diff --git a/analysis/current/analysis-report-hybrid.json b/analysis/current/analysis-report-hybrid.json index f3345d4495977a7b23dc2c3994998f9c29938f97..3be775bcf4551a3bd6eef8b783269cddb622cf7e 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": "20260508T060024Z", - "generated_at": "2026-05-08T06:10:54Z", + "snapshot_id": "20260508T120022Z", + "generated_at": "2026-05-08T12:10:13Z", "evidence_quality": "full", "llm_enrichment": true, "meta_bugs": [ @@ -1684,58 +1684,6 @@ } ] }, - { - "cluster_id": "cluster-44001-3", - "summary": "Cluster of 3 related pull requests linked by soft_similarity.", - "status": "open", - "confidence": 0.5, - "canonical_issue_number": null, - "canonical_pr_number": 44002, - "issue_numbers": [], - "pr_numbers": [ - 44001, - 44002, - 44004 - ], - "evidence_types": [ - "soft_similarity" - ], - "pr_comparisons": [ - { - "left_pr_number": 44001, - "right_pr_number": 44002, - "code_similarity": 0.175, - "size_similarity": 0.595, - "file_overlap": 0.0, - "area_overlap": 0.0, - "patch_similarity": 0.375, - "shared_filenames": [], - "shared_file_areas": [] - }, - { - "left_pr_number": 44001, - "right_pr_number": 44004, - "code_similarity": 0.087, - "size_similarity": 0.237, - "file_overlap": 0.0, - "area_overlap": 0.0, - "patch_similarity": 0.262, - "shared_filenames": [], - "shared_file_areas": [] - }, - { - "left_pr_number": 44002, - "right_pr_number": 44004, - "code_similarity": 0.125, - "size_similarity": 0.398, - "file_overlap": 0.0, - "area_overlap": 0.0, - "patch_similarity": 0.304, - "shared_filenames": [], - "shared_file_areas": [] - } - ] - }, { "cluster_id": "cluster-44018-2", "summary": "Cluster of 2 related pull requests linked by soft_similarity.", @@ -2076,16 +2024,6 @@ "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-44001-3", - "canonical_pr_number": 44002, - "duplicate_pr_numbers": [ - 44001, - 44004 - ], - "target_issue_number": null, - "reason": "PRs in cluster-44001-3 are treated as duplicates because they share soft_similarity evidence." - }, { "cluster_id": "cluster-44018-2", "canonical_pr_number": 44068, diff --git a/analysis/current/analysis-report-hybrid.llm-reviews.json b/analysis/current/analysis-report-hybrid.llm-reviews.json index 1ab873b5f8996120f8337599c84b546306cb89b1..ef036a53ad8c7e26d0253eaca8b422a79d9b3d56 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": "20260508T060024Z", - "generated_at": "2026-05-08T06:10:54Z", + "snapshot_id": "20260508T120022Z", + "generated_at": "2026-05-08T12:10:13Z", "model": "gpt-5.4-mini?service_tier=flex", "reviews": [ { @@ -26,12 +26,12 @@ "issue:13244|issue:16618", "issue:15980|issue:16618" ], - "prepared_review_unit_hash": "3221956896f07db0db30c428630f03850b825467e08522311bf58de4198a6639", + "prepared_review_unit_hash": "163347cf52a23d6c0061f8f90f2a785aee2a1a121517e2921c467a377909dc58", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 2477, + "serialized_chars": 2478, "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": 2478, "estimated_input_tokens": 620, "estimated_eval_tokens": 1496 }, @@ -48,24 +48,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "All three issues appear to be separate: one about Tapas tokenization, one about a private-model authentication/download error, and one about a generic model-load failure. The only mild overlap is between the two model-loading issues, but the titles point to different underlying causes, so I would not merge them as duplicates.", + "summary": "These three issues do not appear to describe the same underlying bug: one is about Tapas tokenization parity, one about private-model download/login error handling, and one about failing to load bert-base-uncased. The soft links are too broad to merge as duplicates.", "confidence": 0.87, - "canonical_issue_reason": "Issue #16618 is the broadest and most central of the set, covering a generic model-loading failure, so it is the best single representative if a canonical issue is needed.", + "canonical_issue_reason": "Issue #16618 is the most concrete and user-facing of the set, with a clear runtime failure scenario and a specific model name, so it is the best representative issue if one must be chosen.", "canonical_pr_reason": null, - "best_issue_reason": "#16618 is the most general and likely to attract/aggregate related reports about model loading, making it the best issue to keep as the cluster representative.", + "best_issue_reason": "#16618 has the clearest actionable symptom and is the most likely to be useful as the cluster representative; the other two are unrelated enough that they should not be treated as duplicates.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:13244", "right": "issue:16618", "accept": false, - "reason": "Tapas tokenization mismatch is a different problem from failing to load bert-base-uncased; they do not look like the same underlying bug." + "reason": "Different problem domains: Tapas tokenization parity vs. model loading failure for bert-base-uncased. No evidence they share the same code path or fix." }, { "left": "issue:15980", "right": "issue:16618", "accept": false, - "reason": "One is specifically about unauthorized access to a private model, while the other is a generic load failure for a public model; the causes are distinct." + "reason": "One is specifically about bad messaging when downloading a private model without login; the other is a load failure for a public model. Related at a very broad level, but not the same bug." } ] }, @@ -188,8 +188,8 @@ "issue:30277|issue:36331", "issue:34928|issue:36010", "issue:43039|issue:44805", - "issue:43901|issue:44512", "issue:41762|issue:43596", + "issue:43901|issue:44512", "issue:39290|issue:41720", "issue:44841|issue:45823", "issue:43039|issue:44560", @@ -211,12 +211,12 @@ "issue:41093|issue:41762", "issue:45800|issue:45823" ], - "prepared_review_unit_hash": "8cb3c5857230e72b115d9816ff6c8e0f49222d8241f23b056296c4767d1af142", + "prepared_review_unit_hash": "2734970753240655d80ec58cc7a5a101573ded43fad79c17f2d0241bb1a34924", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, @@ -224,435 +224,411 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 71, - "serialized_chars": 48868, - "estimated_input_tokens": 12217, - "estimated_eval_tokens": 24690 + "serialized_chars": 48874, + "estimated_input_tokens": 12219, + "estimated_eval_tokens": 24694 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly noisy and spans unrelated model/runtime/docs bugs; only the DeepSpeed ZeRO-3 index-0-out-of-bounds reports around Bert/Gemma3 look like true duplicates.", - "confidence": 0.84, - "canonical_issue_reason": "issue:43596 is the clearest and most central ZeRO-3 index-0-out-of-bounds report, and it links to the only true duplicate chain in this set (issue:41762 and issue:43638).", + "summary": "The cluster is mostly a grab bag of unrelated issues. The only clear duplicate pair is the Deepspeed ZeRO-3/Bert index-out-of-bounds reports (43596 and 43638); the rest are different model, docs, or runtime failures.", + "confidence": 0.61, + "canonical_issue_reason": "Issue 43596 is the best anchor for the ZeRO-3/Bert \"index 0 is out of bounds\" duplicate pair; it is the broader, earlier phrasing of that bug, which also covers 43638.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43596 is the best representative issue for the only coherent duplicate subgroup here: the ZeRO-3 init/load failure with index 0 out of bounds / size 0.", + "best_issue_reason": "43596 is the strongest single representative because it matches the same concrete ZeRO-3/Bert failure mode as 43638 and is the cleanest canonical target in this set.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44322", "right": "issue:45464", "accept": false, - "reason": "Different Qwen3.5 bugs: config attribute missing vs streaming chat/completions failure." + "reason": "Different model and failure mode; not the same bug." }, { "left": "issue:45237", "right": "issue:45685", "accept": false, - "reason": "Different model/backend problems: AMD GPU failure vs MPS histogram op error." + "reason": "Different hardware/backend error paths; not the same issue." }, { "left": "issue:43716", "right": "issue:45237", "accept": false, - "reason": "Different bugs: image preprocessor dtype mismatch vs GPT-OSS AMD GPU failure." + "reason": "Different model family and runtime problem." }, { "left": "issue:43828", "right": "issue:45237", "accept": false, - "reason": "Different model/runtime failures; only broad MoE relevance overlaps." + "reason": "Both mention inference errors, but they are different concrete bugs." }, { "left": "issue:45237", "right": "issue:45507", "accept": false, - "reason": "Different models and failure modes; not the same code-path bug." + "reason": "Different model and error type; not mergeable as one fix." }, { "left": "issue:44292", "right": "issue:45237", "accept": false, - "reason": "Different model-specific runtime errors." + "reason": "Different model/runtime context; no clear shared code path." }, { "left": "issue:30277", "right": "issue:35545", "accept": false, - "reason": "DeepSpeed collective mismatch is unrelated to ONNX export failure." + "reason": "Different subsystems: distributed training vs ONNX export." }, { "left": "issue:35545", "right": "issue:42915", "accept": false, - "reason": "ONNX export bug vs FP8 config failure are different issues." + "reason": "Different model/export bug vs FP8 config failure." }, { "left": "issue:35545", "right": "issue:41720", "accept": false, - "reason": "Different paths: export error vs auto device-map CUDA assert." + "reason": "Different failure modes and model paths." }, { "left": "issue:44509", "right": "issue:44512", "accept": false, - "reason": "Both are docs cleanup issues, but they cover different removed references." + "reason": "Both are docs regressions, but they concern different removed topics." }, { "left": "issue:35545", "right": "issue:36010", "accept": false, - "reason": "ONNX export error and GenerationMixin import error are unrelated." + "reason": "Different bugs: export to ONNX vs import error." }, { "left": "issue:44805", "right": "issue:45823", "accept": false, - "reason": "Mask-shape IndexError vs device_map auto device mismatch are different bugs." + "reason": "Different model/runtime errors; no shared concrete bug." }, { "left": "issue:43638", "right": "issue:44805", "accept": false, - "reason": "Different failure signatures; one is ZeRO-3 index-out-of-bounds, the other is mask-shape mismatch." + "reason": "Both are IndexError-shaped, but the triggering conditions and stack paths differ." }, { "left": "issue:43596", "right": "issue:44805", "accept": false, - "reason": "Same as above: ZeRO-3 index-out-of-bounds vs a different shape-mismatch error." + "reason": "Different error signatures and likely different code paths." }, { "left": "issue:44805", "right": "issue:45161", "accept": false, - "reason": "Different problems: mask/index shape error vs TP not working on GPT-OSS MoE." + "reason": "Different failure modes; only a broad index-error similarity." }, { "left": "issue:44805", "right": "issue:44918", "accept": false, - "reason": "Different runtime bugs with different code paths and symptoms." + "reason": "Different model and runtime context." }, { "left": "issue:34634", "right": "issue:35545", "accept": false, - "reason": "Processor voice_preset bug is unrelated to ONNX export." + "reason": "Unrelated features: BarkProcessor preset handling vs ONNX export." }, { "left": "issue:30277", "right": "issue:43638", "accept": false, - "reason": "Different DeepSpeed failures; collective mismatch is not the same as ZeRO-3 index-out-of-bounds." + "reason": "Different distributed-training bugs and different models." }, { "left": "issue:43596", "right": "issue:43638", "accept": true, - "reason": "Same ZeRO-3 index-0-out-of-bounds / size-0 failure during model load/init; only the model differs." + "reason": "Same ZeRO-3/Bert \"index 0 is out of bounds\" failure; only the pretrained/non-pretrained wording differs." }, { "left": "issue:43975", "right": "issue:44457", "accept": false, - "reason": "Detokenization regression and LoRA save/load mismatch are different bugs." + "reason": "Different models and different tokenization/LoRA behaviors." }, { "left": "issue:43039", "right": "issue:45161", "accept": false, - "reason": "Liger Kernel cross_entropy call issue vs GPT-OSS tensor-parallel failure are unrelated." + "reason": "Different MoE/kernel issue vs TP-only failure." }, { "left": "issue:44292", "right": "issue:44457", "accept": false, - "reason": "NVFP4 model error vs LoRA merge/save inconsistency are different." + "reason": "Different model/runtime bug; no shared underlying change." }, { "left": "issue:34928", "right": "issue:44805", "accept": false, - "reason": "FSDP checkpointing tensor-size mismatch is a different bug from the mask-shape IndexError." + "reason": "Checkpointing/FSDP mismatch is unrelated to the mask-shape IndexError." }, { "left": "issue:24643", "right": "issue:30277", "accept": false, - "reason": "Both involve DeepSpeed, but the concrete errors and code paths differ." + "reason": "Different DeepSpeed-related errors with different symptoms." }, { "left": "issue:43638", "right": "issue:45161", "accept": false, - "reason": "ZeRO-3 loading failure is unrelated to GPT-OSS tensor-parallel behavior." + "reason": "Different model and distributed setup; not the same bug." }, { "left": "issue:34928", "right": "issue:36331", "accept": false, - "reason": "Activation-checkpointing/FSDP mismatch and custom trainer kwarg breakage are unrelated." + "reason": "Activation-checkpointing/FSDP issue is unrelated to CustomTrainer signature mismatch." + }, + { + "left": "issue:43596", + "right": "issue:45161", + "accept": false, + "reason": "Different failure mode and model family." }, { "left": "issue:43716", "right": "issue:45507", "accept": false, - "reason": "Different model-specific bugs: dtype mismatch vs invalid method call." + "reason": "Different model and different error category." }, { "left": "issue:39290", "right": "issue:45081", "accept": false, - "reason": "Gemma3 config/vLLM sliding_window issue is unrelated to the Mistral tokenizer regex crash." + "reason": "Different models and distinct attribute/tokenizer errors." }, { "left": "issue:43828", "right": "issue:45161", "accept": false, - "reason": "Autocast dtype mismatch and GPT-OSS tensor-parallel failure are different issues." - }, - { - "left": "issue:43425", - "right": "issue:44292", - "accept": false, - "reason": "Torch compatibility issue vs NVFP4 model runtime error." + "reason": "Dtype mismatch under autocast is unrelated to TP-only MoE failure." }, { "left": "issue:44918", "right": "issue:45161", "accept": false, - "reason": "TRL SFT trainer embedding unpacking bug is unrelated to GPT-OSS TP failure." + "reason": "Different model and training stack; not the same bug." }, { "left": "issue:34928", "right": "issue:41720", "accept": false, - "reason": "Different training/device bugs with no shared concrete failure." + "reason": "Different distributed-training issues with no common concrete code path." }, { "left": "issue:43827", "right": "issue:44512", "accept": false, - "reason": "Both are docs issues, but they refer to different removed features." + "reason": "Both are documentation regressions, but they target different removed APIs/commands." }, { "left": "issue:43716", "right": "issue:44560", "accept": false, - "reason": "Different model/runtime failures; dtype mismatch vs video StopIteration." + "reason": "Different model/runtime bugs." }, { "left": "issue:43828", "right": "issue:45685", "accept": false, - "reason": "Different bugs: autocast dtype mismatch vs MPS histogram implementation gap." + "reason": "Different backend and symptom; only superficial dtype/runtime overlap." }, { "left": "issue:44560", "right": "issue:45685", "accept": false, - "reason": "Video StopIteration and MPS histogram error are unrelated." + "reason": "Different model areas and distinct backend errors." }, { "left": "issue:43039", "right": "issue:43828", "accept": false, - "reason": "Different failures despite both touching model execution." + "reason": "Different MoE/kernel failure vs autocast dtype mismatch." }, { "left": "issue:30277", "right": "issue:36331", "accept": false, - "reason": "DeepSpeed collective mismatch and trainer signature change are unrelated." + "reason": "Different stack layers: distributed collectives vs trainer API signature." }, { "left": "issue:34928", "right": "issue:36010", "accept": false, - "reason": "FSDP activation-checkpointing mismatch is unrelated to the import error." + "reason": "Different bugs in unrelated subsystems." }, { "left": "issue:43039", "right": "issue:44805", "accept": false, - "reason": "Liger Kernel cross_entropy issue is unrelated to mask-shape IndexError." + "reason": "Different model/runtime failures." }, { - "left": "issue:43901", - "right": "issue:44512", + "left": "issue:41762", + "right": "issue:43596", "accept": false, - "reason": "Both are docs, but they cover different deprecated fields/commands." + "reason": "Both are zero-3 related, but they involve different models and distinct error signatures." }, { "left": "issue:41762", - "right": "issue:43596", - "accept": true, - "reason": "Same ZeRO-3 index-0-out-of-bounds / size-0 failure during model loading; only the model differs." + "right": "issue:43638", + "accept": false, + "reason": "Same broad ZeRO-3 area, but not the same concrete bug." + }, + { + "left": "issue:43901", + "right": "issue:44512", + "accept": false, + "reason": "Different docs topics and different removals." }, { "left": "issue:39290", "right": "issue:41720", "accept": false, - "reason": "Different model/runtime bugs: Gemma3 sliding-window config vs Qwen3 auto device-map assert." + "reason": "Different model families and different runtime failures." }, { "left": "issue:44841", "right": "issue:45084", "accept": false, - "reason": "Processor failure for Voxtral is unrelated to the template compilation error." + "reason": "Different processor/parsing bug vs template compilation error." }, { - "left": "issue:45800", - "right": "issue:45823", + "left": "issue:43039", + "right": "issue:44560", "accept": false, - "reason": "Torch/transformers incompatibility is unrelated to Gemma4 device-map mismatch." + "reason": "Different model/runtime issues; too broad to merge." }, { "left": "issue:43866", "right": "issue:44863", "accept": false, - "reason": "Corrupted checkpoint and model-loading implementation bug are not the same underlying issue." + "reason": "Different model loading problems with no clear shared code path." }, { "left": "issue:43854", "right": "issue:43866", "accept": false, - "reason": "Unit-test load failure for GLM-4.7 differs from Ovis2 checkpoint corruption." + "reason": "Unit-test loading failure vs checkpoint corruption are different bugs." }, { "left": "issue:39290", "right": "issue:43531", "accept": false, - "reason": "Both mention sliding_window, but they involve different models and error contexts." + "reason": "Related Qwen3/Gemma area, but different attribute/shape issues." }, { "left": "issue:41093", "right": "issue:43638", "accept": false, - "reason": "Mask/tensor shape mismatch and ZeRO-3 index-out-of-bounds are different failures." + "reason": "Both are IndexErrors, but the mismatched mask/tensor shape bug is different from the ZeRO-3/Bert zero-size index bug." }, { "left": "issue:43425", "right": "issue:45070", "accept": false, - "reason": "Torch incompatibility and pydantic PretrainedConfig breakage are unrelated." + "reason": "Different compatibility problems: torch version vs pydantic model field." }, { "left": "issue:43596", "right": "issue:45800", "accept": false, - "reason": "ZeRO-3 model-load failure is unrelated to the torch 2.4.1/transformers 5.8.0 incompatibility." + "reason": "Both mention runtime compatibility-ish failures, but they are unrelated." }, { "left": "issue:45362", "right": "issue:45464", "accept": false, - "reason": "Both are Qwen3.5/chat-related, but one is a chat crash and the other is a streaming API failure." + "reason": "Different Qwen3.5 surfaces and different symptoms." }, { "left": "issue:43792", "right": "issue:45070", "accept": false, - "reason": "Whisper load failure and pydantic PretrainedConfig issue are unrelated." + "reason": "Whisper runtime failure is unrelated to pydantic-model breakage." }, { "left": "issue:43404", "right": "issue:43866", "accept": false, - "reason": "Mistral3 lm_head tying bug is unrelated to Ovis2 checkpoint corruption." + "reason": "Different model families and different loading/tie-weight problems." }, { "left": "issue:39290", "right": "issue:45823", "accept": false, - "reason": "Gemma3 sliding_window_pattern and Gemma4 device-map mismatch are different bugs." + "reason": "Different model/config mismatch and device-map forward issue." }, { - "left": "issue:44841", - "right": "issue:45823", + "left": "issue:45464", + "right": "issue:45685", "accept": false, - "reason": "Different multimodal model failures: processor bug vs device-map mismatch." + "reason": "Different models and completely different failure modes." }, { "left": "issue:43541", - "right": "issue:43716", + "right": "issue:45685", "accept": false, - "reason": "Mixtral grouped_mm tracing error is unrelated to the image preprocessor dtype mismatch." + "reason": "Different model/runtime problems; not the same underlying bug." }, { "left": "issue:43541", "right": "issue:43828", "accept": false, - "reason": "Different runtime bugs: grouped_mm tracing vs autocast dtype mismatch." - }, - { - "left": "issue:43541", - "right": "issue:45685", - "accept": false, - "reason": "Different backends and symptoms; not the same bug." + "reason": "Different code paths and distinct error types." }, { "left": "issue:36010", "right": "issue:39290", "accept": false, - "reason": "ImportError for GenerationMixin is unrelated to Gemma3 sliding_window_pattern." + "reason": "Import error vs config attribute error; unrelated bugs." }, { - "left": "issue:43039", - "right": "issue:44560", + "left": "issue:41762", + "right": "issue:43638", "accept": false, - "reason": "Liger Kernel cross_entropy issue and video StopIteration are unrelated." + "reason": "Same broad zero-3 category, but not the same concrete failure." }, { "left": "issue:43828", "right": "issue:44292", "accept": false, - "reason": "Different model/runtime errors with no shared concrete code path." + "reason": "Different model-specific runtime errors." }, { - "left": "issue:43716", + "left": "issue:43425", "right": "issue:44292", "accept": false, - "reason": "Different model-specific failures: dtype mismatch vs NVFP4 runtime error." - }, - { - "left": "issue:45464", - "right": "issue:45685", - "accept": false, - "reason": "Streaming chat failure and MPS histogram issue are unrelated." - }, - { - "left": "issue:43039", - "right": "issue:44918", - "accept": false, - "reason": "Liger Kernel cross_entropy bug is unrelated to the Qwen3.5 SFT trainer issue." - }, - { - "left": "issue:43716", - "right": "issue:45685", - "accept": false, - "reason": "Different model/backend bugs." - }, - { - "left": "issue:43541", - "right": "issue:45685", - "accept": false, - "reason": "Grouped_mm tracing and MPS histogram error are unrelated." + "reason": "Torch compatibility issue vs Qwen3 NVFP4 runtime error; unrelated." }, { - "left": "issue:43039", - "right": "issue:44560", + "left": "issue:45800", + "right": "issue:45823", "accept": false, - "reason": "Different bugs and code paths." + "reason": "Different incompatibility and device-mapping bugs." } ] }, "evaluator_result": { "accept": true, - "feedback": "The cluster summary is well grounded in the packet, and the soft-edge verdicts stay conservative overall. The accepted ZeRO-3 pairs are supported by closely matching index-0-out-of-bounds / size-0 load/init failures, while the other rejections avoid overstating similarity despite some broad topical overlap." + "feedback": "The summary stays within the packet: it treats most pairs conservatively as unrelated and only accepts the very close ZeRO-3/Bert IndexError pair (43596, 43638), which is well supported by the titles. No overstatement stands out." }, "evaluator_used": true, "retried": false, @@ -743,8 +719,8 @@ "issue:43645|issue:45399", "issue:40990|issue:44960", "issue:44530|issue:45005", - "issue:44360|issue:44512", "issue:42915|issue:45399", + "issue:44360|issue:44512", "issue:44863|issue:45005", "issue:43873|issue:45005", "issue:39186|issue:44918", @@ -758,12 +734,12 @@ "issue:43828|issue:44928", "issue:43866|issue:44403" ], - "prepared_review_unit_hash": "c859688ab53f908d17f6330d44859139e0d9151a23fd41f1f1dc159eb582b805", + "prepared_review_unit_hash": "3e1d880e260b5cc772cb18716942d26819e8185ab75ead1eedf62611dda4f08e", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, @@ -771,231 +747,219 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 34, - "serialized_chars": 37472, - "estimated_input_tokens": 9368, - "estimated_eval_tokens": 18992 + "serialized_chars": 37464, + "estimated_input_tokens": 9366, + "estimated_eval_tokens": 18988 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Only one strong duplicate cluster stands out: the Transformers v5 non-persistent-buffer corruption reports. The rest of the items appear to be separate model- or API-specific bugs.", - "confidence": 0.91, - "canonical_issue_reason": "issue:43950 is the clearest statement of the shared v5 regression: it names the non-persistent-buffer corruption directly and describes the affected load path (`from_pretrained`).", + "summary": "The set is mostly unrelated issues. The only clear duplicate family is the Transformers v5 non-persistent-buffer corruption regression (43644/43950/44534), and there is one plausible SigLIP2 duplicate pair (43054/43994).", + "confidence": 0.81, + "canonical_issue_reason": "Issue 43950 is the best canonical issue for the non-persistent-buffer regression: it states the underlying v5 corruption directly and subsumes the older, less specific report.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43950 is the best representative of the duplicate cluster because it is the most explicit about the root problem and is broad enough to cover the near-identical follow-ups.", + "best_issue_reason": "Issue 43950 is the strongest representative issue overall because it names the regression clearly, has the most actionable root-cause framing, and cleanly covers the duplicate buffer-corruption reports.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43296", "right": "issue:43366", "accept": false, - "reason": "Different problems: PaddleOCR-VL loading in vLLM vs GGUF support for gpt-oss." + "reason": "Different products and failure modes: PaddleOCR-VL loading vs GGUF/gpt-oss support." }, { "left": "issue:43572", "right": "issue:45070", "accept": false, - "reason": "Both involve configs, but one is a missing StableLm field and the other is a broader pydantic/PretrainedConfig regression." + "reason": "Both involve config changes in v5, but the concrete bugs differ: missing pad_token_idx vs pydantic PretrainedConfig field handling." }, { "left": "issue:44387", "right": "issue:45005", "accept": false, - "reason": "Unrelated symptoms: int4 quantization memory/OOM vs tied-weights behavior in translation models." + "reason": "Different symptoms and code paths: int4 OOM/reserved memory vs tied-weights behavior in translation models." }, { "left": "issue:43541", "right": "issue:45161", "accept": false, - "reason": "Different code paths: torch dynamo grouped_mm tracing vs GPT-OSS tensor-parallel support." + "reason": "Both mention MoE, but one is torch-dynamo grouped_mm tracing and the other is tensor-parallel behavior; not the same bug." }, { "left": "issue:43828", "right": "issue:45464", "accept": false, - "reason": "Different failures and models: autocast dtype mismatch vs streaming chat/completions inference error." + "reason": "Different models and triggers: autocast dtype mismatch in Phi-tiny-MoE vs streaming chat/completions failure in Qwen3.5." }, { "left": "issue:44291", "right": "issue:45070", "accept": false, - "reason": "`init_empty_weights` argument handling is unrelated to the pydantic `PretrainedConfig` field regression." + "reason": "Unexpected _is_hf_initialized argument during init_empty_weights is unrelated to the pydantic PretrainedConfig regression." }, { "left": "issue:45020", "right": "issue:45800", "accept": false, - "reason": "One is remote-code model breakage; the other is a torch/transformers version incompatibility." + "reason": "Broad remote_code breakage is not the same concrete issue as a torch/transformers version incompatibility." }, { "left": "issue:43366", "right": "issue:45464", "accept": false, - "reason": "GGUF gpt-oss architecture support is unrelated to Qwen3.5 streaming failures." + "reason": "Different subsystems: GGUF architecture support vs chat/completions streaming inference." }, { "left": "issue:43531", "right": "issue:45070", "accept": false, - "reason": "Sliding-window behavior in Qwen3-MoE is not the same as the config/pydantic regression." + "reason": "Qwen3-MoE sliding_window behavior is unrelated to the PretrainedConfig v5.4.0 field regression." }, { "left": "issue:43541", "right": "issue:44589", "accept": false, - "reason": "Tracing grouped_mm errors and missing Float8 storage are distinct runtime failures." + "reason": "Distinct runtime failures: grouped_mm tracing error vs missing Float8 storage type." }, { "left": "issue:41093", "right": "issue:43596", "accept": false, - "reason": "Mask-shape mismatch in indexing is unrelated to the zero3/BertModel empty-index crash." + "reason": "Both are tensor-shape/index errors, but they occur in different contexts and do not indicate the same underlying bug." }, { "left": "issue:43054", "right": "issue:43994", - "accept": false, - "reason": "Both mention SigLIP2, but one is a quality/embedding complaint and the other is a pipeline/AutoModel correctness bug; not clearly the same defect." + "accept": true, + "reason": "Both report SigLIP2 producing bad or nonsensical outputs for the same model family, likely the same model/processor implementation issue." }, { "left": "issue:45542", "right": "issue:45800", "accept": false, - "reason": "Undefined tf backend from tensorboard-only install is unrelated to torch/transformers incompatibility." + "reason": "TensorBoard/TensorFlow backend handling is unrelated to torch-version incompatibility." }, { "left": "issue:43716", "right": "issue:44918", "accept": false, - "reason": "Different models and issues: image-preprocessor dtype mismatch vs Qwen3.5 embedding unpacking with TRL." + "reason": "Different multimodal failures: image preprocessor dtype mismatch vs Qwen3.5 embedding unpacking in TRL SFT." }, { "left": "issue:44918", "right": "issue:45685", "accept": false, - "reason": "TRL embedding unpacking failure is unrelated to the MPS `histogram_mps` integer error." + "reason": "Different errors in different backends: TRL input embedding unpacking vs MPS histogram not implemented for Int." }, { "left": "issue:45632", "right": "issue:45698", "accept": false, - "reason": "Both involve custom/loading paths, but one is a trust_remote_code cache-key collision and the other is wrong module loading after save_pretrained; not clearly the same bug." + "reason": "Related area, but not clearly the same concrete bug: local-model leaf-dir cache collision vs wrong custom module after save_pretrained." }, { "left": "issue:43404", "right": "issue:45005", "accept": false, - "reason": "Both touch weight tying, but the affected models and failure modes are too different to treat as one duplicate." + "reason": "Both mention tied weights, but they target different model families and trigger paths; not enough evidence of one shared bug." }, { "left": "issue:43645", "right": "issue:45399", "accept": false, - "reason": "Notebook/custom-model initialization behavior is unrelated to the flash-attn2 fallback gating problem." + "reason": "Jupyter custom-model initialization regression is unrelated to flash-attn2 fallback gating." }, { "left": "issue:40990", "right": "issue:44960", "accept": false, - "reason": "High perplexity on gpt-oss-20b and the GLM5 issue are unrelated model-specific reports." + "reason": "High perplexity on gpt-oss-20b is unrelated to the GLM5 issue." }, { "left": "issue:44530", "right": "issue:45005", "accept": false, - "reason": "PagedAttentionCache/Qwen3.5 linear_attention crash is not the same as the tied-weights regression." + "reason": "PagedAttentionCache linear_attention crash is a different issue than tied-weights regression." }, { - "left": "issue:44360", - "right": "issue:44512", + "left": "issue:42915", + "right": "issue:45399", "accept": false, - "reason": "A DSA indexer discussion is unrelated to docs still mentioning a removed command." + "reason": "Qwen3-MoE FineGrainedFP8Config failure is unrelated to flash-attn2 fallback logic." }, { - "left": "issue:42915", - "right": "issue:45399", + "left": "issue:44360", + "right": "issue:44512", "accept": false, - "reason": "Qwen3MoE FP8 failure and flash-attn2 fallback checks are separate issues." + "reason": "DSA indexer implementation discussion is unrelated to the removed run-command documentation." }, { "left": "issue:44863", "right": "issue:45005", "accept": false, - "reason": "NemotronH checkpoint loading failure is unrelated to tied weights in translation models." + "reason": "NemotronH checkpoint loading failure is unrelated to tied-weights behavior." }, { "left": "issue:43873", "right": "issue:45005", "accept": false, - "reason": "Quantization offloading behavior is not the same as tied-weights handling." + "reason": "Quantization offloading behavior is a different bug from tied weights in v5 translation models." }, { "left": "issue:39186", "right": "issue:44918", "accept": false, - "reason": "FSDP 2-D weight error and Qwen3.5 embedding unpacking are unrelated." + "reason": "FSDP 2-D weight runtime error is unrelated to Qwen3.5 input embedding unpacking." }, { "left": "issue:44492", "right": "issue:44512", "accept": false, - "reason": "A cache-strategy typo is unrelated to docs referencing a removed run command." + "reason": "A cache-strategies typo and removed-command docs are unrelated." }, { "left": "issue:44918", "right": "issue:45507", "accept": false, - "reason": "TRL embedding unpacking and GraniteMoEHybrid invalid method calls are different failures." + "reason": "Different model families and failures: TRL embedding unpacking vs GraniteMoEHybrid invalid method call." }, { "left": "issue:43975", "right": "issue:44292", "accept": false, - "reason": "Detokenization in v5 and an `_is_hf_initialized` init-empty-weights TypeError are separate bugs." + "reason": "Incorrect detokenization in DeepSeek coder is unrelated to the NVFP4 runtime error." }, { "left": "issue:43950", "right": "issue:44534", "accept": true, - "reason": "Same underlying v5 regression: non-persistent buffers are being mishandled/corrupted during loading." + "reason": "Same underlying v5 regression: non-persistent buffers are being corrupted/filled with junk on load." }, { "left": "issue:43644", "right": "issue:43950", "accept": true, - "reason": "Both report the same non-persistent-buffer corruption regression in Transformers 5.x." + "reason": "Same non-persistent-buffer corruption bug; 43950 is the clearer, more explicit report." }, { "left": "issue:44292", "right": "issue:45507", "accept": false, - "reason": "Init-empty-weights TypeError is unrelated to GraniteMoEHybrid invalid method calls." - }, - { - "left": "issue:39692", - "right": "issue:43054", - "accept": false, - "reason": "SigLIP2 docs example errors and SigLIP2 embedding quality complaints are related by model name only, not clearly the same bug." - }, - { - "left": "issue:43828", - "right": "issue:44928", - "accept": false, - "reason": "Different failure modes and models: dtype mismatch under autocast vs RLHF NaN/explosion from 3D position_ids." + "reason": "Different runtime failures and model families; no shared code-path evidence." }, { "left": "issue:43866", "right": "issue:44403", "accept": false, - "reason": "Corrupted Ovis2 checkpoint is unrelated to generic loading noise." + "reason": "Checkpoint corruption for Ovis2 is unrelated to the transformer-loading noise issue." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is well grounded in the packet. The identified duplicate cluster around the Transformers v5 non-persistent-buffer regression is supported by the issue titles and the accepted soft-edge pairs are conservative. The rejected pairs also look appropriately cautious; I don\u2019t see evidence of overstating duplicates or conflating distinct bugs." + "feedback": "The summary is grounded in the packet, and the duplicate calls are conservative. The non-persistent-buffer regression cluster is well supported by the issue titles, and the SigLIP2 pair is only presented as plausible rather than certain. No obvious overstatement or mergeability problem for PR pairs." }, "evaluator_used": true, "retried": false, @@ -1068,22 +1032,22 @@ "soft_pairs": [ "issue:36331|issue:41762", "issue:41628|issue:45800", - "issue:41553|issue:43883", "issue:43872|issue:44589", + "issue:41553|issue:43883", "issue:38175|issue:43054", - "issue:41553|issue:43881", "issue:43054|issue:45701", + "issue:41553|issue:43881", "issue:42947|issue:44387", "issue:44403|issue:44451", "issue:43643|issue:45020", "issue:43975|issue:45520", "issue:43054|issue:43493", "issue:43975|issue:45237", - "issue:43881|issue:43883", "issue:44403|issue:44488", "issue:42947|issue:43856", - "issue:42491|issue:44368", + "issue:43881|issue:43883", "issue:41762|issue:42915", + "issue:42491|issue:44368", "issue:45685|issue:45823", "issue:43975|issue:44451", "issue:45020|issue:45823", @@ -1102,12 +1066,12 @@ "issue:43638|issue:45823", "issue:43257|issue:43866" ], - "prepared_review_unit_hash": "f88c45918275d9ae063409141bc79fd0ee3fbb31f6ce1b1d818cf41a9b21c6a5", + "prepared_review_unit_hash": "859c30f6e9e12dfec3002bf0ddcd994ac5d065ff99ffcb06fd1294682aaca841", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, @@ -1115,7 +1079,7 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 35, - "serialized_chars": 38121, + "serialized_chars": 38124, "estimated_input_tokens": 9531, "estimated_eval_tokens": 19318 }, @@ -1124,228 +1088,216 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly a heterogeneous set of unrelated Transformers issues. Two soft duplicates stand out: the SigLIP2 quality/regression reports and the Whisper/fbank loading/runtime reports. Everything else looks like separate bugs or broader adjacent regressions rather than the same underlying change.", - "confidence": 0.79, - "canonical_issue_reason": "No single issue cleanly covers the whole cluster; if forced to anchor the set, issue 45020 is the broadest cross-model compatibility regression and best hub-like representative.", + "summary": "This is a loose, mostly heterogeneous cluster of issue reports around loading/regression problems. I only see two clear duplicate-like pairs: the SigLIP2 implementation discrepancy reports and the v5 docs pipeline-removal docs reports. Most other pairs are related only at a subsystem level, not the same underlying bug.", + "confidence": 0.76, + "canonical_issue_reason": "issue:45020 is the best broad umbrella for the cluster\u2019s recurring recent-version loading/compatibility regressions, especially remote_code-related breakages, though it does not cleanly cover the whole heterogeneous set.