "soft_pairs": [ + "issue:44077|issue:44534", + "issue:43295|issue:44871", + "issue:43550|issue:43701", + "issue:43606|issue:43701", + "issue:43646|issue:44913", + "issue:43906|issue:45290", + "issue:44617|issue:45584", + "issue:43761|issue:44242", + "issue:43452|issue:44496", + "issue:43931|issue:44060", + "issue:45563|issue:45584", + "issue:44521|issue:45381", + "issue:43575|issue:43742", + "issue:42617|issue:43575", + "issue:44479|issue:44734", + "issue:44933|issue:45362", + "issue:41720|issue:43575", + "issue:32090|issue:35141", + "issue:44464|issue:45563", + "issue:43065|issue:44610", + "issue:44464|issue:44871", + "issue:44792|issue:44977", + "issue:43827|issue:43994", + "issue:44534|issue:44913", + "issue:41720|issue:45245", + "issue:44938|issue:45542", + "issue:44792|issue:45600", + "issue:44190|issue:44964", + "issue:45127|issue:45357" + ], + "prepared_review_unit_hash": "6a3f814b39c43276d7228d2d59fbfe6b1bec610785dd555d4b5c848dd1911857", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 35677, + "estimated_input_tokens": 8920, + "estimated_eval_tokens": 18096 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This is a loose, heterogeneous cluster of Transformers issues spanning unrelated regressions, loading failures, generation bugs, and model-specific problems. None of the soft pairs look like true duplicates; they usually share only a broad subsystem or version context. Issue 44521 is the best cluster anchor because it is the most active and broadly applicable multimodal bug in the set.", + "confidence": 0.74, + "canonical_issue_reason": "Issue 44521 is the most central/open and has the strongest discussion/inbound reference activity, so it is the best representative anchor for this otherwise mixed cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44521 is broad, currently active, and has the most external references, making it the most useful issue to track as the cluster's representative.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44077", + "right": "issue:44534", + "accept": false, + "reason": "Different failure classes: optional post_init behavior in patchtsmixer vs junk-filled non-persistent buffers in v5." + }, + { + "left": "issue:43295", + "right": "issue:44871", + "accept": false, + "reason": "Both involve model/processor config, but one is a tokenizer/processor regression and the other is an eos_token_id mismatch." + }, + { + "left": "issue:43550", + "right": "issue:43701", + "accept": false, + "reason": "Unrelated bugs: torch.compile SDPA failure for Bamba vs checkpoint key mismatch on resume." + }, + { + "left": "issue:43606", + "right": "issue:43701", + "accept": false, + "reason": "CPU offload device mismatch is a different code path from resume_from_checkpoint key mismatch." + }, + { + "left": "issue:43646", + "right": "issue:44913", + "accept": false, + "reason": "Custom model init breakage is not the same as GPTNeoX config reload losing rotary_pct." + }, + { + "left": "issue:43906", + "right": "issue:45290", + "accept": false, + "reason": "Both touch chat/template behavior, but one is an isolated reproduction of an older issue and the other is a tokenizer crash on tool-call assistant messages." + }, + { + "left": "issue:44617", + "right": "issue:45584", + "accept": false, + "reason": "Completely different models and symptoms: Sam3Video CUDA OOM vs Whisper empty transcription handling." + }, + { + "left": "issue:43761", + "right": "issue:44242", + "accept": false, + "reason": "Different bugs in different models: CLIPVision hidden_states omission vs MoE load-balancing loss not added." + }, + { + "left": "issue:43452", + "right": "issue:44496", + "accept": false, + "reason": "Both are loading failures, but one is gguf_file handling and the other is an unrecognized config/model_type issue." + }, + { + "left": "issue:43931", + "right": "issue:44060", + "accept": false, + "reason": "Shape-mismatch loading for Qwen3-VL is unrelated to the tied-weights warning in Qwen3-Next." + }, + { + "left": "issue:45563", + "right": "issue:45584", + "accept": false, + "reason": "Paged generate warning bug is unrelated to Whisper empty transcription after align_special_tokens." + }, + { + "left": "issue:44521", + "right": "issue:45381", + "accept": false, + "reason": "Both are multimodal, but assistant_masks being all zero is not the same bug as wrong vision_position_ids in Qwen2.5-VL video input." + }, + { + "left": "issue:43575", + "right": "issue:43742", + "accept": false, + "reason": "Tensor-parallel OOM for Qwen2-57B is a different problem from a MobileLLM config key error." + }, + { + "left": "issue:42617", + "right": "issue:43575", + "accept": false, + "reason": "3d_parallel.py runtime failure is not the same as model-loading OOM with tensor parallelism." + }, + { + "left": "issue:44479", + "right": "issue:44734", + "accept": false, + "reason": "Video-input regression in VL models is a different code path from KV-cache continuation indexing in serve." + }, + { + "left": "issue:44933", + "right": "issue:45362", + "accept": false, + "reason": "Missing import from image_utils is a packaging/API issue, not the same as Qwen3.5 chat generation crashes." + }, + { + "left": "issue:41720", + "right": "issue:43575", + "accept": false, + "reason": "cudaErrorAssert on auto device mapping is distinct from a tensor-parallel out-of-memory failure." + }, + { + "left": "issue:32090", + "right": "issue:35141", + "accept": false, + "reason": "Trainer GPU broadcast NoneType error is unrelated to embedding resize/post_init reinitialization." + }, + { + "left": "issue:44464", + "right": "issue:45563", + "accept": false, + "reason": "Compiled-forward chunked generation inconsistency is a different bug from a stale warning in paged generate()." + }, + { + "left": "issue:43065", + "right": "issue:44610", + "accept": false, + "reason": "Sam3PixelDecoder dummy Conv2d and OmDet-Turbo processor size mismatch are separate vision-model issues." + }, + { + "left": "issue:44464", + "right": "issue:44871", + "accept": false, + "reason": "Compiled generation inconsistency and eos_token_id config mismatch are unrelated." + }, + { + "left": "issue:44792", + "right": "issue:44977", + "accept": false, + "reason": "Janus image-generation test failure is not the same as Qwen3.5 flash-attention generation failure." + }, + { + "left": "issue:43827", + "right": "issue:43994", + "accept": false, + "reason": "Docs still referencing pipeline() is a documentation break, not the same as SigLIP2 producing bad outputs." + }, + { + "left": "issue:44534", + "right": "issue:44913", + "accept": false, + "reason": "Non-persistent buffer junk in v5 and GPTNeoX rotary_pct reload regression affect different mechanisms." + }, + { + "left": "issue:41720", + "right": "issue:45245", + "accept": false, + "reason": "Qwen3 device-mapping assert and category-count limit error are unrelated." + }, + { + "left": "issue:44938", + "right": "issue:45542", + "accept": false, + "reason": "Python 3.14 load failure is an environment/runtime compatibility issue, not the TensorBoard-without-TensorFlow backend error." + }, + { + "left": "issue:44190", + "right": "issue:44964", + "accept": false, + "reason": "Local dataset loading failure and Phi-4-multimodal model loading failure are different problems." + }, + { + "left": "issue:45127", + "right": "issue:45357", + "accept": false, + "reason": "LoRA merge collapse with extended vocab and incorrect visual encoder save keys are separate regression areas." + } + ] + }, + "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": 13, + "review_unit_index": 27, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:36246", + "issue:38175", + "issue:38617", + "issue:39692", + "issue:41628", + "issue:41950", + "issue:42175", + "issue:43065", + "issue:43116", + "issue:43295", + "issue:43388", + "issue:43404", + "issue:43479", + "issue:43540", + "issue:43550", + "issue:43582", + "issue:43644", + "issue:43650", + "issue:43761", + "issue:43976", + "issue:44016", + "issue:44077", + "issue:44079", + "issue:44112", + "issue:44190", + "issue:44220", + "issue:44246", + "issue:44279", + "issue:44355", + "issue:44466", + "issue:44514", + "issue:44561", + "issue:44683", + "issue:44734", + "issue:44743", + "issue:44855", + "issue:44913", + "issue:45003", + "issue:45216", + "issue:45245", + "issue:45276", + "issue:45375", + "issue:45406", + "issue:45446", + "issue:45584", + "issue:45588", + "issue:45600", + "issue:45632" + ], + "soft_pairs": [ + "issue:43388|issue:43582", + "issue:43761|issue:44743", + "issue:44855|issue:45588", + "issue:43650|issue:44220", + "issue:44355|issue:44855", + "issue:43540|issue:44734", + "issue:43644|issue:44913", + "issue:45276|issue:45584", + "issue:43976|issue:44855", + "issue:44077|issue:44079", + "issue:43404|issue:45216", + "issue:43550|issue:44190", + "issue:44112|issue:45600", + "issue:43116|issue:44190", + "issue:43295|issue:45276", + "issue:45245|issue:45584", + "issue:41950|issue:44016", + "issue:39692|issue:44190", + "issue:44734|issue:45632", + "issue:36246|issue:41628", + "issue:43479|issue:45375", + "issue:45406|issue:45632", + "issue:44561|issue:45632", + "issue:36246|issue:38617", + "issue:44514|issue:44734", + "issue:38175|issue:43065", + "issue:44016|issue:44220", + "issue:42175|issue:44279", + "issue:44683|issue:45446", + "issue:44466|issue:44913", + "issue:44246|issue:45003" + ], + "prepared_review_unit_hash": "96052cd4bb9d5693a1218cce286e28f274ecd2a8ce54acd91b994cd755f18301", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37130, + "estimated_input_tokens": 9283, + "estimated_eval_tokens": 18822 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items are a broad mix of unrelated bugs, regressions, import errors, and docs/example issues. None of the soft-edge pairs look like the same underlying change or bug, so all are rejected.", + "confidence": 0.93, + "canonical_issue_reason": "Issue 44561 is a strong standalone report: it names a concrete regression, has a clear failure mode, and affects trust_remote_code models broadly.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44561 is the best overall canonical candidate among this set because it is specific, regression-oriented, and points to a well-defined code-path breakage.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43388", + "right": "issue:43582", + "accept": false, + "reason": "Different failures in different areas: metric gathering label truncation vs Apple Silicon allocator warmup TypeError." + }, + { + "left": "issue:43761", + "right": "issue:44743", + "accept": false, + "reason": "Both are model-behavior bugs, but one is CLIPVision hidden_states regression and the other is Qwen recurrent-state caching reset." + }, + { + "left": "issue:44855", + "right": "issue:45588", + "accept": false, + "reason": "Completely unrelated: Python 3.13 import parse error in DebertaV2Model vs flash_attention crash on s_aux=None." + }, + { + "left": "issue:43650", + "right": "issue:44220", + "accept": false, + "reason": "`ADD THE DATA` is not a concrete duplicate of the `_torch_extract_fbank_features()` bug; no shared code-path." + }, + { + "left": "issue:44355", + "right": "issue:44855", + "accept": false, + "reason": "Running compiled Python files is unrelated to the DebertaV2 import/parse issue." + }, + { + "left": "issue:43540", + "right": "issue:44734", + "accept": false, + "reason": "Different code paths: Qwen3OmniMoe video input validation vs server KV-cache continuation tensor indexing." + }, + { + "left": "issue:43644", + "right": "issue:44913", + "accept": false, + "reason": "One is non-persistent buffer initialization junk, the other is GPTNeoX config reload behavior." + }, + { + "left": "issue:45276", + "right": "issue:45584", + "accept": false, + "reason": "Gemma4 embedding resize bug is unrelated to Whisper empty-transcription generation after token alignment." + }, + { + "left": "issue:43976", + "right": "issue:44855", + "accept": false, + "reason": "Broad Python-version support issue is not the same as a Python 3.13 DebertaV2 import parsing error." + }, + { + "left": "issue:44077", + "right": "issue:44079", + "accept": false, + "reason": "Optional post_init enforcement and ModelOutput key assignment are different abstractions and different bugs." + }, + { + "left": "issue:43404", + "right": "issue:45216", + "accept": false, + "reason": "Both involve weights, but they are different failures: Mistral3 lm_head tying vs Qwen3.5 save_pretrained checkpoint corruption." + }, + { + "left": "issue:43550", + "right": "issue:44190", + "accept": false, + "reason": "torch.compile SDPA failure in Bamba is unrelated to local dataset loading in an example script." + }, + { + "left": "issue:44112", + "right": "issue:45600", + "accept": false, + "reason": "Both hit CI, but one is a stale test and the other is a broken auto_mappings reference to removed configs." + }, + { + "left": "issue:43116", + "right": "issue:44190", + "accept": false, + "reason": "Both are example-script issues, but one is empty multi-label results and the other is local dataset loading." + }, + { + "left": "issue:43295", + "right": "issue:45276", + "accept": false, + "reason": "Processor/tokenizer regression is unrelated to Gemma4 embedding resize behavior." + }, + { + "left": "issue:45245", + "right": "issue:45584", + "accept": false, + "reason": "Category-count runtime error has nothing to do with Whisper's empty-transcription bug." + }, + { + "left": "issue:41950", + "right": "issue:44016", + "accept": false, + "reason": "Video-classification pipeline bug and notebook syntax error are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:44190", + "accept": false, + "reason": "SigLIP2 doc/model mismatch and quantization issues are unrelated to dataset loading." + }, + { + "left": "issue:44734", + "right": "issue:45632", + "accept": false, + "reason": "Server KV-cache tensor indexing and trust_remote_code cache-path collision are different bugs in different subsystems." + }, + { + "left": "issue:36246", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but they involve different missing symbols and different modules (`Qwen2_5_VLImageProcessor` vs `AutoImageProcessor`)." + }, + { + "left": "issue:43479", + "right": "issue:45375", + "accept": false, + "reason": "Different config bugs for different models: default multimodal config initialization vs missing deepstack_visual_indexes strict-field handling." + }, + { + "left": "issue:45406", + "right": "issue:45632", + "accept": false, + "reason": "Gemma4Processor missing `_tokenizer` and cache-path collisions are unrelated." + }, + { + "left": "issue:44561", + "right": "issue:45632", + "accept": false, + "reason": "`is_torch_fx_available` removal breaking trust_remote_code is unrelated to local-model cache path collisions." + }, + { + "left": "issue:36246", + "right": "issue:38617", + "accept": false, + "reason": "Both are import errors, but they are not the same missing API or same fix path." + }, + { + "left": "issue:44514", + "right": "issue:44734", + "accept": false, + "reason": "Qwen2_5_VLProcessor batched chat-template crash is separate from server KV-cache continuation indexing." + }, + { + "left": "issue:38175", + "right": "issue:43065", + "accept": false, + "reason": "SigLIP2 zero-probabilities and Sam3PixelDecoder dummy Conv2d are unrelated model bugs." + }, + { + "left": "issue:44016", + "right": "issue:44220", + "accept": false, + "reason": "Notebook syntax error and feature-extraction helper bug do not share an underlying cause." + }, + { + "left": "issue:42175", + "right": "issue:44279", + "accept": false, + "reason": "Dependency packaging for `.[torch]` is not the same as a general transformers dependency issue." + }, + { + "left": "issue:44683", + "right": "issue:45446", + "accept": false, + "reason": "Flex attention compiled failure on torch>=2.9 and an AuxRequest version-check bug are related only by subsystem, not the same fix." + }, + { + "left": "issue:44466", + "right": "issue:44913", + "accept": false, + "reason": "lm_head.weight serialization inconsistency is unrelated to GPTNeoX rotary_pct reload behavior." + }, + { + "left": "issue:44246", + "right": "issue:45003", + "accept": false, + "reason": "Import slowness and unsafe sys.modules access are different import-time problems with different remedies." + } + ] + }, + "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": 13, + "review_unit_index": 28, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:42907", + "issue:43295", + "issue:43299", + "issue:43381", + "issue:43441", + "issue:43479", + "issue:43525", + "issue:43526", + "issue:43531", + "issue:43577", + "issue:43643", + "issue:43673", + "issue:43824", + "issue:43854", + "issue:43901", + "issue:43927", + "issue:43976", + "issue:44016", + "issue:44062", + "issue:44075", + "issue:44112", + "issue:44242", + "issue:44279", + "issue:44336", + "issue:44351", + "issue:44368", + "issue:44462", + "issue:44496", + "issue:44521", + "issue:44683", + "issue:44933", + "issue:44964", + "issue:44987", + "issue:45042", + "issue:45081", + "issue:45200", + "issue:45216", + "issue:45278", + "issue:45325", + "issue:45335", + "issue:45357", + "issue:45405", + "issue:45542", + "issue:45561", + "issue:45584", + "issue:45593", + "issue:45600", + "issue:45632" + ], + "soft_pairs": [ + "issue:43299|issue:45216", + "issue:42907|issue:43441", + "issue:43643|issue:44496", + "issue:43295|issue:45335", + "issue:44016|issue:44062", + "issue:44964|issue:45600", + "issue:44112|issue:44964", + "issue:43976|issue:44987", + "issue:45561|issue:45632", + "issue:43531|issue:45600", + "issue:43673|issue:44336", + "issue:45335|issue:45584", + "issue:43824|issue:44933", + "issue:43976|issue:44279", + "issue:44496|issue:45042", + "issue:43854|issue:44964", + "issue:43577|issue:45216", + "issue:43299|issue:45357", + "issue:43526|issue:43901", + "issue:44075|issue:44368", + "issue:44521|issue:45325", + "issue:44242|issue:45200", + "issue:43381|issue:45593", + "issue:43927|issue:45632", + "issue:43901|issue:44496", + "issue:44351|issue:45278", + "issue:44683|issue:45542", + "issue:43976|issue:45405", + "issue:43479|issue:43525", + "issue:44462|issue:45081" + ], + "prepared_review_unit_hash": "0f4cbc5a0c5c3738f8d13c649ca7fe642435cc85a7c4d881c6b171b97268edb0", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36768, + "estimated_input_tokens": 9192, + "estimated_eval_tokens": 18640 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a mix of unrelated Transformers bugs and regressions across different models/subsystems. None of the soft pairs look like clear same-bug duplicates under a strict triage standard; a few are loosely similar (especially import/loading regressions), but the concrete failure modes differ.", + "confidence": 0.89, + "canonical_issue_reason": "issue:45278 is the broadest umbrella item in the set, describing multiple import failures after an upgrade, so it is the closest thing to a representative issue; however, the rest of the items are mostly separate bugs rather than true duplicates.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the most general and broadly scoped issue in the list, making it the best representative anchor even though the cluster does not form a clean duplicate set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43299", + "right": "issue:45216", + "accept": false, + "reason": "Same general Qwen family, but one is a model-loading regression and the other is a bad save_pretrained checkpoint layout; different concrete bugs." + }, + { + "left": "issue:42907", + "right": "issue:43441", + "accept": false, + "reason": "Both mention Ministral, but one is about saving dequantized models and the other is a FlashAttention loading failure; not the same code path." + }, + { + "left": "issue:43643", + "right": "issue:44496", + "accept": false, + "reason": "Both are config/loading-related, but one is missing fields with trust_remote_code while the other is an unrecognized model_type error; distinct causes." + }, + { + "left": "issue:43295", + "right": "issue:45335", + "accept": false, + "reason": "Processor/tokenizer regression versus token embedding resize not propagating to decoder.embed_tokens; unrelated bugs." + }, + { + "left": "issue:44016", + "right": "issue:44062", + "accept": false, + "reason": "Notebook syntax error and AddedToken argument collision are unrelated failures." + }, + { + "left": "issue:44964", + "right": "issue:45600", + "accept": false, + "reason": "Different model families and different failure modes: Phi-4 multimodal loading versus stale auto_mappings references." + }, + { + "left": "issue:44112", + "right": "issue:44964", + "accept": false, + "reason": "CI test flake in GraniteSpeech versus a model-loading regression; no shared underlying bug." + }, + { + "left": "issue:43976", + "right": "issue:44987", + "accept": false, + "reason": "A Python version compatibility problem is not the same as a specific model-loading failure for physical-intelligence/fast." + }, + { + "left": "issue:45561", + "right": "issue:45632", + "accept": false, + "reason": "Test-worker file race and trust_remote_code cache-path collision are both infrastructure issues, but they are different mechanisms and code paths." + }, + { + "left": "issue:43531", + "right": "issue:45600", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior versus stale auto_mappings config references; unrelated." + }, + { + "left": "issue:43673", + "right": "issue:44336", + "accept": false, + "reason": "Generation cache regression and ANSI escape output handling are unrelated." + }, + { + "left": "issue:45335", + "right": "issue:45584", + "accept": false, + "reason": "Token embedding resize bug versus Whisper empty-transcription generation failure; different models and code paths." + }, + { + "left": "issue:43824", + "right": "issue:44933", + "accept": false, + "reason": "Both are import errors, but they refer to different missing symbols and likely different underlying breakages." + }, + { + "left": "issue:43976", + "right": "issue:44279", + "accept": false, + "reason": "General dependency/version issue versus a vague transformers dependency issue; too broad and not the same concrete bug." + }, + { + "left": "issue:44496", + "right": "issue:45042", + "accept": false, + "reason": "Unrecognized model config loading is unrelated to PIL backend processors incorrectly requiring torchvision." + }, + { + "left": "issue:43854", + "right": "issue:44964", + "accept": false, + "reason": "Two separate model-loading failures for different model families; not a duplicate." + }, + { + "left": "issue:43577", + "right": "issue:45216", + "accept": false, + "reason": "Blip2 dtype propagation bug and Qwen3.5 checkpoint save regression are unrelated." + }, + { + "left": "issue:43299", + "right": "issue:45357", + "accept": false, + "reason": "Both involve Qwen models, but one is loading failure and the other is incorrect visual encoder keys on save_pretrained; different symptoms and fixes." + }, + { + "left": "issue:43526", + "right": "issue:43901", + "accept": false, + "reason": "Image processor label reduction bug versus a docs mismatch about return_all_scores; unrelated." + }, + { + "left": "issue:44075", + "right": "issue:44368", + "accept": false, + "reason": "Unused SGD args and a tie_word_embeddings warning are unrelated." + }, + { + "left": "issue:44521", + "right": "issue:45325", + "accept": false, + "reason": "Both touch multimodal generation, but assistant mask handling and Qwen2.5-VL rope/position-id scaling are different code paths." + }, + { + "left": "issue:44242", + "right": "issue:45200", + "accept": false, + "reason": "Load-balancing loss logic and mm_token_type_ids defaults are separate model-training issues." + }, + { + "left": "issue:43381", + "right": "issue:45593", + "accept": false, + "reason": "Gradient checkpointing in eval mode and D-FINE auxiliary-loss handling are unrelated." + }, + { + "left": "issue:43927", + "right": "issue:45632", + "accept": false, + "reason": "Save/load token ID loss in DiaConfig is unrelated to trust_remote_code cache-path collisions." + }, + { + "left": "issue:43901", + "right": "issue:44496", + "accept": false, + "reason": "A pipeline docs mismatch does not share the same underlying bug as an unrecognized model config." + }, + { + "left": "issue:44351", + "right": "issue:45278", + "accept": false, + "reason": "HybridCache import failure may be one example of broader import regressions, but 45278 is only a generic meta report and not clearly the same concrete bug." + }, + { + "left": "issue:44683", + "right": "issue:45542", + "accept": false, + "reason": "Compiled flex_attention on torch>=2.9 and the TensorFlow/tensorboard backend issue are unrelated." + }, + { + "left": "issue:43976", + "right": "issue:45405", + "accept": false, + "reason": "Python compatibility and a PEFT version bump are different release issues." + }, + { + "left": "issue:43479", + "right": "issue:43525", + "accept": false, + "reason": "Config default initialization for Phi4Multimodal and missing pad_token_id on Llama4Config are unrelated config bugs." + }, + { + "left": "issue:44462", + "right": "issue:45081", + "accept": false, + "reason": "Tokenizer JSON being ignored and a mistral regex patch crashing are different tokenizer-loading 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": 13, + "review_unit_index": 29, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:38175", + "issue:39692", + "issue:41950", + "issue:42994", + "issue:43065", + "issue:43122", + "issue:43262", + "issue:43295", + "issue:43299", + "issue:43317", + "issue:43441", + "issue:43450", + "issue:43650", + "issue:43653", + "issue:43673", + "issue:43723", + "issue:43761", + "issue:43784", + "issue:43854", + "issue:43901", + "issue:44016", + "issue:44162", + "issue:44261", + "issue:44263", + "issue:44279", + "issue:44291", + "issue:44297", + "issue:44462", + "issue:44466", + "issue:44496", + "issue:44521", + "issue:44617", + "issue:44623", + "issue:44671", + "issue:44683", + "issue:44749", + "issue:44779", + "issue:44877", + "issue:44898", + "issue:44987", + "issue:45020", + "issue:45276", + "issue:45290", + "issue:45397", + "issue:45405", + "issue:45542", + "issue:45593" + ], + "soft_pairs": [ + "issue:41950|issue:45020", + "issue:44297|issue:44462", + "issue:44279|issue:45405", + "issue:41950|issue:43650", + "issue:44496|issue:44877", + "issue:43299|issue:43854", + "issue:38175|issue:44617", + "issue:44462|issue:44779", + "issue:43295|issue:44779", + "issue:39692|issue:43901", + "issue:43650|issue:45290", + "issue:43723|issue:44162", + "issue:43450|issue:44279", + "issue:44016|issue:44291", + "issue:43262|issue:44521", + "issue:42994|issue:43317", + "issue:43441|issue:44683", + "issue:44261|issue:44263", + "issue:43065|issue:44898", + "issue:44466|issue:45276", + "issue:44623|issue:45397", + "issue:43122|issue:43650", + "issue:44623|issue:44749", + "issue:43784|issue:45542", + "issue:44671|issue:44779", + "issue:43673|issue:43761", + "issue:44987|issue:45542", + "issue:43653|issue:45593" + ], + "prepared_review_unit_hash": "76eccc8f15cb146bf651200c5a2cf40472cf6d8770d8f4341cb7b747e8a4a8cb", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 28, + "serialized_chars": 35388, + "estimated_input_tokens": 8847, + "estimated_eval_tokens": 17950 + }, + "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 and docs issues, not a single duplicate set. A few items are thematically adjacent (tokenizer/loading, processor/chat-template, v5 regressions), but the concrete failure modes differ enough that none of the soft edges should be merged.", + "confidence": 0.93, + "canonical_issue_reason": "No single canonical issue fits this cluster: it mixes unrelated bugs across tokenizers, processors, model loading, attention, quantization, docs, and model-specific failures.", + "canonical_pr_reason": null, + "best_issue_reason": "If forced to pick a representative issue, 45020 is the broadest v5/remote_code regression umbrella, but it is still too generic to serve as a true duplicate target for the rest.