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45020 is the most general and cross-cutting loading/regression report in the set, so it is the most suitable representative issue.", + "best_issue_reason": "issue:45020 is the strongest representative because it is the broadest open issue and aligns with the dominant theme of recent transformers version regressions; still, it is only a partial fit for this cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:36331", "right": "issue:41762", "accept": false, - "reason": "Different failure modes: trainer API kwarg mismatch vs ZeRO-3 index error during model loading." + "reason": "Different failure modes: custom trainer signature mismatch vs ZeRO-3 index error during Gemma3 loading." }, { "left": "issue:41628", "right": "issue:45800", "accept": false, - "reason": "Import error for AutoImageProcessor is unrelated to torch/transformers version incompatibility." + "reason": "Import error for a missing symbol is not the same bug as a torch/transformers version incompatibility." }, { - "left": "issue:41553", - "right": "issue:43883", + "left": "issue:43872", + "right": "issue:44589", "accept": false, - "reason": "Voxtral tokenizer error message and Molmo tied-weights attribute error are different code paths." + "reason": "Both are compatibility problems, but one is bitsandbytes int8 init and the other is float8 storage resolution; different code paths." }, { - "left": "issue:43872", - "right": "issue:44589", + "left": "issue:41553", + "right": "issue:43883", "accept": false, - "reason": "Both are quantization/storage-related errors, but they involve different dtype/back-end incompatibilities." + "reason": "Bad AutoTokenizer error messaging for Voxtral is unrelated to Molmo missing all_tied_weights_keys." }, { "left": "issue:38175", "right": "issue:43054", - "accept": true, - "reason": "Both are SigLIP2 output-quality regressions and likely the same underlying implementation mismatch." - }, - { - "left": "issue:41553", - "right": "issue:43881", "accept": false, - "reason": "Different models and different load-time failures; no shared concrete bug." + "reason": "Both involve SigLIP2 quality, but the reports describe different symptoms and no shared concrete bug is evident." }, { "left": "issue:43054", "right": "issue:45701", "accept": false, - "reason": "SigLIP2 embedding quality and general tokenization changes are not the same bug." + "reason": "SigLIP2 embedding quality is unrelated to a general tokenization change across transformers versions." + }, + { + "left": "issue:41553", + "right": "issue:43881", + "accept": false, + "reason": "Different models and different load failures; no same underlying bug." }, { "left": "issue:42947", "right": "issue:44387", "accept": false, - "reason": "LoRA gradient-checkpointing behavior is unrelated to int4 CUDA memory growth." + "reason": "Both mention memory/performance, but one is LoRA checkpointing behavior and the other is int4 CUDA reserved memory OOM." }, { "left": "issue:44403", "right": "issue:44451", "accept": false, - "reason": "Generic loading noise vs a specific model load failure; too broad to merge." + "reason": "One is noisy loading output, the other is a concrete model-loading failure for ScandiBERT." }, { "left": "issue:43643", "right": "issue:45020", "accept": false, - "reason": "Remote-code field loss is one manifestation at most, but 45020 is a broader compatibility report, not the same concrete bug." + "reason": "Both touch remote_code, but one is missing fields in AutoConfig and the other is a broader breakage report; not the same concrete bug." }, { "left": "issue:43975", "right": "issue:45520", "accept": false, - "reason": "Tokenizer detokenization regression and flash-attn import utility error are unrelated." + "reason": "DeepSeek detokenization and a flash_attn import_utils KeyError are unrelated issues." }, { "left": "issue:43054", "right": "issue:43493", - "accept": false, - "reason": "Same model family, but one is a quality complaint and the other is a direct HF-vs-JAX discrepancy report." + "accept": true, + "reason": "Both point to the same SigLIP2 implementation discrepancy theme; the JAX-vs-HF mismatch plausibly explains the degraded text embeddings." }, { "left": "issue:43975", "right": "issue:45237", "accept": false, - "reason": "Tokenizer regression and AMD GPU runtime failure are unrelated." - }, - { - "left": "issue:43881", - "right": "issue:43883", - "accept": false, - "reason": "Model load failure vs missing all_tied_weights_keys attribute are different issues." + "reason": "Tokenizer/detokenization behavior is unrelated to AMD GPU execution support." }, { "left": "issue:44403", "right": "issue:44488", "accept": false, - "reason": "Both involve loading, but they are separate model-specific problems." + "reason": "General loading noise and a specific model load failure are not the same bug." }, { "left": "issue:42947", "right": "issue:43856", "accept": false, - "reason": "PEFT gradient checkpointing and Qwen3 MoE memory usage are not the same bug." + "reason": "Both are efficiency-related, but one is gradient checkpointing with PEFT LoRA and the other is Qwen3 MoE training memory usage." }, { - "left": "issue:42491", - "right": "issue:44368", + "left": "issue:43881", + "right": "issue:43883", "accept": false, - "reason": "Both mention Qwen3 variants, but one is a cross-version LoRA incompatibility and the other is a tied-embeddings warning." + "reason": "Different model families and different errors: glm-4v loading vs Molmo weight-tying attribute missing." }, { "left": "issue:41762", "right": "issue:42915", "accept": false, - "reason": "Different model families and different ZeRO/FP8 loading failures." + "reason": "ZeRO-3 index error during Gemma3 loading is not the same as Qwen3 MoE fine-grained FP8 failure." + }, + { + "left": "issue:42491", + "right": "issue:44368", + "accept": false, + "reason": "LoRA compatibility across hf versions and a tie_word_embeddings warning are different issues." }, { "left": "issue:45685", "right": "issue:45823", "accept": false, - "reason": "MPS histogram limitation is unrelated to Gemma4 device-map mismatch." + "reason": "MPS histogram support for Int and Gemma4 PLE device placement mismatch are different device bugs." }, { "left": "issue:43975", "right": "issue:44451", "accept": false, - "reason": "Different tokenizer/model-loading regressions with no shared concrete path." + "reason": "Detokenization regression and a ScandiBERT load failure are unrelated." }, { "left": "issue:45020", "right": "issue:45823", "accept": false, - "reason": "Remote-code breakage is not the same as a Gemma4 forward device mismatch." + "reason": "Remote_code loading regressions do not match a Gemma4 PLE device_map forward mismatch." }, { "left": "issue:43824", "right": "issue:43872", "accept": false, - "reason": "Importing a model class and bitsandbytes int8 parameter construction are unrelated." + "reason": "Importing a Qwen2.5-VL class and a bitsandbytes int8 constructor error are unrelated." }, { "left": "issue:44991", "right": "issue:45399", "accept": false, - "reason": "Tokenizer load failure and flash-attn fallback gating are different subsystems." + "reason": "Tokenizer loading for EMBEDDIA/est-roberta and flash-attn fallback gating are unrelated." }, { "left": "issue:44661", "right": "issue:45020", "accept": false, - "reason": "add-new-model-like template generation failure is not the same as generic remote_code breakage." + "reason": "add-new-model-like failing inside TOKENIZER_MAPPING_NAMES is a registry issue, not the same remote_code regression." }, { "left": "issue:43828", "right": "issue:45823", "accept": false, - "reason": "Autocast dtype mismatch for Phi-tiny-MoE is unrelated to Gemma4 device placement." + "reason": "Autocast dtype mismatch for Phi-tiny-MoE and Gemma4 device mismatch are different runtime errors." }, { "left": "issue:45020", "right": "issue:45356", "accept": false, - "reason": "Both are version regressions, but one is broad remote_code breakage and the other is a specific tokenizer/regex regression." + "reason": "Both concern recent tokenizer regressions, but the concrete failures differ: remote_code loading vs Kimi-K2.5 codec/fix_mistral_regex behavior." }, { "left": "issue:43782", "right": "issue:44960", "accept": false, - "reason": "Qwen3VL weight_only error and a GLM5 issue are different model-specific problems." + "reason": "Qwen3VL weight_only loading error and GLM5 are separate model-specific issues." }, { "left": "issue:45081", "right": "issue:45399", "accept": false, - "reason": "Tokenizer regex crash and flash-attn fallback checks are unrelated." + "reason": "Mistral tokenizer patch crash and flash-attn fallback gating are unrelated code paths." }, { "left": "issue:43827", "right": "issue:44509", - "accept": false, - "reason": "These are the same documentation theme, but not the same underlying code bug; both are docs references to removed pipelines." + "accept": true, + "reason": "These are clear duplicates: both report stale docs still referencing removed v5 pipeline tasks." }, { "left": "issue:43404", "right": "issue:43950", "accept": false, - "reason": "Tied lm_head weights and non-persistent buffer corruption are different implementation bugs." + "reason": "Mistral3 weight tying and non-persistent buffer corruption are different regression types." }, { "left": "issue:43792", "right": "issue:44220", - "accept": true, - "reason": "Both point to the Whisper audio feature-extraction path; the generic run failure and the _torch_extract_fbank_features() issue look like the same underlying bug." + "accept": false, + "reason": "Whisper failing to run may involve feature extraction, but the titles do not show the same concrete bug with enough confidence." }, { "left": "issue:43742", "right": "issue:45399", "accept": false, - "reason": "MobileLLM load failure and flash-attn fallback gating are unrelated." + "reason": "MobileLLM key errors and flash-attn fallback gating are unrelated failures." }, { "left": "issue:42915", - "right": "issue:45020", - "accept": false, - "reason": "Qwen3 MoE + FP8/DeepSpeed loading failure is not the same as broad remote_code regression." - }, - { - "left": "issue:43638", - "right": "issue:45823", - "accept": false, - "reason": "ZeRO-3 Bert training index error and Gemma4 forward device mismatch are different failure modes." - }, - { - "left": "issue:43257", "right": "issue:43866", "accept": false, - "reason": "Qwen3 MoE weight conversion under accelerate/deepspeed and an Ovis2 checkpoint corruption report are unrelated." + "reason": "Qwen3 MoE FP8/deepspeed issues and an Ovis2 checkpoint corruption report are separate problems." } ] }, "evaluator_result": { "accept": true, - "feedback": "The clustering is grounded in the packet and the summary stays conservative. The two accepted soft pairs are both plausible from the titles alone, and the rejected pairs generally avoid over-connecting unrelated failure modes. No mergeability issues apply since these are issue pairs, not PR pairs." + "feedback": "The summary is grounded in the packet and stays appropriately conservative. The two accepted duplicate-like pairs are supported by the titles, and the other soft-edge rejections avoid overclaiming same-bug identity. Minor caution: the umbrella framing around issue:45020 is broad and should remain presented as partial/approximate rather than definitive." }, "evaluator_used": true, "retried": false, @@ -1419,8 +1371,8 @@ "issue:43940|issue:45313", "issue:43872|issue:44291", "issue:45161|issue:45823", - "issue:41553|issue:44991", "issue:43854|issue:44863", + "issue:41553|issue:44991", "issue:42915|issue:43872", "issue:44928|issue:45588", "issue:43257|issue:45305", @@ -1433,8 +1385,8 @@ "issue:24643|issue:30064", "issue:43366|issue:43828", "issue:45663|issue:45823", - "issue:43950|issue:45834", "issue:43366|issue:43531", + "issue:43950|issue:45834", "issue:43550|issue:44910", "issue:43645|issue:43646", "issue:43366|issue:44589", @@ -1443,18 +1395,18 @@ "issue:42617|issue:43366", "issue:43824|issue:43957", "issue:42915|issue:43957", - "issue:43632|issue:45834", "issue:36010|issue:42915", "issue:44661|issue:45823", "issue:38175|issue:43994", + "issue:43632|issue:45834", "issue:44155|issue:45584" ], - "prepared_review_unit_hash": "9fe2f5e89861fd1570e134132cda3b36ae07695d30e6c8c7ae272ed4ed4e5436", + "prepared_review_unit_hash": "ba3dbced55ccc82e9a153bace62548ac658c25b713e5ce02a6f7232a0b48011d", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, @@ -1462,7 +1414,7 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 32, - "serialized_chars": 37423, + "serialized_chars": 37421, "estimated_input_tokens": 9356, "estimated_eval_tokens": 18968 }, @@ -1471,204 +1423,210 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly a heterogeneous set of Transformers regressions and model-specific bugs, with a few true duplicate pairs around custom-model initialization, `_is_hf_initialized` handling, SigLIP2 inference output corruption, and a repeated mask/tensor shape mismatch. The rest look like separate issues, not safe duplicates.", - "confidence": 0.78, - "canonical_issue_reason": "issue:43646 is the cleanest, broadest representative of the custom-model initialization regression; issue:43645 reads like the same bug with an added Jupyter-specific context.", + "summary": "Mostly a heterogeneous set of Transformers bug reports with a few close duplicate pairs around initialization/loading regressions. I did not find any PRs, and the safest umbrella issue is the Transformers 5 `_is_hf_initialized` regression. Accepted duplicates: the custom model init notebook/general pair, the identical mask-shape IndexError pair, and the `_is_hf_initialized`/init_empty_weights pair.", + "confidence": 0.68, + "canonical_issue_reason": "Issue 43632 is the broadest root-cause report in the cluster: it describes the Transformers 5 `_is_hf_initialized` regression that appears to underlie several later loading/initialization failures.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43646 is the best single representative for the closest duplicate subgroup and has the most general title among the custom-model-init reports.", + "best_issue_reason": "Issue 43632 is the best representative issue because it captures the common upstream initialization bug rather than a single model-specific symptom.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43940", "right": "issue:45313", "accept": false, - "reason": "Both are DeepSpeed ZeRO-3 weight-loading problems, but they describe different concrete failures and different Qwen3 variants; too broad to merge." + "reason": "Both are DeepSpeed ZeRO-3 loading failures, but they target different Qwen variants and different symptoms, so they do not look like the same bug." }, { "left": "issue:43872", "right": "issue:44291", "accept": true, - "reason": "Same underlying `_is_hf_initialized` kwarg regression during model loading; 43872 is a bitsandbytes symptom, 44291 is the generic init_empty_weights manifestation." + "reason": "Both report the same `_is_hf_initialized` kwarg regression during model loading; one surfaces through bitsandbytes and the other through init_empty_weights, but the underlying bug is the same." }, { "left": "issue:45161", "right": "issue:45823", "accept": false, - "reason": "Different models and different code paths: tensor-parallel loading vs device_map-forward mismatch." + "reason": "These are unrelated model-specific failures: GPT-OSS MoE tensor-parallel loading vs Gemma4 PLE device placement." }, { - "left": "issue:41553", - "right": "issue:44991", + "left": "issue:43854", + "right": "issue:44863", "accept": false, - "reason": "Both are tokenizer-loading failures, but for different models and likely different tokenizer/config bugs." + "reason": "Different models and different loading failures; no sign of a shared code-path bug." }, { - "left": "issue:43854", - "right": "issue:44863", + "left": "issue:41553", + "right": "issue:44991", "accept": false, - "reason": "Both are load failures, but on unrelated model architectures with no clear shared bug path." + "reason": "Both mention tokenizer loading, but the reported failures and models are different, so this is too broad to merge." }, { "left": "issue:42915", "right": "issue:43872", "accept": false, - "reason": "Different failures: Qwen3Moe FP8 config vs `_is_hf_initialized`/bitsandbytes kwarg handling." + "reason": "Qwen3MoE FP8 config failure is unrelated to the `_is_hf_initialized` bitsandbytes regression." }, { "left": "issue:44928", "right": "issue:45588", "accept": false, - "reason": "Different domains and symptoms: RLHF/3D position_ids versus flash-attention sink-less crash." + "reason": "RLHF NaNs from Qwen3.5 position-ids and Whisper empty-transcription handling are different bugs." }, { "left": "issue:43257", "right": "issue:45305", "accept": false, - "reason": "Both involve DeepSpeed, but one is missing weight conversion and the other is gradient averaging; not the same bug." + "reason": "Both involve DeepSpeed training, but one is missing Qwen3 MoE weights and the other is gradient averaging with GAS." }, { "left": "issue:36331", "right": "issue:41093", "accept": false, - "reason": "Both are TypeError/IndexError reports, but they hit different APIs and failure mechanisms." + "reason": "Unexpected compute_loss kwarg and mask/tensor shape mismatch are different failure modes." }, { "left": "issue:41553", "right": "issue:44488", "accept": false, - "reason": "Same broad area of model loading, but different models and different reported errors." + "reason": "Different tokenizer/model loading problems with no shared concrete bug." }, { "left": "issue:43872", "right": "issue:45538", "accept": false, - "reason": "Unrelated bugs: bitsandbytes init kwarg error vs CLIPTokenizer max-length behavior." + "reason": "Bitsandbytes `_is_hf_initialized` incompatibility is unrelated to CLIPTokenizer's model_max_length value." }, { "left": "issue:44530", "right": "issue:44863", "accept": false, - "reason": "Different models and failures: Qwen3.5 cache/group-type crash vs NemotronH checkpoint loading." + "reason": "PagedAttentionCache invalid group type on Qwen3.5 is not the same as NemotronH checkpoint loading." }, { "left": "issue:41093", "right": "issue:44805", "accept": true, - "reason": "Same mask/tensor shape-mismatch IndexError pattern; the later issue appears to be the same underlying bug reported with generalized placeholders." + "reason": "These are effectively the same IndexError symptom with the same shape-mismatch wording, so they look like duplicate reports of one underlying bug." }, { "left": "issue:44479", "right": "issue:44560", "accept": false, - "reason": "Both are video-related regressions, but they affect different model families and likely different preprocessing paths." + "reason": "Both are Qwen video/position-id issues, but the specific models and failures differ enough that they should stay separate." }, { "left": "issue:24643", "right": "issue:30064", "accept": false, - "reason": "Completely different subsystems: DeepSpeed training weight shape error vs image processor void-segmentation handling." + "reason": "DeepSpeed training weight-dimension error and void segmentation-map processing are unrelated." }, { "left": "issue:43366", "right": "issue:43828", "accept": false, - "reason": "Different bugs: GGUF architecture support vs autocast dtype mismatch in Phi-tiny-MoE." + "reason": "GGUF gpt-oss support and Phi-tiny-MoE autocast dtype mismatch are unrelated." }, { "left": "issue:45663", "right": "issue:45823", "accept": false, - "reason": "Both mention Gemma4, but one is an FSDP2 shared_kv_states bug and the other is a device_map device mismatch." + "reason": "Gemma4 FSDP2 shared_kv_states corruption is a different issue from Gemma4 PLE device mismatch under device_map=auto." }, { - "left": "issue:43950", - "right": "issue:45834", + "left": "issue:43366", + "right": "issue:43531", "accept": false, - "reason": "Different regressions: non-persistent buffer corruption vs long-OCR index error in Kosmos2.5." + "reason": "Both mention GPT-OSS/Qwen-style MoE models, but one is GGUF support and the other is a sliding_window bug on Qwen3-MoE." }, { - "left": "issue:43366", - "right": "issue:43531", + "left": "issue:43950", + "right": "issue:45834", "accept": false, - "reason": "Both touch Qwen3/GPT-OSS-adjacent model support, but the concrete problems are unrelated." + "reason": "Non-persistent buffer corruption in from_pretrained and Kosmos2.5 OCR index errors are unrelated." }, { "left": "issue:43550", "right": "issue:44910", "accept": false, - "reason": "Different model families and different failures: torch.compile/SDPA crash vs Flash Attention position_ids misinterpretation." + "reason": "Bamba SDPA compile failure and Qwen3.5 flash-attn illegal memory access stem from different code paths." }, { "left": "issue:43645", "right": "issue:43646", "accept": true, - "reason": "Same custom-model initialization regression in Transformers 5.0; 43645 just adds a notebook-specific scenario." + "reason": "These are the same custom model initialization regression; one is the notebook repro, the other the general issue." }, { "left": "issue:43366", "right": "issue:44589", "accept": false, - "reason": "Unrelated issues: GGUF support for gpt-oss vs missing Float8 storage type." + "reason": "GGUF gpt-oss support and missing Float8 storage are unrelated." }, { "left": "issue:43950", "right": "issue:45325", "accept": false, - "reason": "Different bugs: buffer loading regression vs Qwen2.5-VL rope-index scaling on still images." + "reason": "Non-persistent buffer handling and Qwen2.5-VL rope-index scaling are different bugs." }, { "left": "issue:44560", "right": "issue:44918", "accept": false, - "reason": "Both involve Qwen3.5/video or embeddings, but the symptoms and failure paths differ." + "reason": "Both involve Qwen3.5-ish inputs, but one is a video StopIteration and the other is TRL SFT embedding unpacking." }, { "left": "issue:42617", "right": "issue:43366", "accept": false, - "reason": "3d_parallel.py runtime failure is unrelated to gpt-oss GGUF support." + "reason": "3d_parallel.py execution failure is unrelated to GPT-OSS GGUF support." }, { "left": "issue:43824", "right": "issue:43957", "accept": false, - "reason": "Different failure modes: missing Qwen2.5-VL import vs meta-device loading regressions." + "reason": "Missing import for Qwen2_5_VLForConditionalGeneration and meta-device loading regressions are not the same bug." }, { "left": "issue:42915", "right": "issue:43957", "accept": false, - "reason": "Different bugs in different areas: FP8/Qwen3Moe vs meta-device loading." - }, - { - "left": "issue:43632", - "right": "issue:45834", - "accept": false, - "reason": "_is_hf_initialized flag regression and Kosmos2.5 OCR index error are unrelated." + "reason": "Qwen3MoE FP8 config failure and meta-device loading regressions differ in both trigger and code path." }, { "left": "issue:36010", "right": "issue:42915", "accept": false, - "reason": "ImportError for GenerationMixin and Qwen3Moe FP8 loading failure are unrelated." + "reason": "GenerationMixin import failure and Qwen3MoE FP8 failure are unrelated." }, { "left": "issue:44661", "right": "issue:45823", "accept": false, - "reason": "Tokenizer-mapping failure and Gemma4 device mismatch are separate bugs." + "reason": "Tokenizer mapping-name handling and Gemma4 device mismatch are unrelated issues." }, { "left": "issue:38175", "right": "issue:43994", - "accept": true, - "reason": "Same SigLIP2 base model regression: one report says zero probabilities, the other says nonsensical outputs; likely the same broken inference behavior." + "accept": false, + "reason": "Both are about SigLIP2 behavior, but one is zero probabilities and the other is nonsensical AutoModel/pipeline output; not enough to call them duplicates." + }, + { + "left": "issue:43632", + "right": "issue:45834", + "accept": false, + "reason": "The `_is_hf_initialized` regression is unrelated to Kosmos2.5 OCR long-input indexing." + }, + { + "left": "issue:44155", + "right": "issue:45584", + "accept": false, + "reason": "AudioFlamingo3 track embedding leakage and Whisper empty-transcription handling are different failures." } ] }, "evaluator_result": { "accept": true, - "feedback": "The analysis is grounded in the packet and stays mostly conservative. The accepted duplicate pairs are supported by close titles/symptoms, and the rejections generally avoid forcing merges across clearly different model paths or failure modes. The summary matches the packet without overclaiming." + "feedback": "The summary stays grounded in the packet and the duplicate calls are conservative: the accepted pairs have clear title-level overlap, and the rejected pairs are appropriately cautious. The umbrella issue choice is plausible given the `_is_hf_initialized` cluster, and there is no overstatement beyond the evidence provided." }, "evaluator_used": true, "retried": false, @@ -1757,8 +1715,8 @@ "issue:43708|issue:44075", "issue:43257|issue:43854", "issue:43856|issue:43873", - "issue:39692|issue:43994", "issue:42915|issue:44756", + "issue:39692|issue:43994", "issue:42491|issue:43931", "issue:43856|issue:44387", "issue:43644|issue:43645", @@ -1770,12 +1728,12 @@ "issue:45276|issue:45335", "issue:43404|issue:43454" ], - "prepared_review_unit_hash": "d6b8d5868a3fb0dbb0b2c858fcf67924f6143fc5331ff52ff4e1cf378fd441d8", + "prepared_review_unit_hash": "f700a6c738a5f94fef5c8355d5a6e4bd06996cb6017a6fd73b6c31721cba25e5", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, @@ -1783,81 +1741,81 @@ "node_count": 47, "item_count": 47, "soft_pair_count": 31, - "serialized_chars": 36416, - "estimated_input_tokens": 9104, - "estimated_eval_tokens": 18464 + "serialized_chars": 36412, + "estimated_input_tokens": 9103, + "estimated_eval_tokens": 18462 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a mix of unrelated transformer regressions, but there are a few clear duplicate mini-groups: non-persistent buffer junk in v5, BERT model loading failures, and resize_token_embeddings not propagating to output/token embeddings.", - "confidence": 0.66, - "canonical_issue_reason": "Issue 45276 is the best anchor for the resize_token_embeddings regression: it gives the clearest, broadest description of the shared failure mode, while 45335 is a narrower model-specific variant.", + "summary": "This cluster is mostly a loose mix of Transformers v5 regression reports across loading, tokenizers, quantization, and model-specific generation bugs. Only one soft pair is a clear duplicate; the rest are too model- or symptom-specific to merge confidently.", + "confidence": 0.62, + "canonical_issue_reason": "Issue 43644 is the clearest, most detailed report of the confirmed duplicate buffer-regression bug, and it is directly echoed by 44534.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45276 is the strongest single issue to keep overall because it is the most general and actionable report among the related resize_token_embeddings cases.", + "best_issue_reason": "43644 is the best overall anchor because it captures the bug concretely and has the strongest duplicate evidence in the set.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44877", "right": "issue:45030", "accept": false, - "reason": "Both are config-validation load failures, but they involve different models and different validation paths." + "reason": "Both are config-validation load failures, but they affect different models and describe different breakages." }, { "left": "issue:44560", "right": "issue:44805", "accept": false, - "reason": "Different concrete bugs: Qwen3-VL video StopIteration vs a mask/tensor shape mismatch." + "reason": "Different failures: Whisper video StopIteration vs a mask/tensor shape mismatch." }, { "left": "issue:43638", "right": "issue:44661", "accept": false, - "reason": "One is a DeepSpeed zero3/BertModel indexing failure; the other is an add-new-model-like tokenizer-mapping issue." + "reason": "BERT ZeRO-3 initialization crash and tokenizer-mapping-name issue are unrelated bugs." }, { "left": "issue:43317", "right": "issue:44756", "accept": false, - "reason": "Offload/dequantized-model loading and Strix Halo mmap OOM are different problems." + "reason": "Both mention offload/memory, but one is a dequantized-model loading failure and the other is mmap OOM on Strix Halo." }, { "left": "issue:43596", "right": "issue:44661", "accept": false, - "reason": "Different symptoms and code paths: zero3/BertModel init vs tokenizer-mapping registration." + "reason": "Different code paths: ZeRO-3/BertModel index error vs add-new-model-like tokenizer mapping failure." }, { "left": "issue:44661", "right": "issue:44805", "accept": false, - "reason": "Tokenizer-mapping registration and mask-shape mismatch are unrelated." + "reason": "Tokenizer-mapping logic and tensor mask shape mismatch are unrelated." }, { "left": "issue:38175", "right": "issue:39692", "accept": false, - "reason": "Same model family, but the bugs differ: zero probabilities vs docs example/model-processor mismatch and quantization failure." + "reason": "Same model family, but one reports zero probabilities and the other reports docs-example/model-processor and quantization errors." }, { "left": "issue:43644", "right": "issue:44534", "accept": true, - "reason": "These describe the same v5 regression where non-persistent buffers are filled with junk." + "reason": "Same underlying bug: Transformers 5.0.0 fills non-persistent buffers with junk; the titles are effectively the same report." }, { "left": "issue:45313", "right": "issue:45357", "accept": false, - "reason": "Different Qwen3.5 failures: zero3 language_model loading vs incorrect visual encoder keys in save_pretrained." + "reason": "Both are Qwen3.5-related, but one is ZeRO-3 weight loading and the other is save_pretrained key serialization." }, { "left": "issue:45488", "right": "issue:45812", "accept": false, - "reason": "Both are tokenizer regressions, but for different model families and different underlying mechanisms." + "reason": "Both are tokenizer regressions, but one is LlamaTokenizer pre-tokenizer override and the other is Granite token-id corruption." }, { "left": "issue:44960", @@ -1868,128 +1826,122 @@ { "left": "issue:44451", "right": "issue:44488", - "accept": true, - "reason": "Both report the same loading regression for specific BERT checkpoints in the current version." + "accept": false, + "reason": "Both are model-load regressions, but the reports are for different models and no shared concrete bug is evident." }, { "left": "issue:42491", "right": "issue:43720", "accept": false, - "reason": "Different model families and different failure modes; not the same concrete bug." + "reason": "Different problems: Qwen3 MoE LoRA compatibility vs BitNet packed-weight loading." }, { "left": "issue:43854", "right": "issue:43931", "accept": false, - "reason": "Different models and different load errors (unit-test loading vs weight-shape mismatch)." + "reason": "Different model load failures with different symptoms and model families." }, { "left": "issue:41720", "right": "issue:42915", "accept": false, - "reason": "Both involve Qwen3 MoE, but one is an auto device-map cuda assert and the other is a FineGrainedFP8Config failure." + "reason": "Both are Qwen3-family issues, but one is auto device mapping cuda assert and the other is FineGrainedFP8Config failure." }, { "left": "issue:42491", "right": "issue:45276", "accept": false, - "reason": "LoRA hf4.x/hf5.x incompatibility and resize_token_embeddings are unrelated bugs." + "reason": "Qwen3 MoE LoRA compatibility and Gemma4 embedding resize behavior are unrelated." }, { "left": "issue:43708", "right": "issue:44075", "accept": false, - "reason": "Trainer resume/max_steps logic and SGD optimizer args are separate issues." + "reason": "Trainer resume/max_steps bug and SGD-args-not-used bug are different trainer/optimizer issues." }, { "left": "issue:43257", "right": "issue:43854", "accept": false, - "reason": "Qwen3 MoE weight conversion/loading and GLM-4.7-Flash test loading are unrelated." + "reason": "Different loading paths and failures: accelerate/deepspeed MoE conversion vs GLM-4.7-Flash unit-test loading." }, { "left": "issue:43856", "right": "issue:43873", "accept": false, - "reason": "Both mention quantization/offloading, but one is a Qwen3 MoE memory issue and the other is a generic offloading bug." + "reason": "Both touch memory/offloading, but one is Qwen3 MoE training memory use and the other is quantization offloading behavior." }, { - "left": "issue:39692", - "right": "issue:43994", + "left": "issue:42915", + "right": "issue:44756", "accept": false, - "reason": "Related SigLIP2 area, but different bugs: documentation example errors vs nonsensical model outputs." + "reason": "Qwen3Moe FP8 failure and Strix Halo mmap OOM are unrelated." }, { - "left": "issue:42915", - "right": "issue:44756", + "left": "issue:39692", + "right": "issue:43994", "accept": false, - "reason": "Different issues: FineGrainedFP8Config failure vs mmap/OOM on Strix Halo." + "reason": "Same SigLIP2 model family, but one is a docs-example/model-processor issue and the other is a runtime nonsensical-output report." }, { "left": "issue:42491", "right": "issue:43931", "accept": false, - "reason": "Different model/version compatibility issue vs a separate weight-shape mismatch." + "reason": "Qwen3 MoE LoRA compatibility and Qwen3-VL weight-shape mismatch are different bugs." }, { "left": "issue:43856", "right": "issue:44387", "accept": false, - "reason": "Both are memory-related, but one is training efficiency and the other is int4 OOM from reserved CUDA memory." + "reason": "Memory inefficiency during Qwen3 MoE training is not the same as increased CUDA reserved memory under int4 quantization." }, { "left": "issue:43644", "right": "issue:43645", "accept": false, - "reason": "Non-persistent buffer junk and Jupyter custom-model initialization are different regressions." + "reason": "Both are Transformers 5 regressions, but one is buffer junk and the other is Jupyter custom-model initialization." }, { "left": "issue:44910", "right": "issue:45588", "accept": false, - "reason": "Different flash-attention crashes with different root causes and model assumptions." + "reason": "Both are flash-attention crashes, but the causes differ: packed-sequence misinterpretation vs s_aux=None AttributeError." }, { "left": "issue:45362", "right": "issue:45406", "accept": false, - "reason": "Qwen3.5 chat crash and Gemma4Processor serve crash are unrelated." + "reason": "Different crash sites and model families: Qwen3.5 chat vs Gemma4Processor _tokenizer missing." }, { "left": "issue:44488", "right": "issue:44991", "accept": false, - "reason": "Both are tokenizer-loading failures, but they affect different models and likely different code paths." - }, - { - "left": "issue:45276", - "right": "issue:45335", - "accept": true, - "reason": "Both report the same resize_token_embeddings regression where the updated embeddings are not propagated to model-specific submodules." + "reason": "Both are tokenizer-loading regressions, but they target different external models and appear to be different root causes." }, { - "left": "issue:42491", - "right": "issue:45292", + "left": "issue:36010", + "right": "issue:39404", "accept": false, - "reason": "LoRA qwen3_moe compatibility and output_embeddings resize behavior are different bugs." + "reason": "Importing GenerationMixin and Whisper pipeline return_language are unrelated issues." }, { - "left": "issue:36010", - "right": "issue:39404", + "left": "issue:45276", + "right": "issue:45335", "accept": false, - "reason": "Importing GenerationMixin and Whisper pipeline return_language are unrelated." + "reason": "Both concern resize_token_embeddings, but they affect different model families and different embedding targets; not enough evidence for one bug." }, { "left": "issue:43404", "right": "issue:43454", "accept": false, - "reason": "Both are lm_head tying problems, but they affect different model classes and are not clearly the same concrete bug." + "reason": "Both mention untied lm_head weights, but they are different model implementations and not clearly the same code-path fix." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative overall. The accepted pairs are well supported by the issue titles, and the rejections generally avoid overclaiming when model family or symptom differs. The resize_token_embeddings anchor choice is also reasonable." + "feedback": "Grounded overall. The 43644/44534 pairing is the only clearly mergeable duplicate in this packet, and the other soft-edge rejections are appropriately conservative given the model/symptom differences. The summary stays within the evidence, though wording like \"confirmed duplicate\" is a bit stronger than the packet explicitly proves." }, "evaluator_used": true, "retried": false, @@ -2064,10 +2016,10 @@ "issue:44402|issue:44488", "issue:43425|issue:43957", "issue:39692|issue:44960", - "issue:43335|issue:45663", "issue:42947|issue:45704", - "issue:45663|issue:45759", + "issue:43335|issue:45663", "issue:43873|issue:44387", + "issue:45663|issue:45759", "issue:44155|issue:45823", "issue:43854|issue:45216", "issue:44387|issue:44756", @@ -2079,8 +2031,8 @@ "issue:43381|issue:44928", "issue:44164|issue:44756", "issue:41720|issue:44155", - "issue:45588|issue:45663", "issue:44479|issue:44877", + "issue:45588|issue:45663", "issue:43646|issue:43708", "issue:43854|issue:44960", "issue:43957|issue:44756", @@ -2091,20 +2043,20 @@ "issue:43257|issue:44863", "issue:43425|issue:43828", "issue:44589|issue:44756", - "issue:44479|issue:45663", "issue:44683|issue:45823", + "issue:44479|issue:45663", "issue:43906|issue:44530", "issue:39404|issue:45701", "issue:43611|issue:43645", "issue:43425|issue:45823", "issue:43931|issue:44863" ], - "prepared_review_unit_hash": "9aa4f6bbaba2523ca725c091f6a0d7a332e92e565f673f9f0deb88df78e747ab", + "prepared_review_unit_hash": "aaa30b88e7224198aca175dcdbfa3ebe465897767d44cdce860708095a08d9c9", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, @@ -2112,7 +2064,7 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 38, - "serialized_chars": 39074, + "serialized_chars": 39073, "estimated_input_tokens": 9769, "estimated_eval_tokens": 19794 }, @@ -2121,246 +2073,246 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly unrelated issue reports, with one clear duplicate family around `resize_token_embeddings` not propagating to model embeddings. The two accepted soft edges are the general/generalized resize issue pair and the T5Gemma-specific variant.", - "confidence": 0.88, - "canonical_issue_reason": "Use issue 45292 as the canonical issue: it states the core regression most generally (`resize_token_embeddings` not affecting `output_embeddings`), while 45276 and 45335 are model-specific manifestations of the same embedding-resize bug.", + "summary": "This cluster is mostly a grab-bag of unrelated Transformers issues. The only strong duplicate candidate is the resize_token_embeddings/output_embeddings regression pair around Gemma4, with one issue being the broader/general form and the other a model-specific manifestation.", + "confidence": 0.67, + "canonical_issue_reason": "issue:45292 is the most general statement of the duplicate pair and cleanly represents the shared bug: `resize_token_embeddings` not updating output embeddings.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45292 is the best representative because it is the broadest statement of the underlying bug and can subsume the more specific Gemma4 and T5Gemma reports.", + "best_issue_reason": "issue:45292 is the best representative issue because it states the core regression in the broadest way and is the most plausible canonical target for the related Gemma4-specific report.