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41950", + "right": "issue:45020", + "accept": false, + "reason": "Different bugs: video-classification pipeline processor lookup vs broad remote_code model-loading breakage." + }, + { + "left": "issue:44297", + "right": "issue:44462", + "accept": false, + "reason": "Both tokenizer-related, but one is save_pretrained metadata/class mismatch and the other is AutoTokenizer ignoring tokenizer.json; different code paths." + }, + { + "left": "issue:44279", + "right": "issue:45405", + "accept": false, + "reason": "Unrelated: generic dependency problem vs a PEFT minimum-version bump issue." + }, + { + "left": "issue:41950", + "right": "issue:43650", + "accept": false, + "reason": "No overlap beyond being noisy issues; video pipeline processor lookup is unrelated to the placeholder 'ADD THE DATA' report." + }, + { + "left": "issue:44496", + "right": "issue:44877", + "accept": false, + "reason": "Different subsystems: strict config loading for granite_speech vs Perceiver resize/interpolate behavior." + }, + { + "left": "issue:43299", + "right": "issue:43854", + "accept": false, + "reason": "Both involve model loading, but for different model families and likely different failure causes." + }, + { + "left": "issue:38175", + "right": "issue:44617", + "accept": false, + "reason": "SigLIP2 zero-probabilities inference bug is unrelated to Sam3Video CUDA OOM." + }, + { + "left": "issue:44462", + "right": "issue:44779", + "accept": false, + "reason": "Tokenizer loading from repository vs DeepSeek tokenization correctness are distinct tokenizer bugs." + }, + { + "left": "issue:43295", + "right": "issue:44779", + "accept": false, + "reason": "Processor.tokenizer regression with images passed to tokenizer is different from DeepSeek tokenizer output drift." + }, + { + "left": "issue:39692", + "right": "issue:43901", + "accept": false, + "reason": "Both docs-related, but different docs and different errors: SigLIP2 example failures vs return_all_scores documentation drift." + }, + { + "left": "issue:43650", + "right": "issue:45290", + "accept": false, + "reason": "Placeholder issue is not the same as the specific apply_chat_template tool-call crash." + }, + { + "left": "issue:43723", + "right": "issue:44162", + "accept": false, + "reason": "AutoTokenizer.from_pretrained regression is not the same as ESM2 model breakage." + }, + { + "left": "issue:43450", + "right": "issue:44279", + "accept": false, + "reason": "Video processor batched-shape bug is unrelated to a dependency issue." + }, + { + "left": "issue:44016", + "right": "issue:44291", + "accept": false, + "reason": "Notebook syntax error vs init_empty_weights unexpected argument TypeError are unrelated." + }, + { + "left": "issue:43262", + "right": "issue:44521", + "accept": false, + "reason": "Both involve apply_chat_template, but one is audio sampling-rate defaulting and the other is multimodal assistant mask generation." + }, + { + "left": "issue:42994", + "right": "issue:43317", + "accept": false, + "reason": "Quantized model save failure and dequantized offload/load failure are different stages and failure modes." + }, + { + "left": "issue:43441", + "right": "issue:44683", + "accept": false, + "reason": "FlashAttention failure on a specific model is not the same as compiled flex_attention failing on newer torch." + }, + { + "left": "issue:44261", + "right": "issue:44263", + "accept": false, + "reason": "Layernorm epsilon precision discussion is unrelated to torch.split return values in GlmMoeDsaIndexer." + }, + { + "left": "issue:43065", + "right": "issue:44898", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder is unrelated to Perceiver image-classification resolution handling." + }, + { + "left": "issue:44466", + "right": "issue:45276", + "accept": false, + "reason": "Both touch serialization/weights, but one is device-dependent lm_head serialization and the other is resize_token_embeddings not propagating to tied embeddings." + }, + { + "left": "issue:44623", + "right": "issue:45397", + "accept": false, + "reason": "processor.save_pretrained missing files is a different bug from gemma-4 zero3 from_pretrained loading." + }, + { + "left": "issue:43122", + "right": "issue:43650", + "accept": false, + "reason": "Tokenizer version drift is unrelated to the placeholder issue." + }, + { + "left": "issue:44623", + "right": "issue:44749", + "accept": false, + "reason": "Missing processor files on save is unrelated to the reported slowdown after upgrading Transformers." + }, + { + "left": "issue:43784", + "right": "issue:45542", + "accept": false, + "reason": "Import-time NameError in sentence-transformers is unrelated to the TensorBoard/TensorFlow backend installation issue." + }, + { + "left": "issue:44671", + "right": "issue:44779", + "accept": false, + "reason": "CamemBERT masked-LM prediction regression is a different model-specific bug from DeepSeek tokenization." + }, + { + "left": "issue:43673", + "right": "issue:43761", + "accept": false, + "reason": "Missing GenerationMixin cache in chunked_prefill is unrelated to CLIPVisionModel not returning hidden_states." + }, + { + "left": "issue:44987", + "right": "issue:45542", + "accept": false, + "reason": "Model loading failure for physical-intelligence/fast is unrelated to the TensorBoard-only backend issue." + }, + { + "left": "issue:43653", + "right": "issue:45593", + "accept": false, + "reason": "BigBirdTokenizer special-token registration bug is unrelated to D-FINE auxiliary-loss 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": 13, + "review_unit_index": 30, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:36246", + "issue:41628", + "issue:41950", + "issue:42175", + "issue:42491", + "issue:42757", + "issue:43295", + "issue:43299", + "issue:43352", + "issue:43475", + "issue:43525", + "issue:43526", + "issue:43531", + "issue:43673", + "issue:43824", + "issue:43881", + "issue:43901", + "issue:43976", + "issue:43994", + "issue:44016", + "issue:44162", + "issue:44188", + "issue:44220", + "issue:44242", + "issue:44246", + "issue:44295", + "issue:44297", + "issue:44336", + "issue:44351", + "issue:44361", + "issue:44373", + "issue:44462", + "issue:44485", + "issue:44496", + "issue:44561", + "issue:44589", + "issue:44617", + "issue:44661", + "issue:45003", + "issue:45200", + "issue:45250", + "issue:45356", + "issue:45362", + "issue:45397", + "issue:45542", + "issue:45561", + "issue:45563", + "issue:45593" + ], + "soft_pairs": [ + "issue:42175|issue:43976", + "issue:43901|issue:43994", + "issue:44297|issue:45397", + "issue:44361|issue:45593", + "issue:45561|issue:45563", + "issue:43475|issue:44016", + "issue:43824|issue:43976", + "issue:43295|issue:44617", + "issue:43352|issue:45250", + "issue:44589|issue:45362", + "issue:43525|issue:43881", + "issue:41628|issue:43976", + "issue:44188|issue:44336", + "issue:43901|issue:44246", + "issue:44295|issue:45397", + "issue:42491|issue:43299", + "issue:41950|issue:44220", + "issue:44242|issue:45593", + "issue:44336|issue:44373", + "issue:44462|issue:45356", + "issue:44661|issue:45542", + "issue:45003|issue:45561", + "issue:44246|issue:44496", + "issue:36246|issue:42757", + "issue:43531|issue:45362", + "issue:36246|issue:44351", + "issue:43526|issue:45003", + "issue:43673|issue:44561", + "issue:44336|issue:44485", + "issue:44162|issue:45200" + ], + "prepared_review_unit_hash": "03d63de90f6ab2089f76b8d997e24cddb9570b00ffe1aff808534e853ad4a001", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36335, + "estimated_input_tokens": 9084, + "estimated_eval_tokens": 18424 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a loose mix of Transformers issues around import failures, model-loading regressions, tokenizer/pipeline bugs, and unrelated docs/test/model-specific problems. There are no PRs here, and none of the soft pairs look like true duplicates of the same underlying bug.", + "confidence": 0.64, + "canonical_issue_reason": "issue:43824 is the strongest anchor: it has the most inbound references and discussion, and it represents the broad import/load-breakage theme shared by several nearby reports.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43824 is the best single representative for the cluster because it is the most referenced/discussed and sits closest to the recurring import/loading regressions, even though the overall cluster is not tight.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42175", + "right": "issue:43976", + "accept": false, + "reason": "TensorFlow backend packaging under `.[torch]` is unrelated to the Python 3.9+/5.1.0 compatibility problem." + }, + { + "left": "issue:43901", + "right": "issue:43994", + "accept": false, + "reason": "Docs about `return_all_scores` do not match the SigLIP2 bad-output model behavior." + }, + { + "left": "issue:44297", + "right": "issue:45397", + "accept": false, + "reason": "Tokenizer class mismatch on save is a different failure mode from Gemma-4 `from_pretrained` breakage." + }, + { + "left": "issue:44361", + "right": "issue:45593", + "accept": false, + "reason": "MLukeTokenizer task AttributeError is unrelated to D-FINE auxiliary-loss behavior." + }, + { + "left": "issue:45561", + "right": "issue:45563", + "accept": false, + "reason": "A pytest-xdist file race is not the same bug as the stale `num_return_sequences` warning in paged generate." + }, + { + "left": "issue:43475", + "right": "issue:44016", + "accept": false, + "reason": "SAM 3 Video missing attribute and a notebook syntax error are entirely different problems." + }, + { + "left": "issue:43824", + "right": "issue:43976", + "accept": false, + "reason": "Qwen2_5_VL import failure is unrelated to Transformers 5.1.0/Python version incompatibility." + }, + { + "left": "issue:43295", + "right": "issue:44617", + "accept": false, + "reason": "Processor/tokenizer regression is a different code path from the SAM3 Video OOM report." + }, + { + "left": "issue:43352", + "right": "issue:45250", + "accept": false, + "reason": "Unsupported Flash Attention 2.0 for Nemotron is not the same as a generic Flash Attention 2.0 issue." + }, + { + "left": "issue:44589", + "right": "issue:45362", + "accept": false, + "reason": "Float8 storage lookup failure and Qwen3.5 chat crash are different model/runtime issues." + }, + { + "left": "issue:43525", + "right": "issue:43881", + "accept": false, + "reason": "Missing `pad_token_id` in Llama4Config is unrelated to glm-4v-9b loading failure." + }, + { + "left": "issue:41628", + "right": "issue:43976", + "accept": false, + "reason": "`AutoImageProcessor` import failure is not the same as the Transformers 5.1.0/Python compatibility bug." + }, + { + "left": "issue:44188", + "right": "issue:44336", + "accept": false, + "reason": "torch.compile attention divergence and ANSI codes in loading_report are unrelated." + }, + { + "left": "issue:43901", + "right": "issue:44246", + "accept": false, + "reason": "A docs mismatch is not the same underlying issue as slow `import transformers`." + }, + { + "left": "issue:44295", + "right": "issue:45397", + "accept": false, + "reason": "Registered-buffer `position_ids` access differs from the Gemma-4 zero3 loading regression." + }, + { + "left": "issue:42491", + "right": "issue:43299", + "accept": false, + "reason": "Both involve Qwen3 MoE, but one is a LoRA hf4.x\u2192hf5.x incompatibility and the other is a model-loading regression on v5 dev, so they are not the same bug." + }, + { + "left": "issue:41950", + "right": "issue:44220", + "accept": false, + "reason": "Video-classification pipeline image-processor lookup and `_torch_extract_fbank_features()` are different pipelines." + }, + { + "left": "issue:44242", + "right": "issue:45593", + "accept": false, + "reason": "MoE load-balancing loss and D-FINE auxiliary losses are unrelated training objectives." + }, + { + "left": "issue:44336", + "right": "issue:44373", + "accept": false, + "reason": "ANSI output in loading_report and a wrong docstring for `position_ids` are not duplicates." + }, + { + "left": "issue:44462", + "right": "issue:45356", + "accept": false, + "reason": "AutoTokenizer ignoring `tokenizer.json` is different from the Kimi-K2.5 codec/regression report." + }, + { + "left": "issue:44661", + "right": "issue:45542", + "accept": false, + "reason": "TOKENIZER_MAPPING_NAMES model-addition failure is unrelated to the missing TensorFlow backend when only tensorboard is installed." + }, + { + "left": "issue:45003", + "right": "issue:45561", + "accept": false, + "reason": "Unsafe `sys.modules` access and the xdist captured-info race are different failure mechanisms." + }, + { + "left": "issue:44246", + "right": "issue:44496", + "accept": false, + "reason": "Slow import timing is not the same as an unrecognized-model config error." + }, + { + "left": "issue:36246", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but they concern different modules and different missing symbols." + }, + { + "left": "issue:43531", + "right": "issue:45362", + "accept": false, + "reason": "Qwen3-MoE `sliding_window` behavior is a different issue from Qwen3.5 chat crashes." + }, + { + "left": "issue:36246", + "right": "issue:44351", + "accept": false, + "reason": "Qwen2_5_VL image-processor import failure is unrelated to missing `HybridCache` import." + }, + { + "left": "issue:43526", + "right": "issue:45003", + "accept": false, + "reason": "BeitImageProcessorFast label reduction and unsafe `sys.modules` access are unrelated bugs." + }, + { + "left": "issue:43673", + "right": "issue:44561", + "accept": false, + "reason": "Chunked-prefill cache behavior in v5 is a different code path from removal of `is_torch_fx_available` breaking trust-remote-code models." + }, + { + "left": "issue:44336", + "right": "issue:44485", + "accept": false, + "reason": "Loading-report ANSI codes are unrelated to GLM-5 RoPE implementation." + }, + { + "left": "issue:44162", + "right": "issue:45200", + "accept": false, + "reason": "ESM2 breakage and Gemma 4 mm token defaults are different model-specific 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": 13, + "review_unit_index": 31, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:36246", + "issue:41628", + "issue:41950", + "issue:42886", + "issue:43065", + "issue:43066", + "issue:43232", + "issue:43257", + "issue:43262", + "issue:43295", + "issue:43408", + "issue:43441", + "issue:43475", + "issue:43540", + "issue:43596", + "issue:43653", + "issue:43901", + "issue:44060", + "issue:44077", + "issue:44162", + "issue:44242", + "issue:44246", + "issue:44295", + "issue:44336", + "issue:44368", + "issue:44466", + "issue:44496", + "issue:44749", + "issue:44779", + "issue:44857", + "issue:44871", + "issue:44877", + "issue:44933", + "issue:44977", + "issue:44987", + "issue:44995", + "issue:45003", + "issue:45137", + "issue:45200", + "issue:45229", + "issue:45292", + "issue:45335", + "issue:45375", + "issue:45459", + "issue:45563", + "issue:45584", + "issue:45588" + ], + "soft_pairs": [ + "issue:44242|issue:44857", + "issue:44295|issue:44749", + "issue:44246|issue:44871", + "issue:44877|issue:45375", + "issue:36246|issue:43596", + "issue:43066|issue:44779", + "issue:43441|issue:43540", + "issue:45292|issue:45584", + "issue:44779|issue:45292", + "issue:44987|issue:45459", + "issue:42886|issue:45229", + "issue:41628|issue:41950", + "issue:44995|issue:45200", + "issue:43065|issue:43408", + "issue:43901|issue:45003", + "issue:43232|issue:44336", + "issue:43257|issue:45137", + "issue:44496|issue:45003", + "issue:44995|issue:45588", + "issue:44060|issue:44077", + "issue:43295|issue:45292", + "issue:43262|issue:44246", + "issue:43653|issue:44162", + "issue:43475|issue:43540", + "issue:44368|issue:45563", + "issue:44368|issue:44977", + "issue:44466|issue:45335", + "issue:44933|issue:45459" + ], + "prepared_review_unit_hash": "716a855b2940d0aa5ee0652ffaf51f7fdca8a503e51f40a0253cb8720ec94aa1", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 28, + "serialized_chars": 35650, + "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 broad and mostly heterogeneous: import/load regressions, tokenizer/config bugs, generation issues, and model-specific SAM/Qwen/DeepSpeed problems. I did not find any pair that clearly describes the same underlying bug/change closely enough to merge as duplicates.", + "confidence": 0.91, + "canonical_issue_reason": "If forced to pick one, issue 45003 is the broadest infrastructure-level bug in the set, but the cluster is not a tight duplicate group.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45003 is the best global representative because it is a general core-library bug rather than a model-specific symptom, though it still does not unify the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44242", + "right": "issue:44857", + "accept": false, + "reason": "Different failures in different subsystems: MoE load-balancing loss vs LW-DETR AMP/CUDA crash." + }, + { + "left": "issue:44295", + "right": "issue:44749", + "accept": false, + "reason": "Position_ids buffer access and post-upgrade data slowdown are unrelated." + }, + { + "left": "issue:44246", + "right": "issue:44871", + "accept": false, + "reason": "Import latency bug vs Gemma eos_token_id config mismatch; no shared code path." + }, + { + "left": "issue:44877", + "right": "issue:45375", + "accept": false, + "reason": "Both involve config strictness, but they affect different model configs and different missing fields." + }, + { + "left": "issue:36246", + "right": "issue:43596", + "accept": false, + "reason": "ImportError for Qwen2.5 VL image processor vs DeepSpeed/BertModel index error are unrelated." + }, + { + "left": "issue:43066", + "right": "issue:44779", + "accept": false, + "reason": "Tokenizer decoder-type warning in v5 vs DeepSeek tokenizer incorrect output; same broad area, different bug." + }, + { + "left": "issue:43441", + "right": "issue:43540", + "accept": false, + "reason": "FlashAttention failure for Ministral-3 and video-processing ValueError for Qwen3OmniMoe are distinct." + }, + { + "left": "issue:45292", + "right": "issue:45584", + "accept": false, + "reason": "Embedding resize propagation bug vs Whisper empty-transcription generation failure are different code paths." + }, + { + "left": "issue:44779", + "right": "issue:45292", + "accept": false, + "reason": "DeepSeek tokenizer regression is not the same as resize_token_embeddings not updating output embeddings." + }, + { + "left": "issue:44987", + "right": "issue:45459", + "accept": false, + "reason": "Model loading failure and protobuf-related tokenizer error masking are unrelated." + }, + { + "left": "issue:42886", + "right": "issue:45229", + "accept": false, + "reason": "Offline cache tokenizer load bug vs multi-GPU CUDA OOM are not duplicates." + }, + { + "left": "issue:41628", + "right": "issue:41950", + "accept": false, + "reason": "General AutoImageProcessor import failure vs video-classification pipeline picking image processors; related area, not same bug." + }, + { + "left": "issue:44995", + "right": "issue:45200", + "accept": false, + "reason": "Stale cache crash in GlmMoeDsa vs mm_token_type_ids defaulting issue are unrelated." + }, + { + "left": "issue:43065", + "right": "issue:43408", + "accept": false, + "reason": "SAM3 pixel decoder dummy layer and sam3_video/sam3_tracker type warning are different defects." + }, + { + "left": "issue:43901", + "right": "issue:45003", + "accept": false, + "reason": "Docs mismatch for return_all_scores is unrelated to sys.modules access in modeling_utils." + }, + { + "left": "issue:43232", + "right": "issue:44336", + "accept": false, + "reason": "Generation kwargs/sync_gpus bug and ANSI color output in loading_report are unrelated." + }, + { + "left": "issue:43257", + "right": "issue:45137", + "accept": false, + "reason": "Qwen3 MoE weight conversion problem and ZeRO3 deque pop error are different DeepSpeed failures." + }, + { + "left": "issue:44496", + "right": "issue:45003", + "accept": false, + "reason": "Unrecognized model config and unsafe sys.modules access are separate loading issues." + }, + { + "left": "issue:44995", + "right": "issue:45588", + "accept": false, + "reason": "Different crashes: stale indexer cache vs flash_attention s_aux=None handling." + }, + { + "left": "issue:44060", + "right": "issue:44077", + "accept": false, + "reason": "Tied-weights warning bug and patchtsmixer post_init restriction are unrelated." + }, + { + "left": "issue:43295", + "right": "issue:45292", + "accept": false, + "reason": "Processor.tokenizer/image handling regression is not the same as resize_token_embeddings not updating output embeddings." + }, + { + "left": "issue:43262", + "right": "issue:44246", + "accept": false, + "reason": "Audio chat-template sampling-rate default vs import slowness are unrelated." + }, + { + "left": "issue:43653", + "right": "issue:44162", + "accept": false, + "reason": "BigBirdTokenizer special-token registration bug and ESM2 regression are different model-specific issues." + }, + { + "left": "issue:43475", + "right": "issue:43540", + "accept": false, + "reason": "Sam3VisionEncoderOutput missing field and Qwen3OmniMoe video ValueError are distinct SAM/Qwen bugs." + }, + { + "left": "issue:44368", + "right": "issue:45563", + "accept": false, + "reason": "Word-embedding tie warning and stale num_return_sequences warning are different warning bugs." + }, + { + "left": "issue:44368", + "right": "issue:44977", + "accept": false, + "reason": "Qwen3.5 tie_word_embeddings warning and DeepSeek tokenizer regression are unrelated." + }, + { + "left": "issue:44466", + "right": "issue:45335", + "accept": false, + "reason": "Serialization inconsistency across devices and t5gemma resize propagation bug are separate weight-handling issues." + }, + { + "left": "issue:44933", + "right": "issue:45459", + "accept": false, + "reason": "Missing import from image_utils and protobuf decode-error masking 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": 13, + "review_unit_index": 32, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:28282", + "issue:30990", + "issue:41628", + "issue:42222", + "issue:42371", + "issue:42673", + "issue:42831", + "issue:42994", + "issue:43232", + "issue:43475", + "issue:43482", + "issue:43525", + "issue:43643", + "issue:43646", + "issue:43673", + "issue:43701", + "issue:43704", + "issue:43873", + "issue:43931", + "issue:44038", + "issue:44162", + "issue:44188", + "issue:44222", + "issue:44297", + "issue:44361", + "issue:44368", + "issue:44623", + "issue:44661", + "issue:44734", + "issue:44749", + "issue:44869", + "issue:44933", + "issue:44945", + "issue:45081", + "issue:45092", + "issue:45103", + "issue:45137", + "issue:45200", + "issue:45230", + "issue:45278", + "issue:45310", + "issue:45356", + "issue:45362", + "issue:45375", + "issue:45381", + "issue:45397", + "issue:45478", + "issue:45600" + ], + "soft_pairs": [ + "issue:43673|issue:44734", + "issue:44869|issue:45356", + "issue:45137|issue:45600", + "issue:43931|issue:44368", + "issue:43232|issue:43673", + "issue:44297|issue:44623", + "issue:43673|issue:45278", + "issue:43646|issue:44162", + "issue:44361|issue:44749", + "issue:42673|issue:43704", + "issue:28282|issue:30990", + "issue:44749|issue:45310", + "issue:45230|issue:45397", + "issue:44038|issue:44623", + "issue:42994|issue:43482", + "issue:43701|issue:44749", + "issue:43475|issue:45381", + "issue:42371|issue:45092", + "issue:45375|issue:45478", + "issue:43475|issue:43643", + "issue:41628|issue:44933", + "issue:45081|issue:45103", + "issue:45310|issue:45375", + "issue:42994|issue:43525", + "issue:42222|issue:45200", + "issue:43873|issue:44945", + "issue:43475|issue:44661", + "issue:42831|issue:44222", + "issue:45310|issue:45397", + "issue:45362|issue:45375", + "issue:43232|issue:44188" + ], + "prepared_review_unit_hash": "9f3295fb9ab485166bb024ca16c141eee772daa4385d74d7c8c13cd9cf0f2c39", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36705, + "estimated_input_tokens": 9177, + "estimated_eval_tokens": 18610 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This packet is still mostly heterogeneous, with many unrelated model-specific regressions and API breakages. There are at least two clear duplicate-like issue pairs by title/symptom: the confirmed Qwen3ForCausalLM VRAM leak pair (42673/43704) and another identical-title pair (45310/45478) about the Qwen3.5 Moe from_pretrained error, even though only the former was surfaced in soft_pairs. The rest of the soft candidates remain conservative non-matches.", + "confidence": 0.94, + "canonical_issue_reason": "issue:42673 is the clearest canonical report for the Qwen3ForCausalLM VRAM leak: it is earlier, more detailed, and matches issue:43704 exactly on title and symptom.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:42673 is the best representative issue because it is the earliest and fuller report in the only confirmed duplicate pair, and it anchors the strongest duplicate signal in the set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43673", + "right": "issue:44734", + "accept": false, + "reason": "Both are generation/cache-related, but they describe different failures in different code paths: chunked_prefill cache missing vs KV-cache continuation tensor indexing." + }, + { + "left": "issue:44869", + "right": "issue:45356", + "accept": false, + "reason": "Both involve tokenizer/decoding regressions, but one is Whisper timestamp decoding and the other is Kimi tokenizer codec handling; not the same bug." + }, + { + "left": "issue:45137", + "right": "issue:45600", + "accept": false, + "reason": "DeepSpeed ZeRO3 deque error and Sam3LiteText auto-mapping CI breakage are unrelated." + }, + { + "left": "issue:43931", + "right": "issue:44368", + "accept": false, + "reason": "Qwen3-VL weight-shape mismatch and a tie_word_embeddings warning are different model/config issues." + }, + { + "left": "issue:43232", + "right": "issue:43673", + "accept": false, + "reason": "These are separate generation bugs: sync_gpus kwargs handling versus missing GenerationMixin cache during chunked prefill." + }, + { + "left": "issue:44297", + "right": "issue:44623", + "accept": false, + "reason": "Both are save_pretrained problems, but one is tokenizer metadata mismatch and the other is missing processor files; different components and failures." + }, + { + "left": "issue:43673", + "right": "issue:45278", + "accept": false, + "reason": "The v5 import-error report is broad and unrelated to the specific generation cache bug in 43673." + }, + { + "left": "issue:43646", + "right": "issue:44162", + "accept": false, + "reason": "Custom model initialization breakage and ESM2-specific breakage are too different to treat as the same underlying bug." + }, + { + "left": "issue:44361", + "right": "issue:44749", + "accept": false, + "reason": "MLukeTokenizer AttributeError and a large slowdown after upgrade are unrelated." + }, + { + "left": "issue:42673", + "right": "issue:43704", + "accept": true, + "reason": "Same title, same model, same symptom: VRAM leak when Qwen3ForCausalLM is used in multiple dataloader threads." + }, + { + "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:44749", + "right": "issue:45310", + "accept": false, + "reason": "Performance regression in data filtering and Qwen3.5 MoE from_pretrained failure are different bugs." + }, + { + "left": "issue:45230", + "right": "issue:45397", + "accept": false, + "reason": "Generic bug report and Gemma-4 Zero3 from_pretrained failure are not the same issue." + }, + { + "left": "issue:44038", + "right": "issue:44623", + "accept": false, + "reason": "Qwen3-VL-Moe v5 bug and missing processor.save_pretrained files are unrelated." + }, + { + "left": "issue:42994", + "right": "issue:43482", + "accept": false, + "reason": "Quantized model saving failure and Qwen2.5-GGUF loading failure are different operations and code paths." + }, + { + "left": "issue:43701", + "right": "issue:44749", + "accept": false, + "reason": "Checkpoint resume key mismatch is unrelated to the reported training slowdown." + }, + { + "left": "issue:43475", + "right": "issue:45381", + "accept": false, + "reason": "SAM 3 Video missing attribute and qwen2.5-vl video position-id bug are different model-specific regressions." + }, + { + "left": "issue:42371", + "right": "issue:45092", + "accept": false, + "reason": "TF32 API guidance and InternVL2 meta-initialization incompatibility are unrelated." + }, + { + "left": "issue:45375", + "right": "issue:45478", + "accept": false, + "reason": "Missing deepstack_visual_indexes field in config and Qwen3.5 Moe from_pretrained error are different problems." + }, + { + "left": "issue:43475", + "right": "issue:43643", + "accept": false, + "reason": "SAM 3 Video output attribute error and AutoConfig missing fields with trust_remote_code are not the same bug." + }, + { + "left": "issue:41628", + "right": "issue:44933", + "accept": false, + "reason": "These are both import-related, but they concern different symbols and likely different import paths; not enough to unify." + }, + { + "left": "issue:45081", + "right": "issue:45103", + "accept": false, + "reason": "Tokenizer regex patch crash and auto_docstring future-annotations crash are unrelated." + }, + { + "left": "issue:45310", + "right": "issue:45375", + "accept": false, + "reason": "Both involve Qwen-related v5 regressions, but one is a from_pretrained error and the other is a config-field drop; different underlying failures." + }, + { + "left": "issue:42994", + "right": "issue:43525", + "accept": false, + "reason": "Quantized model saving failure and Llama4Config missing pad_token_id are different issues." + }, + { + "left": "issue:42222", + "right": "issue:45200", + "accept": false, + "reason": "VitPose breakage and Gemma-4 mm_token_type_ids defaulting are unrelated model-specific bugs." + }, + { + "left": "issue:43873", + "right": "issue:44945", + "accept": false, + "reason": "Quantization offloading behavior and pipeline parallelism output correctness are different problems." + }, + { + "left": "issue:43475", + "right": "issue:44661", + "accept": false, + "reason": "SAM 3 video encoder attribute error and add-new-model-like tokenizer mapping failure are unrelated." + }, + { + "left": "issue:42831", + "right": "issue:44222", + "accept": false, + "reason": "FineGrainedFP8 accuracy regression and FP8 save_pretrained failure are distinct FP8-related issues, not the same bug." + }, + { + "left": "issue:45310", + "right": "issue:45397", + "accept": false, + "reason": "Qwen3.5 Moe from_pretrained failure and Gemma-4 Zero3 from_pretrained failure are different model paths." + }, + { + "left": "issue:45362", + "right": "issue:45375", + "accept": false, + "reason": "Qwen3.5-35B chat crash and missing deepstack_visual_indexes config field are unrelated." + }, + { + "left": "issue:43232", + "right": "issue:44188", + "accept": false, + "reason": "Generation kwargs handling after sync_gpus and attention-kernel divergence under torch.compile are different code paths and symptoms." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The summary overstates uniqueness. Besides the accepted Qwen3ForCausalLM duplicate pair (42673/43704), the packet also contains another identical-title duplicate candidate: issue:45310 and issue:45478 both read \"[BUG] transformers>=5.4.0, Qwen3.5 Moe from_pretrained error\". Even if that pair was not surfaced in soft_pairs, the writeup should not claim there is only one duplicate-like pair in the set. The rest of the conservative pairwise reasoning is mostly grounded, but this omission makes the overall summary too strong." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 33, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:30333", + "issue:30990", + "issue:33290", + "issue:35141", + "issue:36010", + "issue:41628", + "issue:42175", + "issue:42898", + "issue:42994", + "issue:43232", + "issue:43278", + "issue:43377", + "issue:43479", + "issue:43504", + "issue:43526", + "issue:43673", + "issue:43723", + "issue:43784", + "issue:43824", + "issue:43874", + "issue:43976", + "issue:44038", + "issue:44060", + "issue:44079", + "issue:44164", + "issue:44188", + "issue:44222", + "issue:44242", + "issue:44351", + "issue:44373", + "issue:44448", + "issue:44496", + "issue:44568", + "issue:44623", + "issue:44734", + "issue:44779", + "issue:44792", + "issue:44869", + "issue:44933", + "issue:44964", + "issue:45092", + "issue:45103", + "issue:45125", + "issue:45137", + "issue:45310", + "issue:45356", + "issue:45459", + "issue:45561" + ], + "soft_pairs": [ + "issue:41628|issue:44351", + "issue:44222|issue:45310", + "issue:42994|issue:44164", + "issue:44038|issue:45310", + "issue:44496|issue:45561", + "issue:43526|issue:45561", + "issue:43232|issue:44792", + "issue:43504|issue:45561", + "issue:43377|issue:44242", + "issue:36010|issue:41628", + "issue:43673|issue:44188", + "issue:30990|issue:35141", + "issue:42898|issue:44568", + "issue:43479|issue:44079", + "issue:43479|issue:44869", + "issue:43976|issue:44933", + "issue:42175|issue:44933", + "issue:44964|issue:45137", + "issue:43784|issue:43824", + "issue:44623|issue:45310", + "issue:44188|issue:44373", + "issue:44060|issue:45125", + "issue:43723|issue:44568", + "issue:42898|issue:45356", + "issue:44734|issue:45103", + "issue:43278|issue:45137", + "issue:42898|issue:44779", + "issue:30333|issue:33290", + "issue:43874|issue:45092", + "issue:42898|issue:44448", + "issue:41628|issue:45459" + ], + "prepared_review_unit_hash": "7235562a98130ca40aa000b24342bf404212115f1bf79b220407fe280ab08e12", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "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 is a loose collection of mostly unrelated Transformers v5-era bug reports (imports, tokenizer regressions, multimodal configs, save/load, generation, and backend issues). None of the soft pairs looks like the same concrete bug/change, so all are rejected.", + "confidence": 0.89, + "canonical_issue_reason": "issue:42898 is the broadest, most generic user-facing regression in the set and the best placeholder representative for this mostly v5-regression cluster, though it does not duplicate the others.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:42898 is the most reusable canonical issue because it describes a common v5 behavior break rather than a narrow model-specific or infrastructure-specific failure.