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44164", "right": "issue:44291", "accept": false, - "reason": "Both are model-loading failures, but one is about `extra_state` handling and the other about `init_empty_weights` / `_is_hf_initialized`; different code paths." + "reason": "Both involve loading/saving mechanics, but one is about `extra_state` handling and the other about `init_empty_weights` / `_is_hf_initialized`; different failure paths." }, { "left": "issue:44402", "right": "issue:44488", "accept": false, - "reason": "Both involve BERT-style model loading, but the reported failures differ: tokenizer vocab mismatch vs inability to load a specific model." + "reason": "Both mention model loading problems, but the titles point to different concrete issues and different model names; not enough evidence of the same bug." }, { "left": "issue:43425", "right": "issue:43957", "accept": false, - "reason": "One is torch version incompatibility; the other is a `meta`-device loading regression affecting some models. Too broad and different." + "reason": "One is a Torch 2.10 compatibility claim, the other is a `meta`-device loading regression; same broad area, different code-paths." }, { "left": "issue:39692", "right": "issue:44960", "accept": false, - "reason": "Completely unrelated models and failures: SigLIP2 docs errors vs GLM5 issue." - }, - { - "left": "issue:43335", - "right": "issue:45663", - "accept": false, - "reason": "Different subsystems and symptoms: SwitchTransformers sparse-layer construction vs Gemma4 FSDP2 `shared_kv_states` rebuild bug." + "reason": "Completely unrelated topics: SigLIP2 documentation errors versus a GLM5 issue." }, { "left": "issue:42947", "right": "issue:45704", "accept": false, - "reason": "Both mention training behavior, but one is gradient checkpointing with LoRA and the other is a T5 RMSNorm memory leak." + "reason": "Gradient checkpointing/LoRA behavior and a T5 RMSNorm memory leak are unrelated bugs." }, { - "left": "issue:45663", - "right": "issue:45759", + "left": "issue:43335", + "right": "issue:45663", "accept": false, - "reason": "Gemma4 FSDP2 attention state bug vs Qwen multimodal `text_config` unwrapping; not the same bug." + "reason": "Sparse-layer config creation and Gemma4 FSDP2 shared-kv-state handling are different model/config regressions." }, { "left": "issue:43873", "right": "issue:44387", "accept": false, - "reason": "Both are quantization/OOM related, but one is offloading failure and the other is increased reserved memory under int4 quantization." + "reason": "Both touch quantization/memory, but one is offloading behavior and the other is int4 reserved-memory/OOM; not the same underlying defect." + }, + { + "left": "issue:45663", + "right": "issue:45759", + "accept": false, + "reason": "FSDP2 shared_kv_states bug versus custom-module selection after save/load; different code paths." }, { "left": "issue:44155", "right": "issue:45823", "accept": false, - "reason": "AudioFlamingo3 batch leakage and Gemma4 device-mapping mismatch are unrelated." + "reason": "AudioFlamingo3 batched inference corruption and Gemma4 device-map mismatch are unrelated." }, { "left": "issue:43854", "right": "issue:45216", "accept": false, - "reason": "Different models and distinct save/load regressions; no clear shared underlying bug." + "reason": "Different model-loading regressions with no concrete overlap in the reported failure mode." }, { "left": "issue:44387", "right": "issue:44756", "accept": false, - "reason": "Both mention OOM, but one is quantization memory growth and the other is mmap on Strix Halo." + "reason": "Int4 quantization OOM versus disabling mmap on Strix Halo; different symptoms and fixes." }, { "left": "issue:44291", "right": "issue:44756", "accept": false, - "reason": "`init_empty_weights` loading error is unrelated to Strix Halo mmap OOM." + "reason": "`init_empty_weights` argument handling and Strix Halo mmap/OOM are unrelated." }, { "left": "issue:44292", "right": "issue:44912", "accept": false, - "reason": "Both are quantization-related, but one is an NVFP4 runtime error and the other is an MXFP4 load falling back to bf16." + "reason": "`resize_token_embeddings` output embedding propagation and MXFP4 quantization fallback are different bugs." }, { "left": "issue:42947", "right": "issue:43381", "accept": false, - "reason": "Both involve gradient checkpointing, but one is ineffective with PEFT LoRA and the other is a separate eval-mode restriction." + "reason": "Both mention gradient checkpointing, but one is LoRA ineffectiveness and the other is eval-mode prohibition; not the same issue." }, { "left": "issue:45684", "right": "issue:45698", "accept": false, - "reason": "Both concern custom-model save/load flows, but one is file permissions and the other is loading the wrong custom module." + "reason": "One is about read-only file permissions during save, the other about loading the wrong custom module after save; related workflow, different bug." }, { "left": "issue:45276", "right": "issue:45292", "accept": true, - "reason": "Same underlying resize-embedding regression; 45276 is a Gemma4-specific manifestation of the broader `output_embeddings` failure in 45292." + "reason": "Both report the same underlying regression: `resize_token_embeddings` not propagating to output embeddings, with 45276 appearing to be a Gemma4-specific manifestation." }, { "left": "issue:43381", "right": "issue:44928", "accept": false, - "reason": "Gradient checkpointing eval-mode restriction is unrelated to the RLHF NaN/SDPA fallback issue." + "reason": "Gradient checkpointing in eval mode versus RLHF NaNs from 3D position_ids / SDPA fallback are unrelated." }, { "left": "issue:44164", "right": "issue:44756", "accept": false, - "reason": "Different loading/storage vs mmap/OOM problems with no shared code-path evidence." + "reason": "`extra_state` save/load handling and Strix Halo mmap/OOM are unrelated." }, { "left": "issue:41720", "right": "issue:44155", "accept": false, - "reason": "Unrelated failures: Qwen3 auto device mapping crash vs AudioFlamingo3 track-leak bug." + "reason": "Qwen3 auto device-mapping CUDA assert and AudioFlamingo3 batched inference leakage are different failures." }, { - "left": "issue:45588", - "right": "issue:45663", + "left": "issue:44479", + "right": "issue:44877", "accept": false, - "reason": "Flash-attention `s_aux=None` crash is a different code path from Gemma4 FSDP2 attention state rebuilding." + "reason": "Qwen video-input regression and strict config rejection for granite_speech are not the same bug." }, { - "left": "issue:44479", - "right": "issue:44877", + "left": "issue:45588", + "right": "issue:45663", "accept": false, - "reason": "Video-input regression for Qwen variants vs strict Granite Speech config loading; not the same bug." + "reason": "Flash-attention `s_aux=None` crash and Gemma4 FSDP2 shared-state rebuild are unrelated." }, { "left": "issue:43646", "right": "issue:43708", "accept": false, - "reason": "Custom model initialization in notebooks vs Trainer checkpoint-resume math; unrelated." + "reason": "Custom model initialization regression and Trainer resume/max_steps miscalculation are different areas." }, { "left": "issue:43854", "right": "issue:44960", "accept": false, - "reason": "Different model families and failures; no duplicate evidence." + "reason": "Different model-loading problems with no clear shared root cause." }, { "left": "issue:43957", "right": "issue:44756", "accept": false, - "reason": "`meta`-device loading regression and Strix Halo mmap OOM are distinct issues." + "reason": "`meta`-device loading regressions versus Strix Halo mmap/OOM; different code paths." }, { "left": "issue:45292", "right": "issue:45335", - "accept": true, - "reason": "Same resize-token-embeddings bug; 45335 is the T5Gemma-specific variant where `decoder.embed_tokens` is not updated." + "accept": false, + "reason": "Both concern `resize_token_embeddings`, but one is general output embeddings and the other is decoder.embed_tokens in t5gemma; likely related but not clearly the same concrete bug." }, { "left": "issue:44402", "right": "issue:44451", "accept": false, - "reason": "Both are model-loading reports, but one is a vocab-size mismatch and the other is a specific model load failure." + "reason": "Two distinct model-loading failures for different models; insufficient evidence of identity." }, { "left": "issue:43828", "right": "issue:43957", "accept": false, - "reason": "Autocast dtype mismatch on Phi-tiny-MoE is unrelated to `meta`-device loading failures." + "reason": "Autocast dtype mismatch in Phi-tiny-MoE and `meta`-device loading failures are different issues." }, { "left": "issue:43645", "right": "issue:44164", "accept": false, - "reason": "Custom model notebook initialization regression is separate from `extra_state` save/from_pretrained handling." + "reason": "Notebook custom-model init regression and save/from_pretrained `extra_state` handling are different bugs." }, { "left": "issue:43257", "right": "issue:44863", "accept": false, - "reason": "Different model families and different checkpoint-loading failures." + "reason": "Qwen3 MOE conversion with accelerate+deepspeed and NemotronH checkpoint loading are unrelated." }, { "left": "issue:43425", "right": "issue:43828", "accept": false, - "reason": "Torch 2.10 incompatibility and autocast dtype mismatch are not the same bug." + "reason": "Torch version incompatibility and autocast dtype mismatch are different failures." }, { "left": "issue:44589", "right": "issue:44756", "accept": false, - "reason": "Float8 storage lookup error is unrelated to mmap/OOM on Strix Halo." + "reason": "Float8 storage lookup error and mmap-related OOM are unrelated." }, { - "left": "issue:44479", - "right": "issue:45663", + "left": "issue:44683", + "right": "issue:45823", "accept": false, - "reason": "Qwen video-input regression vs Gemma4 FSDP2 attention bug are unrelated." + "reason": "Compiled flex_attention on torch>=2.9 and Gemma4 PLE device mismatch are different code paths." }, { - "left": "issue:44683", - "right": "issue:45823", + "left": "issue:44479", + "right": "issue:45663", "accept": false, - "reason": "Compiled flex_attention on torch >= 2.9 is unrelated to Gemma4 PLE device mismatch." + "reason": "Video-input regression and Gemma4 FSDP2 attention-state bug are unrelated." }, { "left": "issue:43906", "right": "issue:44530", "accept": false, - "reason": "`43906` is only an isolated reproduction reference; there is no clear evidence it is the same concrete bug as the Qwen3.5 PagedAttentionCache crash." + "reason": "Isolated reproduction of another issue and a PagedAttentionCache crash on Qwen3.5 are not the same bug." }, { "left": "issue:39404", "right": "issue:45701", "accept": false, - "reason": "Whisper pipeline `return_language` regression and tokenization changes are too broad and not clearly the same failure." + "reason": "Whisper pipeline `return_language` regression and tokenization changes across versions are different issues." }, { "left": "issue:43611", "right": "issue:43645", "accept": false, - "reason": "Both are Transformers 5.0 custom-model regressions, but one is `base_model_prefix` loading and the other is Jupyter-defined model initialization." + "reason": "Both involve Transformers 5.0.0 custom-model behavior, but one is `base_model_prefix` loading and the other is notebook initialization; not enough to merge." }, { "left": "issue:43425", "right": "issue:45823", "accept": false, - "reason": "Torch version incompatibility vs Gemma4 PLE device mismatch; unrelated." + "reason": "Torch incompatibility and Gemma4 forward device mismatch are unrelated." }, { "left": "issue:43931", "right": "issue:44863", "accept": false, - "reason": "Different checkpoint/model-loading failures for unrelated model families." + "reason": "Different model families and different load failures." } ] }, "evaluator_result": { "accept": true, - "feedback": "The cluster summary is grounded in the packet and stays conservative. The two accepted soft edges are well-supported by the issue titles: 45276 is a Gemma4-specific resize-token-embeddings variant of 45292, and 45335 is the T5Gemma-specific variant. The rejected pairs generally do not overclaim shared causality beyond broad symptom similarity." + "feedback": "The summary is grounded in the packet and stays conservative overall. The single accepted duplicate pair, 45276/45292, is well supported by the titles and the very high similarity score. The other soft-edge rejections are phrased cautiously and do not overclaim identity from the evidence provided." }, "evaluator_used": true, "retried": false, @@ -2438,9 +2390,9 @@ "issue:44265|issue:44898", "issue:43299|issue:43931", "issue:44479|issue:44805", - "issue:43856|issue:44756", "issue:43425|issue:44918", "issue:44589|issue:45084", + "issue:43856|issue:44756", "issue:40990|issue:42947", "issue:39404|issue:44671", "issue:43994|issue:44079", @@ -2456,20 +2408,20 @@ "issue:40990|issue:43421", "issue:43582|issue:43632", "issue:43611|issue:43644", - "issue:43883|issue:44488", "issue:44206|issue:44220", "issue:43716|issue:45084", + "issue:43883|issue:44488", "issue:44488|issue:44987", "issue:43643|issue:44530", "issue:34567|issue:40444", "issue:44811|issue:45584" ], - "prepared_review_unit_hash": "5fdf39ef050e5fa9acc7a2b9c8ac5c531be76b0eaf11ab39c0248e72c1dad59e", + "prepared_review_unit_hash": "2cccaab6747c76850d78bc13c764d77ff1ab854ae157f9c8989b30d2ed753cd2", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, @@ -2477,7 +2429,7 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 32, - "serialized_chars": 37331, + "serialized_chars": 37332, "estimated_input_tokens": 9333, "estimated_eval_tokens": 18922 }, @@ -2486,214 +2438,211 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is dominated by Transformers v5 loading/regression reports across many models and tokenizers, with a few unrelated audio/training outliers. One audio feature-extraction pair looks like a likely duplicate; the rest are too different to merge.", - "confidence": 0.46, - "canonical_issue_reason": "issue:43611 is the most central, broadly phrased report about a core v5 model-loading regression (`base_model_prefix`), which best matches the cluster\u2019s repeated loading-failure theme.", + "summary": "This looks like a loose similarity cluster rather than a true duplicate set. The issues span unrelated subsystems (Whisper, Qwen/VL, tokenizers, docs, loaders, training, torch/export). I did not find any soft-edge pair that clearly describes the same underlying bug or change.", + "confidence": 0.22, + "canonical_issue_reason": "Issue 44479 is the most representative standalone bug in the set: it describes a concrete regression, names the affected model families, and has a clear runtime failure mode.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43611 best represents the cluster because it is the most general and reusable root-cause-style issue among many version-5 loading regressions.", + "best_issue_reason": "Issue 44479 is the strongest issue to keep as the representative example because it is specific, user-visible, and broadly scoped enough to indicate the underlying regression pattern.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44530", "right": "issue:45084", "accept": false, - "reason": "Different failures: a Qwen3.5 PagedAttentionCache crash versus a template-node compilation TypeError; no clear shared code path." + "reason": "Different failures: one is a Qwen3.5 PagedAttentionCache runtime crash, the other is a template-compilation TypeError. No shared code-path evidence." }, { "left": "issue:43425", "right": "issue:43716", "accept": false, - "reason": "Unrelated topics: torch version compatibility versus a multimodal dtype mismatch in Mistral-3." + "reason": "Unrelated problems: Torch 2.10 compatibility vs. a multimodal dtype mismatch in Mistral-3." }, { "left": "issue:43901", "right": "issue:44509", "accept": false, - "reason": "Both are documentation issues, but they concern different API/docs surfaces and do not indicate the same underlying bug." + "reason": "Both are docs-related, but they cover different pipeline API changes and are not the same documentation bug." }, { "left": "issue:39404", "right": "issue:44912", "accept": false, - "reason": "Whisper pipeline language-return regression and MXFP4 quantization fallback are unrelated." + "reason": "Whisper pipeline language output regression vs. MXFP4 quantization fallback; different subsystems and symptoms." }, { "left": "issue:44265", "right": "issue:44898", "accept": false, - "reason": "Different subsystems and symptoms: torch.export with torch_compilable_check versus Perceiver image classification with interpolate_pos_encoding." + "reason": "Different model/export failures: torch.export with torch_compilable_check vs. Perceiver image classification at non-default resolution." }, { "left": "issue:43299", "right": "issue:43931", "accept": false, - "reason": "Both involve Qwen3-VL loading, but the model variants and failure modes differ; not enough evidence of one concrete bug." + "reason": "Both concern Qwen3-VL loading, but one is a dev-version model-loading regression and the other is a specific weight-shape mismatch. Not the same bug." }, { "left": "issue:44479", "right": "issue:44805", "accept": false, - "reason": "Both are shape/multimodal regressions, but they affect different code paths and model families." - }, - { - "left": "issue:43856", - "right": "issue:44756", - "accept": false, - "reason": "Qwen3 MoE training memory usage and Strix Halo mmap OOM are distinct performance/memory problems." + "reason": "Both mention multimodal input failures, but one is a broad video-input regression across Qwen models and the other is a generic mask/index shape error with no concrete match." }, { "left": "issue:43425", "right": "issue:44918", "accept": false, - "reason": "Torch 2.10 compatibility and Qwen3.5 embedding unpacking with TRL are different issues." + "reason": "Torch version incompatibility vs. TRL SFT embedding unpacking failure; no shared defect." }, { "left": "issue:44589", "right": "issue:45084", "accept": false, - "reason": "Float8 storage lookup failure and template compilation error are unrelated." + "reason": "Float8 storage lookup error and non-template-node compilation error are unrelated." + }, + { + "left": "issue:43856", + "right": "issue:44756", + "accept": false, + "reason": "Different memory issues: Qwen3 MoE training inefficiency vs. Apple Silicon mmap OOM mitigation." }, { "left": "issue:40990", "right": "issue:42947", "accept": false, - "reason": "High perplexity on a model/dataset pair and ineffective gradient checkpointing with LoRA are different training behaviors." + "reason": "High perplexity on GPT-OSS evaluation is not the same as ineffective gradient checkpointing with LoRA." }, { "left": "issue:39404", "right": "issue:44671", "accept": false, - "reason": "Whisper return_language regression and CamemBERT masked-LM prediction regression are separate model-specific bugs." + "reason": "Whisper pipeline regression and CamemBERT masked LM prediction regression are unrelated models and code paths." }, { "left": "issue:43994", "right": "issue:44079", "accept": false, - "reason": "A bad AutoModel/pipeline result for SigLIP2 is not the same as incorrect ModelOutput key assignment." + "reason": "SigLIP2 inference issue is not the same as ModelOutput key assignment when a previous value was None." }, { "left": "issue:44164", "right": "issue:45759", "accept": false, - "reason": "extra_state save/load handling and from_config text_config unwrapping are different serialization/loading issues." + "reason": "Different loading/saving problems: extra_state handling vs. from_config text_config unwrapping for composite Qwen multimodal configs." }, { "left": "issue:36032", "right": "issue:43452", "accept": false, - "reason": "Tokenizer special-token method conflict and gguf_file loading breakage are different loader failures." + "reason": "Tokenizer special-token method conflict and gguf_file loading breakage are separate loading bugs." }, { "left": "issue:43596", "right": "issue:44683", "accept": false, - "reason": "Deepspeed ZeRO3/BertModel index error is unrelated to compiled flex_attention failing on newer torch." + "reason": "DeepSpeed ZeRO-3/BertModel index error is unrelated to compiled flex_attention on newer torch versions." }, { - "left": "issue:44661", - "right": "issue:44683", + "left": "issue:44671", + "right": "issue:44991", "accept": false, - "reason": "Model-mapping registration failure and compiled flex_attention compatibility are unrelated." + "reason": "CamemBERT MLM predictions in v5 and tokenizer loading failure for EMBEDDIA/est-roberta are different defects." }, { "left": "issue:44991", "right": "issue:45081", "accept": false, - "reason": "Both are tokenizer loading regressions, but they involve different models and different root causes." + "reason": "Different tokenizer-loading failures affecting different models and different failure points." }, { "left": "issue:32090", "right": "issue:39404", "accept": false, - "reason": "Trainer GPU broadcast NoneType error and Whisper pipeline return_language regression are unrelated." + "reason": "Trainer GPU broadcast TypeError and Whisper return_language regression are unrelated." }, { "left": "issue:44164", "right": "issue:44479", "accept": false, - "reason": "Serialization extra_state handling and video-input regression are different bugs." + "reason": "Extra_state save/load handling is not the same issue as Qwen video-input regression." }, { "left": "issue:44488", "right": "issue:45081", "accept": false, - "reason": "Loading cjvt/sleng-bert and patching Mistral regex are unrelated tokenizer issues." + "reason": "Both are tokenizer-loading related, but the affected models and failing mechanisms differ." }, { "left": "issue:44661", "right": "issue:44683", "accept": false, - "reason": "These touch different areas: tokenizer/model mapping versus attention compilation." + "reason": "Model-registration logic and compiled flex_attention are unrelated areas." }, { "left": "issue:40990", "right": "issue:43421", "accept": false, - "reason": "Perplexity regression and runtime post-processor update behavior are unrelated." + "reason": "Perplexity evaluation regression and runtime special-token post-processor update bug are distinct." }, { "left": "issue:43582", "right": "issue:43632", "accept": false, - "reason": "Apple Silicon warmup TypeError and `_is_hf_initialized` regression are different initialization issues." + "reason": "Apple Silicon caching allocator TypeError does not match the _is_hf_initialized flag regression." }, { "left": "issue:43611", "right": "issue:43644", "accept": false, - "reason": "Both are v5 regressions, but one is about `base_model_prefix` loading and the other about non-persistent buffer initialization; distinct bugs." - }, - { - "left": "issue:43883", - "right": "issue:44488", - "accept": false, - "reason": "Attribute missing on Molmo and a tokenizer loading failure for another model are unrelated." + "reason": "Both are v5 regressions, but one is base_model_prefix loading and the other is non-persistent buffer initialization; not the same code-path bug." }, { "left": "issue:44206", "right": "issue:44220", - "accept": true, - "reason": "Both point to the same audio/fbank feature-extraction path; the second looks like the same `_torch_extract_fbank_features()` regression described from a different angle." + "accept": false, + "reason": "Audio feature-extraction failures, but one is an unsupported argument in LasrFeatureExtractor and the other is a lower-level fbank helper issue; not clearly the same defect." }, { "left": "issue:43716", "right": "issue:45084", "accept": false, - "reason": "Mistral-3 image-preprocessor dtype mismatch and template compilation failure are unrelated." + "reason": "Mistral-3 dtype mismatch and template-compilation error are unrelated." + }, + { + "left": "issue:43883", + "right": "issue:44488", + "accept": false, + "reason": "Missing tied-weights metadata in Molmo is unrelated to the sleng-bert tokenizer loading failure." }, { "left": "issue:44488", - "right": "issue:44987", + "right": "issue:45081", "accept": false, - "reason": "Different tokenizer/model-loading failures for different models; not the same concrete bug." + "reason": "Tokenizer-loading failures for different models with different symptoms; no strong evidence they share one underlying bug." }, { "left": "issue:43643", "right": "issue:44530", "accept": false, - "reason": "Missing fields from `trust_remote_code` config and Qwen3.5 PagedAttentionCache crash are unrelated." + "reason": "trust_remote_code config-field loss and Qwen3.5 PagedAttention crash are different problems." }, { "left": "issue:34567", "right": "issue:40444", "accept": false, - "reason": "TrainerState token counting and Qwen2.5-VL multi-image IterableDataset failure are different training issues." + "reason": "TrainerState token counting and Qwen2.5-VL IterableDataset multi-image finetuning are unrelated." }, { "left": "issue:44811", "right": "issue:45584", "accept": false, - "reason": "Both involve Whisper, but one is batch_decode special-token handling and the other is empty-generation behavior after align_special_tokens; not clearly the same bug." + "reason": "Both are Whisper-related, but batch_decode skip_special_tokens handling and empty-transcription generation after align_special_tokens are different bugs." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet: most items are indeed Transformers v5 loading/regression reports, with a smaller set of audio/training/docs outliers. The one accepted soft-edge pair (44206/44220) is a cautious, evidence-based duplicate call, and the remaining false verdicts are conservative rather than overreaching. No obvious overstatement or mergeability issue stands out." - }, - "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 }, @@ -2711,7 +2660,6 @@ "cluster_id": "cluster-15354-390", "nodes": [ "issue:36032", - "issue:41553", "issue:42915", "issue:43262", "issue:43296", @@ -2724,7 +2672,6 @@ "issue:43531", "issue:43540", "issue:43541", - "issue:43582", "issue:43611", "issue:43632", "issue:43644", @@ -2732,6 +2679,7 @@ "issue:43646", "issue:43742", "issue:43819", + "issue:43856", "issue:43883", "issue:43994", "issue:44062", @@ -2762,13 +2710,13 @@ "soft_pairs": [ "issue:43644|issue:43646", "issue:44451|issue:44987", - "issue:43541|issue:45084", "issue:36032|issue:42915", + "issue:43541|issue:45084", "issue:43452|issue:43482", "issue:42915|issue:44530", "issue:43317|issue:43482", - "issue:43883|issue:44991", "issue:44849|issue:45325", + "issue:43883|issue:44991", "issue:43404|issue:44466", "issue:36032|issue:43645", "issue:45084|issue:45507", @@ -2783,271 +2731,280 @@ "issue:43645|issue:44534", "issue:45216|issue:45357", "issue:44451|issue:45081", - "issue:44265|issue:44610", "issue:44987|issue:45081", + "issue:44265|issue:44610", "issue:44220|issue:44683", "issue:43404|issue:45127", "issue:43632|issue:44756", "issue:43296|issue:43531", - "issue:41553|issue:43582", - "issue:44062|issue:44987", "issue:42915|issue:44291", + "issue:44062|issue:44987", "issue:36032|issue:43742", "issue:43531|issue:44877", "issue:42915|issue:44589", - "issue:43611|issue:44534" + "issue:43611|issue:44534", + "issue:43317|issue:43856" ], - "prepared_review_unit_hash": "99c01ebfbb1a2a63318699590141504d8676e8304cefda0615889706eae0e08f", + "prepared_review_unit_hash": "7a1d5033249f07a064d1d2193d9ab4148bbf02578cbc0f9627103ba61cd7b945", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { - "node_count": 48, - "item_count": 48, + "node_count": 47, + "item_count": 47, "soft_pair_count": 36, - "serialized_chars": 38467, - "estimated_input_tokens": 9617, - "estimated_eval_tokens": 19490 + "serialized_chars": 37909, + "estimated_input_tokens": 9478, + "estimated_eval_tokens": 19212 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is a loose collection of Transformers v5 regression issues, mostly around model loading/initialization, tokenizer loading, and a few unrelated model-specific bugs. I did not find any soft pair that confidently represents the same concrete underlying bug/change, so I rejected all candidate merges.", - "confidence": 0.71, - "canonical_issue_reason": "issue:43646 is the broadest, most generic v5 regression in the set and best fits an umbrella role for the model-initialization/loading breakage theme.", + "summary": "This cluster is mostly a grab-bag of separate Transformers v5/model-loading regressions. I see one exact duplicate pair around non-persistent buffer junk, and one likely duplicate pair around Qwen3.5 save_pretrained serialization; the rest are too different to merge.", + "confidence": 0.78, + "canonical_issue_reason": "issue:43644 is the clearest representative because it states the precise v5 regression and is an exact duplicate of 44534; it is narrower and better-scoped than the other broadly related loading bugs in the cluster.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43646 is the most representative issue because it describes the widest-impact failure mode without being tied to a single model or narrow symptom.", + "best_issue_reason": "issue:43644 is the best issue to keep as the representative duplicate target: concrete, reproducible, and directly matched by an exact duplicate title, while the remaining items are mostly distinct regressions.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43644", "right": "issue:43646", "accept": false, - "reason": "Both are v5 regressions around initialization/serialization, but they describe different concrete symptoms and likely different code paths." + "reason": "Related v5 init regressions, but one is buffer corruption and the other is custom model initialization; different concrete bugs." }, { "left": "issue:44451", "right": "issue:44987", "accept": false, - "reason": "Both are tokenizer/model-loading failures, but for different models and likely different root causes; too broad to merge." + "reason": "Different models and different loading failures; no clear shared underlying bug." }, { - "left": "issue:43541", - "right": "issue:45084", + "left": "issue:36032", + "right": "issue:42915", "accept": false, - "reason": "Mixtral torch-dynamo grouped_mm tracing error is unrelated to a template compilation TypeError." + "reason": "Tokenizer special-token conflict vs Qwen3MoE FP8 config failure; unrelated code paths." }, { - "left": "issue:36032", - "right": "issue:42915", + "left": "issue:43541", + "right": "issue:45084", "accept": false, - "reason": "T5 tokenizer add_special_tokens conflict and Qwen3Moe FineGrainedFP8Config failure are unrelated subsystems and failure modes." + "reason": "Torch dynamo grouped_mm error vs template compilation error; distinct failures." }, { "left": "issue:43452", "right": "issue:43482", "accept": false, - "reason": "Both mention GGUF/loading, but one is a filename/argument path issue and the other is a transformers v5-specific Qwen2.5-GGUF regression." + "reason": "Both involve GGUF loading, but one is a generic from_pretrained/gguf_file regression and the other is a model-specific Qwen2.5-GGUF failure; not enough evidence of the same bug." }, { "left": "issue:42915", "right": "issue:44530", "accept": false, - "reason": "Both involve Qwen3.x models, but one is FP8 config loading and the other is paged attention cache group-type handling." + "reason": "Both Qwen-related, but FP8 config failure and PagedAttentionCache linear_attention crash are different problems." }, { "left": "issue:43317", "right": "issue:43482", "accept": false, - "reason": "Dequantized model device_map offload failure is a different path from GGUF tokenizer/model loading." + "reason": "Different load paths: dequantized device_map offload vs GGUF/Qwen2.5 loading." }, { - "left": "issue:43883", - "right": "issue:44991", + "left": "issue:44849", + "right": "issue:45325", "accept": false, - "reason": "Molmo tied-weights attribute error and est-roberta tokenizer loading failure are unrelated." + "reason": "Different Qwen model bugs with unrelated symptoms and code paths." }, { - "left": "issue:44849", - "right": "issue:45325", + "left": "issue:43883", + "right": "issue:44991", "accept": false, - "reason": "Both are Qwen3.5 regressions, but one is output_hidden_states behavior and the other is RoPE temporal position scaling; different bugs." + "reason": "Missing tied-weights attribute vs tokenizer load failure; unrelated." }, { "left": "issue:43404", "right": "issue:44466", "accept": false, - "reason": "These are both tied-weights issues, but one is missing weight tying in Mistral3 and the other is device-dependent serialization of lm_head.weight." + "reason": "Both touch tied weights, but one is a missing tie in a model class and the other is device-dependent serialization inconsistency; not the same bug." }, { "left": "issue:36032", "right": "issue:43645", "accept": false, - "reason": "T5 tokenizer method conflict and custom model initialization in Jupyter are not the same bug." + "reason": "Tokenizer method conflict vs custom model initialization in notebooks; different regressions." }, { "left": "issue:45084", "right": "issue:45507", "accept": false, - "reason": "Template-node compilation error is not the same as GraniteMoEHybrid calling an invalid method." + "reason": "Template compilation failure vs GraniteMoEHybrid invalid method call; distinct issues." }, { "left": "issue:43262", "right": "issue:43377", "accept": false, - "reason": "Audio processor chat-template sampling-rate default and MIMI padding-mask batching mismatch are different audio bugs." + "reason": "Sampling-rate default bug vs missing padding mask support; unrelated audio/model bugs." }, { "left": "issue:43646", "right": "issue:44534", "accept": false, - "reason": "Both are v5 regressions, but one is custom model initialization and the other is non-persistent buffer corruption; too different to merge." + "reason": "Custom model initialization breakage vs non-persistent buffer junk; different concrete failures." }, { "left": "issue:44987", "right": "issue:44991", "accept": false, - "reason": "Different models and symptoms, both just generic loading failures." + "reason": "Different model-specific loading regressions, only loosely related by Transformers v5." }, { "left": "issue:43994", "right": "issue:44610", "accept": false, - "reason": "Siglip2 bad outputs and OmDet-Turbo processor size mismatch are unrelated vision bugs." + "reason": "Nonsensical model outputs vs processor resolution mismatch; not the same bug." }, { "left": "issue:43322", "right": "issue:43540", "accept": false, - "reason": "Llava Next segmentation fault and Qwen3OmniMoe video ValueError are separate multimodal failures." + "reason": "Segfault loading Llava Next vs ValueError processing Qwen3OmniMoe video inputs; different paths." }, { "left": "issue:44403", "right": "issue:45081", "accept": false, - "reason": "Noise on transformer loading is unrelated to the Mistral regex patch crash." + "reason": "Loading noise issue vs Mistral tokenizer regex patch crash; unrelated." }, { "left": "issue:43377", "right": "issue:43819", "accept": false, - "reason": "Missing padding-mask support in MIMI encoder and DAC STE mismatch are different audio-model correctness bugs." + "reason": "Both are correctness bugs, but one is padding-mask related and the other is missing STE in DAC; different underlying problems." }, { "left": "issue:42915", "right": "issue:45084", "accept": false, - "reason": "FineGrainedFP8Config loading failure and template-node compilation failure have no concrete overlap." + "reason": "Qwen3MoE FP8 config issue vs template compilation failure; unrelated." }, { "left": "issue:43645", "right": "issue:44534", "accept": false, - "reason": "Notebook custom-model init breakage and non-persistent buffer junk are related only at a high level, not the same bug." + "reason": "Custom model init in notebooks vs buffer junk regression; different bugs." }, { "left": "issue:45216", "right": "issue:45357", - "accept": false, - "reason": "Both are Qwen3.5 save_pretrained regressions, but one is a general incorrect checkpoint and the other specifically wrong visual encoder keys." + "accept": true, + "reason": "Both report the same Qwen3.5 save_pretrained serialization regression, with the later issue narrowing it to incorrect visual encoder keys." }, { "left": "issue:44451", "right": "issue:45081", "accept": false, - "reason": "Tokenizer loading failure for ScandiBERT and Mistral regex patch crash are different code paths." + "reason": "Different model/tokenizer failures with no shared code-path evidence." }, { - "left": "issue:44265", - "right": "issue:44610", + "left": "issue:44987", + "right": "issue:45081", "accept": false, - "reason": "torch.export export failure with torch_compilable_check is unrelated to a processor resolution mismatch." + "reason": "Model loading failure vs Mistral tokenizer regex crash; distinct issues." }, { - "left": "issue:44987", - "right": "issue:45081", + "left": "issue:44265", + "right": "issue:44610", "accept": false, - "reason": "Different model families and different failure types; no shared underlying bug." + "reason": "torch.export/exportability issue vs processor image-size mismatch; not the same bug." }, { "left": "issue:44220", "right": "issue:44683", "accept": false, - "reason": "Fbank feature extraction issue and compiled flex_attention failure are unrelated." + "reason": "fbank feature extraction bug vs compiled flex_attention failure on torch>=2.9; unrelated." }, { "left": "issue:43404", "right": "issue:45127", "accept": false, - "reason": "Missing tie on Mistral3 lm_head and LoRA merge collapse with extended vocab are both weight-tying themed but not the same concrete bug." + "reason": "Tied-weights bug in model loading vs LoRA merge collapse after vocab extension; different failure modes." }, { "left": "issue:43632", "right": "issue:44756", "accept": false, - "reason": "_is_hf_initialized flag regression and mmap OOM on Strix Halo are unrelated." + "reason": "_is_hf_initialized regression vs mmap/OOM workaround request; unrelated." }, { "left": "issue:43296", "right": "issue:43531", "accept": false, - "reason": "PaddleOCR-VL loading failure and Qwen3-MoE sliding_window bug are separate model-specific issues." + "reason": "PaddleOCR-VL load failure in vLLM vs Qwen3-MoE sliding_window issue; different model/code paths." }, { - "left": "issue:41553", - "right": "issue:43582", + "left": "issue:42915", + "right": "issue:44291", "accept": false, - "reason": "Bad AutoTokenizer error for Voxtral and Apple Silicon caching_allocator_warmup TypeError are unrelated." + "reason": "FP8 config failure vs unexpected _is_hf_initialized argument in init_empty_weights; distinct regressions." }, { "left": "issue:44062", "right": "issue:44987", "accept": false, - "reason": "AddedToken special-argument conflict and a model loading failure for physical-intelligence/fast are different tokenizer/model bugs." - }, - { - "left": "issue:42915", - "right": "issue:44291", - "accept": false, - "reason": "Qwen3Moe FP8 config failure and init_empty_weights unexpected _is_hf_initialized argument are distinct v5 regressions." + "reason": "AddedToken keyword collision vs model loading failure; unrelated." }, { "left": "issue:36032", "right": "issue:43742", "accept": false, - "reason": "T5 tokenizer conflict and MobileLLM-125M key error are unrelated loading failures." + "reason": "Tokenizer special-token conflict vs MobileLLM key error; different bugs." }, { "left": "issue:43531", "right": "issue:44877", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior and granite_speech strict config loading are different bugs." + "reason": "Qwen3-MoE sliding_window bug vs granite_speech strict-config load failure; unrelated." }, { "left": "issue:42915", "right": "issue:44589", "accept": false, - "reason": "Qwen3Moe FP8 config failure and missing Float8 storage type are different lower-level issues." + "reason": "Qwen3MoE FP8 config issue vs missing Float8 storage object; different problems." }, { "left": "issue:43611", "right": "issue:44534", "accept": false, - "reason": "Base_model_prefix loading regression and non-persistent buffer junk are both v5 regressions but not the same concrete failure." + "reason": "base_model_prefix loading regression vs non-persistent buffer junk; distinct failures." + }, + { + "left": "issue:43644", + "right": "issue:44534", + "accept": true, + "reason": "Exact same v5 regression about non-persistent buffers being filled with junk; this is a clear duplicate." + }, + { + "left": "issue:43317", + "right": "issue:43856", + "accept": false, + "reason": "Device-map/offload load failure vs training memory inefficiency; not duplicates." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative overall. The one clear duplicate pair around non-persistent buffers is well supported by the titles, and the Qwen3.5 save_pretrained pair is presented only as a likely duplicate. The rejected soft-edge pairs are also reasonably cautious and do not overclaim shared root causes based on the available evidence." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -3068,10 +3025,10 @@ "issue:36032", "issue:40444", "issue:40990", + "issue:41553", "issue:41720", "issue:42175", "issue:43296", - "issue:43317", "issue:43377", "issue:43421", "issue:43425", @@ -3079,12 +3036,12 @@ "issue:43482", "issue:43525", "issue:43531", + "issue:43582", "issue:43611", "issue:43632", "issue:43646", "issue:43792", "issue:43818", - "issue:43856", "issue:43994", "issue:44079", "issue:44265", @@ -3114,7 +3071,7 @@ "issue:45812" ], "soft_pairs": [ - "issue:43317|issue:43856", + "issue:41553|issue:43582", "issue:44479|issue:45325", "issue:40990|issue:44811", "issue:42175|issue:45542", @@ -3128,29 +3085,29 @@ "issue:43632|issue:44534", "issue:44403|issue:44991", "issue:44829|issue:45479", - "issue:43482|issue:45538", "issue:44683|issue:45020", + "issue:43482|issue:45538", "issue:33666|issue:40444", "issue:43482|issue:43525", - "issue:40444|issue:45325", "issue:44291|issue:44589", + "issue:40444|issue:45325", "issue:43377|issue:45491", "issue:41720|issue:45081", - "issue:44265|issue:45072", "issue:42175|issue:43296", - "issue:43611|issue:43646", "issue:43531|issue:44291", + "issue:43611|issue:43646", + "issue:44265|issue:45072", "issue:43632|issue:45072", "issue:43454|issue:44466", - "issue:43994|issue:44898", - "issue:44079|issue:44534" + "issue:44079|issue:44534", + "issue:43994|issue:44898" ], - "prepared_review_unit_hash": "757a075b3b95996af1a666cdb33ab9907d4eb5b5bb9dfad976e94aed961e33ac", + "prepared_review_unit_hash": "c0882aae5ad7140050d4831a80f7b5e506dd26e70e49e2c10ad47eafc57c7b26", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, @@ -3158,210 +3115,210 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 37032, - "estimated_input_tokens": 9258, - "estimated_eval_tokens": 18772 + "serialized_chars": 37015, + "estimated_input_tokens": 9254, + "estimated_eval_tokens": 18764 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a set of superficially similar but distinct issues. The only clear duplicate-like pair is the Transformers v5 model-loading/init regression pair; the rest are different bugs that just share model families or broad subsystems.", - "confidence": 0.67, - "canonical_issue_reason": "issue:43611 is the clearest, most concrete representative of the shared Transformers v5 model-loading regression; it captures the core breakage in loading models with `base_model_prefix` and aligns with the nearby custom-init report.", + "summary": "Mostly distinct regression reports with issue 45020 as the best umbrella anchor. The only soft links that look plausibly duplicate-like are 44462\u219445812 and 43421\u219444568, but those are better described as strong title/subsystem similarities than confirmed same-bug matches. The v5 init/_is_hf_initialized-related links do not look like duplicates here and should stay rejected.", + "confidence": 0.66, + "canonical_issue_reason": "Issue 45020 is the broadest and most representative umbrella for the cluster: it captures the general recent-transformers-v5 breakage theme without overcommitting to any single narrow failure mode.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43611 is the best overall issue representative because it is specific, actionable, and likely closest to the root code-path regression among the matched items.", + "best_issue_reason": "Issue 45020 is the best global anchor because it is open, broad, and matches the cluster\u2019s shared regression theme across multiple version-specific reports.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43317", - "right": "issue:43856", + "left": "issue:41553", + "right": "issue:43582", "accept": false, - "reason": "Both mention Qwen/device or memory problems, but one is dequantized model offload loading and the other is MoE training memory usage; not the same bug." + "reason": "Different failure modes and subsystems: AutoTokenizer/Voxtral loading vs Apple Silicon allocator TypeError." }, { "left": "issue:44479", "right": "issue:45325", "accept": false, - "reason": "Same Qwen VL family and version, but one is a broad video-input regression while the other is a specific still-image temporal-position scaling bug; too much ambiguity to merge as one issue." + "reason": "Same broad model family, but different concrete bugs: video-input regression vs still-image rope-index scaling." }, { "left": "issue:40990", "right": "issue:44811", "accept": false, - "reason": "Completely different models and failure modes: perplexity regression vs Whisper `batch_decode` special-token handling." + "reason": "Unrelated behavior: perplexity/eval complaint vs Whisper batch_decode skip_special_tokens handling." }, { "left": "issue:42175", "right": "issue:45542", "accept": false, - "reason": "Both involve TensorFlow/backend packaging, but one is missing TF in the torch extra and the other is an undefined backend error when only tensorboard is installed; related area, different bugs." + "reason": "Both involve TF packaging, but the missing-dependency paths and fixes appear different." }, { "left": "issue:43425", "right": "issue:44403", "accept": false, - "reason": "Torch version incompatibility vs noisy transformer loading are unrelated." + "reason": "Torch compatibility issue vs loading-noise/reporting issue; no shared bug." }, { "left": "issue:44462", "right": "issue:45812", - "accept": false, - "reason": "Both concern tokenizer loading, but one is ignoring `tokenizer.json` and the other is wrong Granite token IDs; not enough evidence of the same root cause." + "accept": true, + "reason": "Plausibly the same tokenizer-loading path: ignoring tokenizer.json could reasonably surface as wrong token IDs, though this is still mostly title-level evidence." }, { "left": "issue:43818", "right": "issue:45357", "accept": false, - "reason": "Different models and subsystems: Video-LLaVA tower/temporal attention vs Qwen3.5 save_pretrained visual-encoder keys." + "reason": "Different model families and different problems: Video-LLaVA architecture issue vs Qwen3.5 save_pretrained key regression." }, { "left": "issue:44079", "right": "issue:45663", "accept": false, - "reason": "ModelOutput key assignment bug vs Gemma4 FSDP2 `shared_kv_states` KeyError are unrelated." + "reason": "ModelOutput key assignment bug and Gemma-4 FSDP2 KeyError are unrelated code paths." }, { "left": "issue:43421", "right": "issue:44568", - "accept": false, - "reason": "Both involve special tokens, but one is runtime post-processor updates and the other is a specific tokenizer not adding BOS/EOS with `add_special_tokens=True`; not clearly the same concrete bug." + "accept": true, + "reason": "Plausible same tokenizer/post-processor area: both point to special-token handling changing behavior at runtime, but evidence is still mostly similarity-based." }, { "left": "issue:36032", "right": "issue:41720", "accept": false, - "reason": "T5 tokenizer API conflict and Qwen3 auto device-map CUDA assert are unrelated." + "reason": "T5 tokenizer attribute conflict vs Qwen3 auto device-mapping crash; unrelated." }, { "left": "issue:43792", "right": "issue:44589", "accept": false, - "reason": "Whisper run failure and missing Float8 storage type are different issues." + "reason": "Whisper runtime failure and float8 storage lookup TypeError are unrelated." }, { "left": "issue:43632", "right": "issue:44534", "accept": false, - "reason": "One is `_is_hf_initialized` handling and the other is non-persistent buffer junk; both are v5 regressions but not the same code path." + "reason": "Both are v5 regressions, but the concrete bugs differ: _is_hf_initialized vs non-persistent buffer corruption." }, { "left": "issue:44403", "right": "issue:44991", "accept": false, - "reason": "General loading noise vs tokenizer loading failure for a specific model are not the same underlying bug." + "reason": "General loading-noise report vs a specific tokenizer-loading failure; not the same bug." }, { "left": "issue:44829", "right": "issue:45479", "accept": false, - "reason": "Degenerate training with flash attention is unrelated to zero-loss single-label classification behavior." + "reason": "Similar symptom class, but different causes: flash_attention_3 training collapse vs num_labels=1 zero-loss logic." }, { - "left": "issue:43482", - "right": "issue:45538", + "left": "issue:44683", + "right": "issue:45020", "accept": false, - "reason": "GGUF loading failure and CLIPTokenizer `model_max_length` are unrelated." + "reason": "A separate torch/compiler flex_attention issue, not the remote_code loading regression." }, { - "left": "issue:44683", - "right": "issue:45020", + "left": "issue:43482", + "right": "issue:45538", "accept": false, - "reason": "Torch flex_attention compilation failure and remote_code breakage are different regressions." + "reason": "GGUF loading failure vs CLIPTokenizer model_max_length sentinel issue; unrelated." }, { "left": "issue:33666", "right": "issue:40444", "accept": false, - "reason": "Both are Qwen2-VL training issues, but one is multi-GPU training and the other is iterable-dataset multi-image prompting; not the same bug." + "reason": "Both are Qwen VL training issues, but they concern different models and failure modes." }, { "left": "issue:43482", "right": "issue:43525", "accept": false, - "reason": "Qwen2.5-GGUF loading failure and missing `pad_token_id` on Llama4Config are unrelated." + "reason": "GGUF/v5 loading failure vs missing pad_token_id on Llama4Config; unrelated." }, { - "left": "issue:40444", - "right": "issue:45325", + "left": "issue:44291", + "right": "issue:44589", "accept": false, - "reason": "Training with multi-image iterable datasets vs temporal position-id scaling in Qwen2.5-VL are different problems." + "reason": "init_empty_weights/_is_hf_initialized bug vs float8 storage lookup error; unrelated." }, { - "left": "issue:44291", - "right": "issue:44589", + "left": "issue:40444", + "right": "issue:45325", "accept": false, - "reason": "Unexpected `_is_hf_initialized` arg in `init_empty_weights` is not the same as missing Float8 storage support." + "reason": "Different Qwen2.5-VL bugs: multi-image iterable-dataset failure vs still-image temporal position scaling." }, { "left": "issue:43377", "right": "issue:45491", "accept": false, - "reason": "Batched-vs-single padding-mask issue in MIMI and Gemma3 NaNs from sliding-window/all-padding behavior are different bugs." + "reason": "Different batching bugs in different models: padding-mask issue vs mixed-length NaNs from all-padding windows." }, { "left": "issue:41720", "right": "issue:45081", "accept": false, - "reason": "Qwen3 device-map CUDA assert and Mistral tokenizer regex patch crash are unrelated." + "reason": "Qwen3 device-mapping crash vs Mistral regex/backend_tokenizer AttributeError; unrelated." }, { - "left": "issue:44265", - "right": "issue:45072", + "left": "issue:42175", + "right": "issue:43296", "accept": false, - "reason": "`torch.export` support via `torch_compilable_check` and bfloat16 dtype mismatches are different issues." + "reason": "Packaging/extras issue vs vLLM PaddleOCR-VL load failure; unrelated." }, { - "left": "issue:42175", - "right": "issue:43296", + "left": "issue:43531", + "right": "issue:44291", "accept": false, - "reason": "Packaging/backend dependency issue and PaddleOCR-VL loading in vLLM are unrelated." + "reason": "Qwen3-MoE sliding_window issue vs init_empty_weights unexpected _is_hf_initialized argument; unrelated." }, { "left": "issue:43611", "right": "issue:43646", - "accept": true, - "reason": "Both report Transformers v5 model-loading/init regressions with the same underlying initialization path; one is the `base_model_prefix` failure and the other is the broader custom-model initialization breakage." + "accept": false, + "reason": "Both are v5-related, but one is base_model_prefix handling and the other is custom model initialization; not the same concrete bug." }, { - "left": "issue:43531", - "right": "issue:44291", + "left": "issue:44265", + "right": "issue:45072", "accept": false, - "reason": "Qwen3-MoE sliding-window issue and `init_empty_weights` `_is_hf_initialized` error are different bugs." + "reason": "torch.export/torch_compilable_check failure vs bf16 dtype mismatch; unrelated." }, { "left": "issue:43632", "right": "issue:45072", "accept": false, - "reason": "Initialization flag handling and bfloat16 inference dtype mismatches are unrelated." + "reason": "_is_hf_initialized regression vs bf16 dtype mismatch; unrelated." }, { "left": "issue:43454", "right": "issue:44466", "accept": false, - "reason": "Both touch `lm_head.weight`/tied weights, but one is a tying bug causing garbage generation and the other is inconsistent serialization by device; not clearly the same fix." + "reason": "Related tied-weight theme, but the concrete failures differ: tying bug vs serialization inconsistency." }, { - "left": "issue:43994", - "right": "issue:44898", + "left": "issue:44079", + "right": "issue:44534", "accept": false, - "reason": "Siglip2 AutoModel/pipeline nonsense and Perceiver non-default-resolution failure are different vision-model issues." + "reason": "ModelOutput key assignment issue vs non-persistent buffer junk; unrelated." }, { - "left": "issue:44079", - "right": "issue:44534", + "left": "issue:43994", + "right": "issue:44898", "accept": false, - "reason": "ModelOutput key assignment and non-persistent buffer initialization are unrelated." + "reason": "Different models and different bugs: SigLIP2 nonsensical outputs vs Perceiver interpolation failure." } ] }, "evaluator_result": { - "accept": true, - "feedback": "Grounded summary overall, and the one accepted pair (issue:43611 / issue:43646) is conservative given both are Transformers v5 model-loading/init regressions. The other pairwise rejections also stay within the evidence in the packet." + "accept": false, + "feedback": "Reject: the broad anchor on issue 45020 is reasonable, and most soft-edge rejections are conservative, but the summary overstates the evidence by implying the v5 init/_is_hf_initialized cases are convincing duplicates when the packet only supports rejecting those links. The accepted pairs (44462\u219445812 and 43421\u219444568) are plausible, but should be framed more cautiously as title-level similarities rather than confirmed same-bug matches." }, "evaluator_used": true, - "retried": false, + "retried": true, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -3397,7 +3354,6 @@ "issue:43606", "issue:43644", "issue:43701", - "issue:43720", "issue:43746", "issue:43792", "issue:43819", @@ -3415,6 +3371,7 @@ "issue:44488", "issue:44610", "issue:44617", + "issue:44683", "issue:44877", "issue:44898", "issue:44991", @@ -3429,45 +3386,45 @@ "issue:45834" ], "soft_pairs": [ + "issue:45325|issue:45834", "issue:42915|issue:43482", "issue:43792|issue:43957", "issue:44079|issue:45072", "issue:40444|issue:45381", - "issue:43881|issue:44488", "issue:45325|issue:45381", "issue:43644|issue:44079", "issue:44387|issue:44617", "issue:43296|issue:45800", + "issue:43881|issue:44488", "issue:44479|issue:45823", "issue:35707|issue:40444", - "issue:45325|issue:45834", "issue:44291|issue:44877", "issue:43317|issue:43873", "issue:43606|issue:44265", "issue:43701|issue:45325", - "issue:43526|issue:43883", "issue:44186|issue:44265", "issue:43606|issue:43819", "issue:43262|issue:43746", "issue:41720|issue:45823", "issue:43454|issue:43550", "issue:43377|issue:44610", - "issue:43881|issue:44991", + "issue:43526|issue:43883", "issue:43454|issue:45072", "issue:43377|issue:44898", "issue:40990|issue:45584", "issue:43572|issue:45759", "issue:39692|issue:40444", + "issue:43881|issue:44991", "issue:44466|issue:45357", "issue:43296|issue:44991", - "issue:43454|issue:43720" + "issue:43792|issue:44683" ], - "prepared_review_unit_hash": "4f2921967117af8a5e4cbe98e2dae3df37c2f329985ff862a875f754f1ec71e8", + "prepared_review_unit_hash": "4952346d1732e0a6c6fd649fc1c278d8061b9428ae5300ca5156dd29f8fdd22f", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, @@ -3475,196 +3432,244 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 32, - "serialized_chars": 37357, - "estimated_input_tokens": 9340, - "estimated_eval_tokens": 18936 + "serialized_chars": 37300, + "estimated_input_tokens": 9325, + "estimated_eval_tokens": 18906 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is heterogeneous: most pairs are only loosely related by broad themes like loading, offloading, or Qwen multimodal regressions, but they do not describe the same concrete bug. No soft edge is strong enough to merge.", - "confidence": 0.94, - "canonical_issue_reason": "issue:43873 is the broadest and most actively discussed issue here, centered on offloading/quantization behavior, so it is the best umbrella representative even though the set is not a true duplicate cluster.", + "summary": "These issues are mostly separate model-loading, quantization, multimodal, and serialization bugs. I don\u2019t see any soft pair that clearly describes the exact same underlying defect, so no duplicates should be merged here.", + "confidence": 0.84, + "canonical_issue_reason": "issue:43873 is the broadest representative of the cluster\u2019s dominant theme: offloading/quantization/device-mapping regressions. It is also open and central to several nearby load/offload reports.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43873 is the most suitable issue to anchor this cluster because it is generic, active, and closest to the recurring device/offload/quantization failures; however, it should not be treated as covering the unrelated items in the set.", + "best_issue_reason": "issue:43873 is the best single issue to keep as the representative because it is the most general and most likely to subsume the offload/quantization subset of this cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:45325", + "right": "issue:45834", + "accept": false, + "reason": "Different bugs: still-image temporal position IDs vs long OCR input indexing on a different model." + }, { "left": "issue:42915", "right": "issue:43482", "accept": false, - "reason": "Different models and different failure modes: FineGrainedFP8 loading vs GGUF/v5 loading." + "reason": "Same model family, but different failure modes: FP8 config failure vs GGUF loading regression." }, { "left": "issue:43792", "right": "issue:43957", "accept": false, - "reason": "Whisper runtime failure and meta-device loading breakage are unrelated code paths." + "reason": "Whisper runtime failure and meta-device loading breakage are different code paths." }, { "left": "issue:44079", "right": "issue:45072", "accept": false, - "reason": "ModelOutput key bookkeeping is unrelated to bf16 dtype mismatches in inference." + "reason": "ModelOutput key assignment bug is unrelated to the bfloat16 dtype mismatch issue." }, { "left": "issue:40444", "right": "issue:45381", "accept": false, - "reason": "Multi-image finetuning failure and Qwen video position-id regression are different bugs." - }, - { - "left": "issue:43881", - "right": "issue:44488", - "accept": false, - "reason": "Model load failure for glm-4v-9b vs tokenizer load failure for a different model." + "reason": "Multi-image finetuning failure is not the same as the video vision_position_ids regression." }, { "left": "issue:45325", "right": "issue:45381", "accept": false, - "reason": "Both involve Qwen2.5-VL position ids, but one is still-image temporal scaling and the other is video-input behavior; too different to merge confidently." + "reason": "Both involve Qwen VL positions, but one is still-image scaling and the other is a video-input bug." }, { "left": "issue:43644", "right": "issue:44079", "accept": false, - "reason": "Non-persistent buffer initialization junk and ModelOutput key assignment are separate issues." + "reason": "Non-persistent buffer junk values and ModelOutput key assignment are unrelated defects." }, { "left": "issue:44387", "right": "issue:44617", "accept": false, - "reason": "Generic int4 reserved-memory OOM and Sam3Video OOM are different failures on different paths." + "reason": "Memory growth under int4 quantization is not the same bug as SAM3Video OOM." }, { "left": "issue:43296", "right": "issue:45800", "accept": false, - "reason": "PaddleOCR-VL/vLLM loading failure is unrelated to torch 2.4.1 and transformers 5.8.0 incompatibility." + "reason": "vLLM/PaddleOCR-VL load failure is unrelated to the torch 2.4.1 / transformers 5.8.0 incompatibility report." + }, + { + "left": "issue:43881", + "right": "issue:44488", + "accept": false, + "reason": "Different models and different loading failures; no shared underlying bug." }, { "left": "issue:44479", "right": "issue:45823", "accept": false, - "reason": "Qwen video-input regression and Gemma4 device mismatch are distinct model-specific bugs." + "reason": "Both are device-map related, but one is a Qwen video regression and the other is a Gemma4 device mismatch." }, { "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:45325", - "right": "issue:45834", - "accept": false, - "reason": "Qwen2.5-VL rope-index scaling and Kosmos2.5 OCR index error are different model paths." + "reason": "Progressive generation with inputs_embeds/past_key_values is unrelated to multi-image iterable finetuning." }, { "left": "issue:44291", "right": "issue:44877", "accept": false, - "reason": "init_empty_weights argument mismatch is unrelated to strict granite_speech config loading." + "reason": "init_empty_weights argument mismatch and strict config loading are different issues." }, { "left": "issue:43317", "right": "issue:43873", "accept": false, - "reason": "Both are offload/quantization-adjacent, but one is a specific dequantized load failure and the other is a broader report; not the same concrete bug." + "reason": "Related offload area, but one is dequantized model loading with gpu/cpu offload and the other is a broader quantization/offload complaint." }, { "left": "issue:43606", "right": "issue:44265", "accept": false, - "reason": "CPU offload device mismatch and torch.export with torch_compilable_check are unrelated." + "reason": "CPU offload device mismatch is unrelated to torch.export failures around torch_compilable_check." }, { "left": "issue:43701", "right": "issue:45325", "accept": false, - "reason": "resume_from_checkpoint key mismatch is unrelated to Qwen2.5-VL rope-index handling." - }, - { - "left": "issue:43526", - "right": "issue:43883", - "accept": false, - "reason": "BeitImageProcessorFast label reduction and Molmo tied-weights attribute errors are separate bugs." + "reason": "Checkpoint resume key mismatch is unrelated to the Qwen2.5-VL positional bug." }, { "left": "issue:44186", "right": "issue:44265", "accept": false, - "reason": "Tokenizer padding/truncation crash and torch.export failures are different subsystems." + "reason": "Tokenizer padding/truncation crash and export checker failure are not the same underlying problem." }, { "left": "issue:43606", "right": "issue:43819", "accept": false, - "reason": "CPU offload device mismatch and DAC.from_latents/STE mismatch are unrelated." + "reason": "CPU offload device mismatch is unrelated to DAC.from_latents vs forward mismatch." }, { "left": "issue:43262", "right": "issue:43746", "accept": false, - "reason": "Audio chat-template sample-rate defaulting and PEFT checkpoint loading are different issues." + "reason": "Audio chat-template sampling-rate default and PEFT checkpoint loading are different bugs." }, { "left": "issue:41720", "right": "issue:45823", "accept": false, - "reason": "Qwen3 auto device-map assert and Gemma4 forward device mismatch are not the same bug." + "reason": "Both mention device mapping, but they affect different models and fail differently." }, { "left": "issue:43454", "right": "issue:43550", "accept": false, - "reason": "lm_head weight tying and torch.compile SDPA failures are unrelated." + "reason": "Weight tying/garbage text is unrelated to the torch.compile SDPA failure." }, { "left": "issue:43377", "right": "issue:44610", "accept": false, - "reason": "Padding-mask batching bug in MIMI encoder and OmDet-Turbo size mismatch are different problems." + "reason": "MIMI batching/padding-mask bug and OmDet processor resolution mismatch are unrelated." }, { - "left": "issue:43881", - "right": "issue:44991", + "left": "issue:43526", + "right": "issue:43883", "accept": false, - "reason": "Two load failures, but for different models and different failure points." + "reason": "reduce_labels returning one label is unrelated to missing all_tied_weights_keys." }, { "left": "issue:43454", - "right": "issue:43720", + "right": "issue:45072", "accept": false, - "reason": "Tied-weights serialization and BitNet packed-weight loading are unrelated." - } - ] - }, - "evaluator_result": null, - "evaluator_used": false, - "retried": false, - "accepted_nontrivial_soft_edge": false, - "error_kind": null, - "error_message": null - }, - { - "label": "issue", - "component_index": 2, - "component_count": 16, - "review_unit_index": 11, - "review_unit_count": 45, - "status": "reviewed", - "reason": null, - "source": "llm", - "cache_hit": false, - "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-390", - "nodes": [ - "issue:34634", - "issue:35707", + "reason": "Serialization/weight-tying bug and bfloat16 dtype mismatch are different issues." + }, + { + "left": "issue:43377", + "right": "issue:44898", + "accept": false, + "reason": "Different models and different failure modes: batching mask bug vs positional interpolation bug." + }, + { + "left": "issue:40990", + "right": "issue:45584", + "accept": false, + "reason": "Perplexity regression on GPT-OSS is unrelated to Whisper empty-transcription generation failure." + }, + { + "left": "issue:43572", + "right": "issue:45759", + "accept": false, + "reason": "Missing pad_token_idx in StableLmConfig is not the same as unwrapping text_config for composite Qwen configs." + }, + { + "left": "issue:39692", + "right": "issue:40444", + "accept": false, + "reason": "Doc-example errors for SigLIP2 are unrelated to Qwen2.5-VL multi-image finetuning failures." + }, + { + "left": "issue:43881", + "right": "issue:44991", + "accept": false, + "reason": "Different models and different tokenizer/loading paths; not a duplicate." + }, + { + "left": "issue:44466", + "right": "issue:45357", + "accept": false, + "reason": "Both touch save_pretrained/serialization, but one is tied lm_head serialization and the other is visual-encoder key saving." + }, + { + "left": "issue:43819", + "right": "issue:44617", + "accept": false, + "reason": "DAC latent mismatch is unrelated to SAM3Video out-of-memory." + }, + { + "left": "issue:43296", + "right": "issue:44991", + "accept": false, + "reason": "Different model families and different loading failures." + }, + { + "left": "issue:43792", + "right": "issue:44683", + "accept": false, + "reason": "Whisper runtime failure and compiled flex_attention failure are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 11, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:34634", + "issue:35707", "issue:36331", "issue:40990", "issue:41720", @@ -3676,6 +3681,7 @@ "issue:43322", "issue:43404", "issue:43450", + "issue:43454", "issue:43526", "issue:43550", "issue:43577", @@ -3683,7 +3689,6 @@ "issue:43708", "issue:43720", "issue:43749", - "issue:43792", "issue:43873", "issue:43881", "issue:44008", @@ -3693,7 +3698,6 @@ "issue:44479", "issue:44534", "issue:44610", - "issue:44683", "issue:44756", "issue:44877", "issue:44898", @@ -3703,6 +3707,7 @@ "issue:44991", "issue:45072", "issue:45081", + "issue:45161", "issue:45357", "issue:45406", "issue:45632", @@ -3713,11 +3718,11 @@ "issue:45823" ], "soft_pairs": [ - "issue:43792|issue:44683", + "issue:43454|issue:43720", "issue:43873|issue:45701", "issue:41720|issue:44977", - "issue:45632|issue:45684", "issue:44008|issue:45823", + "issue:45632|issue:45684", "issue:43404|issue:45357", "issue:44423|issue:45406", "issue:34634|issue:35707", @@ -3728,237 +3733,232 @@ "issue:43749|issue:44534", "issue:44877|issue:44991", "issue:42617|issue:42915", - "issue:43550|issue:43720", "issue:43450|issue:45701", + "issue:43550|issue:43720", "issue:36331|issue:42915", - "issue:43526|issue:43881", "issue:44610|issue:44898", "issue:44186|issue:44610", "issue:44387|issue:45704", "issue:36331|issue:42617", "issue:44479|issue:44918", + "issue:43526|issue:43881", "issue:43316|issue:44913", - "issue:43550|issue:43606", "issue:42915|issue:43317", "issue:45081|issue:45812", + "issue:43550|issue:43606", "issue:41720|issue:43322", "issue:40990|issue:45701", - "issue:43295|issue:45701" + "issue:43295|issue:45701", + "issue:41720|issue:45161" ], - "prepared_review_unit_hash": "07b2f7a21e9f29dabeadcfc7cf009b8e5a5ecbb942b9c7a691803f8376fc23f9", + "prepared_review_unit_hash": "ba3da608036e3681501c0a53f39edb6c439e8fbde2e214f411e00e6f2b6fb379", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 31, - "serialized_chars": 37045, - "estimated_input_tokens": 9262, - "estimated_eval_tokens": 18780 + "soft_pair_count": 32, + "serialized_chars": 37387, + "estimated_input_tokens": 9347, + "estimated_eval_tokens": 18950 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly noisy: many unrelated model-specific bugs were grouped by broad similarity around loading, serving, tokenizer, offloading, and quantization. None of the soft pairs look like the same underlying bug/change closely enough to merge.", - "confidence": 0.87, - "canonical_issue_reason": "issue:43873 is the broadest and most central thread in the set, with multiple references and discussion around offloading/quantization behavior; it best fits the cluster\u2019s weak common theme even though the cluster is largely heterogeneous.", + "summary": "No duplicate cluster here: the soft-similarity pairs are mostly false positives spanning unrelated models, trainers, tokenizers, configs, and runtime/offloading failures. I would not merge any of the suggested pairs.", + "confidence": 0.97, + "canonical_issue_reason": "No single canonical issue: the items cover unrelated bugs across many models and subsystems, so there is no safe duplicate anchor.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43873 is the strongest representative issue because it is active, broadly scoped, and aligns with the most general repeated theme in the cluster (offloading/quantization/memory behavior).", + "best_issue_reason": "No single best issue for deduping this set; if forced to pick a broad representative, 43873 is the closest on offloading/quantization, but it does not represent the rest of the items.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43792", - "right": "issue:44683", + "left": "issue:43454", + "right": "issue:43720", "accept": false, - "reason": "Whisper runtime failure and compiled flex_attention on torch>=2.9 are unrelated problems in different code paths." + "reason": "Different model families and root causes: lm_head tying vs packed-weight unpacking during accelerate loading." }, { "left": "issue:43873", "right": "issue:45701", "accept": false, - "reason": "Quantization/offloading behavior and tokenization differences are distinct bug classes." + "reason": "One is an offloading/quantization runtime bug; the other is a tokenizer/version regression. Not the same code path." }, { "left": "issue:41720", "right": "issue:44977", "accept": false, - "reason": "Both involve Qwen models, but one is a device-map assert and the other is flash-attention generation behavior; different failures." + "reason": "CUDA assert under auto device mapping is unrelated to flash-attention generation behavior." }, { - "left": "issue:45632", - "right": "issue:45684", + "left": "issue:44008", + "right": "issue:45823", "accept": false, - "reason": "Cache-path collision for local models and read-only permissions during save_pretrained are unrelated." + "reason": "Both are Gemma-related, but they are different models and bugs: variable-name collision vs PLE device mismatch." }, { - "left": "issue:44008", - "right": "issue:45823", + "left": "issue:45632", + "right": "issue:45684", "accept": false, - "reason": "Gemma3n variable-name collision in forward and Gemma4 PLE device mismatch are different model bugs." + "reason": "Cache-path collision for trust_remote_code is unrelated to save_pretrained permission propagation." }, { "left": "issue:43404", "right": "issue:45357", "accept": false, - "reason": "Mistral3 lm_head tying and Qwen3.5 visual-encoder save_pretrained keys are unrelated." + "reason": "Mistral3 weight tying and Qwen3.5 visual-key saving are unrelated bugs." }, { "left": "issue:44423", "right": "issue:45406", "accept": false, - "reason": "Both hit serve with multimodal models, but the crashes stem from different processor/tokenizer failures." + "reason": "Both crash in serve, but one is a multimodal batching bug and the other is a missing processor attribute. Different causes." }, { "left": "issue:34634", "right": "issue:35707", "accept": false, - "reason": "BarkProcessor voice_preset and inputs_embeds/past_key_values generation are unrelated." + "reason": "Bark voice_preset failure and inputs_embeds/past_key_values generation regression are unrelated." }, { "left": "issue:44186", "right": "issue:45072", "accept": false, - "reason": "Tokenizer crashes on NER/padding and dtype mismatches in inference are different subsystems and failures." + "reason": "Tokenizer crash on NER padding/truncation is unrelated to dtype mismatches in inference." }, { "left": "issue:43577", "right": "issue:43708", "accept": false, - "reason": "Blip2 dtype loading and Trainer resume max_steps calculation are unrelated." + "reason": "BLIP2 dtype loading bug and Trainer checkpoint-resume max_steps bug are different subsystems." }, { "left": "issue:35707", "right": "issue:41720", "accept": false, - "reason": "Progressive generation with inputs_embeds/past_key_values is unrelated to Qwen3 auto device-map asserts." + "reason": "Different failures: progressive generation with embeddings vs device-map CUDA assert." }, { "left": "issue:43873", "right": "issue:44756", "accept": false, - "reason": "Both touch offloading/memory, but one is quantization offload behavior and the other is mmap on a specific platform; not the same bug." + "reason": "Both mention memory/offload, but one is quantization offload behavior and the other is mmap OOM on Strix Halo." }, { "left": "issue:43749", "right": "issue:44534", "accept": false, - "reason": "FSDP CPU RAM efficient loading and non-persistent buffer junk are different implementation issues." + "reason": "FSDP CPU RAM efficient loading and non-persistent buffer junk are separate loading/state bugs." }, { "left": "issue:44877", "right": "issue:44991", "accept": false, - "reason": "Strict config loading for granite_speech and tokenizer loading regression for est-roberta are unrelated." + "reason": "Strict config loading and tokenizer loading regression are different failures with different root causes." }, { "left": "issue:42617", "right": "issue:42915", "accept": false, - "reason": "3d_parallel.py execution failure and Qwen3Moe FP8 config failure are separate model/runtime issues." - }, - { - "left": "issue:43550", - "right": "issue:43720", - "accept": false, - "reason": "torch.compile SDPA failure in Bamba and packed-weight unpacking in BitNet are different code paths." + "reason": "3d_parallel.py startup failure and FineGrainedFP8Config failure are unrelated." }, { "left": "issue:43450", "right": "issue:45701", "accept": false, - "reason": "Video processor batch-shape bug and tokenization changes are unrelated." + "reason": "Video batch shape handling is unrelated to tokenizer/version changes." }, { - "left": "issue:36331", - "right": "issue:42915", + "left": "issue:43550", + "right": "issue:43720", "accept": false, - "reason": "Trainer compute_loss signature breakage and FineGrainedFP8Config model failure are unrelated." + "reason": "torch.compile SDPA failure in Bamba and BitNet packed-weight loading are unrelated." }, { - "left": "issue:43526", - "right": "issue:43881", + "left": "issue:36331", + "right": "issue:42915", "accept": false, - "reason": "BeitImageProcessorFast label reduction bug and glm-4v-9b loading failure do not share the same underlying cause." + "reason": "CustomTrainer signature regression is unrelated to Qwen3Moe FP8 loading." }, { "left": "issue:44610", "right": "issue:44898", "accept": false, - "reason": "Both concern vision inputs, but one is processor output size mismatch and the other is interpolation/loading on Perceiver; not the same bug." + "reason": "Both are image-size/preprocessing issues, but they affect different models and different code paths; not a single concrete bug." }, { "left": "issue:44186", "right": "issue:44610", "accept": false, - "reason": "LayoutLMv2 tokenizer crashes and OmDet-Turbo processor image-size mismatch are unrelated." + "reason": "Tokenizer padding crash and processor resolution mismatch are unrelated." }, { "left": "issue:44387", "right": "issue:45704", "accept": false, - "reason": "Int4 CUDA reserved-memory/OOM regression and apex RMSNorm memory leak are different memory problems." - }, - { - "left": "issue:36331", - "right": "issue:42617", - "accept": false, - "reason": "Trainer API signature change and 3d_parallel.py runtime failure are unrelated." + "reason": "Both involve memory, but int4 quantization OOM and apex RMSNorm leak are distinct issues." }, { - "left": "issue:44479", - "right": "issue:44918", + "left": "issue:43526", + "right": "issue:43881", "accept": false, - "reason": "Video-input regression in Qwen VL models and SFT trainer unpacking of Qwen3.5 embeddings are separate issues." + "reason": "Beit reduce_labels bug is unrelated to glm-4v-9b loading failure." }, { "left": "issue:43316", "right": "issue:44913", "accept": false, - "reason": "Gemma3TextConfig API discrepancy and GPTNeoX rotary_pct reload regression are unrelated config bugs." - }, - { - "left": "issue:43550", - "right": "issue:43606", - "accept": false, - "reason": "Bamba SDPA compile failure and Bark CPU offload device mismatch are different failures." + "reason": "Config API discrepancy and GPTNeoX rotary_pct reload regression are different model/config bugs." }, { "left": "issue:42915", "right": "issue:43317", "accept": false, - "reason": "FineGrainedFP8Config failure and dequantized model load with device_map=auto are unrelated." + "reason": "FP8 model failure and dequantized model offload loading failure are unrelated." }, { "left": "issue:45081", "right": "issue:45812", "accept": false, - "reason": "Mistral tokenizer regex patch crash and Granite token ID regression are different tokenizer bugs." + "reason": "Tokenizer backend patch crash and Granite token-ID regression are different tokenizer problems." + }, + { + "left": "issue:43550", + "right": "issue:43606", + "accept": false, + "reason": "Bamba torch.compile failure and Bark CPU offload device mismatch are unrelated." }, { "left": "issue:41720", "right": "issue:43322", "accept": false, - "reason": "Qwen3 device-map assert and Llava Next segmentation fault are distinct loading failures." + "reason": "Auto device-map CUDA assert and Llava Next segmentation fault are different model-loading failures." }, { "left": "issue:40990", "right": "issue:45701", "accept": false, - "reason": "High perplexity on gpt-oss-20b and version-dependent tokenization changes are not the same underlying issue." + "reason": "High perplexity on one model is not the same as a general tokenization version-change report." }, { "left": "issue:43295", "right": "issue:45701", "accept": false, - "reason": "Processor.tokenizer regression and tokenization changes across versions are related only broadly; the concrete failures differ." + "reason": "Processor/tokenizer API regression and tokenization changes are related only loosely by version, not by the same bug." + }, + { + "left": "issue:41720", + "right": "issue:45161", + "accept": false, + "reason": "Qwen3 auto device-map assert and GPT-OSS MoE tensor-parallel failure are different issues." } ] }, @@ -3983,6 +3983,7 @@ "cluster_id": "cluster-15354-390", "nodes": [ "issue:30064", + "issue:33666", "issue:34567", "issue:34634", "issue:35707", @@ -4022,7 +4023,6 @@ "issue:45042", "issue:45059", "issue:45072", - "issue:45161", "issue:45357", "issue:45406", "issue:45464", @@ -4032,22 +4032,21 @@ "issue:45812" ], "soft_pairs": [ - "issue:41720|issue:45161", "issue:43531|issue:43572", "issue:44671|issue:44743", "issue:43421|issue:45812", "issue:41720|issue:42617", "issue:36010|issue:42617", - "issue:44186|issue:44361", "issue:43540|issue:43782", + "issue:44186|issue:44361", "issue:45406|issue:45464", "issue:43421|issue:45701", "issue:30064|issue:34634", "issue:44492|issue:44509", - "issue:43606|issue:43720", "issue:44779|issue:45812", - "issue:43388|issue:45059", "issue:42915|issue:43322", + "issue:43606|issue:43720", + "issue:43388|issue:45059", "issue:43550|issue:43653", "issue:44514|issue:44545", "issue:43531|issue:45759", @@ -4057,17 +4056,18 @@ "issue:44368|issue:45357", "issue:43873|issue:45704", "issue:44451|issue:44991", - "issue:44898|issue:45072", "issue:41720|issue:43746", + "issue:44898|issue:45072", "issue:44062|issue:44451", - "issue:44987|issue:45042" + "issue:44987|issue:45042", + "issue:33666|issue:35707" ], - "prepared_review_unit_hash": "f25f3fbab6f0df7ec27d7b15d003fe45fb00bfe812ff5d2c15528e6730611c9c", + "prepared_review_unit_hash": "dcd9c990c8f5714d17b731e95e748d01724b3be4f6d414356a18404810264113", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, @@ -4075,201 +4075,201 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 29, - "serialized_chars": 36356, - "estimated_input_tokens": 9089, - "estimated_eval_tokens": 18434 + "serialized_chars": 36342, + "estimated_input_tokens": 9086, + "estimated_eval_tokens": 18428 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly heterogeneous, with one clear duplicate pair: the two Qwen2_5_VLProcessor.apply_chat_template crashes on batched input with padding=False. Most other soft matches are only subsystem-level similarity, not the same bug.", - "confidence": 0.91, - "canonical_issue_reason": "issue:44514 is the best issue canonical for the only true duplicate pair: it predates the near-identical follow-up, has the fuller report, and centers the same Qwen2_5_VLProcessor batched-input/padding=False crash.", + "summary": "Mostly unrelated issue reports; only one soft pair is a clear duplicate (`Qwen2_5_VLProcessor.apply_chat_template` crashing on batched input with `padding=False`). The remaining pairs share broad subsystems or model families, but not the same concrete bug or change.", + "confidence": 0.97, + "canonical_issue_reason": "Issue 44514 is the best canonical issue because it is the earlier report of the exact same `Qwen2_5_VLProcessor.apply_chat_template` batched-`padding=False` crash as 44545.