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41628", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but for different symbols and different code paths; this is shared symptom, not the same bug." + }, + { + "left": "issue:44222", + "right": "issue:45310", + "accept": false, + "reason": "Both involve Qwen3.5/MoE, but one is FP8 save_pretrained and the other is a from_pretrained load failure; not the same fix." + }, + { + "left": "issue:42994", + "right": "issue:44164", + "accept": false, + "reason": "Both touch persistence, but quantized model saving and extra_state handling are distinct serialization bugs." + }, + { + "left": "issue:44038", + "right": "issue:45310", + "accept": false, + "reason": "Both mention Qwen VL/MoE, but they are different model/version failures and not the same code-path problem." + }, + { + "left": "issue:44496", + "right": "issue:45561", + "accept": false, + "reason": "Completely unrelated: model config loading versus a pytest-xdist race in testing utils." + }, + { + "left": "issue:43526", + "right": "issue:45561", + "accept": false, + "reason": "Different subsystems and failure modes; image processor label reduction is unrelated to the test file race." + }, + { + "left": "issue:43232", + "right": "issue:44792", + "accept": false, + "reason": "One is a generation kwargs bug after sync_gpus; the other is a Janus image generation test failure. Too different." + }, + { + "left": "issue:43504", + "right": "issue:45561", + "accept": false, + "reason": "Semantic-segmentation preset loading and a testing-utils race are unrelated." + }, + { + "left": "issue:43377", + "right": "issue:44242", + "accept": false, + "reason": "Different bugs: padding mask batched-vs-single mismatch versus MoE load-balancing loss gating." + }, + { + "left": "issue:36010", + "right": "issue:41628", + "accept": false, + "reason": "Both are import failures, but they are different missing exports with no shared concrete fix indicated." + }, + { + "left": "issue:43673", + "right": "issue:44188", + "accept": false, + "reason": "Generation cache support and attention-kernel divergence under torch.compile are separate problems." + }, + { + "left": "issue:30990", + "right": "issue:35141", + "accept": false, + "reason": "Stuck loading sentence-transformers is unrelated to token embedding reinitialization during resize." + }, + { + "left": "issue:42898", + "right": "issue:44568", + "accept": false, + "reason": "Both are tokenizer regressions in v5, but they affect different behaviors and different tokenizers." + }, + { + "left": "issue:43479", + "right": "issue:44079", + "accept": false, + "reason": "Both involve None-handling, but in unrelated classes and code paths; not mergeable as one bug." + }, + { + "left": "issue:43479", + "right": "issue:44869", + "accept": false, + "reason": "Multimodal config defaults and Whisper timestamp decoding are unrelated." + }, + { + "left": "issue:43976", + "right": "issue:44933", + "accept": false, + "reason": "Python-version compatibility and a missing import are unrelated issues." + }, + { + "left": "issue:42175", + "right": "issue:44933", + "accept": false, + "reason": "Backend dependency packaging and image_utils import exposure are unrelated." + }, + { + "left": "issue:44964", + "right": "issue:45137", + "accept": false, + "reason": "Model loading failure and DeepSpeed ZeRO3 deque handling are unrelated." + }, + { + "left": "issue:43784", + "right": "issue:43824", + "accept": false, + "reason": "Different import errors affecting different APIs/models; no same underlying bug." + }, + { + "left": "issue:44623", + "right": "issue:45310", + "accept": false, + "reason": "Processor save_pretrained missing files is a different path from Qwen3.5 MoE from_pretrained loading." + }, + { + "left": "issue:44188", + "right": "issue:44373", + "accept": false, + "reason": "Generation runtime behavior and a docstring typo are not the same bug." + }, + { + "left": "issue:44060", + "right": "issue:45125", + "accept": false, + "reason": "Both are Qwen3.5 MoE internals, but tied-weights warning and tensor-parallel plan support are different issues." + }, + { + "left": "issue:43723", + "right": "issue:44568", + "accept": false, + "reason": "Tokenizer loading in v5 and BOS/EOS add_special_tokens behavior are different regressions." + }, + { + "left": "issue:42898", + "right": "issue:45356", + "accept": false, + "reason": "Both are tokenizer-related regressions, but the specific failure modes and affected code paths differ." + }, + { + "left": "issue:44734", + "right": "issue:45103", + "accept": false, + "reason": "Serving KV-cache indexing and auto-docstring annotation handling are unrelated." + }, + { + "left": "issue:43278", + "right": "issue:45137", + "accept": false, + "reason": "Embedding dtype drift in evaluate and a ZeRO3 deque IndexError are unrelated." + }, + { + "left": "issue:42898", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer regressions in v5, but they are model-specific and not the same concrete bug." + }, + { + "left": "issue:30333", + "right": "issue:33290", + "accept": false, + "reason": "MLflow reporting on failed jobs and DeepSpeed OOM are unrelated." + }, + { + "left": "issue:43874", + "right": "issue:45092", + "accept": false, + "reason": "Different multimodal issues: a missing image-processor method versus legacy remote-code checkpoint 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": 13, + "review_unit_index": 34, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:22355", + "issue:28282", + "issue:30333", + "issue:30990", + "issue:34689", + "issue:35141", + "issue:36331", + "issue:38175", + "issue:41628", + "issue:42757", + "issue:42831", + "issue:42886", + "issue:42898", + "issue:42994", + "issue:43295", + "issue:43479", + "issue:43576", + "issue:43644", + "issue:43723", + "issue:43784", + "issue:43824", + "issue:44038", + "issue:44206", + "issue:44222", + "issue:44261", + "issue:44263", + "issue:44295", + "issue:44297", + "issue:44360", + "issue:44373", + "issue:44442", + "issue:44483", + "issue:44484", + "issue:44485", + "issue:44514", + "issue:44623", + "issue:44871", + "issue:44913", + "issue:44977", + "issue:44991", + "issue:45092", + "issue:45103", + "issue:45278", + "issue:45310", + "issue:45357", + "issue:45406", + "issue:45459" + ], + "soft_pairs": [ + "issue:44222|issue:44297", + "issue:42898|issue:43295", + "issue:43479|issue:43644", + "issue:44442|issue:45459", + "issue:44222|issue:44623", + "issue:42831|issue:44623", + "issue:44206|issue:45103", + "issue:41628|issue:42757", + "issue:44297|issue:45310", + "issue:22355|issue:28282", + "issue:44222|issue:44484", + "issue:44483|issue:45406", + "issue:43723|issue:44977", + "issue:44263|issue:44360", + "issue:30333|issue:36331", + "issue:44263|issue:45092", + "issue:30333|issue:34689", + "issue:30333|issue:35141", + "issue:28282|issue:30333", + "issue:44295|issue:44623", + "issue:44514|issue:45103", + "issue:43479|issue:44913", + "issue:43723|issue:44871", + "issue:44261|issue:45092", + "issue:43723|issue:44991", + "issue:43723|issue:44442", + "issue:44373|issue:44485", + "issue:45092|issue:45357", + "issue:30990|issue:38175", + "issue:42886|issue:42994", + "issue:42831|issue:45310", + "issue:41628|issue:43824", + "issue:42831|issue:44038", + "issue:43576|issue:43784", + "issue:42757|issue:45278" + ], + "prepared_review_unit_hash": "46c1584c60316f39b14eaebc1ef462ba6065f7a143c54d82795402c5bcf3cbff", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 35, + "serialized_chars": 37352, + "estimated_input_tokens": 9338, + "estimated_eval_tokens": 18932 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is mostly heterogeneous. Most soft pairs share a subsystem or symptom class, but not the same concrete bug, so they should not be merged as duplicates. The broadest issue is the v5 import-regression report, but it still doesn\u2019t cleanly cover the rest.", + "confidence": 0.43, + "canonical_issue_reason": "issue:45278 is the broadest umbrella here: it describes many import errors after upgrading to v5.5.0, which makes it the best candidate to subsume related import/load regressions.", + "canonical_pr_reason": null, + "best_issue_reason": "It is the most representative high-level issue in the cluster, centered on the recurring post-v5 import breakage theme rather than a narrow model-specific symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44222", + "right": "issue:44297", + "accept": false, + "reason": "Both touch save_pretrained/tokenizer persistence, but one is about FP8 Moe model saving and the other about tokenizer_class metadata; different bugs." + }, + { + "left": "issue:42898", + "right": "issue:43295", + "accept": false, + "reason": "One is about clean_up_tokenization_spaces behavior, the other about processor.tokenizer access and image passing; unrelated regressions." + }, + { + "left": "issue:43479", + "right": "issue:43644", + "accept": false, + "reason": "Different failure modes: default multimodal config initialization vs non-persistent buffers being filled with junk." + }, + { + "left": "issue:44442", + "right": "issue:45459", + "accept": false, + "reason": "Tokenizer load failure for a specific tokenizer is not the same as protobuf-related exception masking." + }, + { + "left": "issue:44222", + "right": "issue:44623", + "accept": false, + "reason": "save_pretrained is shared broadly, but these are different artifacts and bugs: FP8 Moe saving vs missing processor files." + }, + { + "left": "issue:42831", + "right": "issue:44623", + "accept": false, + "reason": "An FP8 accuracy issue is not the same as processor.save_pretrained missing files." + }, + { + "left": "issue:44206", + "right": "issue:45103", + "accept": false, + "reason": "One is a feature-extractor argument regression; the other is an auto-docstring AttributeError from future annotations." + }, + { + "left": "issue:41628", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but for different missing symbols from different packages and likely different causes." + }, + { + "left": "issue:44297", + "right": "issue:45310", + "accept": false, + "reason": "Tokenizer metadata mismatch is unrelated to the Qwen3.5 MoE from_pretrained error." + }, + { + "left": "issue:22355", + "right": "issue:28282", + "accept": false, + "reason": "Both are import problems, but one is missing transformers.onnx and the other is a missing PyTorch dependency; not the same bug." + }, + { + "left": "issue:44222", + "right": "issue:44484", + "accept": false, + "reason": "save_pretrained shard-size behavior is unrelated to FP8 Moe model saving failure." + }, + { + "left": "issue:44483", + "right": "issue:45406", + "accept": false, + "reason": "An API request rejection and a Gemma4Processor _tokenizer AttributeError are different code paths." + }, + { + "left": "issue:43723", + "right": "issue:44977", + "accept": false, + "reason": "Both involve loading/generation, but one is generic tokenizer loading and the other is Qwen3.5 flash-attention generation." + }, + { + "left": "issue:44263", + "right": "issue:44360", + "accept": false, + "reason": "Both concern the DSA indexer, but one is about torch.split outputs and the other about a missing ReLU; different defects." + }, + { + "left": "issue:30333", + "right": "issue:36331", + "accept": false, + "reason": "MLFlow job status reporting and CustomTrainer compute_loss signature handling are unrelated." + }, + { + "left": "issue:44263", + "right": "issue:45092", + "accept": false, + "reason": "Different models and failures: DSA indexer split behavior vs remote-code checkpoint incompatibility with meta init." + }, + { + "left": "issue:30333", + "right": "issue:34689", + "accept": false, + "reason": "Training-job MLFlow reporting is unrelated to Llama 3.2 Vision model-loading regression." + }, + { + "left": "issue:30333", + "right": "issue:35141", + "accept": false, + "reason": "Job reporting and embedding reinitialization after resize are unrelated." + }, + { + "left": "issue:28282", + "right": "issue:30333", + "accept": false, + "reason": "A missing PyTorch dependency import error is unrelated to MLFlow reporting on failed training jobs." + }, + { + "left": "issue:44295", + "right": "issue:44623", + "accept": false, + "reason": "Reading position_ids after buffer registration is not the same as missing files in processor.save_pretrained." + }, + { + "left": "issue:44514", + "right": "issue:45103", + "accept": false, + "reason": "A batched apply_chat_template crash is unrelated to the auto_docstring AttributeError." + }, + { + "left": "issue:43479", + "right": "issue:44913", + "accept": false, + "reason": "Default multimodal config initialization is unrelated to GPTNeoXConfig rotary_pct reload behavior." + }, + { + "left": "issue:43723", + "right": "issue:44871", + "accept": false, + "reason": "Generic tokenizer loading failure and Gemma-3 eos_token_id inconsistency are different issues." + }, + { + "left": "issue:43723", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer-related regressions, but they affect different models and appear to have different root causes." + }, + { + "left": "issue:43723", + "right": "issue:44442", + "accept": false, + "reason": "Tokenizer loading failure and FastSpeech2ConformerTokenizer loading are both load issues, but not the same concrete bug." + }, + { + "left": "issue:44373", + "right": "issue:44485", + "accept": false, + "reason": "A docstring mistake and a GLM-5 RoPE implementation discussion are not duplicates." + }, + { + "left": "issue:45092", + "right": "issue:45357", + "accept": false, + "reason": "Meta-init incompatibility for old InternVL2 checkpoints is unrelated to incorrect visual encoder keys in save_pretrained." + }, + { + "left": "issue:30990", + "right": "issue:38175", + "accept": false, + "reason": "Sentence-Transformers getting stuck loading and SigLIP2 zero probabilities are different problems." + }, + { + "left": "issue:42886", + "right": "issue:42994", + "accept": false, + "reason": "Offline cache tokenizer loading and quantized model saving failure are separate bugs." + }, + { + "left": "issue:42831", + "right": "issue:45310", + "accept": false, + "reason": "FP8 accuracy issues are unrelated to Qwen3.5 MoE from_pretrained errors." + }, + { + "left": "issue:41628", + "right": "issue:43824", + "accept": false, + "reason": "Different missing imports: AutoImageProcessor versus Qwen2_5_VLForConditionalGeneration." + }, + { + "left": "issue:42831", + "right": "issue:44038", + "accept": false, + "reason": "FP8 accuracy and Qwen3.5-v5 bug reports are not the same code-path problem." + }, + { + "left": "issue:43576", + "right": "issue:43784", + "accept": false, + "reason": "Broken `transformers env` command and sentence-transformers import NameError have different causes and effects." + }, + { + "left": "issue:42757", + "right": "issue:45278", + "accept": false, + "reason": "The broad import-regression umbrella may include this symptom, but the specific missing is_offline_mode import is not itself the same bug as the whole cluster." + } + ] + }, + "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": 13, + "review_unit_index": 35, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:29127", + "issue:30990", + "issue:33357", + "issue:36296", + "issue:39401", + "issue:41628", + "issue:42371", + "issue:42831", + "issue:42886", + "issue:42907", + "issue:43066", + "issue:43116", + "issue:43122", + "issue:43232", + "issue:43408", + "issue:43452", + "issue:43475", + "issue:43784", + "issue:43937", + "issue:43976", + "issue:43992", + "issue:44038", + "issue:44117", + "issue:44222", + "issue:44261", + "issue:44263", + "issue:44295", + "issue:44297", + "issue:44360", + "issue:44373", + "issue:44485", + "issue:44488", + "issue:44514", + "issue:44521", + "issue:44625", + "issue:44704", + "issue:44743", + "issue:44779", + "issue:44829", + "issue:44945", + "issue:44964", + "issue:45200", + "issue:45245", + "issue:45278", + "issue:45290", + "issue:45593", + "issue:45600" + ], + "soft_pairs": [ + "issue:43122|issue:44521", + "issue:44263|issue:44373", + "issue:43232|issue:45593", + "issue:42886|issue:43066", + "issue:44117|issue:44704", + "issue:43122|issue:44514", + "issue:30990|issue:33357", + "issue:42371|issue:44263", + "issue:44295|issue:44297", + "issue:44704|issue:45290", + "issue:42907|issue:44945", + "issue:43976|issue:44945", + "issue:43232|issue:44743", + "issue:39401|issue:44488", + "issue:43232|issue:45245", + "issue:42907|issue:43937", + "issue:43408|issue:43475", + "issue:41628|issue:45278", + "issue:43784|issue:45600", + "issue:44625|issue:44829", + "issue:44360|issue:44485", + "issue:43116|issue:45200", + "issue:39401|issue:44521", + "issue:43122|issue:44779", + "issue:29127|issue:30990", + "issue:44038|issue:44297", + "issue:44261|issue:44373", + "issue:44038|issue:44295", + "issue:42371|issue:42831", + "issue:42907|issue:44964", + "issue:36296|issue:43116", + "issue:44038|issue:44222", + "issue:42907|issue:43452", + "issue:43992|issue:44704" + ], + "prepared_review_unit_hash": "54128892aaae869e6a6ccd91519a8c90862d6ed7f75e655bce0fcf3457464c93", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 34, + "serialized_chars": 36859, + "estimated_input_tokens": 9215, + "estimated_eval_tokens": 18686 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is highly heterogeneous: the items cover unrelated tokenizer, generation, import, multimodal, training, and model-specific bugs. None of the soft-edge pairs look like the same underlying issue closely enough to merge as duplicates.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43122", + "right": "issue:44521", + "accept": false, + "reason": "Both mention tokenization/chat behavior, but one is a tokenizer-v4/v5 discrepancy and the other is zero assistant masks for multimodal inputs; different code paths and symptoms." + }, + { + "left": "issue:44263", + "right": "issue:44373", + "accept": false, + "reason": "One is a torch.split indexing bug in a model component, the other is a docstring issue for position_ids; not the same bug." + }, + { + "left": "issue:43232", + "right": "issue:45593", + "accept": false, + "reason": "Generation sync/update logic vs D-FINE auxiliary loss handling are unrelated model subsystems." + }, + { + "left": "issue:42886", + "right": "issue:43066", + "accept": false, + "reason": "Offline cache loading failure and wrong tokenizer decoder type are distinct tokenizer issues." + }, + { + "left": "issue:44117", + "right": "issue:44704", + "accept": false, + "reason": "TOKENIZER_MAPPING_NAMES returning None is a registry bug; AutoProcessor not forwarding kwargs to cached_file is an API plumbing bug." + }, + { + "left": "issue:43122", + "right": "issue:44514", + "accept": false, + "reason": "Both involve tokenization, but one is differing tokenization outputs across versions and the other is a batched apply_chat_template crash with padding=False." + }, + { + "left": "issue:30990", + "right": "issue:33357", + "accept": false, + "reason": "Sentence Transformers loading hang and a MacOS bus error with a CLIP model are unrelated runtime failures." + }, + { + "left": "issue:42371", + "right": "issue:44263", + "accept": false, + "reason": "TF32 configuration guidance and a torch.split return-value bug are unrelated." + }, + { + "left": "issue:44295", + "right": "issue:44297", + "accept": false, + "reason": "Reading position_ids after buffer registration and tokenizer_class mismatch on save_pretrained are separate save/load issues." + }, + { + "left": "issue:44704", + "right": "issue:45290", + "accept": false, + "reason": "Both touch chat/template flows, but one is cached_file kwargs forwarding and the other is a crash on assistant tool-call messages; different failure points." + }, + { + "left": "issue:42907", + "right": "issue:44945", + "accept": false, + "reason": "Saving dequantized Ministral/Devstral models and incorrect output under pipeline parallelism are unrelated." + }, + { + "left": "issue:43976", + "right": "issue:44945", + "accept": false, + "reason": "Python-version compatibility failure and pipeline-parallel output corruption are not the same bug." + }, + { + "left": "issue:43232", + "right": "issue:44743", + "accept": false, + "reason": "Both involve generation/cache internals, but one is sync_gpus update handling and the other is recurrent-state reset in modular_qwen3_5.py; different concrete code paths." + }, + { + "left": "issue:39401", + "right": "issue:44488", + "accept": false, + "reason": "Wrong offset_mapping for Qwen3 tokenizer and failure to load cjvt/sleng-bert are distinct tokenizer problems." + }, + { + "left": "issue:43232", + "right": "issue:45245", + "accept": false, + "reason": "Generation kwargs update after sync_gpus is unrelated to the 2^24 categories runtime error." + }, + { + "left": "issue:42907", + "right": "issue:43937", + "accept": false, + "reason": "Dequantized model save failure and invalid GenerationConfig for GLM-5 are unrelated." + }, + { + "left": "issue:43408", + "right": "issue:43475", + "accept": false, + "reason": "Both are SAM 3 Video related, but one is a model-type warning and the other is a missing attribute on Sam3VisionEncoderOutput; not the same bug." + }, + { + "left": "issue:41628", + "right": "issue:45278", + "accept": false, + "reason": "AutoImageProcessor import failure is a specific symbol-export problem; the other reports many import errors after an upgrade and is much broader." + }, + { + "left": "issue:43784", + "right": "issue:45600", + "accept": false, + "reason": "NameError importing sentence-transformers and auto_mappings references to removed Sam3LiteText configs are unrelated import/compatibility failures." + }, + { + "left": "issue:44625", + "right": "issue:44829", + "accept": false, + "reason": "num_labels propagation in Qwen3.5 and flash_attention_3 degenerate training are different model/configuration bugs." + }, + { + "left": "issue:44360", + "right": "issue:44485", + "accept": false, + "reason": "Missing ReLU in a DSA indexer and GLM-5 RoPE implementation are unrelated architectural issues." + }, + { + "left": "issue:43116", + "right": "issue:45200", + "accept": false, + "reason": "Empty multi-label results in an example script and Gemma 4 mm_token_type_ids defaulting are unrelated application bugs." + }, + { + "left": "issue:39401", + "right": "issue:44521", + "accept": false, + "reason": "Tokenizer offset mapping bug and multimodal assistant_mask zeroing are different failures." + }, + { + "left": "issue:43122", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer regressions in v5, but they affect different models and behaviors; not enough to treat as one duplicate bug." + }, + { + "left": "issue:29127", + "right": "issue:30990", + "accept": false, + "reason": "LayoutLMv3 error-message clarity and Sentence Transformers loading hang have no substantive overlap." + }, + { + "left": "issue:44038", + "right": "issue:44297", + "accept": false, + "reason": "Qwen3-VL-Moe bug and tokenizer_class mismatch on save_pretrained are unrelated." + }, + { + "left": "issue:44261", + "right": "issue:44373", + "accept": false, + "reason": "A numerical precision/config issue in MLA q_a_layernorm is not the same as a wrong docstring for position_ids." + }, + { + "left": "issue:44038", + "right": "issue:44222", + "accept": false, + "reason": "Both mention MOE/FP8-adjacent topics, but one is a Qwen3-VL-Moe load bug and the other is FP8 save_pretrained behavior; different concrete problems." + }, + { + "left": "issue:42907", + "right": "issue:43452", + "accept": false, + "reason": "Saving dequantized models and gguf_file breaking from_pretrained are distinct model-loading/saving bugs." + }, + { + "left": "issue:43992", + "right": "issue:44704", + "accept": false, + "reason": "Missing embed_tokens.weight for UMT5Encoder and AutoProcessor kwargs forwarding are unrelated from_pretrained 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": 13, + "review_unit_index": 36, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:22355", + "issue:29127", + "issue:33453", + "issue:38617", + "issue:39401", + "issue:42222", + "issue:42371", + "issue:42673", + "issue:42757", + "issue:42907", + "issue:43064", + "issue:43116", + "issue:43122", + "issue:43278", + "issue:43441", + "issue:43493", + "issue:43673", + "issue:43784", + "issue:43824", + "issue:43825", + "issue:43827", + "issue:43874", + "issue:43906", + "issue:43931", + "issue:43937", + "issue:43976", + "issue:44038", + "issue:44075", + "issue:44117", + "issue:44222", + "issue:44351", + "issue:44485", + "issue:44779", + "issue:44936", + "issue:44945", + "issue:44977", + "issue:45072", + "issue:45083", + "issue:45216", + "issue:45278", + "issue:45341", + "issue:45405", + "issue:45446", + "issue:45478", + "issue:45561", + "issue:45563", + "issue:45588" + ], + "soft_pairs": [ + "issue:45216|issue:45478", + "issue:43824|issue:44351", + "issue:43122|issue:44977", + "issue:42907|issue:44222", + "issue:42757|issue:44351", + "issue:43278|issue:44945", + "issue:43784|issue:45446", + "issue:42222|issue:43441", + "issue:42673|issue:45072", + "issue:38617|issue:45278", + "issue:43064|issue:43673", + "issue:43937|issue:44485", + "issue:22355|issue:29127", + "issue:42371|issue:43874", + "issue:43116|issue:43493", + "issue:44075|issue:44936", + "issue:44222|issue:45478", + "issue:44038|issue:45478", + "issue:43116|issue:43825", + "issue:43976|issue:45446", + "issue:43937|issue:45563", + "issue:39401|issue:44779", + "issue:33453|issue:39401", + "issue:43931|issue:44945", + "issue:45083|issue:45446", + "issue:44117|issue:45588", + "issue:43827|issue:45446", + "issue:43937|issue:44977", + "issue:45341|issue:45561", + "issue:42673|issue:43906", + "issue:45405|issue:45446" + ], + "prepared_review_unit_hash": "787b2d7c324517c2da68777872efb5e3993813c915429ba1b2f7bc6a3fc49af9", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "serialized_chars": 36001, + "estimated_input_tokens": 9001, + "estimated_eval_tokens": 18258 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These are mostly superficially similar bug reports, but they do not describe the same concrete defect or mergeable fix. I found no true duplicate pair among the soft edges, so there is no safe canonical issue/PR for the cluster.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45216", + "right": "issue:45478", + "accept": false, + "reason": "Same model family and version range, but one is a save_pretrained checkpoint regression and the other is a from_pretrained load error; different code paths and symptoms." + }, + { + "left": "issue:43824", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but they concern different missing symbols with different causes." + }, + { + "left": "issue:43122", + "right": "issue:44977", + "accept": false, + "reason": "Tokenizer regression vs flash-attention generation failure; unrelated underlying bugs." + }, + { + "left": "issue:42907", + "right": "issue:44222", + "accept": false, + "reason": "Both involve saving quantized models, but they target different quantization formats and model families." + }, + { + "left": "issue:42757", + "right": "issue:44351", + "accept": false, + "reason": "Different missing imports; no shared failure mechanism beyond generic ImportError." + }, + { + "left": "issue:43278", + "right": "issue:44945", + "accept": false, + "reason": "Training/eval dtype mismatch is not the same defect as wrong outputs under pipeline parallelism." + }, + { + "left": "issue:43784", + "right": "issue:45446", + "accept": false, + "reason": "Sentence-transformers import breakage vs a flex_attention version check bug; unrelated." + }, + { + "left": "issue:42222", + "right": "issue:43441", + "accept": false, + "reason": "Different model families and different failure modes." + }, + { + "left": "issue:42673", + "right": "issue:45072", + "accept": false, + "reason": "VRAM leak in threaded dataloading is unrelated to bfloat16 dtype mismatches." + }, + { + "left": "issue:38617", + "right": "issue:45278", + "accept": false, + "reason": "One is a specific missing import, the other is a broad report of many import errors; too coarse to treat as the same bug." + }, + { + "left": "issue:43064", + "right": "issue:43673", + "accept": false, + "reason": "Wrong optimizer state distribution and missing generation cache are distinct bugs." + }, + { + "left": "issue:43937", + "right": "issue:44485", + "accept": false, + "reason": "GenerationConfig validation failure vs RoPE implementation discussion; not the same concrete issue." + }, + { + "left": "issue:22355", + "right": "issue:29127", + "accept": false, + "reason": "Module import failure and a LayoutLMv3 error-message clarity issue are unrelated." + }, + { + "left": "issue:42371", + "right": "issue:43874", + "accept": false, + "reason": "TF32 settings guidance vs a missing image-patch helper method; different subsystems and bugs." + }, + { + "left": "issue:43116", + "right": "issue:43493", + "accept": false, + "reason": "Example script multi-label output bug vs SigLIP2 implementation discrepancy; not the same defect." + }, + { + "left": "issue:44075", + "right": "issue:44936", + "accept": false, + "reason": "Unused SGD args and train-then-evaluate failure are separate training bugs." + }, + { + "left": "issue:44222", + "right": "issue:45478", + "accept": false, + "reason": "Both mention Qwen3.5/MoE saving/loading, but one is FP8 save_pretrained and the other is a from_pretrained error." + }, + { + "left": "issue:44038", + "right": "issue:45478", + "accept": false, + "reason": "Same broad model area, but one is a vague Qwen3-VL-Moe bug and the other is a specific Qwen3.5 MoE load error." + }, + { + "left": "issue:43116", + "right": "issue:43825", + "accept": false, + "reason": "Example script behavior vs pipeline API error messaging; not the same bug." + }, + { + "left": "issue:43976", + "right": "issue:45446", + "accept": false, + "reason": "Python version compatibility issue vs a PyTorch version-guard bug." + }, + { + "left": "issue:43937", + "right": "issue:45563", + "accept": false, + "reason": "Invalid GenerationConfig and a stale warning on paged generate are unrelated." + }, + { + "left": "issue:39401", + "right": "issue:44779", + "accept": false, + "reason": "Both tokenizer regressions, but they affect different models and different behaviors (offset mapping vs tokenization output)." + }, + { + "left": "issue:33453", + "right": "issue:39401", + "accept": false, + "reason": "Tokenizer loading regression and offset_mapping bug are not the same concrete defect." + }, + { + "left": "issue:43931", + "right": "issue:44945", + "accept": false, + "reason": "Weight-shape mismatch on model load is unrelated to incorrect outputs under pipeline parallelism." + }, + { + "left": "issue:45083", + "right": "issue:45446", + "accept": false, + "reason": "Multimodal feature helper behavior and a flex_attention import/version check are unrelated." + }, + { + "left": "issue:44117", + "right": "issue:45588", + "accept": false, + "reason": "Tokenizer mapping assumption bug vs flash_attention crash on sink-less models; different code paths." + }, + { + "left": "issue:43827", + "right": "issue:45446", + "accept": false, + "reason": "Documentation still referencing