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44514 is the strongest cluster representative because it is the clearest duplicate target among the issues here; the rest of the items are unrelated regression reports rather than one shared defect.", + "best_issue_reason": "Issue 44514 is the strongest representative in this set since it anchors the only clear duplicate pair and has the clearest, most specific bug description.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:41720", - "right": "issue:45161", - "accept": false, - "reason": "Both are model-parallel/distributed failures, but they involve different models, different setups, and different failure modes." - }, { "left": "issue:43531", "right": "issue:43572", "accept": false, - "reason": "Unrelated bugs: Qwen3-MoE sliding_window behavior vs a StableLmConfig pad_token_idx regression." + "reason": "Different bugs in different models/configs: Qwen3-MoE sliding-window behavior vs StableLm missing `pad_token_idx` after v5 update." }, { "left": "issue:44671", "right": "issue:44743", "accept": false, - "reason": "Different code paths and symptoms: CamemBERT masked-LM predictions vs Qwen3.5 recurrent cache state resetting." + "reason": "Both are model-specific regression reports, but one is CamemBERT MLM output and the other is Qwen modular cache state handling; not the same code path." }, { "left": "issue:43421", "right": "issue:45812", "accept": false, - "reason": "Both tokenizer-related, but one is runtime post-processor updates and the other is a Granite token-id regression; not the same concrete bug." + "reason": "Both concern tokenizer behavior, but one is runtime post-processor updates and the other is wrong token IDs for Granite models; too different to merge." }, { "left": "issue:41720", "right": "issue:42617", "accept": false, - "reason": "Different domains: GPU device-mapping failure vs inability to run a 3D parallel script." + "reason": "Unrelated failures: Qwen3 auto device mapping CUDA assert vs inability to run `3d_parallel.py`." }, { "left": "issue:36010", "right": "issue:42617", "accept": false, - "reason": "GenerationMixin import failure is unrelated to the 3d_parallel.py runtime issue." + "reason": "Importing `GenerationMixin` and running `3d_parallel.py` are unrelated problems." }, { - "left": "issue:44186", - "right": "issue:44361", + "left": "issue:43540", + "right": "issue:43782", "accept": false, - "reason": "Both touch tokenizers, but they are different tokenizer implementations with different task failures." + "reason": "Different Qwen multimodal loading/processing failures with different triggers and code paths." }, { - "left": "issue:43540", - "right": "issue:43782", + "left": "issue:44186", + "right": "issue:44361", "accept": false, - "reason": "Multimodal video processing failure vs from_pretrained weight_only loading error; not the same bug." + "reason": "Both are tokenizer/task issues, but they affect different tokenizers and different failure modes." }, { "left": "issue:45406", "right": "issue:45464", "accept": false, - "reason": "Processor attribute crash in serve vs streaming inference API failure are different code paths." + "reason": "Serve crashes on missing `_tokenizer` versus streaming chat/completions failure on Qwen3.5-0.8B; not the same bug." }, { "left": "issue:43421", "right": "issue:45701", "accept": false, - "reason": "One is a runtime special-token/post-processor sync bug; the other is a broader tokenization regression across versions." + "reason": "`TokenizersBackend` post-processor refresh bug is not the same as a general version-dependent tokenization change report." }, { "left": "issue:30064", "right": "issue:34634", "accept": false, - "reason": "Image segmentation-map processing and BarkProcessor voice_preset are unrelated." + "reason": "Image processor void segmentation maps and Bark voice_preset are unrelated." }, { "left": "issue:44492", "right": "issue:44509", "accept": false, - "reason": "A typo in cache strategies is unrelated to stale docs mentioning removed pipeline tasks." + "reason": "A cache-strategy typo and docs referencing removed pipeline tasks are separate documentation issues." }, { - "left": "issue:43606", - "right": "issue:43720", + "left": "issue:44779", + "right": "issue:45812", "accept": false, - "reason": "Both involve loading/offload behavior, but they affect different models and different failure mechanisms." + "reason": "Both involve tokenizer regressions, but on different model families and different symptoms." }, { - "left": "issue:44779", - "right": "issue:45812", + "left": "issue:42915", + "right": "issue:43322", "accept": false, - "reason": "Both are tokenizer regressions, but they concern different models and different failure symptoms." + "reason": "Qwen3Moe FP8 config failure and Llava Next segmentation fault are unrelated." }, { - "left": "issue:43388", - "right": "issue:45059", + "left": "issue:43606", + "right": "issue:43720", "accept": false, - "reason": "Gather-for-metrics label truncation is unrelated to SAM3 text/bbox weird behavior." + "reason": "CPU offload device mismatch for Bark-small is unrelated to BitNet packed-weight loading." }, { - "left": "issue:42915", - "right": "issue:43322", + "left": "issue:43388", + "right": "issue:45059", "accept": false, - "reason": "Different problems: FineGrainedFP8Config failure vs segmentation fault on Llava Next loading." + "reason": "gather-for-metrics label truncation and SAM3 text/bbox behavior are different bugs." }, { "left": "issue:43550", "right": "issue:43653", "accept": false, - "reason": "torch.compile/SDPA failure and BigBirdTokenizer special-token registration are unrelated." + "reason": "torch.compile SDPA failure in Bamba and BigBird tokenizer special-token decode issue are unrelated." }, { "left": "issue:44514", "right": "issue:44545", "accept": true, - "reason": "Same Qwen2_5_VLProcessor.apply_chat_template batched-input crash with padding=False; titles and failure description match closely." + "reason": "Same bug and same title: `Qwen2_5_VLProcessor.apply_chat_template` crashes on batched input when `padding=False`." }, { "left": "issue:43531", "right": "issue:45759", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior is unrelated to AutoModelForCausalLM.from_config not unwrapping text_config." + "reason": "Both mention Qwen3-related configs, but one is a sliding-window MoE issue and the other is `from_config` unwrapping of `text_config`." }, { "left": "issue:43606", "right": "issue:43653", "accept": false, - "reason": "CPU offload device mismatch and BigBirdTokenizer decode behavior are different bugs." + "reason": "CPU offload device mismatch for Bark-small is not the same as BigBird tokenizer mask-token decoding." }, { "left": "issue:43421", "right": "issue:43927", "accept": false, - "reason": "Runtime special-token post-processing and save/load losing custom token IDs are distinct tokenizer/config bugs." + "reason": "Both are token-related, but one is runtime special-token post-processing and the other is config token IDs lost after save/load." }, { "left": "issue:34567", "right": "issue:35707", "accept": false, - "reason": "TrainerState token counting and progressive generation with inputs_embeds/past_key_values are unrelated." + "reason": "Trainer token-count tracking and progressive generation with `inputs_embeds`/`past_key_values` are unrelated." }, { "left": "issue:44368", "right": "issue:45357", "accept": false, - "reason": "A tie_word_embeddings warning and incorrect visual encoder key saving are different regression classes." + "reason": "A LoRA warning about `tie_word_embeddings` and incorrect visual encoder keys in `save_pretrained` are different issues." }, { "left": "issue:43873", "right": "issue:45704", "accept": false, - "reason": "Quantization/offloading behavior does not match a T5 RMSNorm memory leak." + "reason": "Quantization/offloading behavior and a T5 apex RMSNorm memory leak are unrelated." }, { "left": "issue:44451", "right": "issue:44991", "accept": false, - "reason": "Both are loading failures, but for different models and likely different root causes." + "reason": "Different model-loading regressions for different models; not the same underlying tokenizer/load bug." }, { - "left": "issue:44898", - "right": "issue:45072", + "left": "issue:41720", + "right": "issue:43746", "accept": false, - "reason": "Perceiver image-size handling and dtype mismatch in inference are unrelated." + "reason": "Qwen3 auto device mapping CUDA assert and GraniteSpeech PEFT local checkpoint loading are different failure modes." }, { - "left": "issue:41720", - "right": "issue:43746", + "left": "issue:44898", + "right": "issue:45072", "accept": false, - "reason": "Different model families and different failure modes: auto device mapping vs PEFT local checkpoint loading." + "reason": "Perceiver resolution handling and dtype mismatches in bfloat16 inference are unrelated." }, { "left": "issue:44062", "right": "issue:44451", "accept": false, - "reason": "AddedToken special-argument conflict is too specific to equate with a broad ScandiBERT load failure." + "reason": "`AddedToken` keyword collision and ScandiBERT loading failure are separate tokenizer/model issues." }, { "left": "issue:44987", "right": "issue:45042", "accept": false, - "reason": "A model-loading regression and a PIL image-processor dependency regression are not the same bug." + "reason": "A model load regression and a PIL-backend torchvision dependency regression are unrelated." + }, + { + "left": "issue:33666", + "right": "issue:35707", + "accept": false, + "reason": "Qwen2-VL multi-GPU training and progressive generation with `inputs_embeds`/`past_key_values` are not the same problem." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative: the only accepted soft pair is the near-identical Qwen2_5_VLProcessor batched-input/padding=False crash, and the rest of the verdicts correctly avoid merging merely similar subsystem-level reports. Canonical issue choice and rationale are also supported by the titles, dates, and body sizes." + "feedback": "The summary is well grounded in the packet. The duplicate call on issue:44514/44545 is supported by near-identical titles and dates, and the remaining soft-edge rejections stay conservative by citing distinct bug descriptions rather than broad subsystem overlap. No overstatement noticed." }, "evaluator_used": true, "retried": false, @@ -4291,9 +4291,7 @@ "cluster_id": "cluster-15354-390", "nodes": [ "issue:30064", - "issue:33666", "issue:34634", - "issue:35707", "issue:36010", "issue:39692", "issue:41720", @@ -4305,11 +4303,14 @@ "issue:43525", "issue:43531", "issue:43540", + "issue:43575", "issue:43596", "issue:43618", "issue:43653", "issue:43697", + "issue:43716", "issue:43720", + "issue:43746", "issue:43756", "issue:43782", "issue:43819", @@ -4336,14 +4337,12 @@ "issue:45479", "issue:45588", "issue:45704", - "issue:45759", - "issue:45834" + "issue:45759" ], "soft_pairs": [ - "issue:45588|issue:45759", - "issue:43421|issue:43653", - "issue:33666|issue:35707", "issue:43531|issue:44589", + "issue:43421|issue:43653", + "issue:45588|issue:45759", "issue:42886|issue:44843", "issue:43381|issue:43844", "issue:39692|issue:44610", @@ -4353,238 +4352,246 @@ "issue:44625|issue:45479", "issue:43782|issue:45381", "issue:45081|issue:45356", - "issue:43994|issue:44671", "issue:34634|issue:41720", + "issue:43994|issue:44671", "issue:43381|issue:45704", "issue:39692|issue:43873", "issue:42915|issue:45759", "issue:43596|issue:44220", - "issue:45704|issue:45834", "issue:43540|issue:44008", "issue:43618|issue:43697", "issue:45183|issue:45479", - "issue:43720|issue:43819", "issue:44220|issue:44661", "issue:44077|issue:44625", - "issue:43335|issue:43756", + "issue:43575|issue:45704", "issue:30064|issue:36010", + "issue:43720|issue:43819", + "issue:43335|issue:43756", + "issue:44756|issue:45759", "issue:43653|issue:43720", - "issue:44756|issue:45759" + "issue:43716|issue:44008", + "issue:42915|issue:43746" ], - "prepared_review_unit_hash": "b5ea15c7a87b1e9fee8c58f179fbe1709f82cd0392b4ff002bf3a0558000fafc", + "prepared_review_unit_hash": "c6f6118d23c05bb697c0a6a1e6cf98ab0898e18c40d9a3d9a8b64a1da1d27a44", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 30, - "serialized_chars": 36798, - "estimated_input_tokens": 9200, - "estimated_eval_tokens": 18656 + "soft_pair_count": 31, + "serialized_chars": 37192, + "estimated_input_tokens": 9298, + "estimated_eval_tokens": 18852 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is mostly heterogeneous and does not form one duplicate cluster. The only plausible duplicate subgroup is the HF_HUB_OFFLINE tokenizer-loading problem; everything else looks unrelated by model, subsystem, or failure mode.", - "confidence": 0.78, - "canonical_issue_reason": "No single issue cleanly represents the whole set. If forced to pick the closest anchor for the only near-duplicate subgroup, issue 44843 is best because it states the concrete root cause behind the offline tokenizer failure.", + "summary": "This cluster is mostly heterogeneous issue reports. Only one soft edge looks like a true duplicate: two reports of the same Mistral-regex/offline tokenizer loading regression. The rest share broad themes but not the same concrete bug.", + "confidence": 0.71, + "canonical_issue_reason": "issue:44843 is the clearest representative of the only tightly related subthread in the cluster: it names the _patch_mistral_regex offline regression directly and has inbound reference signal, while most other issues are unrelated one-off model or trainer bugs.", "canonical_pr_reason": null, - "best_issue_reason": "issue 44843 is the most actionable representative of the only coherent subgroup: it names the specific code path (\u0000_patch_mistral_regex\u0000 calling \u0000model_info()\u0000 unconditionally) and the offline-mode breakage.", + "best_issue_reason": "issue:44843 is the best global issue candidate because it is concrete, well-scoped, and central to the only real duplicate pair in this set.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:45588", - "right": "issue:45759", + "left": "issue:43531", + "right": "issue:44589", "accept": false, - "reason": "Different bugs: flash_attention sinkless-model crash vs Qwen 3.5 config unwrapping. No shared code path." + "reason": "Different models and failures: sliding_window config bug vs float8 storage/type error." }, { "left": "issue:43421", "right": "issue:43653", "accept": false, - "reason": "Both involve tokenizer special-token handling, but one is about runtime post-processor updates and the other about missing special-token registration; not the same bug." + "reason": "Both involve tokenizers/special tokens, but one is a runtime post-processor update request and the other is a mask-token decode bug; not the same defect." }, { - "left": "issue:33666", - "right": "issue:35707", - "accept": false, - "reason": "Unrelated: Qwen2-VL multi-GPU training vs progressive generation with inputs_embeds/past_key_values." - }, - { - "left": "issue:43531", - "right": "issue:44589", + "left": "issue:45588", + "right": "issue:45759", "accept": false, - "reason": "Different areas and failures: Qwen3-MoE sliding_window behavior vs Float8 storage import/type error." + "reason": "Different areas: flash-attention sinkless crash vs composite Qwen config unwrapping." }, { "left": "issue:42886", "right": "issue:44843", "accept": true, - "reason": "Same underlying offline-tokenizer failure: both report tokenizer loading breaking in HF_HUB_OFFLINE mode, and 44843 gives the likely concrete cause in _patch_mistral_regex/model_info()." + "reason": "Same underlying tokenizer-loading regression in _patch_mistral_regex; one report emphasizes HF_HUB_OFFLINE/cache failure, the other the direct offline breakage from unconditional model_info()." }, { "left": "issue:43381", "right": "issue:43844", "accept": false, - "reason": "Both mention training/runtime behavior, but eval-mode checkpointing and ZeRO-3 gradient growth are different problems." + "reason": "Both mention gradients/checkpointing, but they describe different training behaviors and code paths." }, { "left": "issue:39692", "right": "issue:44610", "accept": false, - "reason": "Different model families and symptoms: SigLIP2 doc example errors vs OmDet-Turbo processor/model input-size mismatch." + "reason": "Both are vision processor/model mismatches, but for different models and different concrete size/quantization failures." }, { "left": "issue:43421", "right": "issue:44186", "accept": false, - "reason": "Tokenizer backend special-token update feature request vs LayoutLMv2Tokenizer crash on NER/batched padding; not the same issue." + "reason": "Tokenizer-related, but one is special-token post-processing at runtime and the other is LayoutLMv2 NER/padding crashes." }, { "left": "issue:44918", "right": "issue:44936", "accept": false, - "reason": "Qwen3.5 input-embedding unpacking in TRL SFT trainer vs trainer.evaluate() after train(); too different." + "reason": "Trainer-related, but one is embedding unpacking with TRL SFT and the other is evaluate-after-train failure." }, { "left": "issue:43525", "right": "issue:43531", "accept": false, - "reason": "Llama4Config missing pad_token_id vs Qwen3-MoE sliding_window issue; unrelated." + "reason": "Different Qwen/Llama config problems; not the same underlying bug." }, { "left": "issue:44625", "right": "issue:45479", "accept": false, - "reason": "Qwen3.5 num_labels propagation vs single-label-classification zero-loss regression across models; different config paths." + "reason": "Both touch classification config, but one is Qwen3.5 text-config propagation and the other is loss behavior for num_labels=1." }, { "left": "issue:43782", "right": "issue:45381", "accept": false, - "reason": "Qwen3VL weight_only loading error vs qwen2.5-vl video vision_position_ids bug; separate multimodal bugs." + "reason": "Both are Qwen VL issues, but one is from_pretrained weight-only loading and the other is incorrect video vision_position_ids." }, { "left": "issue:45081", "right": "issue:45356", "accept": false, - "reason": "Both touch fix_mistral_regex, but one is a tokenizer-load crash and the other is a Kimi-K2.5 regression with codec handling/warning issues; not clearly the same concrete bug." + "reason": "Related to fix_mistral_regex, but the titles point to different failures: an AttributeError crash versus codec-handling/regression warning issues." }, { - "left": "issue:43994", - "right": "issue:44671", + "left": "issue:34634", + "right": "issue:41720", "accept": false, - "reason": "SigLIP2 nonsensical outputs and CamemBERT MLM prediction regression are different model-specific inference issues." + "reason": "Unrelated model families and errors." }, { - "left": "issue:34634", - "right": "issue:41720", + "left": "issue:43994", + "right": "issue:44671", "accept": false, - "reason": "BarkProcessor voice_preset vs Qwen3 auto device mapping cudaErrorAssert; unrelated." + "reason": "Both are bad outputs, but they are different model-specific regressions with different likely causes." }, { "left": "issue:43381", "right": "issue:45704", "accept": false, - "reason": "Gradient checkpointing in eval mode is unrelated to T5's apex.FusedRMSNorm memory leak." + "reason": "Different bugs: eval-mode checkpointing limitation vs apex RMSNorm memory leak." }, { "left": "issue:39692", "right": "issue:43873", "accept": false, - "reason": "Doc-example/model mismatch and quantization failure vs offloading with quantization; too broad and not the same bug." + "reason": "Different problems: docs/example mismatch vs quantization offloading behavior." }, { "left": "issue:42915", "right": "issue:45759", "accept": false, - "reason": "Qwen3Moe FineGrainedFP8Config failure vs Qwen3.5/3.6 multimodal config unwrapping; different code paths." + "reason": "Both involve Qwen models, but the concrete failures are unrelated." }, { "left": "issue:43596", "right": "issue:44220", "accept": false, - "reason": "Deepspeed ZeRO-3/BertModel index error vs audio fbank feature extraction issue; unrelated." - }, - { - "left": "issue:45704", - "right": "issue:45834", - "accept": false, - "reason": "T5 RMSNorm memory leak vs Kosmos2.5 long-OCR index error; unrelated." + "reason": "Different subsystems: DeepSpeed/BertModel zero3 init vs audio fbank feature extraction." }, { "left": "issue:43540", "right": "issue:44008", "accept": false, - "reason": "Qwen3OmniMoe video-input ValueError vs Gemma 3n variable-name collision in forward(); different models and failures." + "reason": "Different modalities and code paths: Qwen3OmniMoe video processing vs Gemma3n variable collision." }, { "left": "issue:43618", "right": "issue:43697", "accept": false, - "reason": "CLIPOutput attentions regression vs RTDetrV2 differing outputs in v5; not the same bug." + "reason": "Different regressions in different models; no shared concrete fix is evident." }, { "left": "issue:45183", "right": "issue:45479", "accept": false, - "reason": "General XOR validation/error-message bug across models vs sequence-classification zero-loss regression; different behavior and scope." - }, - { - "left": "issue:43720", - "right": "issue:43819", - "accept": false, - "reason": "BitNet packed-weight loading problem vs DAC.from_latents missing STE; unrelated." + "reason": "Different class of bug: input validation messaging vs classification loss degeneracy." }, { "left": "issue:44220", "right": "issue:44661", "accept": false, - "reason": "Audio feature extraction bug vs add-new-model-like failing in TOKENIZER_MAPPING_NAMES; unrelated." + "reason": "Audio feature extraction vs tokenizer/model registration logic; unrelated." }, { "left": "issue:44077", "right": "issue:44625", "accept": false, - "reason": "patchtsmixer post_init policy issue vs Qwen3.5 num_labels propagation; unrelated." + "reason": "Different model/config issues with no shared failure mode." }, { - "left": "issue:43335", - "right": "issue:43756", + "left": "issue:43575", + "right": "issue:45704", "accept": false, - "reason": "SwitchTransformers sparse-layer config bug vs Smollm3 RoPE-layer mismatch; different model/config issues." + "reason": "TP OOM versus RMSNorm memory leak; unrelated." }, { "left": "issue:30064", "right": "issue:36010", "accept": false, - "reason": "Image processor void segmentation maps vs GenerationMixin import error; unrelated." + "reason": "Different domains: image processor segmentation handling vs GenerationMixin import error." }, { - "left": "issue:43653", - "right": "issue:43720", + "left": "issue:43720", + "right": "issue:43819", + "accept": false, + "reason": "Different low-level numerical/loading bugs in unrelated models." + }, + { + "left": "issue:43335", + "right": "issue:43756", "accept": false, - "reason": "BigBirdTokenizer special-token registration bug vs BitNet accelerate loading issue; unrelated." + "reason": "Both are model-architecture quirks, but they concern different components and symptoms." }, { "left": "issue:44756", "right": "issue:45759", "accept": false, - "reason": "mmap/OOM on Strix Halo vs Qwen config unwrapping; unrelated." - } + "reason": "Memory/offloading concern versus composite config unwrapping; not the same issue." + }, + { + "left": "issue:43653", + "right": "issue:43720", + "accept": false, + "reason": "Tokenizer special-token decode bug versus BitNet packed-weight loading bug." + }, + { + "left": "issue:43716", + "right": "issue:44008", + "accept": false, + "reason": "Different multimodal model bugs with no shared code path." + }, + { + "left": "issue:42915", + "right": "issue:43746", + "accept": false, + "reason": "Different Qwen/Moe FP8 loading versus GraniteSpeech PEFT local checkpoint loading." + } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative. The one accepted soft-edge pair (42886/44843) is clearly aligned on the same HF_HUB_OFFLINE tokenizer-loading failure, while the other rejections do not overreach based on the titles alone. No mergeability concerns apply here." + "feedback": "The summary is grounded in the packet, and the accepted soft edge (42886 \u2194 44843) is well-supported by the shared _patch_mistral_regex / HF_HUB_OFFLINE failure mode. The remaining soft-edge rejections are conservative and match the issue titles; no evidence is overstated." }, "evaluator_used": true, "retried": false, @@ -4609,7 +4616,7 @@ "issue:34634", "issue:36010", "issue:36331", - "issue:42915", + "issue:39692", "issue:43295", "issue:43322", "issue:43421", @@ -4621,7 +4628,6 @@ "issue:43606", "issue:43643", "issue:43653", - "issue:43716", "issue:43746", "issue:43782", "issue:43818", @@ -4630,11 +4636,11 @@ "issue:43827", "issue:43873", "issue:43994", - "issue:44008", "issue:44062", "issue:44186", "issue:44442", "issue:44448", + "issue:44479", "issue:44485", "issue:44488", "issue:44509", @@ -4651,242 +4657,238 @@ "issue:45081", "issue:45084", "issue:45381", + "issue:45584", "issue:45685", "issue:45834" ], "soft_pairs": [ - "issue:43716|issue:44008", - "issue:42915|issue:43746", + "issue:43295|issue:45834", "issue:43746|issue:45381", + "issue:43746|issue:43873", "issue:43550|issue:45072", "issue:43550|issue:43819", - "issue:43746|issue:43873", "issue:44186|issue:44898", "issue:44843|issue:45081", "issue:43531|issue:43643", "issue:43643|issue:44877", - "issue:44062|issue:44488", "issue:43421|issue:44811", + "issue:44062|issue:44488", "issue:43577|issue:43818", - "issue:43653|issue:43819", "issue:43540|issue:45381", + "issue:43653|issue:43819", "issue:44448|issue:44671", "issue:43782|issue:44977", + "issue:45584|issue:45834", "issue:44561|issue:45020", "issue:43825|issue:43994", "issue:43322|issue:45685", "issue:44821|issue:45084", - "issue:44485|issue:44509", + "issue:39692|issue:45834", "issue:30064|issue:36331", + "issue:44479|issue:45834", "issue:43825|issue:43827", - "issue:43295|issue:45834", - "issue:43606|issue:45072", + "issue:44485|issue:44509", "issue:44186|issue:44442", + "issue:43606|issue:45072", "issue:43577|issue:43582", "issue:34634|issue:36010" ], - "prepared_review_unit_hash": "3e199cd7ea8fe8cc60085162ae8235ebd63fd7689fb4c62b07a868cb355d4b50", + "prepared_review_unit_hash": "dbea9a34ea5c20b8a6c482a53340fe16b8d2968392b72171f613d0ee605413f6", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "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": 36805, + "estimated_input_tokens": 9202, + "estimated_eval_tokens": 18660 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is mostly a collection of unrelated bug reports across different models and subsystems. The soft-similarity pairs are topical overlaps (often same family or same helper) but not the same concrete bug/change, so none should be merged as duplicates.", - "confidence": 0.9, - "canonical_issue_reason": "issue:45020 is the broadest umbrella-style report in the set and best represents the recurring remote_code regression theme, even though the overall cluster is not made up of true duplicates.", + "summary": "This cluster is mostly a loose collection of unrelated Transformers bug reports, many about v5 regressions, model loading, tokenizers, or modality-specific processing. None of the soft pairs look like the same underlying bug/change, so I would not merge any of them.", + "confidence": 0.93, + "canonical_issue_reason": "issue:45020 is the broadest umbrella item: it captures the recurring theme of recent-version regressions breaking remote-code/custom-model usage. That said, the cluster is still too heterogeneous for a strong single canonical issue.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45020 is the most representative issue to anchor the cluster because it is the most general and inclusive of the repeated 'recent versions break remote_code models' pattern.", + "best_issue_reason": "issue:45020 is the best representative issue by scope and wording, even though it does not truly subsume all items in the cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43716", - "right": "issue:44008", + "left": "issue:43295", + "right": "issue:45834", "accept": false, - "reason": "Different bugs in different models: dtype mismatch in Mistral-3 vs a Gemma3n variable-name collision." + "reason": "Different models and failures: processor/tokenizer regression vs Kosmos2.5 long-OCR index error." }, { - "left": "issue:42915", - "right": "issue:43746", + "left": "issue:43746", + "right": "issue:45381", "accept": false, - "reason": "Unrelated failures: Qwen3Moe FP8 config issue vs GraniteSpeech PEFT/local-checkpoint loading." + "reason": "Local checkpoint/PEFT load failure is unrelated to Qwen video position-id handling." }, { "left": "issue:43746", - "right": "issue:45381", + "right": "issue:43873", "accept": false, - "reason": "Different code paths and symptoms: checkpoint loading for GraniteSpeech vs qwen2.5-vl video position IDs." + "reason": "Loading local PEFT adapters is a different code path from quantization/offloading behavior." }, { "left": "issue:43550", "right": "issue:45072", "accept": false, - "reason": "Separate model-specific problems: Bamba torch.compile/SDPA vs dtype mismatches in other models." + "reason": "Torch.compile + SDPA bug in Bamba is unrelated to dtype mismatch inference issues in SwitchTransformers/TimmWrapperModel." }, { "left": "issue:43550", "right": "issue:43819", "accept": false, - "reason": "Different failures: Bamba compile/SDPA behavior vs DAC latent reconstruction mismatch." - }, - { - "left": "issue:43746", - "right": "issue:43873", - "accept": false, - "reason": "PEFT local-checkpoint loading and quantized offloading are only broadly related, not the same bug." + "reason": "Different subsystems and symptoms: SDPA/compile vs DAC latent reconstruction mismatch." }, { "left": "issue:44186", "right": "issue:44898", "accept": false, - "reason": "Tokenizer padding/NER crash vs Perceiver image-resolution handling; different components and root causes." + "reason": "LayoutLMv2 tokenizer crash is unrelated to Perceiver image classification resizing/interpolation failure." }, { "left": "issue:44843", "right": "issue:45081", "accept": false, - "reason": "Both involve _patch_mistral_regex, but one is an offline model_info call and the other is an attribute-access crash; not clearly the same fixable bug." + "reason": "Both involve _patch_mistral_regex, but one is HF offline/model_info behavior and the other is a backend_tokenizer attribute crash; not the same bug." }, { "left": "issue:43531", "right": "issue:43643", "accept": false, - "reason": "Qwen3-MoE sliding-window bug vs trust_remote_code config-field loss; unrelated." + "reason": "Sliding-window handling for Qwen3-MoE is unrelated to trust_remote_code config field loss." }, { "left": "issue:43643", "right": "issue:44877", "accept": false, - "reason": "Both are config-related, but one is missing fields from trust_remote_code while the other is strict config rejection for granite_speech." + "reason": "Both concern config loading, but one is missing fields from trust_remote_code and the other is strict config rejection for granite_speech." }, { - "left": "issue:44062", - "right": "issue:44488", + "left": "issue:43421", + "right": "issue:44811", "accept": false, - "reason": "Tokenizer construction error vs failing to load a specific tokenizer model; not the same issue." + "reason": "Runtime special-token/post-processor update bug is different from Whisper batch_decode ignoring skip_special_tokens." }, { - "left": "issue:43421", - "right": "issue:44811", + "left": "issue:44062", + "right": "issue:44488", "accept": false, - "reason": "Special-token post-processor update behavior vs Whisper batch_decode skip_special_tokens handling; different APIs." + "reason": "AddedToken constructor error is not the same as a model load failure for cjvt/sleng-bert." }, { "left": "issue:43577", "right": "issue:43818", "accept": false, - "reason": "BLIP2 dtype loading issue vs Video-LLaVA missing temporal attention/weight sharing; unrelated." + "reason": "Blip2 dtype propagation bug is unrelated to Video-LLaVA missing temporal attention/shared weights." }, { - "left": "issue:43653", - "right": "issue:43819", + "left": "issue:43540", + "right": "issue:45381", "accept": false, - "reason": "BigBird special-token decode bug vs DAC latent/forward mismatch; different subsystems." + "reason": "Both are video-related, but they affect different models and different processing failures." }, { - "left": "issue:43540", - "right": "issue:45381", + "left": "issue:43653", + "right": "issue:43819", "accept": false, - "reason": "Different video-input regressions in different Qwen variants; not the same concrete bug." + "reason": "BigBirdTokenizer special-token registration issue is unrelated to DAC forward/from_latents mismatch." }, { "left": "issue:44448", "right": "issue:44671", "accept": false, - "reason": "Two separate model regression reports with different outputs and code paths." + "reason": "Different model regressions: Pegasus output drift vs CamemBERT masked-LM prediction errors." }, { "left": "issue:43782", "right": "issue:44977", "accept": false, - "reason": "Different Qwen issues: weight_only loading error vs flash-attention generation behavior." + "reason": "Weight-only load error in Qwen3VL is different from flash-attention generation problems in Qwen3.5." + }, + { + "left": "issue:45584", + "right": "issue:45834", + "accept": false, + "reason": "Whisper empty-transcription generation failure is unrelated to Kosmos2.5 OCR long-input index errors." }, { "left": "issue:44561", "right": "issue:45020", "accept": false, - "reason": "Same broad remote_code theme, but one is specifically is_torch_fx_available removal and the other is a broader recent-version regression report." + "reason": "44561 is a specific is_torch_fx_available regression; 45020 is a broad umbrella issue, not the same concrete bug." }, { "left": "issue:43825", "right": "issue:43994", "accept": false, - "reason": "Pipeline-v5 error-message/deprecation issue vs SigLIP2 output regression; unrelated." + "reason": "Pipeline error-message wording is unrelated to SigLIP2 nonsensical output from AutoModel/pipeline." }, { "left": "issue:43322", "right": "issue:45685", "accept": false, - "reason": "Segmentation fault in Llava Next loading vs MPS histogram-int error in MoE; different bugs." + "reason": "Llava Next segfault and MPS histogram/int error are unrelated failures." }, { "left": "issue:44821", "right": "issue:45084", "accept": false, - "reason": "AutoImageProcessor URL loading vs template-node compilation error; no shared code path." + "reason": "AutoImageProcessor URL loading is a different problem from the template-node compilation error." }, { - "left": "issue:44485", - "right": "issue:44509", + "left": "issue:39692", + "right": "issue:45834", "accept": false, - "reason": "GLM-5 RoPE discussion vs docs referencing removed pipeline tasks; unrelated." + "reason": "SigLIP2 docs/example issues are unrelated to Kosmos2.5 OCR indexing." }, { "left": "issue:30064", "right": "issue:36331", "accept": false, - "reason": "ImageProcessor void segmentation-map handling vs CustomTrainer.compute_loss signature breakage; different areas." + "reason": "Image processor segmentation-map failure is unrelated to CustomTrainer.compute_loss signature mismatch." }, { - "left": "issue:43825", - "right": "issue:43827", + "left": "issue:44479", + "right": "issue:45834", "accept": false, - "reason": "Both concern removed v5 pipeline tasks, but one is an error message and the other is documentation; not the same bug/change." + "reason": "Qwen video-input regression is unrelated to Kosmos2.5 long OCR input handling." }, { - "left": "issue:43295", - "right": "issue:45834", + "left": "issue:43825", + "right": "issue:43827", "accept": false, - "reason": "Processor/tokenizer regression vs Kosmos2.5 long-OCR index error; different failures." + "reason": "One is an error-message bug; the other is stale docs. Related topic, but not the same change or code-path." }, { - "left": "issue:43606", - "right": "issue:45072", + "left": "issue:44485", + "right": "issue:44509", "accept": false, - "reason": "CPU offload device mismatch with quantization vs general dtype mismatches; not the same bug." + "reason": "GLM-5 RoPE implementation discussion is unrelated to documentation references to removed pipeline tasks." }, { "left": "issue:44186", "right": "issue:44442", "accept": false, - "reason": "LayoutLMv2 tokenizer crash and AutoTokenizer failing to load FastSpeech2ConformerTokenizer are different problems." - }, - { - "left": "issue:43577", - "right": "issue:43582", - "accept": false, - "reason": "BLIP2 dtype issue vs Apple Silicon caching_allocator_warmup TypeError; unrelated." + "reason": "LayoutLMv2 tokenizer crash is unrelated to AutoTokenizer loading FastSpeech2ConformerTokenizer." }, { - "left": "issue:34634", - "right": "issue:36010", + "left": "issue:43606", + "right": "issue:45072", "accept": false, - "reason": "BarkProcessor voice_preset behavior vs GenerationMixin import error; different code paths and symptoms." + "reason": "CPU offload device mismatch in Bark-small is unrelated to bfloat16 dtype mismatches in other models." } ] }, @@ -4910,6 +4912,7 @@ "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-390", "nodes": [ + "issue:36010", "issue:38175", "issue:39692", "issue:42175", @@ -4921,6 +4924,7 @@ "issue:43582", "issue:43638", "issue:43644", + "issue:43645", "issue:43650", "issue:43653", "issue:43697", @@ -4953,238 +4957,229 @@ "issue:45406", "issue:45459", "issue:45538", - "issue:45584", "issue:45600", "issue:45701", - "issue:45803", - "issue:45834" + "issue:45803" ], "soft_pairs": [ "issue:43452|issue:44991", "issue:44805|issue:44936", "issue:42175|issue:45081", "issue:44610|issue:45072", - "issue:43720|issue:45072", "issue:45081|issue:45406", + "issue:43720|issue:45072", "issue:44060|issue:44368", - "issue:43650|issue:43906", "issue:44671|issue:45701", + "issue:43650|issue:43906", "issue:43404|issue:43782", - "issue:45584|issue:45834", "issue:43582|issue:44857", "issue:45459|issue:45803", "issue:43262|issue:43819", "issue:43526|issue:43697", "issue:45084|issue:45538", "issue:43329|issue:45600", - "issue:39692|issue:45834", "issue:43644|issue:43749", - "issue:43653|issue:44912", "issue:43742|issue:45020", + "issue:43653|issue:44912", "issue:43638|issue:44936", "issue:43746|issue:44811", "issue:44589|issue:45042", "issue:43854|issue:44977", "issue:38175|issue:44610", "issue:39692|issue:44912", - "issue:43526|issue:44554" + "issue:43526|issue:44554", + "issue:36010|issue:43645" ], - "prepared_review_unit_hash": "45b6f6679462a000a9f65ba67c18d2e4795d8d21c1bd33570e3f856bf00ba289", + "prepared_review_unit_hash": "17a05f14a1fd45fbd00e236451709943e373bfae302d149ddbb8f1a80f3bf4a5", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 28, - "serialized_chars": 36331, - "estimated_input_tokens": 9083, - "estimated_eval_tokens": 18422 + "soft_pair_count": 27, + "serialized_chars": 36095, + "estimated_input_tokens": 9024, + "estimated_eval_tokens": 18304 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is highly heterogeneous: the soft pairs share only broad surface themes (loading, tokenization, multimodal, dtype, etc.) but not the same concrete bug or code path. I would reject all soft-edge duplicate merges. No PRs are present. If forced to pick a representative issue, issue:45020 is the broadest umbrella, but it is not a true canonical duplicate anchor.", - "confidence": 0.88, - "canonical_issue_reason": "issue:45020 is the broadest, most umbrella-like issue in the set (general version-regression / remote_code loading breakage), but the cluster is too mixed for a true canonical duplicate issue.", + "summary": "These items are a loose collection of closed/open Transformers issues with only topical similarity; the soft pairs mostly share broad themes (tokenizers, loading, warnings, multimodal processors) but not the same concrete bug. I found no safe duplicate merge candidates and no PRs in the set.", + "confidence": 0.95, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:45020 is the closest thing to a global representative because it captures a broad regression pattern, but it should not be treated as a duplicate target for the rest of the items.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43452", "right": "issue:44991", "accept": false, - "reason": "Both are tokenizer-loading problems, but they affect different models and appear to stem from different failure modes (gguf_file path handling vs a specific tokenizer load regression)." + "reason": "Both are tokenizer-loading failures, but one is gguf_file-related and the other is a model-specific regression; different code paths and symptoms." }, { "left": "issue:44805", "right": "issue:44936", "accept": false, - "reason": "Both mention IndexError, but one is a mask/tensor shape mismatch and the other is trainer.evaluate() failing after training; they are not the same bug." + "reason": "Different failure modes: mask/index shape error vs trainer.evaluate() breaking after train(); not the same underlying bug." }, { "left": "issue:42175", "right": "issue:45081", "accept": false, - "reason": "TensorFlow backend packaging and Mistral tokenizer regex patching are unrelated issues with different code paths and symptoms." + "reason": "One is an install/backend packaging issue, the other is a tokenizer regex patch crash; unrelated defects." }, { "left": "issue:44610", "right": "issue:45072", "accept": false, - "reason": "One is an image processor size mismatch, the other is a bfloat16 dtype mismatch in model inference; same broad subsystem, different bugs." - }, - { - "left": "issue:43720", - "right": "issue:45072", - "accept": false, - "reason": "Packed-weight loading failure and dtype mismatch are distinct loading/inference problems, not one underlying defect." + "reason": "Image size mismatch in OmDet-Turbo vs dtype mismatch in bfloat16 inference; separate model paths." }, { "left": "issue:45081", "right": "issue:45406", "accept": false, - "reason": "Both are attribute errors in tokenizer/processor code, but they hit different objects and different call sites; not the same concrete bug." + "reason": "Both involve tokenizer/processor loading, but the failing objects and root causes differ (Mistral regex patch vs Gemma4Processor missing _tokenizer)." }, { - "left": "issue:44060", - "right": "issue:44368", + "left": "issue:43720", + "right": "issue:45072", "accept": false, - "reason": "Both mention tied-weights warnings, but one is an actual bad tie in model code and the other is a config/warning issue during LoRA fine-tuning." + "reason": "BitNet packed-weight unpacking bug is unrelated to the SwitchTransformers/TimmWrapperModel dtype mismatch." }, { - "left": "issue:43650", - "right": "issue:43906", + "left": "issue:44060", + "right": "issue:44368", "accept": false, - "reason": "Generic title noise and an isolated reproduction of a prior issue are not duplicates." + "reason": "Both mention tied-weights warnings, but the model versions and concrete defect are different; too weak to merge." }, { "left": "issue:44671", "right": "issue:45701", "accept": false, - "reason": "CamemBERT masked LM correctness regression and a general tokenization-version change are too broad and not the same concrete bug." + "reason": "CamemBERT masked-LM regression is not the same as a broad tokenization change report." }, { - "left": "issue:43404", - "right": "issue:43782", + "left": "issue:43650", + "right": "issue:43906", "accept": false, - "reason": "Both concern weight tying/loading, but they involve different models and different failure mechanisms." + "reason": "No shared bug: one is a nonspecific request, the other is a reproduction of a separate issue." }, { - "left": "issue:45584", - "right": "issue:45834", + "left": "issue:43404", + "right": "issue:43782", "accept": false, - "reason": "Whisper empty transcription behavior and Kosmos2.5 long-ocr index errors are unrelated multimodal issues." + "reason": "Untied lm_head weights in Mistral3 is different from Qwen3VL from_pretrained weight_only loading failure." }, { "left": "issue:43582", "right": "issue:44857", "accept": false, - "reason": "Apple Silicon allocator TypeError and CUDA AMP image-loss crash are different platform-specific failures." + "reason": "Apple Silicon warmup TypeError and CUDA AMP crash are different platform-specific problems." }, { "left": "issue:45459", "right": "issue:45803", "accept": false, - "reason": "Both involve exception handling, but they are in different APIs and address different hidden-error scenarios." + "reason": "Both are exception-handling bugs, but they affect different functions and hide different errors." }, { "left": "issue:43262", "right": "issue:43819", "accept": false, - "reason": "Audio chat-template sampling-rate defaulting and DAC latent reconstruction mismatch are unrelated." + "reason": "Audio apply_chat_template sample-rate defaulting is unrelated to DAC.from_latents vs forward mismatch." }, { "left": "issue:43526", "right": "issue:43697", "accept": false, - "reason": "One is a label-reduction bug in an image processor; the other is a model output regression in v5." + "reason": "BEiT label reduction bug and RTDetrV2 output drift are separate vision-model regressions." }, { "left": "issue:45084", "right": "issue:45538", "accept": false, - "reason": "Template compilation failure and CLIPTokenizer max-length misconfiguration are unrelated." + "reason": "Template compilation failure and CLIPTokenizer max_length misconfiguration are unrelated." }, { "left": "issue:43329", "right": "issue:45600", "accept": false, - "reason": "Undefined variables in multimodal token counting and stale auto_mappings references are different CI/code-maintenance problems." - }, - { - "left": "issue:39692", - "right": "issue:45834", - "accept": false, - "reason": "Both are multimodal-facing, but one is a SigLIP2 docs/example bug and the other is a Kosmos2.5 long-input runtime error." + "reason": "Multimodal token counting bug and stale auto_mappings config references are different code areas." }, { "left": "issue:43644", "right": "issue:43749", "accept": false, - "reason": "Non-persistent buffer initialization and FSDP RAM-efficient loading are distinct loading regressions." + "reason": "Non-persistent buffer junk initialization and FSDP CPU RAM efficient loading are not the same defect." }, { - "left": "issue:43653", - "right": "issue:44912", + "left": "issue:43742", + "right": "issue:45020", "accept": false, - "reason": "BigBirdTokenizer special-token decode failure and MXFP4 quantization fallback are unrelated." + "reason": "A MobileLLM loading key error is not the same as a broad remote_code regression across recent versions." }, { - "left": "issue:43742", - "right": "issue:45020", + "left": "issue:43653", + "right": "issue:44912", "accept": false, - "reason": "A specific key error for one model is not the same underlying bug as the broad remote_code regression." + "reason": "BigBird special-token decode bug and MXFP4 quantization fallback are unrelated." }, { "left": "issue:43638", "right": "issue:44936", "accept": false, - "reason": "Deepspeed zero3/non-pretrained Bert IndexError and trainer.evaluate() after train are different training lifecycle failures." + "reason": "Zero3/Bert indexing failure and trainer.evaluate() after train() failure do not share a concrete root cause." }, { "left": "issue:43746", "right": "issue:44811", "accept": false, - "reason": "PEFT local-checkpoint loading and Whisper batch_decode skip_special_tokens behavior are unrelated." + "reason": "PEFT checkpoint loading and Whisper batch_decode skip_special_tokens behavior are separate processor/model issues." }, { "left": "issue:44589", "right": "issue:45042", "accept": false, - "reason": "Float8 storage lookup failure and PIL backend torchvision dependency issues are unrelated." + "reason": "Float8 storage lookup error and PIL backend torchvision dependency regression are unrelated." }, { "left": "issue:43854", "right": "issue:44977", "accept": false, - "reason": "Different models, different failure modes: unit-test loading failure vs flash-attention generation bug." + "reason": "GLM-4.7-Flash loading in tests and Qwen3.5 flash-attention generation are different model-specific bugs." }, { "left": "issue:38175", "right": "issue:44610", "accept": false, - "reason": "Both involve model/processor mismatch themes, but one is zero probabilities in SigLIP2 and the other is an image-size mismatch in OmDet-Turbo." + "reason": "SigLIP2 zero probabilities and OmDet input-size mismatch are distinct vision-model issues." }, { "left": "issue:39692", "right": "issue:44912", "accept": false, - "reason": "SigLIP2 documentation/model example errors and MXFP4 quantization fallback are unrelated." + "reason": "Documentation example errors for SigLIP2 are not the same as a quantization loading/fallback bug." }, { "left": "issue:43526", "right": "issue:44554", "accept": false, - "reason": "Image label reduction and MPS attention correctness are unrelated code paths." + "reason": "BEiT label reduction bug is unrelated to the MPS attention correctness issue." + }, + { + "left": "issue:36010", + "right": "issue:43645", + "accept": false, + "reason": "GenerationMixin import failure and custom model initialization in notebooks are different v5 regressions." } ] }, @@ -5229,7 +5224,7 @@ "issue:43577", "issue:43582", "issue:43643", - "issue:43645", + "issue:43696", "issue:43697", "issue:43720", "issue:43742", @@ -5240,6 +5235,7 @@ "issue:43931", "issue:44291", "issue:44479", + "issue:44560", "issue:44568", "issue:44610", "issue:44811", @@ -5254,22 +5250,20 @@ "issue:45488", "issue:45538", "issue:45701", - "issue:45759", - "issue:45834" + "issue:45759" ], "soft_pairs": [ - "issue:43819|issue:43927", - "issue:36010|issue:43645", "issue:34634|issue:36331", "issue:43454|issue:43577", "issue:43257|issue:43329", + "issue:43819|issue:43927", "issue:43720|issue:44610", "issue:43550|issue:44912", "issue:44568|issue:45488", "issue:43749|issue:44291", "issue:43531|issue:45042", - "issue:43643|issue:45759", "issue:43262|issue:44811", + "issue:43643|issue:45759", "issue:44568|issue:45356", "issue:36010|issue:36331", "issue:44849|issue:45701", @@ -5282,248 +5276,244 @@ "issue:41720|issue:43540", "issue:43452|issue:43582", "issue:42915|issue:43742", - "issue:43317|issue:45538", "issue:33357|issue:34567", + "issue:43317|issue:45538", "issue:43927|issue:44912", - "issue:44479|issue:45381", "issue:44987|issue:45538", + "issue:44479|issue:45381", "issue:42915|issue:44821", "issue:42915|issue:45538", "issue:43257|issue:43756", - "issue:44479|issue:45834" + "issue:43540|issue:44560", + "issue:43540|issue:44479", + "issue:43257|issue:43696" ], - "prepared_review_unit_hash": "cbd9f217b5096716aeaacd485e96b4045393aaa7c7d3bb990d6c714872786c19", + "prepared_review_unit_hash": "8d1e70b0a2888148e75ae9031fd2898dd88089c4d701d28af489862e74a94995", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 33, - "serialized_chars": 37729, - "estimated_input_tokens": 9433, - "estimated_eval_tokens": 19122 + "soft_pair_count": 34, + "serialized_chars": 38028, + "estimated_input_tokens": 9507, + "estimated_eval_tokens": 19270 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Only the Qwen video-input pair 44479 \u2194 45381 looks like a true duplicate cluster. The evidence is not enough to merge 43329 into that group: it appears to be a separate bug about undefined helpers in `_get_num_multimodal_tokens` rather than the same video-position-id regression.", - "confidence": 0.79, - "canonical_issue_reason": "issue:44479 is the broadest representative of the single clear duplicate subcluster: a v5.3.0 Qwen video-input regression affecting multiple Qwen VL variants.", + "summary": "Mostly heterogeneous issue set. issue:44479 is still the best umbrella for the Qwen video-input regression family, but issue:43329 looks like a narrower undefined-variable bug in `_get_num_multimodal_tokens`, not a confident duplicate of the broader 5.3.0 regression.", + "confidence": 0.72, + "canonical_issue_reason": "issue:44479 best captures the broad v5.3.0 video-input regression across multiple Qwen VL/MoE variants, so it is the strongest umbrella issue.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44479 is the best overall anchor because it describes the widest version-scoped Qwen video-input failure, with 45381 as a concrete manifestation.", + "best_issue_reason": "issue:44479 is the most representative global issue because it spans the widest user-facing Qwen video regression while matching the shared subsystem.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:43819", - "right": "issue:43927", - "accept": false, - "reason": "Different models and failure modes: DAC latents/STE mismatch vs DiaConfig token-ID persistence." - }, - { - "left": "issue:36010", - "right": "issue:43645", - "accept": false, - "reason": "Both are v5 import/config breakages, but the concrete bugs differ: GenerationMixin import vs Jupyter custom-model init." - }, { "left": "issue:34634", "right": "issue:36331", "accept": false, - "reason": "Unrelated areas: BarkProcessor voice presets vs Trainer compute_loss signature change." + "reason": "Different areas: BarkProcessor voice preset handling vs Trainer compute_loss signature change." }, { "left": "issue:43454", "right": "issue:43577", "accept": false, - "reason": "Different model families and symptoms: AyaVision weight tying vs BLIP2 dtype handling." + "reason": "Unrelated model bugs: AyaVision weight tying vs BLIP-2 dtype loading." }, { "left": "issue:43257", "right": "issue:43329", "accept": false, - "reason": "Qwen MoE loading/conversion is a different bug from an undefined-helper failure in the video token-counting path." + "reason": "Both are Qwen-related, but one is MOE weight conversion on load and the other is a video token-counting bug; different code paths." + }, + { + "left": "issue:43819", + "right": "issue:43927", + "accept": false, + "reason": "DAC latent conversion mismatch vs DiaConfig custom token ID persistence; unrelated model behaviors." }, { "left": "issue:43720", "right": "issue:44610", "accept": false, - "reason": "Different subsystems: BitNet packed-weight loading vs OmDet-Turbo processor image-size mismatch." + "reason": "Accelerate packed-weight loading bug vs OmDet-Turbo image size mismatch; not the same underlying defect." }, { "left": "issue:43550", "right": "issue:44912", "accept": false, - "reason": "Different concrete failures: torch.compile+SDPA on Bamba vs MXFP4 quantization fallback on git-oss-20b." + "reason": "Different failure modes: torch.compile with SDPA vs MXFP4 quantization fallback." }, { "left": "issue:44568", "right": "issue:45488", "accept": false, - "reason": "Tokenizer regressions, but different tokenizers and mechanisms; not the same underlying bug." + "reason": "Both are tokenizer regressions, but they affect different tokenizer implementations and code paths." }, { "left": "issue:43749", "right": "issue:44291", "accept": false, - "reason": "One is FSDP CPU RAM efficient loading; the other is init_empty_weights argument compatibility." + "reason": "Both touch loading, but one is FSDP CPU RAM efficient loading and the other is init_empty_weights/_is_hf_initialized handling; not the same bug." }, { "left": "issue:43531", "right": "issue:45042", "accept": false, - "reason": "No real overlap: Qwen3-MoE sliding_window vs PIL image processors requiring torchvision." + "reason": "Qwen3-MoE sliding-window issue vs PIL backend torchvision dependency regression; unrelated." }, { - "left": "issue:43643", - "right": "issue:45759", + "left": "issue:43262", + "right": "issue:44811", "accept": false, - "reason": "Both involve config loading, but one is missing fields under trust_remote_code and the other is text_config unwrapping for composite multimodal configs." + "reason": "Audio processor chat-template sampling-rate default vs Whisper batch_decode skip_special_tokens; different processor bugs." }, { - "left": "issue:43262", - "right": "issue:44811", + "left": "issue:43643", + "right": "issue:45759", "accept": false, - "reason": "Audio chat-template sampling-rate default vs Whisper batch_decode skip_special_tokens; different code paths." + "reason": "AutoConfig trust_remote_code field loss vs AutoModelForCausalLM from_config text_config unwrapping; separate config-loading issues." }, { "left": "issue:44568", "right": "issue:45356", "accept": false, - "reason": "Tokenizer regressions, but separate models and symptoms: special tokens not added vs codec/warning behavior in Kimi-K2.5." + "reason": "Different tokenizer regressions on different models; not the same code-path problem." }, { "left": "issue:36010", "right": "issue:36331", "accept": false, - "reason": "GenerationMixin import failure is unrelated to a custom Trainer loss-signature change." + "reason": "Import path regression for GenerationMixin vs trainer loss signature mismatch." }, { "left": "issue:44849", "right": "issue:45701", "accept": false, - "reason": "Different failures: Qwen3.5 hidden-states bug vs a broad tokenization-version regression." + "reason": "Qwen3.5 hidden-state output bug vs generic tokenization version-change report; unrelated." }, { "left": "issue:43329", "right": "issue:43450", "accept": false, - "reason": "Both involve video paths, but one is an undefined helper in multimodal token counting and the other is a batched video-processor shape bug." + "reason": "Both involve video features, but one is undefined variables in multimodal token counting and the other is batched video tensor shape handling." }, { "left": "issue:34567", "right": "issue:40990", "accept": false, - "reason": "TrainerState token accounting is unrelated to perplexity on gpt-oss-20b." + "reason": "TrainerState token counter bug vs high perplexity on gpt-oss-20b; no shared root cause." }, { "left": "issue:43329", "right": "issue:44479", "accept": false, - "reason": "The packet does not show the same regression: 43329 is a separate `_get_num_multimodal_tokens` undefined-helper bug, not the broader Qwen video-position-id issue." + "reason": "The packet supports thematic similarity only: 43329 is an undefined-variable bug in video token counting, while 44479 is a broader v5.3.0 video-input/vision_position_ids regression." }, { "left": "issue:43257", "right": "issue:43931", "accept": false, - "reason": "Different Qwen loading bugs: MoE weight conversion with accelerate/deepspeed vs weight-shape mismatch on Qwen3-VL-30B-A3B-Instruct." + "reason": "MOE weight conversion on load vs Qwen3-VL weight-shape mismatch; distinct loading issues." }, { "left": "issue:43697", "right": "issue:45357", "accept": false, - "reason": "RTDetrV2 output differences and Qwen3.5 save_pretrained visual-key regression are unrelated." + "reason": "RTDetrV2 output drift in v5 vs Qwen3.5 visual-encoder save_pretrained key regression; unrelated." }, { "left": "issue:44291", "right": "issue:45042", "accept": false, - "reason": "init_empty_weights argument compatibility is unrelated to PIL backend torchvision requirements." + "reason": "Model init_empty_weights TypeError vs PIL image processor torchvision dependency regression." }, { "left": "issue:41720", "right": "issue:43540", "accept": false, - "reason": "Different Qwen issues: device-map/cuda assert on A800 vs video processing ValueError in Qwen3OmniMoe." + "reason": "Different Qwen video failures: CUDA assert on auto device mapping vs ValueError in Qwen3OmniMoe video processing." }, { "left": "issue:43452", "right": "issue:43582", "accept": false, - "reason": "GGUF tokenizer/model loading failure is unrelated to Apple Silicon allocator warmup TypeError." + "reason": "gguf_file tokenizer/model loading bug vs Apple Silicon caching_allocator_warmup TypeError." }, { "left": "issue:42915", "right": "issue:43742", "accept": false, - "reason": "Qwen3Moe FP8 config failure and MobileLLM key error are different loading bugs." + "reason": "Qwen3Moe FineGrainedFP8Config failure vs MobileLLM key error; unrelated model-loading problems." }, { - "left": "issue:43317", - "right": "issue:45538", + "left": "issue:33357", + "right": "issue:34567", "accept": false, - "reason": "Dequantized model offload failure and CLIPTokenizer model_max_length are unrelated." + "reason": "MacOS CLIP bus error vs TrainerState token counter not updating; no common bug." }, { - "left": "issue:33357", - "right": "issue:34567", + "left": "issue:43317", + "right": "issue:45538", "accept": false, - "reason": "MacOS bus error with CLIP is unrelated to TrainerState token-count updates." + "reason": "Dequantized model offload failure vs CLIPTokenizer model_max_length constant; unrelated." }, { "left": "issue:43927", "right": "issue:44912", "accept": false, - "reason": "DiaConfig token-ID persistence and MXFP4 quantization fallback are unrelated." - }, - { - "left": "issue:44479", - "right": "issue:45381", - "accept": true, - "reason": "Both describe the same Qwen video-input regression; 45381 is a specific qwen2.5-vl manifestation of the broader v5.3.0 bug in 44479." + "reason": "DiaConfig token IDs lost on save/load vs MXFP4 quantization fallback; different failures." }, { "left": "issue:44987", "right": "issue:45538", "accept": false, - "reason": "Loading physical-intelligence/fast on v5.1+ and CLIPTokenizer max_length are unrelated." + "reason": "Model loading failure in 5.1.0 vs CLIPTokenizer max-length issue; unrelated." + }, + { + "left": "issue:44479", + "right": "issue:45381", + "accept": true, + "reason": "Same Qwen video regression: 45381 is a narrower qwen2.5-vl manifestation of the broader v5.3.0 video-input bug described in 44479." }, { "left": "issue:42915", "right": "issue:44821", "accept": false, - "reason": "Qwen3Moe FP8 loading is unrelated to loading AutoImageProcessor from URL." + "reason": "FineGrainedFP8Config loading issue vs AutoImageProcessor-from-URL problem; unrelated." }, { "left": "issue:42915", "right": "issue:45538", "accept": false, - "reason": "Different bugs in different components: Qwen3Moe FP8 config vs CLIPTokenizer max_length." + "reason": "Qwen3Moe FP8 loading failure vs CLIPTokenizer max-length constant; unrelated." }, { "left": "issue:43257", "right": "issue:43756", "accept": false, - "reason": "Qwen3 MoE loading/conversion and Smollm3 RoPE-layer dropping are unrelated." + "reason": "Qwen MOE weight conversion/load issue vs Smollm3 RoPE-layer mismatch; different subsystems." }, { - "left": "issue:44479", - "right": "issue:45834", + "left": "issue:43540", + "right": "issue:44560", "accept": false, - "reason": "Both are multimodal input bugs, but the symptoms and model families differ: Qwen video regression vs Kosmos2.5 long-OCR index error." + "reason": "Both are video-related, but one is Qwen3OmniMoe ValueError and the other is Qwen3-VL-embedding StopIteration; not the same concrete bug." } ] }, "evaluator_result": { "accept": false, - "feedback": "The Qwen video-input pair 44479 \u2194 45381 looks grounded, but the output overreaches by folding 43329 into the same duplicate cluster. 43329 is a different bug report about undefined helpers in `_get_num_multimodal_tokens`, and the packet does not provide enough evidence to treat it as the same underlying regression as 44479/45381. The summary should stay more conservative about that linkage." + "feedback": "The clustering is mostly grounded, but one soft-edge acceptance is too strong for the evidence in the packet. In particular, issue:43329 and issue:44479 are both Qwen/video-related, but their titles point to different concrete failures (_get_num_multimodal_tokens undefined variables vs a broader v5.3.0 video input/vision_position_ids regression). The packet supports thematic similarity, not a confident duplicate/merge decision. The other rejections look conservative, and 44479 is a reasonable representative, but the accepted 43329\u219444479 link overstates the evidence." }, "evaluator_used": true, "retried": true, @@ -5551,15 +5541,15 @@ "issue:36331", "issue:38175", "issue:42175", - "issue:43257", "issue:43452", "issue:43493", "issue:43526", + "issue:43531", "issue:43540", "issue:43577", "issue:43643", "issue:43646", - "issue:43696", + "issue:43697", "issue:43742", "issue:43749", "issue:43756", @@ -5568,10 +5558,10 @@ "issue:43994", "issue:44062", "issue:44291", - "issue:44479", + "issue:44484", "issue:44488", - "issue:44560", "issue:44589", + "issue:44704", "issue:44737", "issue:44756", "issue:44792", @@ -5583,6 +5573,7 @@ "issue:45072", "issue:45081", "issue:45137", + "issue:45216", "issue:45325", "issue:45375", "issue:45381", @@ -5593,9 +5584,6 @@ "issue:45823" ], "soft_pairs": [ - "issue:43540|issue:44560", - "issue:43540|issue:44479", - "issue:43257|issue:43696", "issue:43577|issue:45072", "issue:45137|issue:45405", "issue:38175|issue:44898", @@ -5606,8 +5594,8 @@ "issue:43906|issue:45381", "issue:43646|issue:43749", "issue:44062|issue:45081", - "issue:43643|issue:45375", "issue:43749|issue:44756", + "issue:43643|issue:45375", "issue:34567|issue:36331", "issue:43493|issue:43994", "issue:36010|issue:42175", @@ -5617,222 +5605,219 @@ "issue:44792|issue:44964", "issue:43526|issue:45479", "issue:28282|issue:34689", - "issue:43756|issue:45325", "issue:45042|issue:45081", + "issue:43756|issue:45325", "issue:43742|issue:44589", - "issue:45405|issue:45600" + "issue:45405|issue:45600", + "issue:44484|issue:44704", + "issue:43697|issue:45216", + "issue:43531|issue:44821" ], - "prepared_review_unit_hash": "7357582421def44df243ae0836299dba50a9a887ed2a79dd66ba9fc75f4c22fd", + "prepared_review_unit_hash": "bce97931270d83d25c1debe66f0c5794c63b844ecb28c43a7de10e3e4b99dc8e", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { - "node_count": 47, - "item_count": 47, + "node_count": 48, + "item_count": 48, "soft_pair_count": 28, - "serialized_chars": 35748, - "estimated_input_tokens": 8937, - "estimated_eval_tokens": 18130 + "serialized_chars": 36324, + "estimated_input_tokens": 9081, + "estimated_eval_tokens": 18418 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Most items are unrelated bug reports. Only one soft duplicate is actually accepted: the SigLIP2 discrepancy pair (issue:43493 / issue:43994). The Qwen video-input reports are related thematically, but this packet does not support accepting them as duplicates here. No PRs are present.", - "confidence": 0.78, - "canonical_issue_reason": "issue:44479 is the strongest representative issue because it is an explicit regression report with a clear affected release and model family, making it a good cluster anchor among mostly one-off bug reports.", + "summary": "Mostly a mixed bag of unrelated Transformers issues. The only clear duplicate-like pair is the SigLIP2 bug reports; everything else looks like distinct failures in different models or subsystems. No PRs are present.", + "confidence": 0.83, + "canonical_issue_reason": "issue:43493 is the best canonical issue because it describes the underlying SigLIP2 implementation discrepancy at the root of the duplicate pair; issue:43994 is a downstream user-facing symptom of the same bug.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44479 is the best standalone issue artifact: it is regression-focused, clearly scoped, and broadly representative without overcommitting to duplicate status for the other Qwen reports.", + "best_issue_reason": "issue:43493 is the most representative and actionable issue: it states the core HF-vs-JAX mismatch, which is broader than the end-user symptom in issue:43994.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43540", - "right": "issue:44560", + "left": "issue:43577", + "right": "issue:45072", "accept": false, - "reason": "Both are Qwen video-input failures, but they describe different models and different failure modes (ValueError vs StopIteration), so they are not the same underlying bug." - }, - { - "left": "issue:43540", - "right": "issue:44479", - "accept": false, - "reason": "Same general area, but 43540 is Qwen3OmniMoe-specific while 44479 is a broader 5.3.0 regression across several Qwen video models; the concrete failure described is not the same." - }, - { - "left": "issue:43257", - "right": "issue:43696", - "accept": false, - "reason": "Different problems entirely: Qwen3 MOE weight conversion under accelerate/deepspeed vs GPT-oss OOM." - }, - { - "left": "issue:43577", - "right": "issue:45072", - "accept": false, - "reason": "Both mention dtype handling, but they affect different model families and different code paths; not the same bug." + "reason": "Both are dtype-related, but they affect different models and different code paths; not the same bug." }, { "left": "issue:45137", "right": "issue:45405", "accept": false, - "reason": "DeepSpeed ZeRO3 deque error and a PEFT version-bump issue are unrelated." + "reason": "DeepSpeed ZeRO3 deque failure and a PEFT version bump are unrelated." }, { "left": "issue:38175", "right": "issue:44898", "accept": false, - "reason": "Different models and symptoms: SigLIP2 zero-probability outputs vs Perceiver non-default-resolution failure." + "reason": "Different models, different symptoms, and different processing paths." }, { "left": "issue:44737", "right": "issue:45588", "accept": false, - "reason": "XLNet CPU-device bug and flash-attention sinkless-model AttributeError are unrelated." + "reason": "XLNet CPU device placement and flash-attention crash with s_aux=None are unrelated." }, { "left": "issue:44062", "right": "issue:44991", "accept": false, - "reason": "Tokenizers AddedToken argument duplication is unrelated to the est-roberta tokenizer loading failure." + "reason": "Both involve tokenizers, but one is an AddedToken argument error and the other is a tokenizer loading regression." }, { "left": "issue:43742", "right": "issue:44291", "accept": false, - "reason": "Both are loading-time errors, but one is a MobileLLM key error and the other is an init_empty_weights API mismatch; different root causes." + "reason": "Both fail during loading, but one is a model config key error and the other is an init-empty-weights API mismatch." }, { "left": "issue:43540", "right": "issue:45823", "accept": false, - "reason": "Qwen3OmniMoe video-input error and Gemma4 PLE device mismatch are different bugs." + "reason": "Different models and different failure mechanisms; not mergeable as one fix." }, { "left": "issue:43906", "right": "issue:45381", "accept": false, - "reason": "The isolated reproduction of another issue and the Qwen2.5-VL video position-id regression are not clearly the same bug." + "reason": "One is an isolated reproduction reference, the other is a Qwen2.5-VL position-id bug; insufficient evidence they are the same issue." }, { "left": "issue:43646", "right": "issue:43749", "accept": false, - "reason": "Custom model initialization breakage and FSDP CPU RAM efficient loading are different failure modes." + "reason": "Transformers 5.0 custom model init breakage and FSDP CPU-efficient loading are separate regressions." }, { "left": "issue:44062", "right": "issue:45081", "accept": false, - "reason": "AddedToken special-kwarg duplication and the Mistral regex patch crash are unrelated." + "reason": "Distinct tokenizer bugs: AddedToken keyword collision vs Mistral regex patch crashing on backend_tokenizer." }, { - "left": "issue:43643", - "right": "issue:45375", + "left": "issue:43749", + "right": "issue:44756", "accept": false, - "reason": "Both involve config fields being absent, but they concern different models and different loading paths; not enough evidence they are the same bug." + "reason": "FSDP CPU RAM efficient loading and Strix Halo mmap OOM are different memory/loading problems." }, { - "left": "issue:43749", - "right": "issue:44756", + "left": "issue:43643", + "right": "issue:45375", "accept": false, - "reason": "FSDP loading regression and Strix Halo mmap OOM are different issues." + "reason": "Both mention missing config fields, but the reported contexts and root causes differ." }, { "left": "issue:34567", "right": "issue:36331", "accept": false, - "reason": "TrainerState token tracking and CustomTrainer compute_loss signature mismatch are separate trainer bugs." + "reason": "Trainer state token counting and custom compute_loss signature are unrelated Trainer issues." }, { "left": "issue:43493", "right": "issue:43994", "accept": true, - "reason": "Both report the same SigLIP2 implementation problem: HF outputs are wrong/nonsensical compared with expected behavior, and the JAX-vs-HF discrepancy matches the user-facing bad results." + "reason": "Both reports point to the same SigLIP2 model-implementation discrepancy causing bad outputs." }, { "left": "issue:36010", "right": "issue:42175", "accept": false, - "reason": "GenerationMixin import failure and missing TensorFlow backend in the torch extra are unrelated packaging/import problems." + "reason": "Importing GenerationMixin and backend selection for torch installs are unrelated." }, { "left": "issue:42175", "right": "issue:43824", "accept": false, - "reason": "The TensorFlow-backend packaging issue is unrelated to the Qwen2.5-VL import error." + "reason": "TensorFlow backend packaging and missing Qwen2.5-VL export are different issues." }, { "left": "issue:43452", "right": "issue:44488", "accept": false, - "reason": "gguf_file loading breakage and a specific model load failure for cjvt/sleng-bert are not the same underlying bug." + "reason": "gguf_file handling and a specific model load failure are not the same bug." }, { "left": "issue:44291", "right": "issue:44821", "accept": false, - "reason": "init_empty_weights argument handling and AutoImageProcessor URL loading are unrelated." + "reason": "init_empty_weights argument handling and loading AutoImageProcessor from URL are unrelated." }, { "left": "issue:44792", "right": "issue:44964", "accept": false, - "reason": "A janus image-generation test failure and a Phi-4 multimodal model load failure are different model-specific issues." + "reason": "Different multimodal models and different failure points; no shared underlying code-path is evident." }, { "left": "issue:43526", "right": "issue:45479", "accept": false, - "reason": "BeitImageProcessorFast label reduction and zero-loss sequence-classification behavior are different code paths and symptoms." + "reason": "Processor label reduction and single-label classification zero-loss behavior are different bugs." }, { "left": "issue:28282", "right": "issue:34689", "accept": false, - "reason": "PyTorch import availability and TrainerState token-count tracking are unrelated." + "reason": "AutoModel missing PyTorch and Llama 3.2 Vision load failure are unrelated import/load issues." }, { - "left": "issue:43756", - "right": "issue:45325", + "left": "issue:45042", + "right": "issue:45081", "accept": false, - "reason": "Smollm3 RoPE-layer dropping and Qwen2.5-VL temporal position-id scaling are different model-specific bugs." + "reason": "Torchvision requirement in PIL image processors and a Mistral tokenizer patch crash are distinct problems." }, { - "left": "issue:45042", - "right": "issue:45081", + "left": "issue:43756", + "right": "issue:45325", "accept": false, - "reason": "Torchvision dependency in PIL image processors is unrelated to the Mistral regex crash." + "reason": "Both involve positional encoding, but they are different models and different calculations." }, { "left": "issue:43742", "right": "issue:44589", "accept": false, - "reason": "MobileLLM key error and Float8 storage import/type error are different loading failures." + "reason": "A MobileLLM key error and a Float8 storage lookup failure are not the same failure mode." }, { "left": "issue:45405", "right": "issue:45600", "accept": false, - "reason": "An unreleased PEFT version bump and a removed-config CI break are unrelated." + "reason": "A dependency version bump and broken auto_mappings references are unrelated changes." }, { - "left": "issue:44792", - "right": "issue:44964", + "left": "issue:44484", + "right": "issue:44704", "accept": false, - "reason": "A janus image-generation test failure and a Phi-4 multimodal model load failure are different model-specific issues." + "reason": "Shard-size behavior and AutoProcessor kwarg forwarding are separate API issues." + }, + { + "left": "issue:43697", + "right": "issue:45216", + "accept": false, + "reason": "Different models, different regressions, and no shared code-path is indicated." + }, + { + "left": "issue:43531", + "right": "issue:44821", + "accept": false, + "reason": "Qwen3-MoE sliding window behavior and AutoImageProcessor URL loading are unrelated." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The issue-level classification is mostly grounded, but the summary is not fully consistent with the packet. In particular, it says two soft duplicates are plausible, yet only one soft pair is actually accepted, and the claimed Qwen video-input duplicate is not supported by an accepted verdict in the soft-edge list. That makes the summary a bit overconfident and not fully conservative. The canonical issue choice is reasonable, but I would reject until the soft-edge summary matches the actual verdicts more precisely." + "accept": true, + "feedback": "The summary is grounded in the packet: the items are mostly unrelated issue reports, and the only plausible duplicate-like pair is the SigLIP2 pair (43493/43994). The soft-edge verdicts are conservative, with rejections justified by different models, subsystems, or failure modes. No PR pairs are present." }, "evaluator_used": true, - "retried": true, + "retried": false, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -5862,6 +5847,7 @@ "issue:43295", "issue:43452", "issue:43531", + "issue:43550", "issue:43577", "issue:43582", "issue:43643", @@ -5869,21 +5855,20 @@ "issue:43688", "issue:43697", "issue:43720", + "issue:43742", "issue:43819", "issue:43906", + "issue:43927", "issue:44361", "issue:44442", "issue:44464", "issue:44466", - "issue:44484", "issue:44514", "issue:44561", "issue:44568", "issue:44625", - "issue:44704", "issue:44743", "issue:44811", - "issue:44821", "issue:44843", "issue:44877", "issue:44898", @@ -5892,253 +5877,274 @@ "issue:44977", "issue:44991", "issue:45005", - "issue:45216", "issue:45290", "issue:45356", "issue:45381", "issue:45440", + "issue:45588", "issue:45823" ], "soft_pairs": [ - "issue:44484|issue:44704", - "issue:43697|issue:45216", - "issue:43531|issue:44821", - "issue:44514|issue:45381", "issue:28282|issue:29127", + "issue:44514|issue:45381", "issue:43582|issue:44977", - "issue:43643|issue:44561", "issue:44625|issue:44877", - "issue:43720|issue:44898", + "issue:43643|issue:44561", "issue:42175|issue:44938", + "issue:43720|issue:44898", "issue:43452|issue:43577", "issue:44514|issue:45290", - "issue:43452|issue:44843", "issue:44466|issue:45005", + "issue:43452|issue:44843", "issue:41762|issue:44936", "issue:43295|issue:45356", "issue:43819|issue:44811", "issue:43653|issue:44568", - "issue:44936|issue:45823", "issue:24643|issue:29127", - "issue:43653|issue:44361", - "issue:44361|issue:44442", + "issue:44936|issue:45823", "issue:30064|issue:33666", "issue:38175|issue:43295", - "issue:43577|issue:43697", + "issue:44361|issue:44442", + "issue:43653|issue:44361", "issue:44464|issue:44743", + "issue:43577|issue:43697", "issue:44843|issue:44991", "issue:41720|issue:43906", "issue:44977|issue:45356", - "issue:43688|issue:45440" + "issue:43688|issue:45440", + "issue:43531|issue:43742", + "issue:43653|issue:43927", + "issue:44464|issue:44977", + "issue:43577|issue:45588", + "issue:43550|issue:43927", + "issue:43550|issue:44361" ], - "prepared_review_unit_hash": "1e55996ba7e72f3004dbae760b2638b5e1358380ff8c9ac0b9bddce2b775f958", + "prepared_review_unit_hash": "6ba49062fb3c928af44b91b3051d4ef06dbefeefa2166e5a659335cf4d896b38", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 30, - "serialized_chars": 36836, - "estimated_input_tokens": 9209, - "estimated_eval_tokens": 18674 + "soft_pair_count": 33, + "serialized_chars": 37761, + "estimated_input_tokens": 9441, + "estimated_eval_tokens": 19138 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous. The soft links are driven by superficial topic overlap (tokenizers, v5 regressions, Qwen/DeepSpeed, tied weights), but none looks like the same concrete bug/change with enough confidence to merge.", + "summary": "These items are mostly a heterogeneous mix of unrelated bugs with only superficial title similarity. I would not merge any of the proposed soft pairs; they do not look like the same underlying issue or change.", "confidence": 0.89, - "canonical_issue_reason": "No single canonical issue fits the cluster well; the items cover many unrelated regressions across loading, tokenization, generation, device mapping, and model-specific behavior.", + "canonical_issue_reason": "issue:43653 is the most self-contained and concrete bug in the set, with clear tokenizer special-token behavior and nearby tokenizer-related similarities, making it the best anchor among otherwise unrelated reports.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 44466 is the most concrete, self-contained regression report and the closest thing to a representative bug, but it is still not a clear duplicate anchor for the rest of the set.", + "best_issue_reason": "issue:43653 is the best representative issue because it is narrowly scoped, reproducible, and more canonical than the broader config/training regressions in the cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44484", - "right": "issue:44704", - "accept": false, - "reason": "Different bugs: shard size default versus kwargs not forwarded to cached_file." - }, - { - "left": "issue:43697", - "right": "issue:45216", - "accept": false, - "reason": "Unrelated model regressions: RTDetr output drift vs Qwen3.5 checkpoint saving." - }, - { - "left": "issue:43531", - "right": "issue:44821", + "left": "issue:28282", + "right": "issue:29127", "accept": false, - "reason": "Different areas and failure modes: Qwen3-MoE sliding window vs AutoImageProcessor URL loading." + "reason": "Different problems: missing PyTorch import vs unclear LayoutLMv3 box-validation error." }, { "left": "issue:44514", "right": "issue:45381", "accept": false, - "reason": "Same model family, but different code paths: chat-template batching crash vs video position IDs." + "reason": "Both involve Qwen2.5-VL, but one is chat-template batching and the other is video position IDs; different code paths." }, { - "left": "issue:28282", - "right": "issue:29127", + "left": "issue:43582", + "right": "issue:44977", "accept": false, - "reason": "Completely unrelated: missing PyTorch import vs LayoutLMv3 box-content error messaging." + "reason": "Apple Silicon allocator TypeError vs Qwen3.5 flash-attention generation failure; unrelated bugs." }, { - "left": "issue:43582", - "right": "issue:44977", + "left": "issue:44625", + "right": "issue:44877", "accept": false, - "reason": "Different subsystems: Apple Silicon warmup TypeError vs Qwen3.5 flash-attention generation." + "reason": "Different config issues for different models; num_labels propagation is not the same as strict config loading." }, { "left": "issue:43643", "right": "issue:44561", "accept": false, - "reason": "Both involve trust_remote_code, but one is missing fields and the other is a v5 API removal breakage." + "reason": "Both touch trust_remote_code, but one is missing config fields and the other is removal of is_torch_fx_available; not the same bug." }, { - "left": "issue:44625", - "right": "issue:44877", + "left": "issue:42175", + "right": "issue:44938", "accept": false, - "reason": "Different model/config bugs: Qwen3.5 num_labels propagation vs granite_speech strict config loading." + "reason": "Dependency packaging issue vs Python 3.14 import failure; no shared underlying defect." }, { "left": "issue:43720", "right": "issue:44898", "accept": false, - "reason": "Unrelated failures: BitNet packed-weight loading vs Perceiver interpolation on non-default resolution." - }, - { - "left": "issue:42175", - "right": "issue:44938", - "accept": false, - "reason": "No overlap in bug mechanism: packaging backend composition vs Python 3.14 import/load failure." + "reason": "BitNet accelerate-loading/unpacking problem vs Perceiver interpolation failure; unrelated model paths." }, { "left": "issue:43452", "right": "issue:43577", "accept": false, - "reason": "Different problems: gguf_file loading breakage vs BLIP2 dtype propagation." + "reason": "gguf_file loading regression vs Blip2 dtype retention; different subsystems and symptoms." }, { "left": "issue:44514", "right": "issue:45290", "accept": false, - "reason": "Both touch apply_chat_template, but the crashes are triggered by different inputs and likely different fixes." + "reason": "Same processor family, but batching/padding crash is distinct from tool-call messages with empty content." }, { - "left": "issue:43452", - "right": "issue:44843", + "left": "issue:44466", + "right": "issue:45005", "accept": false, - "reason": "Tokenizer loading issues, but one is gguf_file handling and the other is offline Mistral regex patching." + "reason": "Both mention tied weights, but one is serialization behavior and the other is translation-model loading issues; not the same change." }, { - "left": "issue:44466", - "right": "issue:45005", + "left": "issue:43452", + "right": "issue:44843", "accept": false, - "reason": "Both mention tied weights in v5, but one is device-dependent lm_head serialization and the other is a translation-model report." + "reason": "gguf_file tokenizer/model loading issue vs offline model_info call in Mistral regex patch; unrelated." }, { "left": "issue:41762", "right": "issue:44936", "accept": false, - "reason": "Different failure classes: DeepSpeed ZeRO-3 load-time IndexError vs train/evaluate lifecycle failure." + "reason": "Gemma3 ZeRO-3 load failure vs trainer.evaluate after train; different failure modes." }, { "left": "issue:43295", "right": "issue:45356", "accept": false, - "reason": "Both are regressions, but they concern different processors/tokenizers and different symptoms." + "reason": "Processor/tokenizer regression vs Kimi codec-handling regression; same broad area but different bugs." }, { "left": "issue:43819", "right": "issue:44811", "accept": false, - "reason": "No shared code path: DAC latent reconstruction vs Whisper batch_decode skipping special tokens." + "reason": "DAC latent/forward mismatch vs Whisper batch_decode special-token handling; unrelated." }, { "left": "issue:43653", "right": "issue:44568", "accept": false, - "reason": "Both are special-token-related, but the underlying tokenizer bugs are different." + "reason": "Both tokenizer-special-token bugs, but different tokenizers and different missing-token behavior." + }, + { + "left": "issue:24643", + "right": "issue:29127", + "accept": false, + "reason": "DeepSpeed weight-dimension runtime error vs LayoutLMv3 box-content clarity issue; unrelated." }, { "left": "issue:44936", "right": "issue:45823", "accept": false, - "reason": "Unrelated: trainer post-train evaluation issue vs Gemma4 device-map forward mismatch." + "reason": "trainer.evaluate lifecycle issue vs Gemma4 device-map mismatch; different code paths." }, { - "left": "issue:24643", - "right": "issue:29127", + "left": "issue:30064", + "right": "issue:33666", "accept": false, - "reason": "Different errors and components: DeepSpeed training weight shape vs LayoutLMv3 error clarity." + "reason": "Void segmentation map processing vs Qwen2-VL multi-GPU training; not the same bug." }, { - "left": "issue:43653", - "right": "issue:44361", + "left": "issue:38175", + "right": "issue:43295", "accept": false, - "reason": "Different tokenizers and failures: BigBird special-token registration vs MLuke task-time AttributeError." + "reason": "siglip2 zero-probabilities issue vs processor/tokenizer regression; no concrete overlap." }, { "left": "issue:44361", "right": "issue:44442", "accept": false, - "reason": "Both tokenizer-related, but one is an AttributeError in tasks and the other is a tokenizer class loading failure." + "reason": "MLuke task AttributeError vs FastSpeech2ConformerTokenizer loading failure; unrelated tokenizer bugs." }, { - "left": "issue:30064", - "right": "issue:33666", + "left": "issue:43653", + "right": "issue:44361", "accept": false, - "reason": "Unrelated image-segmentation processor bug vs Qwen2-VL multi-GPU training issue." + "reason": "BigBird special-token decode bug vs MLuke task AttributeError; different models and code paths." }, { - "left": "issue:38175", - "right": "issue:43295", + "left": "issue:44464", + "right": "issue:44743", "accept": false, - "reason": "Different model families and symptoms: zero probabilities vs processor/tokenizer regression." + "reason": "Compiled-forward chunked generation inconsistency vs Qwen3-MoE recurrent-state reset; different generation issues." }, { "left": "issue:43577", "right": "issue:43697", "accept": false, - "reason": "Different regressions: BLIP2 dtype handling vs RTDetr output divergence." - }, - { - "left": "issue:44464", - "right": "issue:44743", - "accept": false, - "reason": "Both generation/cache-related, but one is compiled-forward chunked generation and the other is recurrent-state reset logic." + "reason": "Blip2 dtype mismatch vs RTDetrV2 output divergence; unrelated model behaviors." }, { "left": "issue:44843", "right": "issue:44991", "accept": false, - "reason": "Different tokenizer-loading regressions with different root causes and models." + "reason": "Offline hub/model_info regression vs tokenizer load failure for a specific model; not the same defect." }, { "left": "issue:41720", "right": "issue:43906", "accept": false, - "reason": "The second is only an isolated reproduction reference; the reported failures do not clearly match." + "reason": "Qwen3 auto device-map cuda assert vs isolated reproduction of another issue; no evidence of a shared root cause." }, { "left": "issue:44977", "right": "issue:45356", "accept": false, - "reason": "Unrelated: flash-attention generation failure vs tokenizer codec/warning regression." + "reason": "Flash-attention generation failure vs tokenizer codec regression; unrelated." }, { "left": "issue:43688", "right": "issue:45440", "accept": false, - "reason": "Both concern MoE models, but one is auxiliary-loss normalization and the other is DeepSeekV3 implementation parity." + "reason": "Both are MoE-related correctness issues, but auxiliary-loss normalization and DeepSeekV3 divergence are distinct concrete bugs." + }, + { + "left": "issue:43531", + "right": "issue:43742", + "accept": false, + "reason": "Qwen3-MoE sliding_window issue vs MobileLLM loading key error; unrelated." + }, + { + "left": "issue:43653", + "right": "issue:43927", + "accept": false, + "reason": "Tokenizer special-token bug vs config token-ID persistence bug; similar theme but different underlying problem." + }, + { + "left": "issue:44464", + "right": "issue:44977", + "accept": false, + "reason": "Compiled-forward output inconsistency vs flash-attention generation failure; different code paths." + }, + { + "left": "issue:43577", + "right": "issue:45588", + "accept": false, + "reason": "Blip2 dtype issue vs flash_attention s_aux=None crash; unrelated." + }, + { + "left": "issue:43550", + "right": "issue:43927", + "accept": false, + "reason": "torch.compile/SDPA failure vs DiaConfig save/load token-ID loss; different subsystems." + }, + { + "left": "issue:43550", + "right": "issue:44361", + "accept": false, + "reason": "Bamba compile failure vs MLuke tokenizer AttributeError; unrelated." } ] }, @@ -6181,12 +6187,11 @@ "issue:43493", "issue:43504", "issue:43525", - "issue:43531", + "issue:43540", "issue:43550", "issue:43572", "issue:43577", "issue:43606", - "issue:43653", "issue:43688", "issue:43720", "issue:43742", @@ -6204,288 +6209,213 @@ "issue:44821", "issue:44849", "issue:44913", + "issue:44964", "issue:44977", "issue:45325", "issue:45357", - "issue:45588", + "issue:45405", "issue:45704", "issue:45812" ], "soft_pairs": [ - "issue:43653|issue:43927", - "issue:43531|issue:43742", - "issue:44464|issue:44977", - "issue:43550|issue:43927", - "issue:43577|issue:45588", - "issue:43550|issue:44361", + "issue:32090|issue:34567", "issue:43504|issue:43550", "issue:43504|issue:43720", - "issue:32090|issue:34567", "issue:43122|issue:43906", - "issue:43504|issue:44610", "issue:32090|issue:33666", "issue:28282|issue:35141", + "issue:43504|issue:44610", "issue:43452|issue:44451", - "issue:44568|issue:45812", "issue:44849|issue:45357", + "issue:44568|issue:45812", "issue:43742|issue:44821", "issue:41720|issue:44464", + "issue:33666|issue:36010", + "issue:43525|issue:43572", "issue:43329|issue:45325", "issue:43688|issue:43749", - "issue:33666|issue:36010", - "issue:43756|issue:44913", "issue:43493|issue:43825", - "issue:43525|issue:43572", + "issue:43756|issue:44913", + "issue:43262|issue:43295", "issue:43606|issue:43927", "issue:43720|issue:43927", - "issue:43262|issue:43295", "issue:28282|issue:32090", "issue:28282|issue:33357", "issue:43577|issue:44554", - "issue:43720|issue:44361", - "issue:43334|issue:43572", "issue:33666|issue:36331", + "issue:43334|issue:43572", + "issue:39692|issue:43493", "issue:43688|issue:45704", - "issue:39692|issue:43493" + "issue:43720|issue:44361", + "issue:44964|issue:45405", + "issue:43540|issue:44977" ], - "prepared_review_unit_hash": "2998eb870105b853940b7dd2d85fd02b0233a995049b73b7b27ffb1fb03b4d90", + "prepared_review_unit_hash": "3aa6e0ba9d981cc2ef0075952ceb76cb3e016615e1d8c638bca72d8260453fbe", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 35, - "serialized_chars": 38457, - "estimated_input_tokens": 9615, - "estimated_eval_tokens": 19486 + "soft_pair_count": 31, + "serialized_chars": 37228, + "estimated_input_tokens": 9307, + "estimated_eval_tokens": 18870 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is highly heterogeneous: it mixes unrelated tokenizer, trainer, multimodal, config, and runtime issues. No pull requests are present. I would keep a tokenizer-regression issue as the most representative anchor, but the soft links do not look like true duplicates.", - "confidence": 0.83, - "canonical_issue_reason": "Issue 45812 is the strongest cluster anchor: it describes a broad, user-impacting tokenizer regression across all Granite models, with clear repro and recent activity. The rest of the cluster is too diverse to justify a narrower canonical choice.", + "summary": "This cluster is mostly heterogeneous: the soft edges are topical similarities, but none look like the same underlying bug or change. There are no PRs to compare. The strongest representative issue is the Granite tokenizer regression (#45812), because it is concrete, recent, and clearly actionable.", + "confidence": 0.47, + "canonical_issue_reason": "#45812 is the clearest, most actionable report here: it describes a concrete tokenizer regression with a specific model family, silent incorrect outputs, and real downstream impact. It is a better representative than the more speculative or niche issues in the cluster.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45812 is the best single representative of the cluster\u2019s most general pattern (silent tokenizer regression), and it is more broadly framed than the other tokenizer-specific reports.", + "best_issue_reason": "#45812 is the best standalone issue candidate because it has a well-scoped failure mode, clear reproduction context, and a broad user-facing regression signal. The rest of the cluster does not form a single duplicate family.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43653", - "right": "issue:43927", - "accept": false, - "reason": "Different bug classes: BigBird special-token decode issue vs. DiaConfig save/load token-ID loss." - }, - { - "left": "issue:43531", - "right": "issue:43742", - "accept": false, - "reason": "Both are model-loading/training failures, but they affect different models and different failure paths." - }, - { - "left": "issue:44464", - "right": "issue:44977", - "accept": false, - "reason": "Different generation regressions: compiled forward chunking vs flash-attention behavior in Qwen3.5." - }, - { - "left": "issue:43550", - "right": "issue:43927", - "accept": false, - "reason": "Bamba compile/SDPA failure is unrelated to DiaConfig token-ID persistence." - }, - { - "left": "issue:43577", - "right": "issue:45588", - "accept": false, - "reason": "Blip2 dtype-loading issue and flash_attention s_aux=None crash are distinct code paths." - }, - { - "left": "issue:43550", - "right": "issue:44361", + "left": "issue:32090", + "right": "issue:34567", "accept": false, - "reason": "Torch.compile/SDPA failure is unrelated to CustomTrainer.compute_loss signature mismatch." + "reason": "Different failures: GPU broadcast NoneType vs TrainerState token counter not updating. Same training area, not the same bug." }, { "left": "issue:43504", "right": "issue:43550", "accept": false, - "reason": "Legacy-field load failure for Beit is unrelated to Bamba compile/SDPA." + "reason": "Legacy-field preset loading bug vs torch.compile/SDPA failure in a specific model. Unrelated code paths." }, { "left": "issue:43504", "right": "issue:43720", "accept": false, - "reason": "Different model families and different loading failures; not the same underlying bug." - }, - { - "left": "issue:32090", - "right": "issue:34567", - "accept": false, - "reason": "Trainer broadcast TypeError and TrainerState token counter not updating are separate Trainer bugs." + "reason": "Both involve loading, but one is a legacy config field issue and the other is packed-weight unpacking during accelerate loading. Not the same defect." }, { "left": "issue:43122", "right": "issue:43906", "accept": false, - "reason": "43906 is only a reproduction pointer to another issue; no evidence it is the same tokenizer bug as 43122." - }, - { - "left": "issue:43504", - "right": "issue:44610", - "accept": false, - "reason": "Beit legacy-field loading issue is unrelated to OmDet-Turbo processor/model image-size mismatch." + "reason": "One is a tokenization regression across versions; the other is only a reproduction of a different issue. No evidence they share the same root cause." }, { "left": "issue:32090", "right": "issue:33666", "accept": false, - "reason": "Trainer GPU broadcast failure and Qwen2-VL multi-GPU training are different problems." + "reason": "Trainer broadcast error and multi-GPU training request are not the same problem." }, { "left": "issue:28282", "right": "issue:35141", "accept": false, - "reason": "PyTorch import error and embedding reinitialization in post_init are unrelated." + "reason": "ImportError about missing PyTorch is unrelated to embedding reinitialization after resize." }, { - "left": "issue:43452", - "right": "issue:44451", + "left": "issue:43504", + "right": "issue:44610", "accept": false, - "reason": "Both are load/import failures, but for different models and different root causes." + "reason": "Model preset loading vs processor image-size mismatch. Different bugs in different subsystems." }, { - "left": "issue:44568", - "right": "issue:45812", + "left": "issue:43452", + "right": "issue:44451", "accept": false, - "reason": "Both are tokenizer regressions, but one is missing BOS/EOS insertion for a specific tokenizer while the other is wrong token IDs for Granite models." + "reason": "Both are model/tokenizer loading failures, but the affected APIs and likely causes differ; not enough to merge as one bug." }, { "left": "issue:44849", "right": "issue:45357", "accept": false, - "reason": "Qwen3.5 hidden-states bug and save_pretrained visual-key regression are distinct issues." + "reason": "One is an output_hidden_states behavior bug; the other is incorrect save_pretrained visual encoder keys. Different regression surfaces." }, { - "left": "issue:43742", - "right": "issue:44821", - "accept": false, - "reason": "MobileLLM key error and AutoImageProcessor-from-URL loading are unrelated loading failures." - }, - { - "left": "issue:41720", - "right": "issue:44464", + "left": "issue:44568", + "right": "issue:45812", "accept": false, - "reason": "CUDA assert with auto device mapping is not the same as inconsistent chunked generation under compiled forward." + "reason": "Both are tokenizer regressions, but they affect different model families and different behaviors. Too broad to treat as the same bug." }, { - "left": "issue:43329", - "right": "issue:45325", + "left": "issue:43742", + "right": "issue:44821", "accept": false, - "reason": "Undefined helpers in multimodal token counting are unrelated to Qwen2.5-VL temporal position scaling." + "reason": "Key error loading a model is unrelated to loading an AutoImageProcessor from a URL." }, { - "left": "issue:43688", - "right": "issue:43749", + "left": "issue:41720", + "right": "issue:44464", "accept": false, - "reason": "Aux-loss normalization and FSDP CPU RAM efficient loading are different training/runtime problems." + "reason": "CUDA assert during auto device mapping and inconsistent chunked generation under compile are distinct failures." }, { "left": "issue:33666", "right": "issue:36010", "accept": false, - "reason": "Multi-GPU training request for Qwen2-VL and GenerationMixin import error do not share a concrete code path." - }, - { - "left": "issue:43756", - "right": "issue:44913", - "accept": false, - "reason": "Smollm3 RoPE-layer mismatch and GPTNeoX rotary_pct reload bug are different configuration issues." - }, - { - "left": "issue:43493", - "right": "issue:43825", - "accept": false, - "reason": "SigLIP2 HF-vs-JAX discrepancy is not the same as the pipeline() translation-task error message regression." + "reason": "Multi-GPU training issue and GenerationMixin import failure do not share a concrete root cause." }, { "left": "issue:43525", "right": "issue:43572", "accept": false, - "reason": "Similar symptom class, but different model configs and different missing fields (pad_token_id vs pad_token_idx)." + "reason": "Both are missing-config-field reports, but they concern different models and different fields. Similar pattern, not the same issue." }, { - "left": "issue:43606", - "right": "issue:43927", + "left": "issue:43329", + "right": "issue:45325", "accept": false, - "reason": "CPU offload device mismatch for bark-small is unrelated to DiaConfig token-ID loss." + "reason": "Video multimodal token counting bug vs still-image rope index scaling bug. Different branches and symptoms." }, { - "left": "issue:43720", - "right": "issue:44361", + "left": "issue:43688", + "right": "issue:43749", "accept": false, - "reason": "BitNet packed-weight loading failure is unrelated to CustomTrainer.compute_loss keyword mismatch." + "reason": "Aux-loss normalization and FSDP CPU RAM-efficient loading are unrelated." }, { - "left": "issue:43262", - "right": "issue:43295", + "left": "issue:43493", + "right": "issue:43825", "accept": false, - "reason": "Audio processor sampling-rate defaulting and processor.tokenizer regression are distinct processor bugs." + "reason": "SigLIP2 implementation discrepancy and pipeline translation-task error message are different topics entirely." }, { - "left": "issue:28282", - "right": "issue:32090", + "left": "issue:43756", + "right": "issue:44913", "accept": false, - "reason": "PyTorch import failure and Trainer broadcast NoneType error are unrelated." + "reason": "Both mention rotary-related settings, but one is a model architecture discrepancy and the other is a config reload defaulting issue. Not the same bug." }, { - "left": "issue:28282", - "right": "issue:33357", + "left": "issue:43262", + "right": "issue:43295", "accept": false, - "reason": "AutoModel import error and Mac bus error with CLIP on 4.43.0 are different failure modes." + "reason": "Audio sampling-rate defaulting and processor.tokenizer regression are separate processor-layer problems." }, { - "left": "issue:43577", - "right": "issue:44554", + "left": "issue:43606", + "right": "issue:43927", "accept": false, - "reason": "Blip2 dtype loading and MPS attention correctness issue are unrelated." + "reason": "CPU offload device mismatch and DiaConfig token-id loss are unrelated failures." }, { "left": "issue:43720", "right": "issue:44361", "accept": false, - "reason": "BitNet loading bug and Trainer compute_loss signature bug do not match." - }, - { - "left": "issue:43334", - "right": "issue:43572", - "accept": false, - "reason": "Qwen3-VL pad_token_id AttributeError and StableLm pad_token_idx regression are separate config issues." - }, - { - "left": "issue:33666", - "right": "issue:36331", - "accept": false, - "reason": "Qwen2-VL multi-GPU training and compute_loss num_items_in_batch error are different trainer/model workflows." + "reason": "Packed-weight loading bug and MLukeTokenizer AttributeError are different components and code paths." }, { - "left": "issue:43688", - "right": "issue:45704", + "left": "issue:44964", + "right": "issue:45405", "accept": false, - "reason": "Aux-loss normalization bug and T5 apex FusedRMSNorm memory leak are unrelated." + "reason": "Model loading failure and dependency version bump are not the same underlying bug." }, { - "left": "issue:39692", - "right": "issue:43493", + "left": "issue:43540", + "right": "issue:44977", "accept": false, - "reason": "SigLIP2 docs example errors are unrelated to the HF-vs-JAX implementation discrepancy." + "reason": "Video-input processing error in Qwen3OmniMoe and flash-attention generation bug in Qwen3.5 are distinct issues." } ] }, @@ -6509,6 +6439,8 @@ "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-390", "nodes": [ + "issue:29942", + "issue:30333", "issue:33357", "issue:33666", "issue:39692", @@ -6519,7 +6451,6 @@ "issue:43334", "issue:43493", "issue:43504", - "issue:43540", "issue:43572", "issue:43575", "issue:43606", @@ -6535,6 +6466,7 @@ "issue:44291", "issue:44361", "issue:44423", + "issue:44464", "issue:44466", "issue:44479", "issue:44488", @@ -6545,38 +6477,35 @@ "issue:44734", "issue:44792", "issue:44843", - "issue:44964", - "issue:44977", "issue:45083", "issue:45200", "issue:45229", "issue:45290", "issue:45405", "issue:45520", + "issue:45584", "issue:45701", "issue:45759", "issue:45823" ], "soft_pairs": [ - "issue:44964|issue:45405", - "issue:43540|issue:44977", - "issue:43493|issue:43844", "issue:44479|issue:44625", "issue:43334|issue:45759", - "issue:43756|issue:45083", + "issue:43493|issue:43844", "issue:45200|issue:45229", - "issue:43278|issue:43844", + "issue:43756|issue:45083", "issue:44488|issue:44843", "issue:43257|issue:43299", + "issue:43278|issue:43844", "issue:43646|issue:44466", "issue:43824|issue:44589", "issue:45229|issue:45823", - "issue:43688|issue:45701", "issue:44589|issue:45520", + "issue:43688|issue:45701", "issue:39692|issue:43295", - "issue:43504|issue:43606", "issue:33357|issue:33666", "issue:43572|issue:44291", + "issue:43504|issue:43606", "issue:44423|issue:44734", "issue:43927|issue:44361", "issue:43504|issue:43653", @@ -6585,204 +6514,206 @@ "issue:43606|issue:44112", "issue:44792|issue:45405", "issue:43994|issue:44493", - "issue:44521|issue:45290" + "issue:44521|issue:45290", + "issue:44464|issue:45584", + "issue:29942|issue:30333" ], - "prepared_review_unit_hash": "92add81809984e438cce90ae1c25a15039dc7e5caa6d952cc6aaa86fe397716d", + "prepared_review_unit_hash": "ed6aeb5db6aa5ca2ec6f148266c6f28228d6da7f73f66a0fab8b4707334252ea", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { - "node_count": 47, - "item_count": 47, + "node_count": 48, + "item_count": 48, "soft_pair_count": 28, - "serialized_chars": 35699, - "estimated_input_tokens": 8925, - "estimated_eval_tokens": 18106 + "serialized_chars": 36266, + "estimated_input_tokens": 9067, + "estimated_eval_tokens": 18390 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a grab-bag of unrelated model-loading, multimodal, tokenizer, and CI/runtime regressions. The only recurring theme is Qwen/multimodal config plumbing, but the soft-edge pairs still look like distinct bugs rather than mergeable duplicates.", - "confidence": 0.46, - "canonical_issue_reason": "issue:45759 is the most representative of the recurring Qwen multimodal config-loading theme and is a concrete, well-scoped regression that aligns with several nearby config-related reports.", + "summary": "These items are mostly unrelated single-issue reports. Several are in similar model families (Qwen, Gemma, SigLIP2), but the paired bugs are different concrete failure modes, so none of the soft duplicate candidates should be merged.", + "confidence": 0.95, + "canonical_issue_reason": "issue:44479 is a concrete regression report with a clear, specific failure mode and broad impact across multiple Qwen multimodal variants, making it the strongest representative issue in this set.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45759 is the best single representative because it captures a central, user-facing multimodal configuration bug rather than a narrow model-specific failure or a test/CI symptom.", + "best_issue_reason": "issue:44479 is the most self-contained and representative bug report here; the others are either narrowly scoped loading/config edge cases, CI flakes, or unrelated feature/regression reports.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:44964", - "right": "issue:45405", - "accept": false, - "reason": "Phi-4 multimodal loading vs an unreleased PEFT version bump; unrelated failures." - }, - { - "left": "issue:43540", - "right": "issue:44977", - "accept": false, - "reason": "Different Qwen models and different code paths: video preprocessing ValueError vs flash-attention generation behavior." - }, - { - "left": "issue:43493", - "right": "issue:43844", - "accept": false, - "reason": "SigLIP2 implementation mismatch and ZeRO-3 gradient growth are separate problems." - }, { "left": "issue:44479", "right": "issue:44625", "accept": false, - "reason": "Both are Qwen-related, but one is a video-input regression and the other is config propagation for num_labels; not the same bug." + "reason": "Both involve Qwen models, but one is a video-input regression and the other is config propagation for num_labels; different bug classes and code paths." }, { "left": "issue:43334", "right": "issue:45759", "accept": false, - "reason": "Both involve Qwen config/loading, but one is missing pad_token_id and the other is text_config unwrapping; distinct concrete failures." + "reason": "Both are Qwen multimodal loading issues, but one is a missing pad_token_id on text config and the other is from_config not unwrapping composite configs; not the same defect." }, { - "left": "issue:43756", - "right": "issue:45083", + "left": "issue:43493", + "right": "issue:43844", "accept": false, - "reason": "Smollm3 RoPE-layer issue and qwen3_omni_moe feature-length helper behavior are unrelated." + "reason": "SigLIP2 implementation discrepancy and ZeRO-3 gradient growth are unrelated problems." }, { "left": "issue:45200", "right": "issue:45229", "accept": false, - "reason": "Text-only mm_token_type_ids defaulting and Gemma4 multi-GPU OOM are different issues." + "reason": "Gemma4 token-type defaults and Gemma4 multi-GPU OOM are different issues with different symptoms and fixes." }, { - "left": "issue:43278", - "right": "issue:43844", + "left": "issue:43756", + "right": "issue:45083", "accept": false, - "reason": "Embedding dtype drift and ZeRO-3 gradient inflation are not the same underlying defect." + "reason": "Smollm3 RoPE-layer loss and qwen3_omni_moe feature-length helper behavior are unrelated model bugs." }, { "left": "issue:44488", "right": "issue:44843", "accept": false, - "reason": "Different model-loading failures: one specific model won't load, the other is an offline-mode bug in model_info calls." + "reason": "A model load failure for cjvt/sleng-bert is not the same as an offline-mode tokenizer patch issue." }, { "left": "issue:43257", "right": "issue:43299", "accept": false, - "reason": "Both mention Qwen3 MoE loading, but one is weight conversion with accelerate/deepspeed and the other is a dev-version load regression." + "reason": "Both mention Qwen3 MoE loading, but one is about accelerate+deepspeed weight conversion and the other about a dev-version config/loading regression; different concrete failures." + }, + { + "left": "issue:43278", + "right": "issue:43844", + "accept": false, + "reason": "Embedding dtype drift during evaluate is unrelated to the ZeRO-3 gradient anomaly." }, { "left": "issue:43646", "right": "issue:44466", "accept": false, - "reason": "Custom model init breakage and lm_head serialization inconsistency are separate bugs." + "reason": "Custom model init regression and lm_head serialization inconsistency are separate bugs." }, { "left": "issue:43824", "right": "issue:44589", "accept": false, - "reason": "Importing Qwen2.5-VL and Float8 storage lookup are unrelated failures." + "reason": "An import error for Qwen2.5-VL is unrelated to the missing Float8 storage type error." }, { "left": "issue:45229", "right": "issue:45823", "accept": false, - "reason": "Gemma4 OOM during inference vs device mismatch in forward pass are different concrete problems." - }, - { - "left": "issue:43688", - "right": "issue:45701", - "accept": false, - "reason": "Aux-loss normalization and tokenization changes do not share the same code path." + "reason": "Both are Gemma4 inference issues, but one is OOM and the other is a device mismatch during forward; not the same bug." }, { "left": "issue:44589", "right": "issue:45520", "accept": false, - "reason": "Float8 storage error and flash_attn import key error are unrelated." + "reason": "Different failures: missing Float8 storage support versus a flash_attn import_utils KeyError on Python 3.13." }, { - "left": "issue:39692", - "right": "issue:43295", + "left": "issue:43688", + "right": "issue:45701", "accept": false, - "reason": "Both touch multimodal/model-processor behavior, but one is a docs example mismatch and the other is a runtime API regression." + "reason": "Aux-loss normalization and tokenization-version changes are unrelated." }, { - "left": "issue:43504", - "right": "issue:43606", + "left": "issue:39692", + "right": "issue:43295", "accept": false, - "reason": "Legacy field loading for Beit and CPU-offload device mismatch for bark-small are unrelated." + "reason": "SigLIP2 doc example errors are not the same as a regression in processor.tokenizer/image handling." }, { "left": "issue:33357", "right": "issue:33666", "accept": false, - "reason": "MacOS CLIP bus error and Qwen2-VL multi-GPU training are completely different issues." + "reason": "A MacOS bus error for CLIP is unrelated to Qwen2-VL multi-GPU training." }, { "left": "issue:43572", "right": "issue:44291", "accept": false, - "reason": "Config missing pad_token_idx and unexpected _is_hf_initialized argument are both init/config regressions but not the same bug." + "reason": "Both are 5.0 compatibility regressions, but they affect different APIs and model-loading paths." + }, + { + "left": "issue:43504", + "right": "issue:43606", + "accept": false, + "reason": "Legacy-field loading for Beit and CPU-offload device mismatch for bark-small are unrelated." }, { "left": "issue:44423", "right": "issue:44734", "accept": false, - "reason": "Different serve crashes with different failure modes and tensor paths." + "reason": "Both are serve regressions, but one is multimodal input handling and the other is KV-cache continuation indexing; different code paths." }, { "left": "issue:43927", "right": "issue:44361", "accept": false, - "reason": "DiaConfig save/load token ID loss and MLukeTokenizer AttributeError are unrelated." + "reason": "DiaConfig save/load token-id loss and MLukeTokenizer task failures are not the same underlying bug." }, { "left": "issue:43504", "right": "issue:43653", "accept": false, - "reason": "Beit legacy field loading and BigBirdTokenizer special-token registration are different issues." + "reason": "Beit legacy-field loading and BigBirdTokenizer special-token registration are unrelated." }, { "left": "issue:43575", "right": "issue:45405", "accept": false, - "reason": "Tensor-parallel OOM and an unreleased dependency bump are unrelated." + "reason": "A tensor-parallel OOM and a dependency-version bump are entirely different issues." }, { "left": "issue:44625", "right": "issue:45759", "accept": false, - "reason": "Both are Qwen3.5 config-plumbing issues, but num_labels propagation and text_config unwrapping are different concrete bugs." + "reason": "These are related in theme, but one is num_labels propagation and the other is composite-config unwrapping in from_config; too different to treat as one duplicate." }, { "left": "issue:43606", "right": "issue:44112", "accept": false, - "reason": "A runtime device mismatch and a stale CI test are not the same underlying issue." + "reason": "A real device-mismatch bug is not the same as a stale CI test." }, { "left": "issue:44792", "right": "issue:45405", "accept": false, - "reason": "Janus image-generation test failure and PEFT version pinning are unrelated." + "reason": "A failing janus image-generation test is unrelated to the PEFT minimum-version bump." }, { "left": "issue:43994", "right": "issue:44493", "accept": false, - "reason": "SigLIP2 wrong outputs and unexpected position-id keys are distinct symptoms with different likely causes." + "reason": "SigLIP2 nonsensical outputs and unexpected position-id keys are different bugs with different failure modes." }, { "left": "issue:44521", "right": "issue:45290", "accept": false, - "reason": "Both are apply_chat_template bugs, but one is zeroed assistant masks and the other is a crash on tool-call messages; not the same defect." + "reason": "All-zero assistant masks and a crash on tool-call messages are distinct chat-template issues." + }, + { + "left": "issue:44464", + "right": "issue:45584", + "accept": false, + "reason": "Compiled-forward inconsistency and empty-transcription Whisper failure are unrelated." + }, + { + "left": "issue:29942", + "right": "issue:30333", + "accept": false, + "reason": "Flash Attention 2 test failures and MLflow job-reporting problems are unrelated." } ] }, @@ -6808,12 +6739,11 @@ "nodes": [ "issue:15354", "issue:28218", - "issue:29942", - "issue:30333", "issue:33357", "issue:34567", "issue:37428", "issue:38175", + "issue:42915", "issue:43232", "issue:43278", "issue:43295", @@ -6822,12 +6752,12 @@ "issue:43493", "issue:43525", "issue:43540", - "issue:43550", "issue:43572", "issue:43688", "issue:43701", "issue:43824", "issue:43844", + "issue:43856", "issue:43873", "issue:43957", "issue:43975", @@ -6839,6 +6769,7 @@ "issue:44610", "issue:44849", "issue:44898", + "issue:44936", "issue:44964", "issue:44987", "issue:45072", @@ -6851,15 +6782,12 @@ "issue:45412", "issue:45446", "issue:45520", - "issue:45584", "issue:45701", "issue:45823" ], "soft_pairs": [ - "issue:44464|issue:45584", - "issue:29942|issue:30333", - "issue:43844|issue:44964", "issue:28218|issue:34567", + "issue:43844|issue:44964", "issue:45084|issue:45520", "issue:44554|issue:45446", "issue:44568|issue:45701", @@ -6883,243 +6811,236 @@ "issue:43572|issue:44987", "issue:43572|issue:43957", "issue:43873|issue:44464", - "issue:43550|issue:43844", "issue:43295|issue:43450", + "issue:43844|issue:44936", "issue:43824|issue:43975", "issue:43295|issue:43873", "issue:38175|issue:45412", - "issue:37428|issue:43824" + "issue:37428|issue:43824", + "issue:43278|issue:43856", + "issue:42915|issue:43824" ], - "prepared_review_unit_hash": "c31a2cb39eb5d09fd25d29784987fb76e469f03377241c42b17362cf42bd053f", + "prepared_review_unit_hash": "edb404142f0c82fe857af4f35e30a4eafb756567749ba15b5c30541a80b60800", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { - "node_count": 48, - "item_count": 48, + "node_count": 47, + "item_count": 47, "soft_pair_count": 33, - "serialized_chars": 37688, - "estimated_input_tokens": 9422, - "estimated_eval_tokens": 19100 + "serialized_chars": 37104, + "estimated_input_tokens": 9276, + "estimated_eval_tokens": 18808 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly heterogeneous; nearly all pairs are unrelated regressions. The only plausible duplicate pair is the shared pad_token_id config-loading failure between 43334 and 43525.", - "confidence": 0.57, - "canonical_issue_reason": "Issue 43525 is the clearest concrete instance of the shared pad_token_id config regression and best represents the one plausible duplicate pair with 43334.", + "summary": "This cluster is highly heterogeneous: the soft-similarity pairs mostly connect unrelated tokenizer, training, loading, multimodal, import, and runtime bugs. I would not merge any of the candidate soft edges.", + "confidence": 0.87, + "canonical_issue_reason": "Issue 43873 is the broadest active bug with inbound references, but there is no true duplicate hub here because the cluster spans many unrelated failure modes.", "canonical_pr_reason": null, - "best_issue_reason": "43525 is the most specific, user-facing report of the missing pad_token_id AttributeError, so it is the best issue anchor for deduping the only close match.", + "best_issue_reason": "Issue 43873 is the most suitable representative thread only in a loose triage sense; it is open and has the strongest external interest, but it does not unify the rest of the items as duplicates.