pipeline() is unrelated to the flex_attention import guard." + }, + { + "left": "issue:43937", + "right": "issue:44977", + "accept": false, + "reason": "Different GLM-5 generation-config bug vs Qwen3.5 flash-attention generation bug." + }, + { + "left": "issue:45341", + "right": "issue:45561", + "accept": false, + "reason": "A generic testing_utils bug is not the same as a pytest-xdist race on captured_info.txt." + }, + { + "left": "issue:42673", + "right": "issue:43906", + "accept": false, + "reason": "An isolated reproduction of another issue is not itself the same bug as a VRAM leak." + }, + { + "left": "issue:45405", + "right": "issue:45446", + "accept": false, + "reason": "A dependency minimum-version bump issue is unrelated to the AuxRequest flex_attention import guard." + } + ] + }, + "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": 13, + "review_unit_index": 37, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:38617", + "issue:39401", + "issue:41628", + "issue:42175", + "issue:42222", + "issue:42371", + "issue:42617", + "issue:42673", + "issue:43012", + "issue:43066", + "issue:43097", + "issue:43122", + "issue:43408", + "issue:43421", + "issue:43441", + "issue:43450", + "issue:43577", + "issue:43582", + "issue:43673", + "issue:43742", + "issue:43874", + "issue:43931", + "issue:43937", + "issue:43986", + "issue:44117", + "issue:44220", + "issue:44261", + "issue:44263", + "issue:44291", + "issue:44410", + "issue:44483", + "issue:44484", + "issue:44485", + "issue:44493", + "issue:44496", + "issue:44829", + "issue:44933", + "issue:45003", + "issue:45071", + "issue:45081", + "issue:45216", + "issue:45278", + "issue:45310", + "issue:45341", + "issue:45459", + "issue:45464", + "issue:45478", + "issue:45542" + ], + "soft_pairs": [ + "issue:44291|issue:45071", + "issue:39401|issue:43421", + "issue:43450|issue:43986", + "issue:44484|issue:45310", + "issue:44829|issue:45216", + "issue:38617|issue:41628", + "issue:44410|issue:45310", + "issue:44117|issue:45081", + "issue:42673|issue:43582", + "issue:43408|issue:43742", + "issue:42222|issue:45542", + "issue:42673|issue:43577", + "issue:42371|issue:44261", + "issue:43937|issue:44496", + "issue:42175|issue:42222", + "issue:38617|issue:44220", + "issue:43012|issue:43577", + "issue:44483|issue:45464", + "issue:44933|issue:45278", + "issue:42617|issue:45341", + "issue:44484|issue:45478", + "issue:43066|issue:43122", + "issue:43673|issue:45341", + "issue:44410|issue:45478", + "issue:43097|issue:44493", + "issue:42222|issue:45459", + "issue:43874|issue:44261", + "issue:43441|issue:44829", + "issue:43012|issue:43408", + "issue:43986|issue:44484", + "issue:44263|issue:44485", + "issue:41628|issue:45071", + "issue:45071|issue:45542", + "issue:43931|issue:44410", + "issue:45003|issue:45341" + ], + "prepared_review_unit_hash": "b13c14c8e13dac9fb9bd15434edc9d166d64339caf3f7fa3213104e35e601f71", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 35, + "serialized_chars": 37973, + "estimated_input_tokens": 9494, + "estimated_eval_tokens": 19244 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is highly heterogeneous: most items are distinct bug reports spanning tokenizers, model loading, multimodal processors, packaging/import regressions, and API behavior. I don\u2019t see a single underlying defect that cleanly subsumes the whole set.", + "confidence": 0.95, + "canonical_issue_reason": "No single issue cleanly represents the whole cluster; the items are mostly unrelated. If forced to pick a broad umbrella, #45278 is the closest because it describes many import errors after a version upgrade, but it does not actually cover most of the other reports.", + "canonical_pr_reason": null, + "best_issue_reason": "#45278 is the broadest and most recent open issue in the set, so it is the best umbrella candidate for generic import-regression triage, though it is still not a true duplicate target for the rest of the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44291", + "right": "issue:45071", + "accept": false, + "reason": "Both are version-regression loader failures, but one is an init_empty_weights/_is_hf_initialized TypeError and the other is a PretrainedConfig type-checking break; different code paths." + }, + { + "left": "issue:39401", + "right": "issue:43421", + "accept": false, + "reason": "Both involve tokenizers, but one is wrong offset mapping and the other is runtime special-token/post-processor updates; not the same bug." + }, + { + "left": "issue:43450", + "right": "issue:43986", + "accept": false, + "reason": "One is a batched video-processor shape bug; the other is an AutoProcessor crash without torchvision. Different failure modes." + }, + { + "left": "issue:44484", + "right": "issue:45310", + "accept": false, + "reason": "Unrelated issues: max_shard_size behavior versus a Qwen3.5 MoE from_pretrained error." + }, + { + "left": "issue:44829", + "right": "issue:45216", + "accept": false, + "reason": "One is FA3 training degeneration; the other is incorrect checkpoint saving for Qwen3.5. Different concrete problems." + }, + { + "left": "issue:38617", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but they concern different missing symbols and modules." + }, + { + "left": "issue:44410", + "right": "issue:45310", + "accept": false, + "reason": "Different model bugs: missing Qwen3Next projections versus Qwen3.5 MoE loading failure." + }, + { + "left": "issue:44117", + "right": "issue:45081", + "accept": false, + "reason": "Tokenizer internals are involved in both, but one is TOKENIZER_MAPPING_NAMES returning None and the other is a Mistral regex patch crash." + }, + { + "left": "issue:42673", + "right": "issue:43582", + "accept": false, + "reason": "VRAM leak in Qwen3ForCausalLM vs Apple Silicon caching_allocator_warmup TypeError; unrelated." + }, + { + "left": "issue:43408", + "right": "issue:43742", + "accept": false, + "reason": "Different model-loading issues: sam3 type mismatch versus MobileLLM key error." + }, + { + "left": "issue:42222", + "right": "issue:45542", + "accept": false, + "reason": "Vitpose model breakage and a TensorFlow backend-install issue are unrelated." + }, + { + "left": "issue:42673", + "right": "issue:43577", + "accept": false, + "reason": "Both mention memory/dtype concerns, but the VRAM leak and Blip2 dtype loading bug are different code paths." + }, + { + "left": "issue:42371", + "right": "issue:44261", + "accept": false, + "reason": "TF32 API warning and MLA rms_norm_eps precision issue are unrelated." + }, + { + "left": "issue:43937", + "right": "issue:44496", + "accept": false, + "reason": "GenerationConfig validation for GLM-5 versus missing model_type for an unrecognized model are different loader/config problems." + }, + { + "left": "issue:42175", + "right": "issue:42222", + "accept": false, + "reason": "Package extra/backend dependency issue versus a vitpose model regression; no shared underlying bug." + }, + { + "left": "issue:38617", + "right": "issue:44220", + "accept": false, + "reason": "ImportError for a missing config symbol is not the same as an audio feature-extraction failure." + }, + { + "left": "issue:43012", + "right": "issue:43577", + "accept": false, + "reason": "Both touch precision/dtype, but one is a PyTorch warning on compilation and the other is incorrect dtype propagation while loading Blip2." + }, + { + "left": "issue:44483", + "right": "issue:45464", + "accept": false, + "reason": "Both are chat/completions-related, but one is a general request rejection and the other is a streaming inference failure on a specific model." + }, + { + "left": "issue:44933", + "right": "issue:45278", + "accept": false, + "reason": "The latter is a broad import-regression report, but this pair does not establish the same missing symbol or exact failure." + }, + { + "left": "issue:42617", + "right": "issue:45341", + "accept": false, + "reason": "A 3d_parallel runtime issue and a testing_utils bug are unrelated." + }, + { + "left": "issue:44484", + "right": "issue:45478", + "accept": false, + "reason": "Different issues: shard-size behavior versus another Qwen3.5 MoE from_pretrained error report." + }, + { + "left": "issue:43066", + "right": "issue:43122", + "accept": false, + "reason": "Both concern tokenizer behavior across v5, but one is decoder type and the other is tokenization output changes; not the same defect." + }, + { + "left": "issue:43673", + "right": "issue:45341", + "accept": false, + "reason": "Generation cache missing in chunked_prefill is unrelated to a testing utility bug." + }, + { + "left": "issue:44410", + "right": "issue:45478", + "accept": false, + "reason": "Different Qwen3-related loader/model bugs, not the same concrete failure." + }, + { + "left": "issue:43097", + "right": "issue:44493", + "accept": false, + "reason": "One is a removed config flag in v5; the other is unexpected position-id keys. Related theme, but not the same bug." + }, + { + "left": "issue:42222", + "right": "issue:45459", + "accept": false, + "reason": "Vitpose model breakage and tokenizer error hiding when protobuf is absent are unrelated." + }, + { + "left": "issue:43874", + "right": "issue:44261", + "accept": false, + "reason": "Missing image-patch helper in GLM46V versus MLA layernorm epsilon precision issue; different subsystems." + }, + { + "left": "issue:43441", + "right": "issue:44829", + "accept": false, + "reason": "Ministral FlashAttention failure and FA3 degenerate training are different model/attention problems." + }, + { + "left": "issue:43012", + "right": "issue:43408", + "accept": false, + "reason": "Precision-warning behavior and a sam3_video/sam3_tracker type warning are unrelated." + }, + { + "left": "issue:43986", + "right": "issue:44484", + "accept": false, + "reason": "Video processor import/runtime crash versus save_pretrained shard sizing; not the same issue." + }, + { + "left": "issue:44263", + "right": "issue:44485", + "accept": false, + "reason": "torch.split return handling in GlmMoeDsaIndexer is unrelated to GLM-5 RoPE implementation." + }, + { + "left": "issue:41628", + "right": "issue:45071", + "accept": false, + "reason": "AutoImageProcessor import failure and PretrainedConfig type-checking break are different regressions." + }, + { + "left": "issue:45071", + "right": "issue:45542", + "accept": false, + "reason": "PretrainedConfig type checking and TensorFlow backend installation are unrelated." + }, + { + "left": "issue:43931", + "right": "issue:44410", + "accept": false, + "reason": "Qwen3-VL weight-shape mismatch and qwen3next missing projections are different model-loading problems." + }, + { + "left": "issue:45003", + "right": "issue:45341", + "accept": false, + "reason": "Unsafe sys.modules access in modeling_utils is not the same as a testing_utils 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": 13, + "review_unit_index": 38, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:38617", + "issue:42757", + "issue:42886", + "issue:42907", + "issue:43012", + "issue:43064", + "issue:43066", + "issue:43097", + "issue:43335", + "issue:43352", + "issue:43381", + "issue:43408", + "issue:43452", + "issue:43502", + "issue:43531", + "issue:43550", + "issue:43824", + "issue:43825", + "issue:43873", + "issue:43874", + "issue:43906", + "issue:43931", + "issue:43976", + "issue:43986", + "issue:43992", + "issue:44038", + "issue:44062", + "issue:44117", + "issue:44261", + "issue:44263", + "issue:44315", + "issue:44351", + "issue:44368", + "issue:44380", + "issue:44410", + "issue:44484", + "issue:44485", + "issue:44655", + "issue:44704", + "issue:44829", + "issue:44987", + "issue:45071", + "issue:45103", + "issue:45245", + "issue:45341", + "issue:45372", + "issue:45375", + "issue:45588" + ], + "soft_pairs": [ + "issue:44117|issue:44987", + "issue:43986|issue:45341", + "issue:43097|issue:43452", + "issue:43931|issue:44038", + "issue:43335|issue:45071", + "issue:43408|issue:44368", + "issue:43874|issue:44263", + "issue:43976|issue:45071", + "issue:44829|issue:45245", + "issue:43986|issue:45372", + "issue:43064|issue:44315", + "issue:43531|issue:45341", + "issue:38617|issue:42757", + "issue:44261|issue:44485", + "issue:44410|issue:45375", + "issue:44038|issue:44410", + "issue:38617|issue:44351", + "issue:44062|issue:44117", + "issue:43097|issue:45588", + "issue:43986|issue:44117", + "issue:44704|issue:45103", + "issue:43502|issue:43992", + "issue:43097|issue:43873", + "issue:43992|issue:44484", + "issue:43824|issue:43986", + "issue:43066|issue:43906", + "issue:43352|issue:44380", + "issue:43825|issue:44655", + "issue:38617|issue:43097", + "issue:43012|issue:44368", + "issue:43012|issue:43550", + "issue:42886|issue:43381", + "issue:42907|issue:44655" + ], + "prepared_review_unit_hash": "4200dc2148cffb64509de27e2126b29db432f7f4a2d0bcec79102b0fa49b932d", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37583, + "estimated_input_tokens": 9396, + "estimated_eval_tokens": 19048 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: it mixes unrelated Transformers v5 regressions across imports, tokenizer/model loading, multimodal processors, training, and attention backends. None of the proposed soft pairs look like the same underlying bug/change, so no soft edge should be merged.", + "confidence": 0.93, + "canonical_issue_reason": "No single canonical duplicate: the items span many distinct failures and API regressions, so there is no clear one-bug anchor for the whole cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43097 is the strongest representative because it captures a broad v5 breaking-change regression with clear API impact, but it is still not a duplicate target for the rest of the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44117", + "right": "issue:44987", + "accept": false, + "reason": "Tokenizer mapping None vs a specific model-loading failure for physical-intelligence/fast; different code paths and symptoms." + }, + { + "left": "issue:43986", + "right": "issue:45341", + "accept": false, + "reason": "Video-model loading without torchvision vs a small testing_utils bug; unrelated components." + }, + { + "left": "issue:43097", + "right": "issue:43452", + "accept": false, + "reason": "Removed config flag in v5 vs gguf_file handling for AutoTokenizer/AutoModel loading; not the same bug." + }, + { + "left": "issue:43931", + "right": "issue:44038", + "accept": false, + "reason": "Different Qwen3-VL model failures: weight-shape mismatch vs a Qwen3-VL-Moe bug." + }, + { + "left": "issue:43335", + "right": "issue:45071", + "accept": false, + "reason": "SwitchTransformers sparse-layer construction bug vs PretrainedConfig type-checking regression; unrelated." + }, + { + "left": "issue:43408", + "right": "issue:44368", + "accept": false, + "reason": "SAM3 video-type warning vs a Qwen3.5 tie_word_embeddings warning; different models and failure modes." + }, + { + "left": "issue:43874", + "right": "issue:44263", + "accept": false, + "reason": "Missing image-processor method in GLM46V vs torch.split return handling in GlmMoeDsaIndexer; unrelated." + }, + { + "left": "issue:43976", + "right": "issue:45071", + "accept": false, + "reason": "Python-version compatibility problem vs config type checking; not the same underlying issue." + }, + { + "left": "issue:44829", + "right": "issue:45245", + "accept": false, + "reason": "Degenerate training with flash_attention_3 vs categorical cardinality limit error; completely different problems." + }, + { + "left": "issue:43986", + "right": "issue:45372", + "accept": false, + "reason": "Missing torchvision for video processor loading vs mistral_common ReasoningEffort import failure; unrelated." + }, + { + "left": "issue:43064", + "right": "issue:44315", + "accept": false, + "reason": "FSDP2/PEFT optimizer-state corruption vs Liger Kernel not applied with model_init; different training paths." + }, + { + "left": "issue:43531", + "right": "issue:45341", + "accept": false, + "reason": "Qwen3-MoE sliding_window bug vs a testing_utils issue; no shared bug." + }, + { + "left": "issue:38617", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but for different symbols/modules and unrelated dependency paths." + }, + { + "left": "issue:44261", + "right": "issue:44485", + "accept": false, + "reason": "MLA q_a_layernorm epsilon/config precision issue vs GLM-5 RoPE implementation; distinct model internals." + }, + { + "left": "issue:44410", + "right": "issue:45375", + "accept": false, + "reason": "Missing projections in qwen3next vs missing deepstack_visual_indexes in Qwen3_5MoeVisionConfig; different configs and symptoms." + }, + { + "left": "issue:44038", + "right": "issue:44410", + "accept": false, + "reason": "Qwen3-VL-Moe issue vs qwen3next projection bug; different architectures and failures." + }, + { + "left": "issue:38617", + "right": "issue:44351", + "accept": false, + "reason": "layer_type_validation import error vs HybridCache import error; separate missing exports." + }, + { + "left": "issue:44062", + "right": "issue:44117", + "accept": false, + "reason": "AddedToken special-argument conflict vs TOKENIZER_MAPPING_NAMES returning None; different tokenizer code paths." + }, + { + "left": "issue:43097", + "right": "issue:45588", + "accept": false, + "reason": "v5 config removal vs flash_attention sink-less crash; unrelated subsystems." + }, + { + "left": "issue:43986", + "right": "issue:44117", + "accept": false, + "reason": "Video processor loading without torchvision vs tokenizer mapping None; unrelated." + }, + { + "left": "issue:44704", + "right": "issue:45103", + "accept": false, + "reason": "AutoProcessor kwargs not forwarded to cached_file vs auto_docstring crash with future annotations; unrelated utility layers." + }, + { + "left": "issue:43502", + "right": "issue:43992", + "accept": false, + "reason": "local_files_only still causing network requests vs missing embed_tokens.weight in UMT5Encoder; different loading bugs." + }, + { + "left": "issue:43097", + "right": "issue:43873", + "accept": false, + "reason": "API removal in v5 vs offloading/quantization behavior; not the same issue." + }, + { + "left": "issue:43992", + "right": "issue:44484", + "accept": false, + "reason": "Missing checkpoint weight in UMT5Encoder vs max_shard_size question; unrelated save/load behavior." + }, + { + "left": "issue:43824", + "right": "issue:43986", + "accept": false, + "reason": "Qwen2_5_VL import error vs video-model loading crash without torchvision; different models and root causes." + }, + { + "left": "issue:43066", + "right": "issue:43906", + "accept": false, + "reason": "Wrong tokenizer decoder type vs an isolated reproduction of a separate issue; no concrete shared bug." + }, + { + "left": "issue:43352", + "right": "issue:44380", + "accept": false, + "reason": "Flash Attention 2 unsupported gate vs GPT2 attention-scaling ignored under SDPA/FlashAttention; different backend problems." + }, + { + "left": "issue:43825", + "right": "issue:44655", + "accept": false, + "reason": "Pipeline translation-task error vs inability to save Pipeline objects; different pipeline concerns." + }, + { + "left": "issue:38617", + "right": "issue:43097", + "accept": false, + "reason": "ImportError for layer_type_validation vs removed tie_embeddings_and_encoder_decoder; unrelated regressions." + }, + { + "left": "issue:43012", + "right": "issue:44368", + "accept": false, + "reason": "bfloat16 compile warning vs tie_word_embeddings warning during Qwen3.5 LoRA; same general warning category, but not the same bug." + }, + { + "left": "issue:43012", + "right": "issue:43550", + "accept": false, + "reason": "PyTorch precision warning during compile vs Bamba SDPA compile failure; different failure modes." + }, + { + "left": "issue:42886", + "right": "issue:43381", + "accept": false, + "reason": "Offline tokenizer cache loading vs gradient checkpointing in eval mode; unrelated." + }, + { + "left": "issue:42907", + "right": "issue:44655", + "accept": false, + "reason": "Failed save of dequantized Ministrals vs saving Pipeline objects; both involve save_pretrained, but distinct object types and causes." + } + ] + }, + "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": 13, + "review_unit_index": 39, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:36010", + "issue:36683", + "issue:38617", + "issue:42757", + "issue:42994", + "issue:43012", + "issue:43064", + "issue:43066", + "issue:43208", + "issue:43299", + "issue:43352", + "issue:43475", + "issue:43502", + "issue:43525", + "issue:43526", + "issue:43550", + "issue:43582", + "issue:43618", + "issue:43756", + "issue:43761", + "issue:43824", + "issue:43867", + "issue:43901", + "issue:43937", + "issue:43976", + "issue:43992", + "issue:44038", + "issue:44077", + "issue:44188", + "issue:44230", + "issue:44242", + "issue:44263", + "issue:44380", + "issue:44483", + "issue:44485", + "issue:44492", + "issue:44514", + "issue:44655", + "issue:44683", + "issue:44938", + "issue:45216", + "issue:45290", + "issue:45310", + "issue:45381", + "issue:45440", + "issue:45478", + "issue:45479", + "issue:45593" + ], + "soft_pairs": [ + "issue:43208|issue:43550", + "issue:44380|issue:45479", + "issue:43352|issue:43976", + "issue:43064|issue:44380", + "issue:43208|issue:43526", + "issue:44483|issue:44514", + "issue:43618|issue:44380", + "issue:36683|issue:43582", + "issue:43618|issue:43761", + "issue:43012|issue:44683", + "issue:44483|issue:45290", + "issue:44038|issue:44230", + "issue:42757|issue:43824", + "issue:44483|issue:45381", + "issue:43299|issue:43867", + "issue:38617|issue:43502", + "issue:43901|issue:44655", + "issue:43756|issue:44485", + "issue:42994|issue:44655", + "issue:43867|issue:45216", + "issue:36683|issue:43475", + "issue:44655|issue:45478", + "issue:43352|issue:43937", + "issue:43066|issue:45381", + "issue:44077|issue:44380", + "issue:43064|issue:44492", + "issue:44263|issue:45440", + "issue:43976|issue:44938", + "issue:36683|issue:44077", + "issue:36683|issue:43525", + "issue:36010|issue:42757", + "issue:44188|issue:44380", + "issue:43618|issue:45216", + "issue:43352|issue:45593", + "issue:43992|issue:45310", + "issue:36683|issue:44242" + ], + "prepared_review_unit_hash": "868e9c0ac85c00d2176448438500caf85a0fa5280a7fb9b3d4a3ae0bfa1c11a8", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 36, + "serialized_chars": 38123, + "estimated_input_tokens": 9531, + "estimated_eval_tokens": 19318 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly unrelated Transformers issues; the only clear duplicate pair is the Qwen3.5 MoE from_pretrained regression. No pull requests were present.", + "confidence": 0.89, + "canonical_issue_reason": "issue:45310 is the earlier, more specific report of the shared Qwen3.5 MoE from_pretrained failure, and issue:45478 reads as a later duplicate of the same version-regression.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45310 is the best cluster representative because it captures the concrete bug shape and version scope most clearly, with a near-identical follow-up report duplicating it.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43208", + "right": "issue:43550", + "accept": false, + "reason": "Different models and failure modes: xLSTM training bugs vs Bamba torch.compile/SDPA issue." + }, + { + "left": "issue:44380", + "right": "issue:45479", + "accept": false, + "reason": "Both are model bugs, but one is GPT-2 attention scaling and the other is a sequence-classification zero-loss bug; different code paths." + }, + { + "left": "issue:43352", + "right": "issue:43976", + "accept": false, + "reason": "Unrelated problems: Flash Attention 2 support for Nemotron vs Python-version compatibility." + }, + { + "left": "issue:43064", + "right": "issue:44380", + "accept": false, + "reason": "FSDP2 optimizer-state corruption is unrelated to GPT-2 attention scaling under SDPA/FlashAttention." + }, + { + "left": "issue:43208", + "right": "issue:43526", + "accept": false, + "reason": "xLSTM training bugs and BeitImageProcessorFast label reduction are different subsystems and symptoms." + }, + { + "left": "issue:44483", + "right": "issue:44514", + "accept": false, + "reason": "Both touch chat-related APIs, but one is request acceptance and the other is batched chat template padding behavior." + }, + { + "left": "issue:43618", + "right": "issue:44380", + "accept": false, + "reason": "CLIP output attentions regression is not the same bug as GPT-2 attention scaling being ignored." + }, + { + "left": "issue:36683", + "right": "issue:43582", + "accept": false, + "reason": "Gemma3Config missing vocab_size and Apple Silicon allocator TypeError are unrelated." + }, + { + "left": "issue:43618", + "right": "issue:43761", + "accept": false, + "reason": "Both involve CLIP regressions, but one is missing attentions assignment and the other is hidden_states=None; not the same defect." + }, + { + "left": "issue:43012", + "right": "issue:44683", + "accept": false, + "reason": "A warning about bf16 precision is distinct from a compiled flex_attention failure on torch>=2.9." + }, + { + "left": "issue:44483", + "right": "issue:45290", + "accept": false, + "reason": "Different chat-template/API failures: request validation vs assistant tool-call content handling." + }, + { + "left": "issue:44038", + "right": "issue:44230", + "accept": false, + "reason": "Both mention Qwen VL/MoE, but one is broad v5 loading support and the other is fp8 inference support; different requests." + }, + { + "left": "issue:42757", + "right": "issue:43824", + "accept": false, + "reason": "Both are import errors, but for different missing symbols and likely different fixes." + }, + { + "left": "issue:44483", + "right": "issue:45381", + "accept": false, + "reason": "Chat/completions request handling is unrelated to Qwen2.5-VL vision_position_ids generation." + }, + { + "left": "issue:43299", + "right": "issue:43867", + "accept": false, + "reason": "Qwen3VL-Moe loading breakage and sorted-state_dict load error are not the same underlying issue." + }, + { + "left": "issue:38617", + "right": "issue:43502", + "accept": false, + "reason": "ImportError from configuration_utils and local_files_only network leakage are different bug classes." + }, + { + "left": "issue:43901", + "right": "issue:44655", + "accept": false, + "reason": "Documentation mismatch for return_all_scores is unrelated to saving Pipeline objects." + }, + { + "left": "issue:43756", + "right": "issue:44485", + "accept": false, + "reason": "Smollm3 RoPE layer dropout and GLM-5 RoPE implementation discussion are different model-specific issues." + }, + { + "left": "issue:42994", + "right": "issue:44655", + "accept": false, + "reason": "Quantized model saving failure is not the same as Pipeline save_pretrained serialization failure." + }, + { + "left": "issue:43867", + "right": "issue:45216", + "accept": false, + "reason": "Both concern loading/saving, but one is sorted state_dict loading and the other is Qwen3.5 checkpoint correctness on save_pretrained." + }, + { + "left": "issue:36683", + "right": "issue:43475", + "accept": false, + "reason": "Gemma3Config missing vocab_size and Sam3VisionEncoderOutput missing fpn_position_embeddings are different attribute errors." + }, + { + "left": "issue:44655", + "right": "issue:45478", + "accept": false, + "reason": "Pipeline serialization and Qwen3.5 MoE from_pretrained are unrelated." + }, + { + "left": "issue:43352", + "right": "issue:43937", + "accept": false, + "reason": "Flash Attention support for Nemotron and GLM-5 GenerationConfig validation are different issues." + }, + { + "left": "issue:43066", + "right": "issue:45381", + "accept": false, + "reason": "Tokenizer decoder type mismatch is unrelated to Qwen2.5-VL video position IDs." + }, + { + "left": "issue:44077", + "right": "issue:44380", + "accept": false, + "reason": "A patchtsmixer post_init policy issue is unrelated to GPT-2 attention scaling under SDPA/FlashAttention." + }, + { + "left": "issue:43064", + "right": "issue:44492", + "accept": false, + "reason": "Optimizer-state corruption and a typo in cache strategies are not the same bug." + }, + { + "left": "issue:44263", + "right": "issue:45440", + "accept": false, + "reason": "Different MoE-related code paths and models; not the same concrete defect." + }, + { + "left": "issue:43976", + "right": "issue:44938", + "accept": false, + "reason": "Both are environment compatibility reports, but for different Python versions and failure causes." + }, + { + "left": "issue:43618", + "right": "issue:45216", + "accept": false, + "reason": "CLIP attentions regression and Qwen3.5 save_pretrained corruption are unrelated." + }, + { + "left": "issue:43352", + "right": "issue:45593", + "accept": false, + "reason": "Flash Attention support for Nemotron and D-FINE auxiliary-loss logic are different subsystems." + }, + { + "left": "issue:43992", + "right": "issue:45310", + "accept": false, + "reason": "UMT5 missing embed_tokens.weight and Qwen3.5 MoE from_pretrained are unrelated model-loading bugs." + }, + { + "left": "issue:36683", + "right": "issue:44242", + "accept": false, + "reason": "Gemma3Config attribute error and missing load-balancing loss are different problems." + }, + { + "left": "issue:45310", + "right": "issue:45478", + "accept": true, + "reason": "Same concrete Qwen3.5 MoE from_pretrained failure with the same version regression; these look like duplicates that one fix could resolve together." + }, + { + "left": "issue:44188", + "right": "issue:44380", + "accept": false, + "reason": "Both involve attention/compile behavior, but one is divergent kernels from branching under torch.compile and the other is scaling config being ignored in backend selection." + }, + { + "left": "issue:36010", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but for different exports from different modules and no shared concrete bug path." + } + ] + }, + "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": 13, + "review_unit_index": 40, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:28282", + "issue:33453", + "issue:36296", + "issue:36683", + "issue:41669", + "issue:42548", + "issue:42890", + "issue:43010", + "issue:43064", + "issue:43065", + "issue:43232", + "issue:43352", + "issue:43502", + "issue:43575", + "issue:43618", + "issue:43723", + "issue:43867", + "issue:43976", + "issue:43992", + "issue:44062", + "issue:44075", + "issue:44077", + "issue:44112", + "issue:44222", + "issue:44246", + "issue:44351", + "issue:44355", + "issue:44360", + "issue:44387", + "issue:44484", + "issue:44485", + "issue:44556", + "issue:44749", + "issue:44857", + "issue:44938", + "issue:44964", + "issue:45071", + "issue:45125", + "issue:45278", + "issue:45341", + "issue:45357", + "issue:45375", + "issue:45381", + "issue:45440", + "issue:45478", + "issue:45561", + "issue:45588", + "issue:45600" + ], + "soft_pairs": [ + "issue:43010|issue:45278", + "issue:36683|issue:43352", + "issue:41669|issue:44246", + "issue:43867|issue:45375", + "issue:36683|issue:43064", + "issue:42890|issue:45561", + "issue:43992|issue:45478", + "issue:44938|issue:45071", + "issue:43867|issue:45357", + "issue:43010|issue:43976", + "issue:44938|issue:45381", + "issue:44360|issue:45440", + "issue:43618|issue:44077", + "issue:36296|issue:43575", + "issue:43867|issue:44484", + "issue:43618|issue:45588", + "issue:43618|issue:44857", + "issue:28282|issue:33453", + "issue:42890|issue:44964", + "issue:42890|issue:45600", + "issue:42890|issue:44112", + "issue:43010|issue:44075", + "issue:43502|issue:44062", + "issue:43723|issue:44556", + "issue:42890|issue:45341", + "issue:44222|issue:45125", + "issue:44387|issue:44556", + "issue:43010|issue:43065", + "issue:43010|issue:43232", + "issue:42548|issue:44351", + "issue:45125|issue:45478", + "issue:44355|issue:44749", + "issue:45125|issue:45375", + "issue:43502|issue:44485" + ], + "prepared_review_unit_hash": "bc45c234b685a155e7aad7879932f23317729e6cea89d949a042066af2ea63f3", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37341, + "estimated_input_tokens": 9336, + "estimated_eval_tokens": 18928 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is mostly a grab bag of unrelated Transformers issues. The only clear soft duplicate is the import-time slowdown pair; most other pairs share a subsystem or release version but not the same concrete bug.", + "confidence": 0.6, + "canonical_issue_reason": "issue:41669 is the most concrete root-cause report for the import slowdown; issue:44246 is the vaguer symptom report and fits as the duplicate.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:41669 is the best representative because it identifies the specific cause and is actionable, unlike the broader symptom-only report.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43010", + "right": "issue:45278", + "accept": false, + "reason": "Both touch import/generation ergonomics, but one is a cache no_grad concern and the other is a broad import-regression report; different bugs." + }, + { + "left": "issue:36683", + "right": "issue:43352", + "accept": false, + "reason": "Gemma3 config vocab_size and Nemotron flash-attn support are unrelated model-specific failures." + }, + { + "left": "issue:41669", + "right": "issue:44246", + "accept": true, + "reason": "Both describe the same import-time slowdown; 41669 gives the concrete cause (model import *) and 44246 reports the symptom." + }, + { + "left": "issue:43867", + "right": "issue:45375", + "accept": false, + "reason": "One is a state_dict loading error, the other is a Qwen3.5 vision config field being dropped; not the same code path." + }, + { + "left": "issue:36683", + "right": "issue:43064", + "accept": false, + "reason": "Different failures: missing Gemma3Config attribute vs FSDP2/PEFT optimizer-state mismatch." + }, + { + "left": "issue:42890", + "right": "issue:45561", + "accept": false, + "reason": "Both are test-related, but one is missing set_seed coverage and the other is an xdist file race; distinct bugs." + }, + { + "left": "issue:43992", + "right": "issue:45478", + "accept": false, + "reason": "Different Qwen/UMT5 load failures with different symptoms and likely different causes." + }, + { + "left": "issue:44938", + "right": "issue:45071", + "accept": false, + "reason": "Both are version-related regressions, but one is Python 3.14 loading and the other is PretrainedConfig type checking." + }, + { + "left": "issue:43867", + "right": "issue:45357", + "accept": false, + "reason": "A state_dict sorting/load issue is not the same as incorrect visual encoder keys in save_pretrained." + }, + { + "left": "issue:43010", + "right": "issue:43976", + "accept": false, + "reason": "No-no_grad cache update and Python-version support failure are unrelated." + }, + { + "left": "issue:44938", + "right": "issue:45381", + "accept": false, + "reason": "Python 3.14 import/load failure and Qwen2.5-VL video position ids are different problems." + }, + { + "left": "issue:44360", + "right": "issue:45440", + "accept": false, + "reason": "DSA indexer/ReLU discussion and DeepSeekV3MoE divergence are unrelated model implementation issues." + }, + { + "left": "issue:43618", + "right": "issue:44077", + "accept": false, + "reason": "CLIPOutput attentions and patchtsmixer post_init policy do not match the same bug." + }, + { + "left": "issue:36296", + "right": "issue:43575", + "accept": false, + "reason": "Tensor-parallel training bug vs TP OOM on loading a large model: related area, but not the same underlying issue." + }, + { + "left": "issue:43867", + "right": "issue:44484", + "accept": false, + "reason": "Loading error from sorted state_dict is unrelated to max_shard_size behavior in save_pretrained." + }, + { + "left": "issue:43618", + "right": "issue:45588", + "accept": false, + "reason": "Different crash sites and causes: CLIP attentions vs flash_attention on sink-less models." + }, + { + "left": "issue:43618", + "right": "issue:44857", + "accept": false, + "reason": "Different issues in different code paths; not duplicates." + }, + { + "left": "issue:28282", + "right": "issue:33453", + "accept": false, + "reason": "AutoModel PyTorch import error and tokenizer loading regression are unrelated." + }, + { + "left": "issue:42890", + "right": "issue:44964", + "accept": false, + "reason": "Test seeding failures and Phi-4 multimodal model loading are unrelated." + }, + { + "left": "issue:42890", + "right": "issue:45600", + "accept": false, + "reason": "A test seeding problem is not the same as stale auto_mappings references breaking CI." + }, + { + "left": "issue:42890", + "right": "issue:44112", + "accept": false, + "reason": "Both are CI/test failures, but the specific causes differ." + }, + { + "left": "issue:43010", + "right": "issue:44075", + "accept": false, + "reason": "Cache update no_grad and SGD args ignored are different behavior bugs." + }, + { + "left": "issue:43502", + "right": "issue:44062", + "accept": false, + "reason": "Offline download enforcement and AddedToken argument handling are unrelated tokenizer/loading issues." + }, + { + "left": "issue:43723", + "right": "issue:44556", + "accept": false, + "reason": "Tokenizer loading in v5 and checkpoint reload incompatibility after upgrade are not the same concrete bug." + }, + { + "left": "issue:42890", + "right": "issue:45341", + "accept": false, + "reason": "Missing set_seed in tests and a testing_utils bug are too different without clearer evidence." + }, + { + "left": "issue:44222", + "right": "issue:45125", + "accept": false, + "reason": "FP8 save_pretrained for MoE and missing _tp_plan for Qwen3_5Moe are different features/failures." + }, + { + "left": "issue:44387", + "right": "issue:44556", + "accept": false, + "reason": "Quantization memory OOM and checkpoint reload incompatibility are unrelated." + }, + { + "left": "issue:43010", + "right": "issue:43065", + "accept": false, + "reason": "Cache/layer no_grad and Sam3PixelDecoder dummy Conv2d are unrelated implementation issues." + }, + { + "left": "issue:43010", + "right": "issue:43232", + "accept": false, + "reason": "Generic generation kwargs handling and cache update no_sync behavior are different bugs." + }, + { + "left": "issue:42548", + "right": "issue:44351", + "accept": false, + "reason": "Cannot import PreTrainedModel and cannot import HybridCache are distinct import/export regressions." + }, + { + "left": "issue:45125", + "right": "issue:45478", + "accept": false, + "reason": "Both involve Qwen3.5 MoE, but one is tensor-parallel metadata and the other is a from_pretrained loading error." + }, + { + "left": "issue:44355", + "right": "issue:44749", + "accept": false, + "reason": "Compiled Python file errors and a performance regression after upgrade are not the same issue." + }, + { + "left": "issue:45125", + "right": "issue:45375", + "accept": false, + "reason": "Missing _tp_plan and missing deepstack_visual_indexes are different Qwen3.5 model/config problems." + }, + { + "left": "issue:43502", + "right": "issue:44485", + "accept": false, + "reason": "Offline API blocking and GLM-5 RoPE implementation are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The only accepted soft edge, issue:41669 vs issue:44246, is well supported by the titles and the import-slowdown theme. The remaining rejections read as cautious and do not overclaim duplicates. No mergeability concerns apply since these are issue pairs, not PR pairs." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 41, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:30333", + "issue:30990", + "issue:31795", + "issue:33453", + "issue:34689", + "issue:36296", + "issue:38617", + "issue:41628", + "issue:41669", + "issue:42548", + "issue:42757", + "issue:42831", + "issue:43010", + "issue:43299", + "issue:43502", + "issue:43526", + "issue:43576", + "issue:43673", + "issue:43824", + "issue:43827", + "issue:43874", + "issue:43901", + "issue:44038", + "issue:44075", + "issue:44222", + "issue:44230", + "issue:44261", + "issue:44273", + "issue:44315", + "issue:44351", + "issue:44355", + "issue:44360", + "issue:44368", + "issue:44393", + "issue:44485", + "issue:44492", + "issue:44556", + "issue:44623", + "issue:44655", + "issue:44871", + "issue:44908", + "issue:44961", + "issue:45003", + "issue:45071", + "issue:45125", + "issue:45230", + "issue:45468", + "issue:45542" + ], + "soft_pairs": [ + "issue:30990|issue:31795", + "issue:44075|issue:44871", + "issue:44315|issue:44360", + "issue:30333|issue:33453", + "issue:43010|issue:44368", + "issue:43502|issue:44222", + "issue:43299|issue:44556", + "issue:43502|issue:44961", + "issue:44222|issue:44230", + "issue:44355|issue:44655", + "issue:30333|issue:36296", + "issue:44355|issue:45071", + "issue:42831|issue:43874", + "issue:33453|issue:34689", + "issue:42757|issue:43576", + "issue:33453|issue:36296", + "issue:43827|issue:44961", + "issue:43576|issue:45071", + "issue:43576|issue:43824", + "issue:38617|issue:43576", + "issue:43673|issue:44492", + "issue:44961|issue:45468", + "issue:31795|issue:38617", + "issue:43576|issue:44351", + "issue:41628|issue:42548", + "issue:44908|issue:44961", + "issue:44485|issue:44961", + "issue:36296|issue:43901", + "issue:36296|issue:43526", + "issue:41628|issue:44355", + "issue:44273|issue:45003", + "issue:44261|issue:44360", + "issue:44623|issue:45230", + "issue:44273|issue:45542", + "issue:43576|issue:44556", + "issue:44038|issue:45125", + "issue:44393|issue:45071", + "issue:41669|issue:43673" + ], + "prepared_review_unit_hash": "43c46936dabf8bac77d0fe6b71c11ebd2f6c5deb41751d62bc61df348f5c09ed", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 38, + "serialized_chars": 38352, + "estimated_input_tokens": 9588, + "estimated_eval_tokens": 19432 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is highly heterogeneous: it mixes unrelated import errors, model-loading regressions, docs issues, cache/FP8/tensor-parallel bugs, and CLI/runtime problems. I don\u2019t see any safe duplicate merges, and there are no PRs to evaluate.", + "confidence": 0.19, + "canonical_issue_reason": "If forced to pick one, issue 43576 is the broadest v5 regression-style report and the closest thing to a generic umbrella issue, but it does not \u05d1\u05d0\u05de\u05ea subsume the rest of the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43576 is the best single representative only because it is broad and version-gated; however, the overall set is too mixed for a strong canonical issue.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:30990", + "right": "issue:31795", + "accept": false, + "reason": "Unrelated symptoms: a loading hang vs documentation confusion about model.forward arguments." + }, + { + "left": "issue:44075", + "right": "issue:44871", + "accept": false, + "reason": "Different bugs in different areas: SGD optimizer arguments vs Gemma EOS token configuration." + }, + { + "left": "issue:44315", + "right": "issue:44360", + "accept": false, + "reason": "Liger Kernel application bug and DSA indexer ReLU complaint are unrelated." + }, + { + "left": "issue:30333", + "right": "issue:33453", + "accept": false, + "reason": "MLflow job-status reporting and tokenizer loading regression are different code paths." + }, + { + "left": "issue:43010", + "right": "issue:44368", + "accept": false, + "reason": "Cache update no_grad issue is unrelated to tie_word_embeddings warnings." + }, + { + "left": "issue:43502", + "right": "issue:44222", + "accept": false, + "reason": "local_files_only network leakage and FP8 save_pretrained are separate failures." + }, + { + "left": "issue:43299", + "right": "issue:44556", + "accept": false, + "reason": "Both are loading regressions, but they involve different models and failure modes; not the same concrete bug." + }, + { + "left": "issue:43502", + "right": "issue:44961", + "accept": false, + "reason": "API requests despite local_files_only is unrelated to the racoon issue." + }, + { + "left": "issue:44222", + "right": "issue:44230", + "accept": false, + "reason": "Same FP8/MoE theme, but one is save_pretrained behavior and the other is inference support; too different to merge." + }, + { + "left": "issue:44355", + "right": "issue:44655", + "accept": false, + "reason": "Compiled Python file errors and Pipeline save_pretrained are unrelated." + }, + { + "left": "issue:30333", + "right": "issue:36296", + "accept": false, + "reason": "MLflow reporting failure and tensor parallel training bug do not share the same underlying cause." + }, + { + "left": "issue:44355", + "right": "issue:45071", + "accept": false, + "reason": "Compiled-file runtime errors are unrelated to PretrainedConfig type checking regressions." + }, + { + "left": "issue:42831", + "right": "issue:43874", + "accept": false, + "reason": "FineGrainedFP8 accuracy issue and missing image-processor method are different bugs." + }, + { + "left": "issue:33453", + "right": "issue:34689", + "accept": false, + "reason": "Both are loading-related, but one is a tokenizer regression and the other is a specific Llama 3.2 vision model-loading breakage." + }, + { + "left": "issue:42757", + "right": "issue:43576", + "accept": false, + "reason": "ImportError from huggingface_hub and broken transformers env command are separate issues." + }, + { + "left": "issue:33453", + "right": "issue:36296", + "accept": false, + "reason": "Tokenizer loading regression and tensor-parallel training bug are unrelated." + }, + { + "left": "issue:43827", + "right": "issue:44961", + "accept": false, + "reason": "Docs still referencing pipeline() is unrelated to racoon." + }, + { + "left": "issue:43576", + "right": "issue:45071", + "accept": false, + "reason": "Both are v5 regressions, but one is a broken CLI command and the other is a type-checking issue; not the same code path." + }, + { + "left": "issue:43576", + "right": "issue:43824", + "accept": false, + "reason": "Broken env command and missing Qwen2_5_VLForConditionalGeneration import are different failures." + }, + { + "left": "issue:38617", + "right": "issue:43576", + "accept": false, + "reason": "Missing layer_type_validation import and broken env command are unrelated import/CLI problems." + }, + { + "left": "issue:43673", + "right": "issue:44492", + "accept": false, + "reason": "Chunked_prefill cache missing and a typo in cache strategies are not the same bug." + }, + { + "left": "issue:44961", + "right": "issue:45468", + "accept": false, + "reason": "A placeholder racoon issue is unrelated to Gemma-4 audio positional encoding." + }, + { + "left": "issue:31795", + "right": "issue:38617", + "accept": false, + "reason": "Documentation confusion and an ImportError are different issue types with different fixes." + }, + { + "left": "issue:43576", + "right": "issue:44351", + "accept": false, + "reason": "Broken env command and missing HybridCache import are both v5-related but not the same concrete defect." + }, + { + "left": "issue:41628", + "right": "issue:42548", + "accept": false, + "reason": "Both are import errors, but they concern different exported symbols and likely different loader paths." + }, + { + "left": "issue:44908", + "right": "issue:44961", + "accept": false, + "reason": "Scheduler kwargs bug and racoon are unrelated." + }, + { + "left": "issue:44485", + "right": "issue:44961", + "accept": false, + "reason": "GLM-5 RoPE implementation discussion is unrelated to racoon." + }, + { + "left": "issue:36296", + "right": "issue:43901", + "accept": false, + "reason": "Tensor parallel training bug and docs mentioning return_all_scores are unrelated." + }, + { + "left": "issue:36296", + "right": "issue:43526", + "accept": false, + "reason": "Tensor parallel training and BeitImageProcessorFast reduce_labels are unrelated." + }, + { + "left": "issue:41628", + "right": "issue:44355", + "accept": false, + "reason": "ImportError for AutoImageProcessor and compiled-file errors are not the same issue." + }, + { + "left": "issue:44273", + "right": "issue:45003", + "accept": false, + "reason": "Lazy loading malfunction and unsafe sys.modules access are different bug reports." + }, + { + "left": "issue:44261", + "right": "issue:44360", + "accept": false, + "reason": "MLA q_a_layernorm epsilon mismatch and missing ReLU in DSA indexer are unrelated." + }, + { + "left": "issue:44623", + "right": "issue:45230", + "accept": false, + "reason": "Processor save_pretrained missing files and a generic bug report do not establish a shared underlying bug." + }, + { + "left": "issue:44273", + "right": "issue:45542", + "accept": false, + "reason": "Lazy loading and undefined tf backend error are different problems." + }, + { + "left": "issue:43576", + "right": "issue:44556", + "accept": false, + "reason": "Broken env command and checkpoint reload failure after upgrading to v5.2/v5.3 are distinct regressions." + }, + { + "left": "issue:44038", + "right": "issue:45125", + "accept": false, + "reason": "Qwen3-VL-Moe loading bug and missing _tp_plan for tensor parallelism are different code paths." + }, + { + "left": "issue:44393", + "right": "issue:45071", + "accept": false, + "reason": "Qwen3-VL 2D box output error and PretrainedConfig type-checking regression are unrelated." + }, + { + "left": "issue:41669", + "right": "issue:43673", + "accept": false, + "reason": "Import-star cleanup in models and missing GenerationMixin cache during chunked_prefill are different changes." + } + ] + }, + "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": 13, + "review_unit_index": 42, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:31515", + "issue:31795", + "issue:33453", + "issue:34689", + "issue:41669", + "issue:42371", + "issue:42890", + "issue:42913", + "issue:43066", + "issue:43352", + "issue:43408", + "issue:43502", + "issue:43519", + "issue:43576", + "issue:43606", + "issue:43704", + "issue:43723", + "issue:43827", + "issue:43976", + "issue:44077", + "issue:44246", + "issue:44261", + "issue:44263", + "issue:44273", + "issue:44295", + "issue:44297", + "issue:44315", + "issue:44351", + "issue:44360", + "issue:44393", + "issue:44485", + "issue:44492", + "issue:44556", + "issue:44623", + "issue:44655", + "issue:44704", + "issue:44829", + "issue:44861", + "issue:44908", + "issue:44945", + "issue:44998", + "issue:45071", + "issue:45092", + "issue:45230", + "issue:45310", + "issue:45341", + "issue:45468", + "issue:45478" + ], + "soft_pairs": [ + "issue:44556|issue:45092", + "issue:42371|issue:44492", + "issue:42890|issue:44908", + "issue:44704|issue:44908", + "issue:44246|issue:44273", + "issue:43408|issue:44315", + "issue:44297|issue:45230", + "issue:43352|issue:44393", + "issue:43576|issue:44908", + "issue:43976|issue:44393", + "issue:44908|issue:45071", + "issue:44295|issue:45230", + "issue:41669|issue:44351", + "issue:41669|issue:45341", + "issue:44492|issue:44945", + "issue:41669|issue:44492", + "issue:44315|issue:44829", + "issue:44393|issue:45478", + "issue:31795|issue:33453", + "issue:43827|issue:44908", + "issue:44077|issue:44861", + "issue:41669|issue:44908", + "issue:43723|issue:44393", + "issue:44655|issue:44861", + "issue:43576|issue:44273", + "issue:44360|issue:45468", + "issue:45230|issue:45310", + "issue:44273|issue:44908", + "issue:41669|issue:43704", + "issue:43519|issue:44485", + "issue:43519|issue:44908", + "issue:31795|issue:34689", + "issue:31515|issue:31795", + "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:44261|issue:45468", + "issue:43606|issue:45468", + "issue:42913|issue:43066", + "issue:42890|issue:43704", + "issue:44908|issue:44998" + ], + "prepared_review_unit_hash": "2f1a6c3146f9f6aef6f43e633bba86536aa2493ab5902d72058799d42db9201e", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 46, + "serialized_chars": 40776, + "estimated_input_tokens": 10194, + "estimated_eval_tokens": 20644 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This packet is mostly a set of unrelated issue reports. I\u2019m not accepting the two title-similar pairs as duplicates: 44556/45092 and 44246/44273 only have thematic overlap, with no body/diff evidence that they share the same root cause or would be fixed cleanly by one change.", + "confidence": 0.9, + "canonical_issue_reason": "issue:44556 is the clearest standalone report of the v5 checkpoint-reload regression theme and the strongest representative issue in this set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44556 is the best overall anchor here because it is specific, high-signal, and describes a concrete loading failure rather than a vague symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44556", + "right": "issue:45092", + "accept": false, + "reason": "Only title-level similarity about v5 checkpoint/model loading; no body or diff evidence that the same code path or root cause is involved." + }, + { + "left": "issue:42371", + "right": "issue:44492", + "accept": false, + "reason": "TF32 configuration guidance and a cache-strategy typo are different bugs in different areas." + }, + { + "left": "issue:42890", + "right": "issue:44908", + "accept": false, + "reason": "Test flakiness from missing seeds is unrelated to inverse_sqrt scheduler kwargs handling." + }, + { + "left": "issue:44704", + "right": "issue:44908", + "accept": false, + "reason": "AutoProcessor kwargs forwarding and scheduler kwargs are separate code paths with different failures." + }, + { + "left": "issue:44246", + "right": "issue:44273", + "accept": false, + "reason": "Only thematic overlap around loading/import performance; no evidence they are the same underlying bug or one fix would cover both." + }, + { + "left": "issue:43408", + "right": "issue:44315", + "accept": false, + "reason": "Wrong model-type warning and Liger Kernel not applied with model_init are unrelated symptoms." + }, + { + "left": "issue:44297", + "right": "issue:45230", + "accept": false, + "reason": "Tokenizer_class mismatch on save_pretrained is not the same as a generic bug report." + }, + { + "left": "issue:43352", + "right": "issue:44393", + "accept": false, + "reason": "Flash Attention 2 support warning and Qwen3-VL bbox output issues are different model problems." + }, + { + "left": "issue:43576", + "right": "issue:44908", + "accept": false, + "reason": "Broken transformers env command is unrelated to scheduler kwargs handling." + }, + { + "left": "issue:43976", + "right": "issue:44393", + "accept": false, + "reason": "Python version support issue and Qwen3-VL output bug do not share a concrete code path." + }, + { + "left": "issue:44908", + "right": "issue:45071", + "accept": false, + "reason": "Scheduler kwargs handling and PretrainedConfig type checking are unrelated." + }, + { + "left": "issue:44295", + "right": "issue:45230", + "accept": false, + "reason": "position_ids buffer access error is unrelated to a vague generic bug report." + }, + { + "left": "issue:41669", + "right": "issue:44351", + "accept": false, + "reason": "Import-star performance slowdown and missing HybridCache import are different problems." + }, + { + "left": "issue:41669", + "right": "issue:45341", + "accept": false, + "reason": "Import-time slowdown and a testing_utils bug are unrelated." + }, + { + "left": "issue:44492", + "right": "issue:44945", + "accept": false, + "reason": "Cache-strategy typo and pipeline-parallelism output corruption are different bugs." + }, + { + "left": "issue:41669", + "right": "issue:44492", + "accept": false, + "reason": "Model import performance regression and cache-strategy typo are unrelated." + }, + { + "left": "issue:44315", + "right": "issue:44829", + "accept": false, + "reason": "Liger Kernel application issue and flash_attention_3 training degeneration are distinct problems." + }, + { + "left": "issue:44393", + "right": "issue:45478", + "accept": false, + "reason": "Qwen3-VL bounding-box hallucination/error and Qwen3.5 MoE from_pretrained failure are different model issues." + }, + { + "left": "issue:31795", + "right": "issue:33453", + "accept": false, + "reason": "Documentation confusion about model.forward is not the same as a tokenizer-loading regression." + }, + { + "left": "issue:43827", + "right": "issue:44908", + "accept": false, + "reason": "Docs still referencing pipeline() and scheduler kwargs handling are unrelated." + }, + { + "left": "issue:44077", + "right": "issue:44861", + "accept": false, + "reason": "post_init policy and _tied_weights_keys AttributeError are separate model-internal issues." + }, + { + "left": "issue:41669", + "right": "issue:44908", + "accept": false, + "reason": "Import-time performance slowdown and scheduler config handling have no overlap in code path." + }, + { + "left": "issue:43723", + "right": "issue:44393", + "accept": false, + "reason": "Tokenizer loading regression and Qwen3-VL bbox output bug are unrelated." + }, + { + "left": "issue:44655", + "right": "issue:44861", + "accept": false, + "reason": "Saving pipeline objects and tied-weight key handling are different failure modes." + }, + { + "left": "issue:43576", + "right": "issue:44273", + "accept": false, + "reason": "Broken env command and lazy-loading/import slowdown are different features and bugs." + }, + { + "left": "issue:44360", + "right": "issue:45468", + "accept": false, + "reason": "DSA ReLU concern and Gemma4 audio positional encoding are unrelated." + }, + { + "left": "issue:45230", + "right": "issue:45310", + "accept": false, + "reason": "Generic bug report is too vague to be the same as the specific Qwen3.5 MoE from_pretrained error." + }, + { + "left": "issue:44273", + "right": "issue:44908", + "accept": false, + "reason": "Lazy loading is not working properly and scheduler kwargs handling are separate subsystems." + }, + { + "left": "issue:41669", + "right": "issue:43704", + "accept": false, + "reason": "Import-time slowdown and VRAM leak in dataloader threads are unrelated." + }, + { + "left": "issue:43519", + "right": "issue:44485", + "accept": false, + "reason": "Timestamp calculation bug and GLM-5 RoPE implementation are different model-specific problems." + }, + { + "left": "issue:43519", + "right": "issue:44908", + "accept": false, + "reason": "Processor timestamp math and scheduler kwargs handling are unrelated." + }, + { + "left": "issue:31795", + "right": "issue:34689", + "accept": false, + "reason": "Documentation confusion and Llama 3.2 Vision loading regression are not the same bug." + }, + { + "left": "issue:31515", + "right": "issue:31795", + "accept": false, + "reason": "Checkpoint loading slowdown and forward documentation confusion are unrelated." + }, + { + "left": "issue:44315", + "right": "issue:45092", + "accept": false, + "reason": "Liger Kernel application and v5 checkpoint/meta-init loading failure are different code paths." + }, + { + "left": "issue:43704", + "right": "issue:44485", + "accept": false, + "reason": "VRAM leak in dataloader threads is unrelated to RoPE implementation issues." + }, + { + "left": "issue:44485", + "right": "issue:45468", + "accept": false, + "reason": "GLM-5 RoPE discussion and Gemma4 audio positional encoding are different model implementations." + }, + { + "left": "issue:42371", + "right": "issue:43704", + "accept": false, + "reason": "TF32 settings and VRAM leak in dataloader threads are unrelated." + }, + { + "left": "issue:43502", + "right": "issue:43519", + "accept": false, + "reason": "local_files_only network requests and Qwen3VL timestamp calculation are separate bugs." + }, + { + "left": "issue:43519", + "right": "issue:44623", + "accept": false, + "reason": "Timestamp computation bug and processor.save_pretrained missing files are different issues." + }, + { + "left": "issue:43519", + "right": "issue:43704", + "accept": false, + "reason": "Timestamp computation bug and VRAM leak are unrelated." + }, + { + "left": "issue:44263", + "right": "issue:45468", + "accept": false, + "reason": "torch.split return semantics and Gemma4 audio positional encoding are different problems." + }, + { + "left": "issue:44261", + "right": "issue:45468", + "accept": false, + "reason": "MLA q_a_layernorm precision/config issue is unrelated to Gemma4 audio positional encoding." + }, + { + "left": "issue:43606", + "right": "issue:45468", + "accept": false, + "reason": "CPU offload device mismatch is unrelated to Gemma4 audio positional encoding." + }, + { + "left": "issue:42913", + "right": "issue:43066", + "accept": false, + "reason": "Tokenizer behavior differences and wrong decoder type in v5 are related thematically but not the same concrete bug." + }, + { + "left": "issue:42890", + "right": "issue:43704", + "accept": false, + "reason": "Test seeding flakiness is unrelated to VRAM leakage." + }, + { + "left": "issue:44908", + "right": "issue:44998", + "accept": false, + "reason": "Scheduler configuration bug and an unrelated placeholder issue are not a match." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The writeup is mostly conservative, but it still overstates the evidence for the two accepted soft edges. In the packet, 44556/45092 and 44246/44273 are only supported by title-level thematic similarity; there is no body/diff evidence showing the same root cause or that a single PR would cleanly fix both. I\u2019d keep those pairs as tentative rather than accepted duplicate clusters." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 43, + "review_unit_count": 43, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-374", + "nodes": [ + "issue:30333", + "issue:31515", + "issue:33453", + "issue:36296", + "issue:38617", + "issue:43298", + "issue:43525", + "issue:43572", + "issue:43618", + "issue:44230", + "issue:44492", + "issue:44556", + "issue:44623", + "issue:44861", + "issue:44998", + "issue:45290", + "issue:45310", + "issue:45341" + ], + "soft_pairs": [ + "issue:44861|issue:45290", + "issue:44998|issue:45341", + "issue:44492|issue:44998", + "issue:43618|issue:44998", + "issue:44556|issue:44998", + "issue:43525|issue:44861", + "issue:43572|issue:44861", + "issue:31515|issue:38617", + "issue:44230|issue:44623", + "issue:31515|issue:36296", + "issue:30333|issue:31515", + "issue:44230|issue:45310", + "issue:31515|issue:33453", + "issue:43298|issue:44230" + ], + "prepared_review_unit_hash": "55065f5b7a5682e02817892a07b80cd0bb68e1231277967451f0fb63768bfbd6", + "component_budget": { + "node_count": 374, + "item_count": 374, + "soft_pair_count": 1395, + "serialized_chars": 720210, + "estimated_input_tokens": 180053, + "estimated_eval_tokens": 360362 + }, + "budget": { + "node_count": 18, + "item_count": 18, + "soft_pair_count": 14, + "serialized_chars": 14257, + "estimated_input_tokens": 3565, + "estimated_eval_tokens": 7386 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is highly heterogeneous: most items are unrelated bugs, and every soft-similarity pair appears to be a false positive. I would not merge any of these issues as duplicates.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "No single issue is a safe canonical representative because the connected items span unrelated subsystems and failure modes.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44861", + "right": "issue:45290", + "accept": false, + "reason": "Different bugs in different paths: tied-weight key handling vs chat template/tool-call serialization." + }, + { + "left": "issue:44998", + "right": "issue:45341", + "accept": false, + "reason": "One is a nonsense-title issue and the other is a testing_utils bug; no shared symptom or code path." + }, + { + "left": "issue:44492", + "right": "issue:44998", + "accept": false, + "reason": "A typo in cache strategy docs/config is unrelated to the unrelated 'Unemployment' issue." + }, + { + "left": "issue:43618", + "right": "issue:44998", + "accept": false, + "reason": "CLIPOutput attentions regression is unrelated to the other issue." + }, + { + "left": "issue:44556", + "right": "issue:44998", + "accept": false, + "reason": "Checkpoint reload incompatibility is not the same as the unrelated 'Unemployment' issue." + }, + { + "left": "issue:43525", + "right": "issue:44861", + "accept": false, + "reason": "Llama4Config pad_token_id attribute missing is unrelated to tied-weight key list handling." + }, + { + "left": "issue:43572", + "right": "issue:44861", + "accept": false, + "reason": "StableLmConfig pad_token_idx regression is a different config attribute bug than the tied-weight crash." + }, + { + "left": "issue:31515", + "right": "issue:38617", + "accept": false, + "reason": "Slow from_pretrained checkpoint loading is unrelated to an ImportError for layer_type_validation." + }, + { + "left": "issue:44230", + "right": "issue:44623", + "accept": false, + "reason": "FP8 Qwen model support and missing processor save_pretrained files are different issues." + }, + { + "left": "issue:31515", + "right": "issue:36296", + "accept": false, + "reason": "Tokenizer/checkpoint loading slowness is not the same as a tensor-parallel training bug." + }, + { + "left": "issue:30333", + "right": "issue:31515", + "accept": false, + "reason": "MLflow reporting on failed training jobs and slow checkpoint loading are unrelated problems." + }, + { + "left": "issue:44230", + "right": "issue:45310", + "accept": false, + "reason": "Qwen3-VL/Qwen3.5 FP8 support request and a from_pretrained error on Qwen3.5 MoE are not the same concrete bug." + }, + { + "left": "issue:31515", + "right": "issue:33453", + "accept": false, + "reason": "Both involve loading, but one is checkpoint load slowness and the other is a tokenizer loading regression; not the same bug." + }, + { + "left": "issue:43298", + "right": "issue:44230", + "accept": false, + "reason": "Continuous batching audio-model support and FP8 Qwen inference support are distinct feature gaps." + } + ] + }, + "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": 13, + "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": "ad8d1b620509c568a6a760a93a5e059838298c90968b34d1ad4ed61ae5ebe562", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1590, + "estimated_input_tokens": 398, + "estimated_eval_tokens": 1052 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1590, + "estimated_input_tokens": 398, + "estimated_eval_tokens": 1052 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are not duplicates: one requests Flash Attention 2 support for more architectures, the other requests GGUF support for more architectures. They share a broad \u201ccommunity contribution\u201d theme but describe different feature work.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "Issue 26350 is the stronger representative thread in this cluster because it has substantially more discussion and is the older, more established request; however, it should not be treated as a duplicate of 33260.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:26350", + "right": "issue:33260", + "accept": false, + "reason": "Different requested features and code paths: Flash Attention 2 architecture support vs GGUF architecture support. Similar framing, but not the same underlying change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 4, + "component_count": 13, + "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": "2148375c0b5f798b8c6e75714948c6cc19bfc19dc443baaf8853195fcd1247fe", + "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": "All four issues are language-translation requests using the same template. The Turkish-specific issue is the most concrete, but the other three appear to be separate template instances rather than the same underlying request; high text similarity alone is not enough to merge them as duplicates.", + "confidence": 0.71, + "canonical_issue_reason": "issue:27088 is the only concrete, specific request (Turkish). The others are generic placeholder-style variants, so this is the clearest representative of the actual problem being reported.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:27088 is the best standalone issue because it names a specific language and has the least ambiguity; the other issues look like templated duplicates or separate language requests.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:27088", + "right": "issue:44370", + "accept": false, + "reason": "Both are translation-request templates, but one is specifically Turkish while the other is a generic placeholder-style issue. That is not enough to prove the same underlying request." + }, + { + "left": "issue:27088", + "right": "issue:44365", + "accept": false, + "reason": "High similarity likely comes from the shared i18n template; the language target is not the same concrete request, so this should not be merged as a duplicate." + }, + { + "left": "issue:27088", + "right": "issue:43834", + "accept": false, + "reason": "The titles/body patterns are similar, but this looks like a different translation request instance rather than the same Turkish issue." + }, + { + "left": "issue:43834", + "right": "issue:44370", + "accept": false, + "reason": "These are near-identical template issues, but there is no evidence they target the exact same language/request; template similarity alone is insufficient." + }, + { + "left": "issue:43834", + "right": "issue:44365", + "accept": false, + "reason": "Both look like generic translation-request variants, but not enough evidence that they are the same underlying bug/change." + }, + { + "left": "issue:44365", + "right": "issue:44370", + "accept": false, + "reason": "Near-duplicate wording is likely due to the shared template, but they still appear to be separate issue instances without proof of the same concrete request." + } + ] + }, + "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": 13, + "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-36817-14", + "nodes": [ + "issue:36817", + "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:37015|issue:43837", + "issue:37015|issue:44121", + "issue:37015|issue:43909", + "issue:37015|issue:42503", + "issue:37015|issue:45027", + "issue:41115|issue:43837", + "issue:41115|issue:44121", + "issue:41115|issue:42503", + "issue:41115|issue:45027", + "issue:41211|issue:43671", + "issue:42503|issue:43837", + "issue:42503|issue:43671", + "issue:42503|issue:42738", + "issue:42738|issue:45027", + "issue:43671|issue:43837", + "issue:43671|issue:45027", + "issue:43671|issue:45177", + "issue:43671|issue:44121", + "issue:43671|issue:43909", + "issue:43837|issue:43909", + "issue:43837|issue:45322", + "issue:43837|issue:44121", + "issue:43909|issue:44205", + "issue:44121|issue:45322", + "issue:43837|issue:45027", + "issue:43837|issue:45177" + ], + "prepared_review_unit_hash": "65b828b3117a9d9d6cfbb4f9604d3489c66ca1d7a13e12b4647103307d97f1ee", + "component_budget": { + "node_count": 14, + "item_count": 14, + "soft_pair_count": 28, + "serialized_chars": 17644, + "estimated_input_tokens": 4411, + "estimated_eval_tokens": 9078 + }, + "budget": { + "node_count": 14, + "item_count": 14, + "soft_pair_count": 28, + "serialized_chars": 17644, + "estimated_input_tokens": 4411, + "estimated_eval_tokens": 9078 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These items are thematically similar model-request issues, but they are not duplicates: each asks for a different model, task, or modality (e.g. BERT variants, audio ASR/TTS, OCR, sparse transformers).", + "confidence": 0.98, + "canonical_issue_reason": "No single canonical issue: the cluster spans distinct model requests rather than the same underlying bug/change.", + "canonical_pr_reason": null, + "best_issue_reason": "No clear global representative for deduplication because the requests target different models and code paths.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36817", + "right": "issue:41211", + "accept": false, + "reason": "EuroBERT config vs DEIMv2 are different model additions with different implementations." + }, + { + "left": "issue:36817", + "right": "issue:43671", + "accept": false, + "reason": "EuroBERT vs Qwen3-TTS are unrelated model families and modalities." + }, + { + "left": "issue:37015", + "right": "issue:43837", + "accept": false, + "reason": "NeoBERT and Qwen3-ASR are different models; ASR support is not the same change as adding a BERT variant." + }, + { + "left": "issue:37015", + "right": "issue:44121", + "accept": false, + "reason": "NeoBERT vs a weight-sparse transformer request are different architectures and code paths." + }, + { + "left": "issue:37015", + "right": "issue:43909", + "accept": false, + "reason": "NeoBERT is unrelated to LFM2.5 Audio; different family and modality." + }, + { + "left": "issue:37015", + "right": "issue:42503", + "accept": false, + "reason": "NeoBERT and ModernVBERT are different model requests, not the same bug/change." + }, + { + "left": "issue:37015", + "right": "issue:45027", + "accept": false, + "reason": "NeoBERT vs Voxtral TTS are unrelated model/support requests." + }, + { + "left": "issue:41115", + "right": "issue:43837", + "accept": false, + "reason": "MiniCPM3 architecture support and Qwen3-ASR support are distinct model integrations." + }, + { + "left": "issue:41115", + "right": "issue:44121", + "accept": false, + "reason": "MiniCPM3 vs weight-sparse transformer are different requested changes." + }, + { + "left": "issue:41115", + "right": "issue:42503", + "accept": false, + "reason": "MiniCPM3 and ModernVBERT are separate model additions." + }, + { + "left": "issue:41115", + "right": "issue:45027", + "accept": false, + "reason": "MiniCPM3 and Voxtral TTS target different models and modalities." + }, + { + "left": "issue:41211", + "right": "issue:43671", + "accept": false, + "reason": "DEIMv2 and Qwen3-TTS are unrelated model requests." + }, + { + "left": "issue:42503", + "right": "issue:43837", + "accept": false, + "reason": "ModernVBERT and Qwen3-ASR are different model/task integrations." + }, + { + "left": "issue:42503", + "right": "issue:43671", + "accept": false, + "reason": "ModernVBERT and Qwen3-TTS are unrelated model requests." + }, + { + "left": "issue:42503", + "right": "issue:42738", + "accept": false, + "reason": "ModernVBERT is a concrete model request; BERT-like models with RoPE is a broader architecture discussion, not the same change." + }, + { + "left": "issue:42738", + "right": "issue:45027", + "accept": false, + "reason": "A generic BERT-with-RoPE request is unrelated to Voxtral TTS support." + }, + { + "left": "issue:43671", + "right": "issue:43837", + "accept": false, + "reason": "Qwen3-TTS and Qwen3-ASR share a prefix but are different concrete support changes (TTS vs ASR)." + }, + { + "left": "issue:43671", + "right": "issue:45027", + "accept": false, + "reason": "Qwen3-TTS and Voxtral TTS are different model integrations." + }, + { + "left": "issue:43671", + "right": "issue:45177", + "accept": false, + "reason": "Qwen3-TTS and DeepSeek-OCR2 are different modalities and implementations." + }, + { + "left": "issue:43671", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3-TTS support is unrelated to a weight-sparse transformer request." + }, + { + "left": "issue:43671", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-TTS and LFM2.5 Audio are different audio-model requests, not the same underlying change." + }, + { + "left": "issue:43837", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-ASR and LFM2.5 Audio are distinct audio model requests with different code paths." + }, + { + "left": "issue:43837", + "right": "issue:45322", + "accept": false, + "reason": "Qwen3-ASR support and EUPE are unrelated model requests." + }, + { + "left": "issue:43837", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3-ASR and a weight-sparse transformer request are different changes." + }, + { + "left": "issue:43909", + "right": "issue:44205", + "accept": false, + "reason": "LFM2.5 Audio support and SAM3-LiteText are different model additions." + }, + { + "left": "issue:44121", + "right": "issue:45322", + "accept": false, + "reason": "Weight-sparse transformer and EUPE are unrelated research-model requests." + }, + { + "left": "issue:43837", + "right": "issue:45027", + "accept": false, + "reason": "Qwen3-ASR and Voxtral TTS differ by model and task; not a duplicate." + }, + { + "left": "issue:43837", + "right": "issue:45177", + "accept": false, + "reason": "Qwen3-ASR and DeepSeek-OCR2 are different model requests." + } + ] + }, + "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": 13, + "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": "bb2cc08e747d7e77db1527f9f7b77d434c7014832549efc89efb6073efcf1bd3", + "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 items are only loosely text-similar; they describe different bugs in different areas (model norms, loss handling, config typing, a typo, and tokenizer warnings), so they should not be deduplicated together.", + "confidence": 0.98, + "canonical_issue_reason": "No single canonical issue: the cluster spans unrelated problems across different components and bug types.", + "canonical_pr_reason": null, + "best_issue_reason": "No issue here is a good global representative for the whole set, because they are not the same underlying defect.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:37934", + "right": "issue:43668", + "accept": false, + "reason": "Different models and defects: Llama4 norm semantics vs ModernBERTConfig type-hint correctness." + }, + { + "left": "issue:42936", + "right": "issue:43240", + "accept": false, + "reason": "Mask2Former ignore_value usage is a separate loss-parameter bug from kwargs not being forwarded to the loss function." + }, + { + "left": "issue:42936", + "right": "issue:44031", + "accept": false, + "reason": "Unrelated subsystems: a model loss argument issue vs tokenizer regex warning behavior." + }, + { + "left": "issue:42936", + "right": "issue:43813", + "accept": false, + "reason": "Different underlying problem: unused ignore_value vs a typo in a quantization attribute name." + }, + { + "left": "issue:42936", + "right": "issue:43668", + "accept": false, + "reason": "These concern different models and bug classes, not the same code-path failure." + }, + { + "left": "issue:43240", + "right": "issue:43668", + "accept": false, + "reason": "Loss kwargs forwarding and a config type-hint error are unrelated." + }, + { + "left": "issue:43668", + "right": "issue:44031", + "accept": false, + "reason": "A ModernBERT config annotation issue is not the same as the tokenizer regex warning bug." + }, + { + "left": "issue:43668", + "right": "issue:43813", + "accept": false, + "reason": "Type-hint mistake vs literal typo in a different quantization-related string." + } + ] + }, + "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": 13, + "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": "ff882ecfdd7846ea64e48964f8f053805d271ca58e6f3ba487a29533b675ca33", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1480, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1480, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two issues are unrelated: one is about Block Decoding and the other is a request for DeepSeek v3.2 model support, so they should not be deduplicated.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "If one had to be highlighted, #43037 is the more specific, actionable request, but it is not a duplicate of #41084.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41084", + "right": "issue:43037", + "accept": false, + "reason": "Different topics and likely different code paths: Block Decoding vs model support for DeepSeek v3.2. Similarity is too weak to treat as the same underlying issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 8, + "component_count": 13, + "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": "838b2c5d64b6819652f7fe8558f40fe979826318d318a7e5340d3e597809f1d9", + "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": "The two issues are related only at a high level to Trainer customization, but they describe different problems: one is about `remove_unused_column`, the other about FLOPS estimation for custom trainers. They should not be clustered as duplicates.", + "confidence": 0.91, + "canonical_issue_reason": "Issue #43598 is the more specific customization concern around `remove_unused_column` in `Trainer`, and it is better suited as the representative issue for that narrow topic.", + "canonical_pr_reason": null, + "best_issue_reason": "#43598 is the clearer, more actionable report with a concrete Trainer behavior to revisit; #43600 is a separate concern about FLOPS accounting and should remain distinct.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43598", + "right": "issue:43600", + "accept": false, + "reason": "They mention Trainer customization, but one is about column removal behavior and the other about FLOPS estimation. These are different code paths and different fixes." + } + ] + }, + "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": 13, + "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": "37218c8cb1bcd3773dedee66f9130321e3a0ad936562cfc73088da017d90561e", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1611, + "estimated_input_tokens": 403, + "estimated_eval_tokens": 1062 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1611, + "estimated_input_tokens": 403, + "estimated_eval_tokens": 1062 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are two different feature requests for different Qwen model support paths: one for Qwen3-Omni auto-registration, the other for Qwen3.5 sequence-classification support. They are not duplicates.", + "confidence": 0.97, + "canonical_issue_reason": "Issue 43684 is the broader/cleaner anchor because it asks for AutoModel and AutoModelForConditionalGeneration registration support, while 44405 is a separate, task-specific AutoModelForSequenceClassification request for a different Qwen variant.", + "canonical_pr_reason": null, + "best_issue_reason": "43684 is the best representative if one issue must be chosen, since it targets general auto-class registration; 44405 is a distinct head-specific request and should not be merged into it.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43684", + "right": "issue:44405", + "accept": false, + "reason": "Different underlying changes: Qwen3-Omni registration for auto classes vs Qwen3.5 sequence-classification support. Different model family and different task head, so not the same bug or fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 10, + "component_count": 13, + "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": "a92bcc515c8921ceed06ab44a9dcec731b333292f66b00fea325c9d5f709fc1e", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4264, + "estimated_input_tokens": 1066, + "estimated_eval_tokens": 2388 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4264, + "estimated_input_tokens": 1066, + "estimated_eval_tokens": 2388 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Three issues are near-identical duplicate reports with the title \"huggingface \"; the \"Fett\" issue is unrelated on the available evidence. I\u2019d cluster the three huggingface issues together and keep them separate from 43835.", + "confidence": 0.71, + "canonical_issue_reason": "Issue 43859 is the best canonical representative among the duplicate huggingface reports because it matches the repeated title and has the most discussion activity, while the others appear to be the same report.", + "canonical_pr_reason": null, + "best_issue_reason": "43859 is the strongest issue to keep as the cluster representative: same duplicated title as the other matching issues and slightly more activity, so it is the most informative anchor for triage.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43835", + "right": "issue:43845", + "accept": false, + "reason": "Different titles and no shared body or target evidence; not enough to treat \"Fett\" and \"huggingface\" as the same underlying issue." + }, + { + "left": "issue:43835", + "right": "issue:43846", + "accept": false, + "reason": "Different titles and no concrete evidence of the same bug/change." + }, + { + "left": "issue:43835", + "right": "issue:43859", + "accept": false, + "reason": "Different titles and no shared issue target or descriptive evidence; should not be merged." + }, + { + "left": "issue:43845", + "right": "issue:43846", + "accept": true, + "reason": "Same title, very high textual similarity, and no contrary evidence; these look like duplicate reports of the same issue." + }, + { + "left": "issue:43845", + "right": "issue:43859", + "accept": true, + "reason": "Same title and strong similarity; these appear to be the same underlying report." + }, + { + "left": "issue:43846", + "right": "issue:43859", + "accept": true, + "reason": "Same title and strong similarity with no distinguishing details; likely duplicates." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The clustering is grounded in the packet: 43845/43846/43859 share the same title and strong soft-similarity evidence, while 43835 has a different title and only weak soft similarity. Choosing 43859 as the canonical representative is also conservative because it has the only discussion activity. " + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 11, + "component_count": 13, + "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": "b921ee5f6beb117d409d2218412d4ee66a9d39e33afbd400bd292145d865e555", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 9, + "serialized_chars": 5794, + "estimated_input_tokens": 1449, + "estimated_eval_tokens": 3154 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 9, + "serialized_chars": 5794, + "estimated_input_tokens": 1449, + "estimated_eval_tokens": 3154 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "All items look like unrelated low-signal or spam issues; there is no substantive evidence that any two describe the same underlying bug or request.", + "confidence": 0.98, + "canonical_issue_reason": "issue:44418 is the only item with a non-placeholder topical title, so it is the least bad representative if one must be chosen; however, it is still too generic to be a strong canonical issue.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44418 is the most usable anchor only because it has an actual topic label rather than a spam placeholder; none of the issues are strong enough to serve as a meaningful canonical report.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44371", + "right": "issue:44572", + "accept": false, + "reason": "Both titles are identical spam placeholders with no body/detail, so this is not evidence of the same underlying issue." + }, + { + "left": "issue:44371", + "right": "issue:44573", + "accept": false, + "reason": "Both are generic spam placeholders; similarity is not enough to infer a shared bug or request." + }, + { + "left": "issue:44371", + "right": "issue:44418", + "accept": false, + "reason": "One is a spam placeholder and the other is a vague documentation request; no concrete shared problem is shown." + }, + { + "left": "issue:44371", + "right": "issue:44937", + "accept": false, + "reason": "A spam placeholder and an unrelated branded title do not indicate the same underlying issue." + }, + { + "left": "issue:44418", + "right": "issue:44572", + "accept": false, + "reason": "A generic documentation suggestion and a spam placeholder are not the same substantive report." + }, + { + "left": "issue:44418", + "right": "issue:44573", + "accept": false, + "reason": "The two titles are too generic and one is clear spam; there is no shared concrete issue." + }, + { + "left": "issue:44572", + "right": "issue:44573", + "accept": false, + "reason": "Identical spam placeholders are not sufficient evidence of duplicate substantive content." + }, + { + "left": "issue:44572", + "right": "issue:44937", + "accept": false, + "reason": "A spam placeholder and an unrelated brand-name title do not describe the same bug or change." + }, + { + "left": "issue:44573", + "right": "issue:44937", + "accept": false, + "reason": "No concrete overlap beyond generic spammy wording; not a duplicate pair." + } + ] + }, + "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": 13, + "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": "b1517103c377d88d4edaf8b204c2f1f235d0c8fd3e57a6f9d9d62bc121f0178b", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1646, + "estimated_input_tokens": 412, + "estimated_eval_tokens": 1080 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1646, + "estimated_input_tokens": 412, + "estimated_eval_tokens": 1080 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two closed issues share an identical title and close body lengths, and 45145 is earlier with one inbound reference. That makes 45145 the better consolidation target, but the packet only provides soft-similarity evidence, so I would not treat the pair as conclusively duplicate with high confidence.", + "confidence": 0.78, + "canonical_issue_reason": "Issue 45145 is the earlier report and has an inbound reference, so it is the more established thread to keep as the canonical issue. The evidence here is limited to identical titles and soft similarity, so the choice is pragmatic rather than definitive.", + "canonical_pr_reason": null, + "best_issue_reason": "45145 is the best issue representative because it predates 45151 and already has inbound linkage, while the available evidence does not strongly distinguish the two beyond soft similarity.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45145", + "right": "issue:45151", + "accept": false, + "reason": "Reject: the packet only marks this as soft similarity and explicitly says deterministic acceptance is false. Identical titles and similar body lengths suggest a possible duplicate, but there is not enough direct content evidence to confidently merge them as the same report." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The canonical choice is plausible, but the soft-edge verdict is too strong for the packet: the pair is only linked by soft similarity, and the packet explicitly marks the pair as not deterministically acceptable. The summary also overstates the evidence by saying the bodies are \"very similar\" / \"same report duplicated\" without direct content comparison in the packet. A more conservative stance would note identical titles, similar body lengths, and 45145\u2019s earlier timestamp plus inbound reference, but stop short of asserting duplication with high confidence." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 13, + "component_count": 13, + "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": "pull_request", + "component_index": 1, + "component_count": 23, + "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:45587", + "pull_request:45622" + ], + "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:43995", + "pull_request:43823|pull_request:45622", + "pull_request:43995|pull_request:45213", + "pull_request:43995|pull_request:44827", + "pull_request:44827|pull_request:45622", + "pull_request:44827|pull_request:45587", + "pull_request:44827|pull_request:45170", + "pull_request:44827|pull_request:45213", + "pull_request:43823|pull_request:45213", + "pull_request:43251|pull_request:43254" + ], + "prepared_review_unit_hash": "4d91f79365bfd5170a0abdce3d9b1ff8f084393f331f803f6bc6a655b6aae8fc", + "component_budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 18, + "serialized_chars": 35175, + "estimated_input_tokens": 8794, + "estimated_eval_tokens": 17844 + }, + "budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 18, + "serialized_chars": 35175, + "estimated_input_tokens": 8794, + "estimated_eval_tokens": 17844 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Mostly unrelated PRs are bundled by loose similarity. The only true duplicate-looking pair is the fixed_cross_entropy kwargs fix (43251/43254).", + "confidence": 0.86, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 43251 is the best representative of the only real duplicate pair: it directly targets issue 43240 and cleanly implements the cross_entropy kwargs forwarding fix.", + "best_issue_reason": null, + "best_pr_reason": "PR 43251 is the strongest overall candidate: same code path as 43254, explicit issue linkage, and the more complete bugfix framing.", + "soft_edge_verdicts": [ + { + "left": "pull_request:39895", + "right": "pull_request:43424", + "accept": false, + "reason": "Different domains: new VideoPrism model docs/code vs an ExecuTorch dynamic-shape test." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43823", + "accept": false, + "reason": "Tokenizer helper methods vs adding a new MobileLLM model; not the same change." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43424", + "accept": false, + "reason": "Mistral tokenizer methods and ExecuTorch export tests are unrelated." + }, + { + "left": "pull_request:42668", + "right": "pull_request:43823", + "accept": false, + "reason": "Processor auto-loading robustness vs introducing MobileLLM; only broad processor/model theme overlaps." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43823", + "accept": false, + "reason": "Cross-entropy kwargs fix and a new model addition are unrelated code paths." + }, + { + "left": "pull_request:43251", + "right": "pull_request:44827", + "accept": false, + "reason": "Loss utility fix vs Mistral4/model/PEFT-related changes; not the same bug." + }, + { + "left": "pull_request:43424", + "right": "pull_request:44827", + "accept": false, + "reason": "ExecuTorch dynamic-shape export tests do not match the Mistral4 test/model fix." + }, + { + "left": "pull_request:43424", + "right": "pull_request:43823", + "accept": false, + "reason": "ExecuTorch export testing and MobileLLM model addition are unrelated." + }, + { + "left": "pull_request:43823", + "right": "pull_request:43995", + "accept": false, + "reason": "Adding MobileLLM and refactoring Falcon output collection are different model-specific changes." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45622", + "accept": false, + "reason": "MobileLLM introduction vs PEFT constructor internals; no shared concrete fix." + }, + { + "left": "pull_request:43995", + "right": "pull_request:45213", + "accept": false, + "reason": "Falcon refactor is unrelated to the model-creation skill/meta PR." + }, + { + "left": "pull_request:43995", + "right": "pull_request:44827", + "accept": false, + "reason": "Falcon output-collection refactor and Mistral4 test fixes are different model paths." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45622", + "accept": false, + "reason": "Mistral4 test/model fixes and PEFT constructor internals are not the same concrete bug, despite superficial overlap." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45587", + "accept": false, + "reason": "Mistral4/code fixes vs documentation on continuous batching memory management." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45170", + "accept": false, + "reason": "Mistral4 fixes are unrelated to the layrnorm->layernorm renaming sweep." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45213", + "accept": false, + "reason": "Mistral4 model/test work is unrelated to the meta model-creation skill PR." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43254", + "accept": true, + "reason": "Same file, same issue target 43240, and both implement the same cross_entropy kwargs-forwarding fix." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45213", + "accept": false, + "reason": "MobileLLM model addition vs a meta skill/documentation PR; no shared code fix." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The only accepted duplicate pair is the clearly linked fixed_cross_entropy kwargs fix (43251/43254), and the other soft pairs are reasonably rejected as unrelated or at most loosely similar rather than mergeable into one bugfix PR." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 2, + "component_count": 23, + "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": "94b2ead41312d1c75c358f72a301b6421334f42f69d7dac8bb0026954c18b07d", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 7226, + "estimated_input_tokens": 1807, + "estimated_eval_tokens": 3870 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 7226, + "estimated_input_tokens": 1807, + "estimated_eval_tokens": 3870 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs are about the VibeVoice family, but they are not the same change: #40546 implements the core VibeVoice integration, while #42781 is a draft add-on for VibeVoice Realtime with an acoustic tokenizer and generation tweaks.", + "confidence": 0.92, + "canonical_issue_reason": null, + "canonical_pr_reason": "#40546 is the earlier, more complete base implementation of VibeVoice and has substantial review activity; #42781 is a later draft that builds on the same model family but targets realtime support.", + "best_issue_reason": null, + "best_pr_reason": "#40546 is the best representative of the cluster because it covers the primary integration and is far more mature than the draft realtime extension.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40546", + "right": "pull_request:42781", + "accept": false, + "reason": "They share the VibeVoice codebase, but the concrete changes are different: one is the original model integration, the other is a draft realtime variant with additional tokenizer/generation work. This is related work, not 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": 3, + "component_count": 23, + "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": "471bc1970432799dc4197b6974defc8c1d588f3ab7aa19f653bdb067a78309e6", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4675, + "estimated_input_tokens": 1169, + "estimated_eval_tokens": 2594 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4675, + "estimated_input_tokens": 1169, + "estimated_eval_tokens": 2594 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two PRs are unrelated feature additions in different model families: TimesFM covariate forecasting vs. DINOv3 image classification support. They should not be clustered as duplicates.", + "confidence": 0.99, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single PR is a clear canonical for the cluster because the items are unrelated; if forced, PR #40755 is the broader standalone feature with more implementation depth.", + "best_issue_reason": null, + "best_pr_reason": "PR #40755 is the better cluster representative only by size/scope, but it is not a semantic match to PR #41224 and should not imply duplication.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40755", + "right": "pull_request:41224", + "accept": false, + "reason": "Different models, different tasks, and different code paths: TimesFM forecasting with covariates vs. DINOv3 image classification. No evidence they fix the same underlying bug or could be merged into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 4, + "component_count": 23, + "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": "5ca5622c9633bbe7eef9d70a2eb0e3cf7982d42dc10a27ffb1990f021d804327", + "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": "Both items are PRs for adding DEIMv2 support to Transformers. PR #44339 is the more complete later submission and appears to subsume the earlier #41356 work, so it is the better canonical PR candidate. There is no issue in this cluster.", + "confidence": 0.86, + "canonical_issue_reason": null, + "canonical_pr_reason": "#44339 is the broader, later DEIMv2 implementation and includes the core model integration plus additional framework wiring (auto-mappings, conversion, loss/modular updates), making it the best representative PR.", + "best_issue_reason": null, + "best_pr_reason": "#44339 is the most complete and maintainable PR for the DEIMv2 addition; it covers the same feature area as #41356 but with substantially more finished integration work.", + "soft_edge_verdicts": [ + { + "left": "pull_request:41356", + "right": "pull_request:44339", + "accept": true, + "reason": "Both PRs target the same DEIMv2 model addition, and #44339 looks like a superset that could plausibly replace the earlier implementation in one merged change." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: both items are PRs tied to the same issue target (41211) and the later PR #44339 clearly adds broader DEIMv2 integration while overlapping core files with #41356. The soft-edge verdict is conservative, phrased as a plausible supersession rather than a certainty. No issue is present in this cluster." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 5, + "component_count": 23, + "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-41797-2", + "nodes": [ + "pull_request:41797", + "pull_request:45186" + ], + "soft_pairs": [ + "pull_request:41797|pull_request:45186" + ], + "prepared_review_unit_hash": "fa0dda77675745a6de0c8b882e73a88bda88b0377e98fcf4f9c18588a20b2b63", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6723, + "estimated_input_tokens": 1681, + "estimated_eval_tokens": 3618 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6723, + "estimated_input_tokens": 1681, + "estimated_eval_tokens": 3618 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are two separate model-addition PRs with similar scaffold files, but they implement different architectures and code paths (DeepSeek OCR vs Isaac). They should not be treated as duplicates.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single canonical PR: each submission adds a different model package, docs, autos, tests, and model-specific implementation for a distinct architecture.", + "best_issue_reason": null, + "best_pr_reason": "Neither PR is a good global representative for the cluster because the similarity is mostly boilerplate from new-model integration rather than the same underlying change.", + "soft_edge_verdicts": [ + { + "left": "pull_request:41797", + "right": "pull_request:45186", + "accept": false, + "reason": "Reject: both are new-model integration PRs, but for different models (DeepSeek OCR vs Isaac) with different implementation files and model-specific behavior; they do not fix the same code-path problem and would not plausibly merge into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 6, + "component_count": 23, + "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-42166-2", + "nodes": [ + "pull_request:42166", + "pull_request:45426" + ], + "soft_pairs": [ + "pull_request:42166|pull_request:45426" + ], + "prepared_review_unit_hash": "ce8dd96152cebfb51ed746af1b8c4baad518a0af1baa4233a596f9dae202a2d2", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5408, + "estimated_input_tokens": 1352, + "estimated_eval_tokens": 2960 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5408, + "estimated_input_tokens": 1352, + "estimated_eval_tokens": 2960 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two separate model-addition PRs, not duplicates: one introduces InternVLFlash, the other introduces AXK1. They share generic auto-registration/documentation files, but they target different models and code paths.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 42166 is the more complete and established integration (more files, docs, tests, and review activity), but it is not a duplicate of 45426.", + "best_issue_reason": null, + "best_pr_reason": "PR 42166 is the best representative of the cluster only by maturity and completeness; 45426 is a separate AXK1 addition with no evidence of being the same change.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42166", + "right": "pull_request:45426", + "accept": false, + "reason": "Different model integrations (InternVLFlash vs AXK1). Shared auto-registry scaffolding is incidental and not the same concrete feature or bug 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": 7, + "component_count": 23, + "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-42227-4", + "nodes": [ + "pull_request:42227", + "pull_request:43291", + "pull_request:43665", + "pull_request:44815" + ], + "soft_pairs": [ + "pull_request:42227|pull_request:43291", + "pull_request:42227|pull_request:43665", + "pull_request:42227|pull_request:44815", + "pull_request:43291|pull_request:43665", + "pull_request:43291|pull_request:44815", + "pull_request:43665|pull_request:44815" + ], + "prepared_review_unit_hash": "661b99a165240e0ca813366c9dc70884d3eb7517243fe45e4a0acc737e83fd3a", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 10170, + "estimated_input_tokens": 2543, + "estimated_eval_tokens": 5342 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 10170, + "estimated_input_tokens": 2543, + "estimated_eval_tokens": 5342 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are mostly unrelated despite some superficial model-area overlap. The two Whisper PRs touch different code paths, while the CLIP/ViT test edit and the FP8 dequant fix are clearly separate.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 42227 is the strongest standalone bug fix: it changes the ASR pipeline to actually forward `return_language` into the Whisper generation path and adds targeted tests.", + "best_issue_reason": null, + "best_pr_reason": "PR 42227 is the best representative of a concrete user-facing fix; the others are either test-only, obviously unrelated, or broad multi-file refactors/fixes.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42227", + "right": "pull_request:43291", + "accept": false, + "reason": "Both are Whisper-related, but they fix different problems in different layers: ASR pipeline parameter forwarding vs tokenizer decode/timestamp handling. They do not look mergeable as one PR." + }, + { + "left": "pull_request:42227", + "right": "pull_request:43665", + "accept": false, + "reason": "Unrelated changes. 42227 fixes Whisper return-language forwarding; 43665 is a test-file-only edit in CLIP/ViT and does not share the same bug or code path." + }, + { + "left": "pull_request:42227", + "right": "pull_request:44815", + "accept": false, + "reason": "Different subsystems and different bugs: Whisper ASR pipeline vs FP8 dequant/model-loading changes. No common underlying fix." + }, + { + "left": "pull_request:43291", + "right": "pull_request:43665", + "accept": false, + "reason": "Whisper tokenizer work vs unrelated CLIP/ViT test edits. No shared concrete issue." + }, + { + "left": "pull_request:43291", + "right": "pull_request:44815", + "accept": false, + "reason": "Different areas and different fixes. The Whisper tokenizer change is unrelated to FP8 dequant/loading work." + }, + { + "left": "pull_request:43665", + "right": "pull_request:44815", + "accept": false, + "reason": "These are clearly unrelated; one is nonsensical test-file edits, the other is a substantial FP8/dequant implementation 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": 8, + "component_count": 23, + "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": "58b856be31fef752c97b8d77ad05161ad9571103fc8424f715e96475de5aaa48", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5934, + "estimated_input_tokens": 1484, + "estimated_eval_tokens": 3224 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5934, + "estimated_input_tokens": 1484, + "estimated_eval_tokens": 3224 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two workflow-dependency upgrade PRs with overlapping filenames but different action/version changes; they are related maintenance, not the same fix/change.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #42975 is the better canonical PR candidate because it has the broader, more explicit goal ('Upgrade GitHub Actions for Node 24 compatibility') and touches a larger set of workflow action versions in a single compatibility-driven sweep.", + "best_issue_reason": null, + "best_pr_reason": "PR #42975 is the best representative of the cluster since it is the more general workflow-action compatibility upgrade and appears more central than the narrower docker-action bump in #42976.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42975", + "right": "pull_request:42976", + "accept": false, + "reason": "Reject: both are GitHub Actions version bumps, but they change different actions and different workflow surfaces (checkout/cache/upload-artifact vs docker/build-push-action). They do not look like the same underlying bug or concrete code-path 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": 23, + "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-42978-10", + "nodes": [ + "pull_request:42978", + "pull_request:43448", + "pull_request:43451", + "pull_request:43973", + "pull_request:44601", + "pull_request:45283", + "pull_request:45490", + "pull_request:45616", + "pull_request:45626", + "pull_request:45630" + ], + "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:43448|pull_request:45616", + "pull_request:43451|pull_request:45490", + "pull_request:43451|pull_request:45616", + "pull_request:43973|pull_request:45283", + "pull_request:44601|pull_request:45626", + "pull_request:45283|pull_request:45626", + "pull_request:45490|pull_request:45626", + "pull_request:45490|pull_request:45630", + "pull_request:45626|pull_request:45630" + ], + "prepared_review_unit_hash": "4e1e2d0adc6d93b03bf55f37a89c9c17bc15dae33f71f0f25238cc3dc7d08e52", + "component_budget": { + "node_count": 10, + "item_count": 10, + "soft_pair_count": 14, + "serialized_chars": 33117, + "estimated_input_tokens": 8280, + "estimated_eval_tokens": 16816 + }, + "budget": { + "node_count": 10, + "item_count": 10, + "soft_pair_count": 14, + "serialized_chars": 33117, + "estimated_input_tokens": 8280, + "estimated_eval_tokens": 16816 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is not a duplicate set. It mixes unrelated model-add PRs (ViT NEPA, Molmo, Molmo2, CTSM, DeepSeek V4, Kimi2-6, PP-FormulaNet, Lfm2Audio) plus two infrastructure changes (pipeline parallel support, Qwen3.5 GGUF loading). The shared filenames are mostly broad auto/doc scaffolding, not the same underlying change.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "pull_request:42978", + "right": "pull_request:43448", + "accept": false, + "reason": "Different model additions: ViT NEPA vs Molmo. Shared docs/auto registry edits are boilerplate, not the same change." + }, + { + "left": "pull_request:42978", + "right": "pull_request:43451", + "accept": false, + "reason": "Different model additions: ViT NEPA vs Molmo2. Same broad model-onboarding pattern, but not the same model or code path." + }, + { + "left": "pull_request:42978", + "right": "pull_request:45490", + "accept": false, + "reason": "Different model additions: ViT NEPA vs CTSM. No overlapping bug or change target beyond generic docs/auto wiring." + }, + { + "left": "pull_request:43448", + "right": "pull_request:43451", + "accept": false, + "reason": "Molmo and Molmo2 are distinct model integrations with different files and behavior; they are not the same underlying PR." + }, + { + "left": "pull_request:43448", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo vs CTSM are unrelated model additions; shared repo plumbing is too generic to merge as duplicates." + }, + { + "left": "pull_request:43448", + "right": "pull_request:45616", + "accept": false, + "reason": "Molmo and DeepSeek V4 are separate model integrations with different architectures and files." + }, + { + "left": "pull_request:43451", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo2 vs CTSM are different model additions; no shared concrete bug or implementation path." + }, + { + "left": "pull_request:43451", + "right": "pull_request:45616", + "accept": false, + "reason": "Molmo2 and DeepSeek V4 are unrelated model integrations; shared auto-registration is incidental." + }, + { + "left": "pull_request:43973", + "right": "pull_request:45283", + "accept": false, + "reason": "Lfm2Audio model support and Qwen3.5 GGUF loading are unrelated changes; one is model onboarding, the other is loading-format support." + }, + { + "left": "pull_request:44601", + "right": "pull_request:45626", + "accept": false, + "reason": "Native pipeline-parallel loading support is infrastructure work, while PP-FormulaNet is a model-add PR; they do not fix the same code-path problem." + }, + { + "left": "pull_request:45283", + "right": "pull_request:45626", + "accept": false, + "reason": "Qwen3.5 GGUF mapping changes and PP-FormulaNet model support are different features with different targets." + }, + { + "left": "pull_request:45490", + "right": "pull_request:45626", + "accept": false, + "reason": "CTSM model addition and PP-FormulaNet model support are separate model PRs, not duplicates." + }, + { + "left": "pull_request:45490", + "right": "pull_request:45630", + "accept": false, + "reason": "CTSM and Kimi2-6 are distinct model additions with different implementations and test coverage." + }, + { + "left": "pull_request:45626", + "right": "pull_request:45630", + "accept": false, + "reason": "PP-FormulaNet and Kimi2-6 are unrelated model additions; the overlap is only generic onboarding files." + } + ] + }, + "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": 23, + "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-43488-3", + "nodes": [ + "pull_request:43488", + "pull_request:43532", + "pull_request:45476" + ], + "soft_pairs": [ + "pull_request:43488|pull_request:43532", + "pull_request:43488|pull_request:45476", + "pull_request:43532|pull_request:45476" + ], + "prepared_review_unit_hash": "b3131465548bef1fa2e299b189e40654d592439467b2a1a31cce3533f7e7f785", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 7468, + "estimated_input_tokens": 1867, + "estimated_eval_tokens": 3990 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 7468, + "estimated_input_tokens": 1867, + "estimated_eval_tokens": 3990 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These three pull requests are not duplicates of one another. They are all \"don't merge\"/demo-style changes, but they touch different code paths and subsystems: packaging/versioning, CI/workflow plumbing, and a workflow-caller plus unrelated tokenization/test edits. The shared vit test filename appears incidental rather than indicating the same change.", + "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 concrete changes: 43488 edits setup/dependency/version metadata and a ViT test, while 43532 rewrites self-comment CI workflows and testing utilities. Shared test filename is not enough to make them the same fix." + }, + { + "left": "pull_request:43488", + "right": "pull_request:45476", + "accept": false, + "reason": "43488 is packaging/version/dependency housekeeping; 45476 adds a PR CI caller workflow and unrelated dummy edits in CLIP/Chinese-CLIP/ViT files. No single underlying bug or change matches." + }, + { + "left": "pull_request:43532", + "right": "pull_request:45476", + "accept": false, + "reason": "Both mention tests/workflows, but they target different code paths and repos: 43532 changes self-comment/self-scheduled/slack notification logic, while 45476 adds a workflow-caller and unrelated tokenization/test edits. 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": 11, + "component_count": 23, + "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": "25d55e9326efa426b03fcc769db20a121adebd7abf12862a2d0d2b7e6dcd7652", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6082, + "estimated_input_tokens": 1521, + "estimated_eval_tokens": 3298 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6082, + "estimated_input_tokens": 1521, + "estimated_eval_tokens": 3298 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are related pipeline-addition PRs, but they implement different features: promptable concept segmentation vs promptable visual segmentation, with different task docs, pipeline modules, and model/test coverage. They should not be merged as duplicates.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: the two PRs target different segmentation pipelines and different underlying integrations, so they are not the same change.", + "best_issue_reason": null, + "best_pr_reason": "If a representative is needed, PR 43613 is the broader feature PR, touching more model integrations and tests, but it is still not a duplicate of 43612.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43612", + "right": "pull_request:43613", + "accept": false, + "reason": "Same general area, but not the same underlying change. One adds promptable concept segmentation and the other adds promptable visual segmentation, with different docs, pipeline files, and model/test targets." + } + ] + }, + "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": 23, + "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": "68b3d90c3f85dcb3b6c96790e7c9d56b2e399c8f289fbbc0b917b6527abaadc8", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4293, + "estimated_input_tokens": 1074, + "estimated_eval_tokens": 2404 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4293, + "estimated_input_tokens": 1074, + "estimated_eval_tokens": 2404 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are two unrelated Trainer enhancement PRs that only overlap on the same file and subsystem. One changes gradient-accumulation loss scaling, the other factors out signature-column inspection for custom trainers/PEFT handling.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 43651 is a slightly stronger canonical representative because it has more discussion and a clearer end-to-end behavioral change; 43663 is a separate, independent refactor/extension point.", + "best_issue_reason": null, + "best_pr_reason": "PR 43651 is the better cluster representative overall, but only by convention; the PRs are not duplicates and should not be merged into one triage bucket as the same fix.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43651", + "right": "pull_request:43663", + "accept": false, + "reason": "Different underlying problems: 43651 fixes loss normalization during gradient accumulation, while 43663 adds an overridable signature-column helper for trainer input filtering. Same file/subsystem is not enough to treat them as the same change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 13, + "component_count": 23, + "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": "ef859ae9ccf165169fc29c86d809480ce17573e63b703af51b58ab9f8826f290", + "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": "43842 looks like the cleanest representative for the concrete `TypeAdapter`/pydantic NameError fix in `src/transformers/cli/serve.py`. 43836 is closely related and appears to be the same file-level fix family, while 43656 is only superficially similar and seems broader and tied to a different explicit issue target.", + "confidence": 0.79, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 43842 is the most focused patch for the specific CLI `TypeAdapter` NameError path, with the clearest narrow fix shape and explicit pydantic-not-installed context.", + "best_issue_reason": null, + "best_pr_reason": "PR 43842 is the best representative because it is the most targeted and least invasive fix for the concrete runtime failure in `serve.py`.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43656", + "right": "pull_request:43842", + "accept": false, + "reason": "Both touch `src/transformers/cli/serve.py`, but 43656 is broader and only softly similar to 43842; its different explicit issue target and wider diff make it unsafe to treat as the same underlying bugfix." + }, + { + "left": "pull_request:43836", + "right": "pull_request:43842", + "accept": true, + "reason": "These are tightly related fixes in the same file, share the same explicit issue target, and both address the same `TypeAdapter` NameError/annotation evaluation problem in the CLI serve path." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The summary is a bit too strong for the packet. 43836 and 43842 are well-supported as closely related fixes in the same file and even share an issue target, but 43656 only has soft_similarity with 43842 and a different explicit issue target. Its previewed diff also looks broader than a TypeAdapter-only patch. So I would not state that all three are clearly the same concrete bugfix or that the 43656\u219443842 pair is definitely mergeable without more evidence." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 14, + "component_count": 23, + "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": 15, + "component_count": 23, + "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:44024", + "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:44071|pull_request:44722", + "pull_request:44018|pull_request:44116", + "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:44722", + "pull_request:44017|pull_request:44161", + "pull_request:44017|pull_request:44073", + "pull_request:44068|pull_request:44071", + "pull_request:44071|pull_request:44086", + "pull_request:43997|pull_request:44073", + "pull_request:44017|pull_request:44071", + "pull_request:44059|pull_request:44071", + "pull_request:44073|pull_request:44101", + "pull_request:44059|pull_request:44068", + "pull_request:44018|pull_request:44059", + "pull_request:44056|pull_request:44101", + "pull_request:44073|pull_request:44161", + "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:43997|pull_request:44071", + "pull_request:44010|pull_request:44071", + "pull_request:44010|pull_request:44073", + "pull_request:44018|pull_request:44129", + "pull_request:43997|pull_request:44074", + "pull_request:43997|pull_request:44129", + "pull_request:44010|pull_request:44018", + "pull_request:44071|pull_request:44129", + "pull_request:43996|pull_request:44161", + "pull_request:43996|pull_request:44017", + "pull_request:44010|pull_request:44044", + "pull_request:44044|pull_request:44074", + "pull_request:44066|pull_request:44722", + "pull_request:44085|pull_request:44722", + "pull_request:44085|pull_request:44129", + "pull_request:43996|pull_request:44007", + "pull_request:43996|pull_request:44129", + "pull_request:44044|pull_request:44129", + "pull_request:44044|pull_request:44154", + "pull_request:44024|pull_request:44076" + ], + "prepared_review_unit_hash": "9a8e3d4fec07214ea05d3b70985cde2248d4fec0b5472f6d432ba0d0b4d141af", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 77, + "serialized_chars": 84507, + "estimated_input_tokens": 21127, + "estimated_eval_tokens": 42510 + }, + "budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 72, + "serialized_chars": 76941, + "estimated_input_tokens": 19236, + "estimated_eval_tokens": 38728 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a wave of model-by-model output-tracing refactors. The closest duplicates are the GPT-J/CodeGen cluster and the GPT-Neo pair; the rest are separate model implementations that only share the same refactor pattern.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "pull_request:44722 is the best canonical PR for the GPT-J/CodeGen subcluster: it is the broadest file-level refactor, covering both modeling_codegen.py and modeling_gptj.py, and subsumes the narrower GPT-J-only variant.", + "best_issue_reason": null, + "best_pr_reason": "pull_request:44722 is the strongest overall representative because it most completely captures the shared GPT-J/CodeGen output-tracing change and overlaps the narrower GPT-J-only PRs.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43996", + "right": "pull_request:44085", + "accept": false, + "reason": "CVT/FNet and GPT-J are different concrete model code paths; only the high-level output-tracing theme matches." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44044", + "accept": false, + "reason": "CVT/FNet and DeBERTa are unrelated model implementations with different forward paths." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44085", + "accept": true, + "reason": "Both are GPT-J output-tracing refactors in src/transformers/models/gptj/modeling_gptj.py; 44066 just bundles the extra CodeGen companion change, so this is the same underlying GPT-J edit." + }, + { + "left": "pull_request:44007", + "right": "pull_request:44072", + "accept": false, + "reason": "RegNet and EfficientNet are separate image-model implementations; not the same change." + }, + { + "left": "pull_request:44072", + "right": "pull_request:44722", + "accept": false, + "reason": "EfficientNet and GPT-J/CodeGen are different model code paths." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44072", + "accept": false, + "reason": "GPT-J/CodeGen output tracing and EfficientNet output tracing are different concrete edits." + }, + { + "left": "pull_request:44013", + "right": "pull_request:44044", + "accept": false, + "reason": "MobileNetV2 and DeBERTa are unrelated model implementations." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J/CodeGen and MGP-STR touch different files and different model code paths." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-J/CodeGen and MPT are different concrete implementations." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44068", + "accept": true, + "reason": "Both are GPT-Neo output-tracing refactors in the same GPT-Neo file/test area, so they look like the same underlying change." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44068", + "accept": false, + "reason": "GPT-J/CodeGen and GPT-Neo are different model code paths; similar refactor style is not enough." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44066", + "accept": false, + "reason": "GPT-Neo and GPT-J/CodeGen are related refactors but not the same concrete change." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44722", + "accept": false, + "reason": "ResNet and GPT-J/CodeGen are unrelated model-specific edits." + }, + { + "left": "pull_request:44086", + "right": "pull_request:44722", + "accept": false, + "reason": "MGP-STR and GPT-J/CodeGen are different concrete model implementations." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44085", + "accept": false, + "reason": "ResNet and GPT-J are separate model implementations." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44019", + "accept": false, + "reason": "GPT-Neo and ResNet are unrelated code paths." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44071", + "accept": false, + "reason": "ResNet and MPT are different model implementations." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo and Flaubert/XLM are different code paths." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT-Neo and GPT-J/CodeGen are different model refactors; same wave, not the same change." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44722", + "accept": false, + "reason": "MPT and GPT-J/CodeGen are unrelated model implementations." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-2 and MGP-STR are different concrete model paths." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J and MGP-STR are unrelated concrete changes." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT-2 and GPT-J/CodeGen are distinct model refactors." + }, + { + "left": "pull_request:44098", + "right": "pull_request:44101", + "accept": false, + "reason": "ViLT and Flaubert/XLM are different model families and different code paths." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44722", + "accept": false, + "reason": "Segformer and GPT-J/CodeGen are not the same underlying change." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44161", + "accept": false, + "reason": "Segformer and LongT5 are different implementations." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44073", + "accept": false, + "reason": "Segformer and VisualBert are different concrete model edits." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-Neo and MPT are different model code paths." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44076", + "accept": false, + "reason": "MPT and ImageGPT are unrelated model-specific refactors." + }, + { + "left": "pull_request:44074", + "right": "pull_request:44101", + "accept": false, + "reason": "TextNet and Flaubert/XLM are different model implementations." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44101", + "accept": false, + "reason": "MPNet and Flaubert/XLM are unrelated concrete changes." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44017", + "accept": false, + "reason": "RegNet and Segformer are different architectures." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44056", + "accept": false, + "reason": "RegNet and MPNet are unrelated implementations." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44129", + "accept": false, + "reason": "MPT and SpeechT5 share only the output-tracing pattern, not the same code path." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44161", + "accept": false, + "reason": "CVT/FNet and LongT5 are unrelated concrete edits." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44017", + "accept": false, + "reason": "CVT/FNet and Segformer are different model code paths." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44071", + "accept": false, + "reason": "SqueezeBert and MPT are different model implementations." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44073", + "accept": false, + "reason": "SqueezeBert and VisualBert are not the same underlying bug or change." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44129", + "accept": false, + "reason": "GPT-Neo and SpeechT5 are distinct model-specific refactors." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44018", + "accept": false, + "reason": "RegNet and GPT-Neo are unrelated model implementations." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44161", + "accept": false, + "reason": "RegNet and LongT5 have no concrete code-path overlap." + }, + { + "left": "pull_request:44074", + "right": "pull_request:44161", + "accept": false, + "reason": "TextNet and LongT5 are separate model-specific changes." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44071", + "accept": false, + "reason": "RegNet and MPT only share the broad refactor theme, not the same edit." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44044", + "accept": false, + "reason": "SqueezeBert and DeBERTa are unrelated concrete changes." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44074", + "accept": false, + "reason": "DeBERTa and TextNet are separate model refactors." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44722", + "accept": true, + "reason": "Same GPT-J/CodeGen output-tracing refactor family with overlapping file-level changes; 44722 is the broader later version." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44722", + "accept": true, + "reason": "Both target GPT-J output tracing in the same file family; 44722 adds the CodeGen companion change." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44129", + "accept": false, + "reason": "GPT-J and SpeechT5 are unrelated model code paths." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44007", + "accept": false, + "reason": "CVT/FNet and RegNet are different architectures." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44129", + "accept": false, + "reason": "CVT/FNet and SpeechT5 are different concrete changes." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44129", + "accept": false, + "reason": "DeBERTa and SpeechT5 are unrelated model-specific edits." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44154", + "accept": false, + "reason": "DeBERTa and ViLT are different model implementations; same refactor style is not enough." + }, + { + "left": "pull_request:44024", + "right": "pull_request:44076", + "accept": false, + "reason": "FocalNet and ImageGPT are different concrete model paths." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "Reject: the overall clustering is mostly grounded, but one soft-edge rationale is not precise enough. In particular, the 44066 vs 44085 note mislabels the pair as CVT/FNet vs GPT-J; both PRs are in the GPT-J/CodeGen family and share the same underlying output-tracing file area. More generally, keep the pair reasons tied to the exact PR contents and avoid broad model-family labels when the packet shows a closer same-file overlap." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 15, + "component_count": 23, + "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:44056", + "pull_request:44073", + "pull_request:44074", + "pull_request:44129" + ], + "soft_pairs": [ + "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": "fab376b91c26278c8513a71afc5b414e828cf2c47e09cd19e314b13893bc747e", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 77, + "serialized_chars": 84507, + "estimated_input_tokens": 21127, + "estimated_eval_tokens": 42510 + }, + "budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 5, + "serialized_chars": 13066, + "estimated_input_tokens": 3267, + "estimated_eval_tokens": 6790 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These PRs are all model-specific refactors for standardized output tracing/capture, but they affect different architectures and code paths. They are thematically similar, not duplicates of the same change.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44129 is the best anchor for this cluster because it has an explicit issue target (#43979) and a concrete SpeechT5 output-tracing refactor, while the others are separate model migrations.", + "best_issue_reason": null, + "best_pr_reason": "PR 44129 is the strongest representative: it is tied to a tracked issue and makes a specific behavior change in one concrete model path. The other PRs are similar refactors, but each is model-local and not mergeable into a single duplicate PR.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44073", + "right": "pull_request:44074", + "accept": false, + "reason": "Same refactor theme, but different models (VisualBert vs TextNet) and different files; these do not fix the same underlying bug and would not be merged into one PR." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44073", + "accept": false, + "reason": "Both standardize output tracing, but MPNet and VisualBert are unrelated code paths with different layer hooks and model behavior." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44074", + "accept": false, + "reason": "These are separate model migrations in different architectures; similarity is only at the abstraction level, not the concrete change." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44010", + "accept": false, + "reason": "RegNet and SqueezeBert are distinct models with different output plumbing; this is shared refactor pattern, not the same fix." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44129", + "accept": false, + "reason": "Different models and different output semantics; SpeechT5 has an explicit tracked issue, while SqueezeBert is a separate migration." + } + ] + }, + "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": 23, + "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": "86bd509fa3dea8c762ecdb9a744480991765b3e84d897f5f2c95497876aea6e6", + "component_budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 40, + "serialized_chars": 40172, + "estimated_input_tokens": 10043, + "estimated_eval_tokens": 20342 + }, + "budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 40, + "serialized_chars": 40172, + "estimated_input_tokens": 10043, + "estimated_eval_tokens": 20342 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are all similar output-tracing refactors, but they target different model implementations and code paths. They are not duplicates of the same underlying bug/change, so none of the soft edges should be merged.", + "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 files and architectures; same refactor theme, not the same concrete change." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44000", + "accept": false, + "reason": "Different model implementations; similar output-tracing cleanup only." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44001", + "accept": false, + "reason": "Different model code paths; not plausibly one merged PR for a single bug/change." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44003", + "accept": false, + "reason": "Only shares the general refactor pattern; the affected models are unrelated." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44029", + "accept": false, + "reason": "Different target model and file; not the same underlying fix." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44001", + "accept": false, + "reason": "Separate models and implementations; same housekeeping pattern only." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44002", + "accept": false, + "reason": "Not the same code path or bug; just another tracing refactor." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44025", + "accept": false, + "reason": "Different model families and files; no shared concrete defect." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44026", + "accept": false, + "reason": "Both are refactors, but for different model wrappers/code paths." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44027", + "accept": false, + "reason": "Different encoder-decoder model; not mergeable as one PR fixing one issue." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44001", + "accept": false, + "reason": "Different model implementations; same refactor style only." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44002", + "accept": false, + "reason": "Unrelated model files and behavior; not the same concrete change." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44003", + "accept": false, + "reason": "Different subsystems and code paths; too broad to be a duplicate." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44025", + "accept": false, + "reason": "Same tracing theme, but distinct models and outputs." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44002", + "accept": false, + "reason": "Separate model-specific refactors; no single underlying bug." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44003", + "accept": false, + "reason": "Different architectures and filenames; not a duplicate PR pair." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44025", + "accept": false, + "reason": "Different models; similar API cleanup only." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44029", + "accept": false, + "reason": "Different model families and code paths; not one change." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44003", + "accept": false, + "reason": "No shared concrete bug; only a shared refactoring pattern." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44028", + "accept": false, + "reason": "Falcon/Mamba vs SuperPoint are unrelated implementations." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44004", + "accept": false, + "reason": "Different model internals; not plausibly merged as one PR." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44004", + "accept": false, + "reason": "Different model code paths; same broad tracing refactor only." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44004", + "accept": false, + "reason": "Different models and behavior changes; not the same bug or feature." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44004", + "accept": false, + "reason": "Different target files and implementations; too broad to dedupe." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44004", + "accept": false, + "reason": "Codegen and vision-text dual encoder are unrelated concrete changes." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44026", + "accept": false, + "reason": "Both are output-tracing refactors, but for distinct encoder-decoder wrappers." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44027", + "accept": false, + "reason": "Different model families and forward paths; not the same fix." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44028", + "accept": false, + "reason": "Different model code and tests; not one underlying change." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44029", + "accept": false, + "reason": "Depth Anything and RWKV are unrelated concrete implementations." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44030", + "accept": false, + "reason": "Different model targets; same refactor theme only." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44029", + "accept": false, + "reason": "Distinct model wrappers and code paths; not mergeable as one PR." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44027", + "accept": false, + "reason": "Different encoder-decoder models; no common underlying defect." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44028", + "accept": false, + "reason": "Unrelated model implementations; only generic similarity." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44030", + "accept": false, + "reason": "Different model subsystems; not the same change." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44028", + "accept": false, + "reason": "Speech encoder-decoder and SuperPoint are different code paths entirely." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44029", + "accept": false, + "reason": "Different model families; no shared concrete bug." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44030", + "accept": false, + "reason": "Different targets and behavior; not a duplicate PR." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44029", + "accept": false, + "reason": "Different architectures and files; same refactor motif only." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44030", + "accept": false, + "reason": "Separate model implementations; not the same underlying fix." + }, + { + "left": "pull_request:44029", + "right": "pull_request:44030", + "accept": false, + "reason": "RWKV and DPR are unrelated models; cannot be merged as one concrete 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": 17, + "component_count": 23, + "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": "5bd462574ec678926dad52daf9985bdc3166fc8f315e2fcb8cd66c0fccef5cdc", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 11072, + "estimated_input_tokens": 2768, + "estimated_eval_tokens": 5792 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 11072, + "estimated_input_tokens": 2768, + "estimated_eval_tokens": 5792 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "All three PRs are separate model-addition implementations for different architectures (PenguinVL, DeepSeek-OCR-2, Voxtral TTS). They share only boilerplate integration files and docs registration, so they are not duplicates.", + "confidence": 0.99, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR among these: each PR targets a different model with distinct configs, processors, and modeling code.", + "best_issue_reason": null, + "best_pr_reason": "PR #44662 is the most complete/representative implementation in the set, with broad model, image-processing, processing, docs, and test coverage.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44662", + "right": "pull_request:45401", + "accept": false, + "reason": "Different models and codepaths: PenguinVL vs Voxtral TTS. Shared auto/docs files are just integration scaffolding, not the same bug or change." + }, + { + "left": "pull_request:44662", + "right": "pull_request:45075", + "accept": false, + "reason": "Different model implementations (PenguinVL vs DeepSeek-OCR-2) with unrelated modeling, conversion, and test files. Not mergeable as one fix." + }, + { + "left": "pull_request:45075", + "right": "pull_request:45401", + "accept": false, + "reason": "DeepSeek-OCR-2 and Voxtral TTS are distinct model additions touching different logic and artifacts; overlap is only generic registry/docs boilerplate." + } + ] + }, + "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": 23, + "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": "87438852cca3efb6caab9f559a68504e66d6a60519924ac47058b9ff2f892c4f", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4408, + "estimated_input_tokens": 1102, + "estimated_eval_tokens": 2460 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4408, + "estimated_input_tokens": 1102, + "estimated_eval_tokens": 2460 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two related but distinct pull requests around module/kernel fusion. One introduces a new Module Fusion API scaffold, while the other wires n-to-1 kernel fusion through KernelConfig and model loading. They share a feature area, but they are not the same concrete change.", + "confidence": 0.87, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45363 is the stronger canonical PR for the cluster: it is the broader, more user-facing implementation of kernel fusion via KernelConfig across loading/integration paths, whereas #44979 is mainly the underlying Module Fusion API scaffolding.", + "best_issue_reason": null, + "best_pr_reason": "PR #45363 is the best representative because it covers the concrete end-to-end fusion behavior and multiple integration points, making it the most complete expression of the cluster\u2019s feature theme.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44979", + "right": "pull_request:45363", + "accept": false, + "reason": "Related fusion work, but not the same code-path change. #44979 adds a new Module Fusion API/module_fusion.py scaffold, while #45363 implements n-to-1 kernel fusion via KernelConfig and integration changes. They would not plausibly be merged as one single PR without collapsing distinct layers of the feature." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 19, + "component_count": 23, + "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": "b7e0704b31f03fee64399c486c1d0bb2faa141fce568bebf317340f83f72241a", + "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 fix the same concrete bug in `_patch_mistral_regex`: using `tokenizer.backend_tokenizer.pre_tokenizer` caused an AttributeError, and both switch to `tokenizer.pre_tokenizer`. The second PR is a clearer, more complete implementation because it includes test coverage.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "pull_request:45317 is the better canonical PR: it addresses the same bug as 45086 but is more complete, with test changes and a clearer title tied to the exact failure mode.", + "best_issue_reason": null, + "best_pr_reason": "pull_request:45317 is the best overall PR because it fixes the same code path as 45086 and adds regression tests, making it the more complete merge candidate.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45086", + "right": "pull_request:45317", + "accept": true, + "reason": "Same underlying bug and same code path in `tokenization_utils_tokenizers.py`; the diffs are effectively the same fix, with 45317 adding tests." + } + ] + }, + "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": 23, + "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": "8977d3259a77e06e7c5c632e8a082bfc95071efae99f70ca41f56ed5938e75e1", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6066, + "estimated_input_tokens": 1517, + "estimated_eval_tokens": 3290 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6066, + "estimated_input_tokens": 1517, + "estimated_eval_tokens": 3290 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two PRs are thematically related around NemotronH, but they address different changes: one is a conversion-mapping/model inheritance refactor, while the other splits NemotronH into dense and sparse model families with docs/tests updates. They are not the same underlying change and should not be merged as duplicates.", + "confidence": 0.89, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45569 is the broader, more central architecture refactor, introducing the dense/sparse model split and associated registry/docs/test updates.", + "best_issue_reason": null, + "best_pr_reason": "PR #45569 is the best representative of the cluster because it covers the main public-facing NemotronH restructuring, while #45115 is a narrower conversion-mapping/inheritance adjustment.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45115", + "right": "pull_request:45569", + "accept": false, + "reason": "Different concrete changes: #45115 focuses on checkpoint conversion mapping and structural renames for NemotronH compatibility, whereas #45569 creates separate NemotronH dense/sparse model variants and updates docs/tests. Related but not the same code-path fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 21, + "component_count": 23, + "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": "61f7a1dc27ee1ce1592e27e151bad0f6f2184cfd449135eaefa17c8ba9915192", + "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 related pull requests for heterogeneous-model work, but they are not duplicates: one adds per-layer config plumbing, the other adds broader heterogeneous modeling support built on top of that plumbing.", + "confidence": 0.89, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45332 is the broader, more central change: it adds heterogeneous model support across modeling/cache/masking and naturally subsumes the config plumbing work.", + "best_issue_reason": null, + "best_pr_reason": "PR #45332 is the best representative artifact for the cluster because it covers the end-to-end heterogeneous-model feature rather than only the configuration layer.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45332", + "right": "pull_request:45333", + "accept": false, + "reason": "Related feature work, but not the same underlying change: #45333 only adds per-layer config support, while #45332 implements the larger heterogeneous modeling path and several runtime integrations. 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": 22, + "component_count": 23, + "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-45394-5", + "nodes": [ + "pull_request:45394", + "pull_request:45487", + "pull_request:45592", + "pull_request:45596", + "pull_request:45615" + ], + "soft_pairs": [ + "pull_request:45394|pull_request:45596", + "pull_request:45487|pull_request:45592", + "pull_request:45487|pull_request:45596", + "pull_request:45487|pull_request:45615", + "pull_request:45592|pull_request:45596", + "pull_request:45592|pull_request:45615", + "pull_request:45596|pull_request:45615" + ], + "prepared_review_unit_hash": "1b7fda14751503616bdfd180ca7f1a7060c379fc1fb79f2abdd55deeedeb0229", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 7, + "serialized_chars": 13275, + "estimated_input_tokens": 3319, + "estimated_eval_tokens": 6894 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 7, + "serialized_chars": 13275, + "estimated_input_tokens": 3319, + "estimated_eval_tokens": 6894 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "One substantive code fix PR (AltCLIP/ChineseCLIP model-parallel handling) sits alongside several unrelated test-only expectation updates for other models. The cluster is not a set of true duplicates.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45487 is the strongest representative of the cluster: it fixes an actual model-parallel code-path bug with implementation changes (not just test expectations) and affects multiple related model files.", + "best_issue_reason": null, + "best_pr_reason": "PR 45487 is the best standalone representative because it addresses the underlying runtime issue directly, while the other PRs are narrower test-only adjustments or unrelated model-specific fixes.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45394", + "right": "pull_request:45596", + "accept": false, + "reason": "Different models and different problems: XCLIP model-parallel split-module fix vs BLT XPU test expectation updates." + }, + { + "left": "pull_request:45487", + "right": "pull_request:45592", + "accept": false, + "reason": "AltCLIP/ChineseCLIP runtime/model-parallel fix is unrelated to FastVLM test padding-side changes." + }, + { + "left": "pull_request:45487", + "right": "pull_request:45596", + "accept": false, + "reason": "Different underlying bug/change; one is a broad model-parallel code fix, the other is BLT-specific XPU test expectations." + }, + { + "left": "pull_request:45487", + "right": "pull_request:45615", + "accept": false, + "reason": "ChineseCLIP/AltCLIP model-parallel fix and Qianfan OCR XPU expectations are model-specific and do not share the same concrete code path." + }, + { + "left": "pull_request:45592", + "right": "pull_request:45596", + "accept": false, + "reason": "Both are test-oriented, but they target different models and different failures, so they are not the same change." + }, + { + "left": "pull_request:45592", + "right": "pull_request:45615", + "accept": false, + "reason": "FastVLM padding-side test adjustment is unrelated to Qianfan OCR XPU expectation updates." + }, + { + "left": "pull_request:45596", + "right": "pull_request:45615", + "accept": false, + "reason": "Both add XPU-specific test expectations, but they are for different models and expected outputs, not one shared bug 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": 23, + "component_count": 23, + "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": "d436a76c44eb3fddf78e17b6a3fb51def215043e587f4230dc9097d1c1da9175", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5514, + "estimated_input_tokens": 1379, + "estimated_eval_tokens": 3014 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5514, + "estimated_input_tokens": 1379, + "estimated_eval_tokens": 3014 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are related only at a very broad type-checking level, but they are not the same PR: one is a sweeping type-check cleanup across many files, while the other adds specific typing helpers and targeted modeling fixes.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45415 is the broader umbrella change: it touches many files and updates type-checking config, so it is the more canonical representative of the cluster.", + "best_issue_reason": null, + "best_pr_reason": "PR 45415 is the best overall representative because it is the largest, most general type-checking pass in the set; 45425 is narrower and more specialized.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45415", + "right": "pull_request:45425", + "accept": false, + "reason": "Reject: both are typing-related, but they address different scopes and code paths. 45415 is a repo-wide type-checking sweep, while 45425 adds concrete typing protocols/helpers and fixes around modeling utilities; 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 + } + ] +} diff --git a/snapshots/20260424T180025Z/analysis-runs/hybrid-model-20260424t180025z/manifest.json b/snapshots/20260424T180025Z/analysis-runs/hybrid-model-20260424t180025z/manifest.json new file mode 100644 index 0000000000000000000000000000000000000000..f81acd2c16c43292ce1eb0a808b9702c99f67dea --- /dev/null +++ b/snapshots/20260424T180025Z/analysis-runs/hybrid-model-20260424t180025z/manifest.json @@ -0,0 +1,14 @@ +{ + "analysis_id": "hybrid-model-20260424t180025z", + "artifacts": { + "hybrid": "snapshots/20260424T180025Z/analysis-runs/hybrid-model-20260424t180025z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260424T180025Z/analysis-runs/hybrid-model-20260424t180025z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "model": null, + "published_at": "2026-04-24T18:16:19Z", + "repo": "huggingface/transformers", + "schema_version": 1, + "snapshot_id": "20260424T180025Z", + "variant": "hybrid" +} diff --git a/snapshots/20260424T180025Z/manifest.json b/snapshots/20260424T180025Z/manifest.json index 999a0cf65275c8e528595600e5a5a504b5626a2e..d9192a55cd280b756255cf4a83c59393e2189f76 100644 --- a/snapshots/20260424T180025Z/manifest.json +++ b/snapshots/20260424T180025Z/manifest.json @@ -32,6 +32,24 @@ "timeline_events": 668 }, "extracted_at": "2026-04-24T18:00:25Z", + "published_analysis": { + "canonical_analysis_id": "hybrid-model-20260424t180025z", + "runs": { + "hybrid-model-20260424t180025z": { + "analysis_id": "hybrid-model-20260424t180025z", + "artifacts": { + "hybrid": "snapshots/20260424T180025Z/analysis-runs/hybrid-model-20260424t180025z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260424T180025Z/analysis-runs/hybrid-model-20260424t180025z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "manifest_path": "snapshots/20260424T180025Z/analysis-runs/hybrid-model-20260424t180025z/manifest.json", + "model": null, + "published_at": "2026-04-24T18:16:19Z", + "variant": "hybrid" + } + }, + "schema_version": 1 + }, "repo": "huggingface/transformers", "snapshot_id": "20260424T180025Z", "watermark": {