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44464", - "right": "issue:45584", - "accept": false, - "reason": "Different generation bugs: compiled-forward inconsistency vs Whisper empty-transcription handling." - }, - { - "left": "issue:29942", - "right": "issue:30333", + "left": "issue:28218", + "right": "issue:34567", "accept": false, - "reason": "Unrelated CI/test failure and MLflow job-status reporting bug." + "reason": "Tokenizer spacing vs TrainerState token-count tracking; unrelated bugs." }, { "left": "issue:43844", "right": "issue:44964", "accept": false, - "reason": "ZeRO-3 gradient abnormality vs model loading failure; different code paths." - }, - { - "left": "issue:28218", - "right": "issue:34567", - "accept": false, - "reason": "Tokenizer spacing bug vs TrainerState token counter not updating." + "reason": "ZeRO-3 gradient growth vs Phi-4 model loading failure; different code paths." }, { "left": "issue:45084", "right": "issue:45520", "accept": false, - "reason": "Template/compile error and flash_attn import error are unrelated." + "reason": "Compile/template-node error vs flash_attn import guard; unrelated." }, { "left": "issue:44554", "right": "issue:45446", "accept": false, - "reason": "MPS attention correctness issue vs PyTorch version check bug in flex_attention." + "reason": "MPS attention correctness bug vs PyTorch version-check/import bug; not the same issue." }, { "left": "issue:44568", "right": "issue:45701", "accept": false, - "reason": "Both involve tokenization, but the model/symptom differ too much to be the same bug." + "reason": "Specific add_special_tokens regression vs broad tokenizer-version change report; too different." }, { "left": "issue:43688", "right": "issue:43873", "accept": false, - "reason": "Aux loss normalization bug vs quantization/offloading behavior." + "reason": "Aux-loss normalization and quantized offloading are unrelated." }, { "left": "issue:15354", "right": "issue:38175", "accept": false, - "reason": "TorchScript GeneratorExp export issue vs SigLIP2 zero-probability regression." + "reason": "TorchScript export limitation vs SigLIP2 zero-probability bug; unrelated." }, { "left": "issue:43540", "right": "issue:45200", "accept": false, - "reason": "Video-input processing error vs Gemma4 mm_token_type_ids defaulting issue." + "reason": "Video processing ValueError vs Gemma4 fine-tuning token-ID requirement; different failures." }, { "left": "issue:43232", "right": "issue:44849", "accept": false, - "reason": "Generation kwargs update bug vs Qwen3.5 hidden_states output bug." + "reason": "Generation kwarg update after sync_gpus vs hidden-states output bug; different paths." }, { "left": "issue:45200", "right": "issue:45823", "accept": false, - "reason": "Same model family, but the failures are different: token-type ids vs device-map forward mismatch." + "reason": "Same model family, but mm_token_type_ids defaulting and device mismatch are distinct bugs." }, { "left": "issue:45072", "right": "issue:45198", "accept": false, - "reason": "Dtype mismatch CI issue vs Wav2Vec2 save_pretrained/tokenization failure." + "reason": "bfloat16 dtype mismatch in inference vs Wav2Vec2 save/tokenization failure; unrelated." }, { "left": "issue:44315", "right": "issue:44849", "accept": false, - "reason": "Liger kernel application bug and hidden_states bug are unrelated." + "reason": "model_init/Liger application issue vs Qwen3.5 hidden-states bug; unrelated." }, { "left": "issue:43278", "right": "issue:43701", "accept": false, - "reason": "Embedding dtype drift vs resume_from_checkpoint key mismatch." + "reason": "BF16-to-FP32 eval dtype drift vs checkpoint key mismatch; unrelated." }, { "left": "issue:28218", "right": "issue:33357", "accept": false, - "reason": "Tokenizer spacing issue vs Mac bus error on CLIP model loading." + "reason": "Tokenizer added-space bug vs CLIP bus error on macOS; unrelated." }, { "left": "issue:44554", "right": "issue:45356", "accept": false, - "reason": "MPS attention correctness issue vs Kimi tokenizer codec regression." + "reason": "MPS attention bug vs Kimi tokenizer regression; unrelated." }, { "left": "issue:45200", "right": "issue:45325", "accept": false, - "reason": "Different multimodal tensor semantics: Gemma4 token-type ids vs Qwen2.5-VL rope indexing." + "reason": "Gemma4 token-ID fine-tuning issue vs Qwen2.5-VL rope indexing bug; unrelated." }, { "left": "issue:44466", "right": "issue:45127", "accept": false, - "reason": "Both mention tied weights, but one is serialization/device-dependent and the other is LoRA-merge collapse." + "reason": "Serialization/tied-weights inconsistency vs LoRA merge collapse; similar area but not the same bug." }, { "left": "issue:43295", "right": "issue:44610", "accept": false, - "reason": "Processor/tokenizer regression vs wrong default image resolution." + "reason": "Processor.tokenizer regression vs video-input size mismatch; different code paths." }, { "left": "issue:44898", "right": "issue:45412", "accept": false, - "reason": "Perceiver resolution failure vs RT-DETR memory leak." + "reason": "Perceiver resolution failure vs RT-DETR memory leak; unrelated." }, { "left": "issue:43334", "right": "issue:43525", - "accept": true, - "reason": "Both report the same missing pad_token_id config regression causing model loading AttributeErrors across different model classes." + "accept": false, + "reason": "Both mention pad_token_id, but they affect different model configs and load paths." }, { "left": "issue:37428", "right": "issue:43957", "accept": false, - "reason": "Flash-attn import failure vs meta-device model-loading breakage." + "reason": "Flash-attn import error vs meta-device loading breakage; unrelated." }, { "left": "issue:43572", "right": "issue:44987", "accept": false, - "reason": "Missing pad_token_idx in StableLmConfig is not the same as a broad transformers>=5.1 loading failure." + "reason": "StableLmConfig pad_token_idx regression vs unrelated model-loading failure." }, { "left": "issue:43572", "right": "issue:43957", "accept": false, - "reason": "These are different regressions with different failure modes and models." + "reason": "Missing pad_token_idx in StableLmConfig vs meta-device loading breakage; unrelated." }, { "left": "issue:43873", "right": "issue:44464", "accept": false, - "reason": "Quantization offloading behavior vs compiled-forward generation inconsistency." + "reason": "Quantized offloading vs compiled-forward chunked generation; unrelated." }, { - "left": "issue:43550", - "right": "issue:43844", + "left": "issue:43295", + "right": "issue:43450", "accept": false, - "reason": "torch.compile/SDPA failure vs ZeRO-3 gradient blow-up." + "reason": "Processor.tokenizer/images regression vs batched video-shape bug; different issues." }, { - "left": "issue:43295", - "right": "issue:43450", + "left": "issue:43844", + "right": "issue:44936", "accept": false, - "reason": "Different processor bugs: tokenizer/image handling vs batched video shape output." + "reason": "ZeRO-3 gradient anomaly vs trainer.evaluate() after train() failure; unrelated." }, { "left": "issue:43824", "right": "issue:43975", "accept": false, - "reason": "Import failure for Qwen2.5-VL class vs DeepSeek detokenization regression." + "reason": "ImportError for a VL class vs DeepSeek detokenization regression; unrelated." }, { "left": "issue:43295", "right": "issue:43873", "accept": false, - "reason": "Processor regression and quantization offloading issue are unrelated." + "reason": "Processor/tokenizer regression vs quantization offloading bug; unrelated." }, { "left": "issue:38175", "right": "issue:45412", "accept": false, - "reason": "SigLIP2 probability bug vs RT-DETR garbage-collection leak." + "reason": "SigLIP2 probability issue vs RT-DETR memory-release bug; unrelated." }, { "left": "issue:37428", "right": "issue:43824", "accept": false, - "reason": "Flash-attn import error and missing Qwen2.5-VL import are different problems." + "reason": "Different missing-import failures in different modules; not the same bug." + }, + { + "left": "issue:42915", + "right": "issue:43824", + "accept": false, + "reason": "FP8 config failure vs Qwen2.5-VL import failure; unrelated." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The summary is well grounded in the packet and stays conservative overall. The only accepted pair, 43334/43525, is supported by the shared pad_token_id AttributeError pattern in the titles, and the other soft-edge rejections are appropriately cautious rather than overstated." - }, - "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 }, @@ -7138,22 +7059,23 @@ "nodes": [ "issue:37428", "issue:38175", - "issue:42915", + "issue:39692", + "issue:43262", "issue:43278", "issue:43335", + "issue:43388", "issue:43425", "issue:43450", "issue:43493", + "issue:43526", "issue:43550", "issue:43575", "issue:43606", "issue:43611", "issue:43653", "issue:43819", - "issue:43824", "issue:43825", "issue:43827", - "issue:43856", "issue:43901", "issue:43931", "issue:44112", @@ -7182,241 +7104,255 @@ "issue:45584", "issue:45588", "issue:45593", - "issue:45834" + "issue:45823" ], "soft_pairs": [ - "issue:43278|issue:43856", "issue:44514|issue:44521", - "issue:42915|issue:43824", "issue:44442|issue:45198", "issue:38175|issue:43493", "issue:43827|issue:43901", "issue:43653|issue:44112", "issue:43450|issue:43493", + "issue:43450|issue:43575", "issue:44792|issue:45563", "issue:44360|issue:44561", - "issue:43450|issue:43575", "issue:45127|issue:45245", "issue:43819|issue:45083", "issue:44206|issue:45584", "issue:43819|issue:44112", - "issue:43450|issue:45834", + "issue:43262|issue:43450", "issue:44610|issue:44857", "issue:37428|issue:43425", "issue:44857|issue:45593", "issue:43278|issue:43825", - "issue:43606|issue:45083", - "issue:43335|issue:43550", "issue:45290|issue:45381", + "issue:43606|issue:45083", "issue:45200|issue:45588", + "issue:43335|issue:43550", "issue:44448|issue:44743", "issue:37428|issue:44351", "issue:43611|issue:43931", + "issue:39692|issue:43526", "issue:44561|issue:44779", - "issue:44462|issue:44561" + "issue:44462|issue:44561", + "issue:44206|issue:45823", + "issue:43388|issue:43526", + "issue:43335|issue:43653" ], - "prepared_review_unit_hash": "9e15eafff074840d447c9b3f441db51411a19f25af702ae0d0e9144da6fbb5ad", + "prepared_review_unit_hash": "6776169d6a956f50038302a2f9db6a982a8d75c552581e622f21565e6bf50cd2", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 29, - "serialized_chars": 35677, - "estimated_input_tokens": 8920, - "estimated_eval_tokens": 18096 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37070, + "estimated_input_tokens": 9268, + "estimated_eval_tokens": 18792 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is a mixed bag of unrelated Transformers bug reports and regressions. Several items share broad themes like import/load breakages, chat-template issues, or model-specific failures, but none are the same concrete bug.", - "confidence": 0.86, - "canonical_issue_reason": null, + "summary": "This is not a true duplicate cluster: the soft pairs span unrelated bugs, regressions, docs issues, tokenizer/model problems, and CI failures. I would reject all soft edges; issue 44521 is only the closest representative because it is the most active open item, not because it duplicates the others.", + "confidence": 0.79, + "canonical_issue_reason": "Issue 44521 is the closest representative of the set only because it is open, high-activity, and user-facing; however, the surrounding items are too heterogeneous to form a real duplicate group.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43824 is the strongest representative by signal (high discussion and inbound references) and frames a broad import-regression, but the cluster is too heterogeneous to treat it as a true canonical duplicate anchor.", + "best_issue_reason": "Issue 44521 is the best standalone anchor among these items due to the highest discussion/inbound activity and a broadly relevant apply_chat_template bug, but it does not subsume the rest.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:43278", - "right": "issue:43856", - "accept": false, - "reason": "Both involve Qwen3 MoE, but one is an embedding dtype mismatch and the other is training memory usage; different failures." - }, { "left": "issue:44514", "right": "issue:44521", "accept": false, - "reason": "Both touch chat template/batched multimodal flows, but one crashes on padding=False and the other returns empty assistant masks; not the same bug." - }, - { - "left": "issue:42915", - "right": "issue:43824", - "accept": false, - "reason": "Different models and code paths: FineGrainedFP8Config failure vs an import error for Qwen2.5-VL." + "reason": "Both involve chat-template paths, but one is a batched crash and the other is an all-zero mask bug; different symptoms and likely different fixes." }, { "left": "issue:44442", "right": "issue:45198", "accept": false, - "reason": "Tokenizer loading for FastSpeech2Conformer is unrelated to Wav2Vec2 save/tokenization failures." + "reason": "Different models and different failure modes: AutoTokenizer loading vs save_pretrained/tokenization failure." }, { "left": "issue:38175", "right": "issue:43493", "accept": false, - "reason": "Both mention SigLIP2, but one reports zero probabilities while the other is a JAX-vs-HF implementation discrepancy; not the same concrete defect." + "reason": "Both mention SigLIP2, but one is zero probabilities and the other is an HF-vs-JAX discrepancy; not enough to treat as the same bug." }, { "left": "issue:43827", "right": "issue:43901", "accept": false, - "reason": "Both are docs-related, but they concern different pipeline deprecations and behaviors." + "reason": "Both are docs-related, but they cover different pipeline deprecations and different API details." }, { "left": "issue:43653", "right": "issue:44112", "accept": false, - "reason": "Different CI/test issues: BigBirdTokenizer special-token decoding vs a stale device override test in GraniteSpeech." + "reason": "Unrelated: tokenizer special-token registration vs a GraniteSpeech CI device-override test failure." }, { "left": "issue:43450", "right": "issue:43493", "accept": false, - "reason": "Unrelated problems: batched video processor shape vs SigLIP2 output mismatch." + "reason": "Video batching shape bug vs SigLIP2 implementation discrepancy; different subsystems and symptoms." + }, + { + "left": "issue:43450", + "right": "issue:43575", + "accept": false, + "reason": "Unrelated: video processor shape issue vs Qwen2 TP load OOM." }, { "left": "issue:44792", "right": "issue:45563", "accept": false, - "reason": "Different generate-path issues: a Janus image-generation test failure vs a stale warning in paged generate()." + "reason": "Janus image generation test failure and a paged-generate warning are different code paths and failures." }, { "left": "issue:44360", "right": "issue:44561", "accept": false, - "reason": "No shared bug: one is a DSA indexer discussion, the other is a v5 trust_remote_code breakage from a removed helper." - }, - { - "left": "issue:43450", - "right": "issue:43575", - "accept": false, - "reason": "Video processor shape bug and tensor-parallel OOM are different issues." + "reason": "Different areas entirely: DSA indexer discussion vs removal of is_torch_fx_available breaking trust_remote_code." }, { "left": "issue:45127", "right": "issue:45245", "accept": false, - "reason": "LoRA/tied-embeddings collapse is unrelated to the categories-limit runtime error." + "reason": "LoRA/extended-vocab collapse and category-cardinality overflow are unrelated bugs." }, { "left": "issue:43819", "right": "issue:45083", "accept": false, - "reason": "Different helper/model bugs in different architectures; not the same underlying defect." + "reason": "DAC from_latents mismatch is unrelated to the qwen3_omni_moe feature-length helper behavior." }, { "left": "issue:44206", "right": "issue:45584", "accept": false, - "reason": "Audio feature extractor crash from unsupported args is unrelated to Whisper empty-transcription generation failure." + "reason": "Laser feature-extractor center-arg crash vs Whisper empty-transcription failure are different issues." }, { "left": "issue:43819", "right": "issue:44112", "accept": false, - "reason": "DAC latent mismatch and GraniteSpeech CI device override are unrelated." + "reason": "No shared code path: DAC latent conversion vs GraniteSpeech CI device override." }, { - "left": "issue:43450", - "right": "issue:45834", + "left": "issue:43262", + "right": "issue:43450", "accept": false, - "reason": "Batched video-shape handling and Kosmos2.5 OCR index errors are different code paths." + "reason": "Audio chat-template sampling-rate default and video batching shape are unrelated." }, { "left": "issue:44610", "right": "issue:44857", "accept": false, - "reason": "Both are vision/detection bugs, but one is a processor size mismatch and the other is an AMP/CUDA loss crash." + "reason": "Processor input-size mismatch vs float16 AMP CUDA crash; different layers of the stack." }, { "left": "issue:37428", "right": "issue:43425", "accept": false, - "reason": "An ImportError for a missing flash-attention symbol is not the same as a general Torch 2.10 incompatibility report." + "reason": "ImportError for a missing flash-attention helper is not the same concrete bug as general Torch 2.10 incompatibility." }, { "left": "issue:44857", "right": "issue:45593", "accept": false, - "reason": "Different D-FINE/LwDetr failures: AMP crash vs missing auxiliary losses." + "reason": "AMP/CUDA crash and missing auxiliary losses are unrelated model-training bugs." }, { "left": "issue:43278", "right": "issue:43825", "accept": false, - "reason": "Embedding dtype drift and an incorrect pipeline error message are unrelated." + "reason": "Embedding dtype drift is unrelated to a pipeline docs/error-message regression." }, { - "left": "issue:43606", - "right": "issue:45083", - "accept": false, - "reason": "CPU offload device mismatch and a Qwen3 Omni helper behavior issue are different bugs." - }, - { - "left": "issue:43335", - "right": "issue:43550", + "left": "issue:45290", + "right": "issue:45381", "accept": false, - "reason": "SwitchTransformers config misbuild and Bamba torch.compile/SDPA failure do not share the same code path." + "reason": "One is a chat-template tool-call crash; the other is a video vision_position_ids bug." }, { - "left": "issue:45290", - "right": "issue:45381", + "left": "issue:43606", + "right": "issue:45083", "accept": false, - "reason": "Chat-template tool-call crash and Qwen2.5-VL video position-id bug are separate multimodal issues." + "reason": "CPU offload device mismatch and qwen3_omni_moe feature-length behavior are unrelated." }, { "left": "issue:45200", "right": "issue:45588", "accept": false, - "reason": "Gemma 4 token-type defaults and flash_attention sinkless-model AttributeError are unrelated." + "reason": "Gemma4 mm_token_type_ids defaulting and flash_attention s_aux handling are different bugs in different components." + }, + { + "left": "issue:43335", + "right": "issue:43550", + "accept": false, + "reason": "SwitchTransformers sparse-layer construction and Bamba torch.compile/SDPA failure are unrelated." }, { "left": "issue:44448", "right": "issue:44743", "accept": false, - "reason": "Pegasus v4/v5 output drift is unrelated to Qwen3_5 recurrent-state cache reset behavior." + "reason": "Pegasus v4/v5 output drift and qwen3_5 recurrent-state reset are different model-specific issues." }, { "left": "issue:37428", "right": "issue:44351", "accept": false, - "reason": "Both are ImportErrors, but for different missing symbols and different features." + "reason": "Both are import errors, but they miss different symbols in different places and do not point to one shared fix." }, { "left": "issue:43611", "right": "issue:43931", "accept": false, - "reason": "Base-model-prefix loading breakage and Qwen3-VL weight-shape mismatch are distinct model-loading failures." + "reason": "Base-model-prefix loading breakage and Qwen3-VL weight-shape mismatch are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:43526", + "accept": false, + "reason": "SigLIP2 doc/example problems and BeitImageProcessorFast reduce_labels behavior are different issues." }, { "left": "issue:44561", "right": "issue:44779", "accept": false, - "reason": "A removed helper breaking trust_remote_code is unrelated to Deepseek tokenizer output regression." + "reason": "trust_remote_code breakage from a removed helper is unrelated to DeepSeek tokenizer correctness." }, { "left": "issue:44462", "right": "issue:44561", "accept": false, - "reason": "Tokenizer.json being ignored is a different bug from the removed-is_torch_fx_available regression." + "reason": "Tokenizer.json loading behavior and is_torch_fx_available removal are different failures." + }, + { + "left": "issue:44206", + "right": "issue:45823", + "accept": false, + "reason": "Different Gemma/feature-extractor device issues with different code paths and symptoms." + }, + { + "left": "issue:43388", + "right": "issue:43526", + "accept": false, + "reason": "Distributed metric gathering label truncation is not the same as BeitImageProcessorFast reduce_labels returning only one label." + }, + { + "left": "issue:43335", + "right": "issue:43653", + "accept": false, + "reason": "SwitchTransformers sparse-layer config bug and BigBirdTokenizer special-token registration are unrelated." } ] }, @@ -7446,22 +7382,23 @@ "issue:32090", "issue:34689", "issue:35141", + "issue:36010", + "issue:37428", "issue:38175", "issue:39692", + "issue:40444", "issue:43335", - "issue:43388", + "issue:43412", "issue:43504", "issue:43526", "issue:43550", "issue:43606", - "issue:43653", "issue:43701", "issue:43720", "issue:43819", + "issue:43873", "issue:43927", "issue:44112", - "issue:44162", - "issue:44206", "issue:44292", "issue:44448", "issue:44493", @@ -7474,6 +7411,7 @@ "issue:45083", "issue:45198", "issue:45229", + "issue:45245", "issue:45310", "issue:45372", "issue:45459", @@ -7485,277 +7423,296 @@ "issue:45593", "issue:45698", "issue:45712", - "issue:45803", - "issue:45823", - "issue:45834" + "issue:45803" ], "soft_pairs": [ - "issue:39692|issue:43526", - "issue:44206|issue:45823", - "issue:43388|issue:43526", - "issue:43335|issue:43653", "issue:45310|issue:45478", "issue:43819|issue:44493", + "issue:29942|issue:32090", "issue:43550|issue:44112", "issue:44855|issue:45083", - "issue:43335|issue:45083", "issue:43335|issue:43504", - "issue:29942|issue:32090", + "issue:43335|issue:45083", "issue:39692|issue:44493", "issue:44292|issue:45520", "issue:44448|issue:44779", "issue:38175|issue:44493", "issue:28218|issue:35141", - "issue:44162|issue:45834", "issue:43335|issue:45072", "issue:43720|issue:44112", "issue:43335|issue:45593", "issue:44977|issue:45229", - "issue:44568|issue:45491", "issue:44448|issue:44977", - "issue:45459|issue:45712", + "issue:44568|issue:45491", "issue:43606|issue:44857", + "issue:45459|issue:45712", "issue:44857|issue:45072", "issue:29127|issue:32090", - "issue:43927|issue:45698", "issue:45198|issue:45803", + "issue:43927|issue:45698", "issue:44977|issue:45563", + "issue:34689|issue:35141", "issue:45372|issue:45588", + "issue:40444|issue:43526", "issue:43701|issue:45083", - "issue:34689|issue:35141" + "issue:43550|issue:45083", + "issue:43412|issue:45588", + "issue:45245|issue:45563", + "issue:29942|issue:35141", + "issue:43873|issue:44493", + "issue:36010|issue:37428", + "issue:45372|issue:45459" ], - "prepared_review_unit_hash": "0dd30ea4ab1f777d3dcbce1fcdc88c1f31d4c8cec5092326ec66291f6b326213", + "prepared_review_unit_hash": "970963853e7ef349ca114f33ae30a73e4db994a43e4971447a2ba06eef13b5b9", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 33, - "serialized_chars": 37843, - "estimated_input_tokens": 9461, - "estimated_eval_tokens": 19178 + "soft_pair_count": 36, + "serialized_chars": 38716, + "estimated_input_tokens": 9679, + "estimated_eval_tokens": 19614 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Most items are unrelated bug reports. The only clear duplicate pair is the repeated Qwen3.5 MoE `from_pretrained` regression (45310/45478), which should be merged; the rest are distinct issues across different models, subsystems, or failure modes.", - "confidence": 0.97, - "canonical_issue_reason": "issue:45310 is the earlier, more detailed report of the duplicate Qwen3.5 MoE `from_pretrained` error; issue:45478 repeats the same problem with a shorter body.", + "summary": "This cluster is mostly a set of loosely related transformer/model bug reports with one clear exact duplicate pair. Most soft matches are false positives based on broad keyword similarity rather than the same underlying defect.", + "confidence": 0.74, + "canonical_issue_reason": "issue:45310 is the clearest representative of the one real duplicate pair: it\u2019s the earlier, concrete report and matches issue:45478 by title and failure mode exactly.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45310 is the best issue candidate in this set because it is the clearest canonical target for the one true duplicate pair and has the fuller initial report.", + "best_issue_reason": "issue:45310 is the best issue anchor because it is a precise, concrete bug report with an exact duplicate counterpart and the strongest evidence of true duplication in the cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:39692", - "right": "issue:43526", - "accept": false, - "reason": "Different components and failures: SigLIP2 doc example errors vs. BEiT fast image processor label reduction." - }, - { - "left": "issue:44206", - "right": "issue:45823", - "accept": false, - "reason": "Both involve runtime failures, but one is an unsupported argument crash in a feature extractor and the other is a device-mismatch bug in Gemma4 PLE forward." - }, - { - "left": "issue:43388", - "right": "issue:43526", - "accept": false, - "reason": "Unrelated logic: metric gathering drops labels in the last batch, while BEiT fast processor reduces labels incorrectly." - }, - { - "left": "issue:43335", - "right": "issue:43653", - "accept": false, - "reason": "Different subsystems and symptoms: SwitchTransformers sparse-layer construction vs. BigBirdTokenizer mask-token registration." - }, { "left": "issue:45310", "right": "issue:45478", "accept": true, - "reason": "Same exact bug report: identical Qwen3.5 MoE `from_pretrained` regression under transformers>=5.4.0." + "reason": "Exact duplicate: same Qwen3.5 MoE from_pretrained error, same title and underlying failure." }, { "left": "issue:43819", "right": "issue:44493", "accept": false, - "reason": "Different model/code paths: DAC latent decoding mismatch vs. many models showing unexpected position-id key issues." + "reason": "Different bug classes: DAC forward/latents mismatch vs position-id unexpected key handling." }, { - "left": "issue:43550", - "right": "issue:44112", + "left": "issue:29942", + "right": "issue:32090", "accept": false, - "reason": "One is a real Bamba compile/SDPA failure; the other is a stale CI test about GraniteSpeech device overrides." + "reason": "Unrelated failures: Flash Attention 2 tests vs Trainer GPU broadcast NoneType error." }, { - "left": "issue:44855", - "right": "issue:45083", + "left": "issue:43550", + "right": "issue:44112", "accept": false, - "reason": "Different failures: Python 3.13 import/IndentationError in DebertaV2Model vs. a helper-length computation issue in qwen3_omni_moe." + "reason": "Different models and failure paths: torch.compile/SDPA vs CI stale device override test." }, { - "left": "issue:43335", + "left": "issue:44855", "right": "issue:45083", "accept": false, - "reason": "Both are model internals, but the bugs are unrelated: SwitchTransformers sparse-layer config vs. qwen3_omni_moe feature-length helper behavior." + "reason": "Different code paths: Python 3.13 import/parsing error vs feature-extract output length helper behavior." }, { "left": "issue:43335", "right": "issue:43504", "accept": false, - "reason": "Different code paths and outcomes: SwitchTransformers config creation vs. BEiT semantic-segmentation pretrained loading with a legacy field." + "reason": "Different models and bugs: SwitchTransformers sparse layer creation vs BEiT pretrained preset loading." }, { - "left": "issue:29942", - "right": "issue:32090", + "left": "issue:43335", + "right": "issue:45083", "accept": false, - "reason": "Unrelated problems: Flash Attention 2 test failures vs. Trainer broadcasting a NoneType." + "reason": "No shared underlying defect; config construction bug vs helper output-length behavior." }, { "left": "issue:39692", "right": "issue:44493", "accept": false, - "reason": "Doc-example/model-processor mismatch and quantization issues are not the same as the generic unexpected position-id key regression." + "reason": "Docs/example errors and model/processor mismatch are not the same as unexpected position-id keys." }, { "left": "issue:44292", "right": "issue:45520", "accept": false, - "reason": "Both mention modern runtime environments, but one is Qwen-3 NVFP4 execution and the other is a Python 3.13 `flash_attn` import key error." + "reason": "Different failures: Qwen-3-8B-NVFP4 runtime issue vs flash_attn import KeyError on Python 3.13." }, { "left": "issue:44448", "right": "issue:44779", "accept": false, - "reason": "Different models and bug classes: Pegasus v4/v5 output drift vs. Deepseek tokenizer regressions in v5." + "reason": "Both concern model behavior changes across versions, but they are different models and distinct regressions." }, { "left": "issue:38175", "right": "issue:44493", "accept": false, - "reason": "SigLIP2 zero-probability outputs are not the same underlying issue as broad unexpected position-id key warnings." + "reason": "Different symptoms and likely causes: zero probabilities vs unexpected position-id keys." }, { "left": "issue:28218", "right": "issue:35141", "accept": false, - "reason": "Tokenizer spacing after added token is unrelated to embedding reinitialization after resizing with untied word embeddings." - }, - { - "left": "issue:44162", - "right": "issue:45834", - "accept": false, - "reason": "ESM2 model breakage is unrelated to Kosmos2.5 long-OCR index errors." + "reason": "Tokenizer spacing after added tokens is unrelated to output embedding reinitialization on resize." }, { "left": "issue:43335", "right": "issue:45072", "accept": false, - "reason": "Different failure modes in different model families: SwitchTransformers config bug vs. dtype mismatch in inference for SwitchTransformers/TimmWrapperModel." + "reason": "Different bugs: sparse-layer construction vs dtype mismatches in bfloat16 inference." }, { "left": "issue:43720", "right": "issue:44112", "accept": false, - "reason": "BitNet packed-weight loading bug is unrelated to a GraniteSpeech stale device-override CI test." + "reason": "Packed-weight loading failure is unrelated to a stale CI device override test." }, { "left": "issue:43335", "right": "issue:45593", "accept": false, - "reason": "SwitchTransformers sparse-layer config bug is unrelated to D-FINE not using auxiliary losses when denoising is off." + "reason": "Different models and behavior: SwitchTransformers config bug vs D-FINE auxiliary-loss handling." }, { "left": "issue:44977", "right": "issue:45229", "accept": false, - "reason": "Qwen3.5 flash-attention generation bug and Gemma4 multi-GPU CUDA OOM are different problems." - }, - { - "left": "issue:44568", - "right": "issue:45491", - "accept": false, - "reason": "Tokenizer special-token behavior is unrelated to Gemma3 NaN embeddings with mixed-length batching." + "reason": "Flash-attention generation issue is unrelated to a multi-GPU CUDA OOM." }, { "left": "issue:44448", "right": "issue:44977", "accept": false, - "reason": "Different model families and symptoms: Pegasus output differences vs. Qwen3.5 flash-attention generation issues." + "reason": "Both are generation regressions, but on different models and different attention paths." }, { - "left": "issue:45459", - "right": "issue:45712", + "left": "issue:44568", + "right": "issue:45491", "accept": false, - "reason": "Tokenizer exception masking is unrelated to dummy PT classes leaking into `dir(transformers)` and repo checks." + "reason": "Tokenizer add_special_tokens behavior is unrelated to Gemma3 NaN embeddings with mixed-length batching." }, { "left": "issue:43606", "right": "issue:44857", "accept": false, - "reason": "Device mismatch with CPU offload in Bark is not the same as LwDetrImageLoss failing under float16 AMP on CUDA." + "reason": "CPU offload device mismatch is unrelated to float16 AMP CUDA crashes." + }, + { + "left": "issue:45459", + "right": "issue:45712", + "accept": false, + "reason": "Tokenizer error masking is unrelated to leftover dummy classes and repo-check failures." }, { "left": "issue:44857", "right": "issue:45072", "accept": false, - "reason": "Both are numeric/precision-related, but one is AMP loss failure and the other is dtype mismatch during inference in different models." + "reason": "Different symptoms and subsystems: AMP/CUDA loss crash vs bfloat16 dtype mismatch in inference." }, { "left": "issue:29127", "right": "issue:32090", "accept": false, - "reason": "Completely different issues: LayoutLMv3 error-message clarity vs. Trainer `_gpu_broadcast_one` NoneType handling." + "reason": "Clarifying an error message for LayoutLMv3 boxes is not the same bug as GPU broadcast NoneType handling." }, { - "left": "issue:43927", - "right": "issue:45698", + "left": "issue:45198", + "right": "issue:45803", "accept": false, - "reason": "Both involve save/load behavior, but one loses custom token IDs and the other loads the wrong custom module; different persistence bugs." + "reason": "Wav2Vec2 save/tokenization failure is unrelated to a bare-except swallowing errors in FuyuBatchFeature." }, { - "left": "issue:45198", - "right": "issue:45803", + "left": "issue:43927", + "right": "issue:45698", "accept": false, - "reason": "Wav2Vec2 save/tokenization failure is unrelated to a broad bare-except swallowing errors in Fuyu batch tensor conversion." + "reason": "Both involve save/load behavior, but custom token IDs being lost is not the same as loading the wrong custom module." }, { "left": "issue:44977", "right": "issue:45563", "accept": false, - "reason": "Qwen3.5 flash-attention generation failure is unrelated to a stale warning in paged generate() for `num_return_sequences`." + "reason": "One is a flash-attention generation bug, the other is a stale warning about num_return_sequences." + }, + { + "left": "issue:34689", + "right": "issue:35141", + "accept": false, + "reason": "Model loading breakage for Llama vision is unrelated to embedding resize/post_init reinitialization." }, { "left": "issue:45372", "right": "issue:45588", "accept": false, - "reason": "Gemma4 processor loading import error and flash_attention `s_aux=None` crash are different code paths and different root causes." + "reason": "Gemma 4 processor import failure is unrelated to flash_attention integration crashing on s_aux=None." + }, + { + "left": "issue:40444", + "right": "issue:43526", + "accept": false, + "reason": "Different BEiT/Qwen2.5-VL data handling bugs with no shared concrete code path." }, { "left": "issue:43701", "right": "issue:45083", "accept": false, - "reason": "Checkpoint key mismatch is unrelated to the qwen3_omni_moe feature-length helper behavior." + "reason": "Checkpoint key mismatch is unrelated to a helper function returning unexpected lengths." }, { - "left": "issue:34689", + "left": "issue:43550", + "right": "issue:45072", + "accept": false, + "reason": "Different model/runtime issues: torch.compile SDPA failure vs bfloat16 dtype mismatch." + }, + { + "left": "issue:43412", + "right": "issue:45588", + "accept": false, + "reason": "Executorch export guard/support issues are unrelated to flash_attention sink-less model crashes." + }, + { + "left": "issue:45245", + "right": "issue:45563", + "accept": false, + "reason": "Category-count limit runtime error is unrelated to a paged-generate warning." + }, + { + "left": "issue:29942", "right": "issue:35141", "accept": false, - "reason": "Llama 3.2 vision model loading regression is unrelated to embedding reinitialization after token resize." + "reason": "Flash Attention 2 test failures are unrelated to embedding reinitialization after resizing." + }, + { + "left": "issue:43873", + "right": "issue:44493", + "accept": false, + "reason": "Quantization/offloading behavior is not the same as unexpected position-id key reports." + }, + { + "left": "issue:36010", + "right": "issue:37428", + "accept": false, + "reason": "Two different import errors in different modules; same broad theme, not the same bug." + }, + { + "left": "issue:45372", + "right": "issue:45459", + "accept": false, + "reason": "Gemma 4 processor import error is unrelated to protobuf tokenizer error masking." } ] }, "evaluator_result": { "accept": true, - "feedback": "The assessment is grounded in the packet: the only accepted duplicate pair is the clearly matching Qwen3.5 MoE `from_pretrained` issue (45310/45478), with 45310 correctly chosen as the earlier, fuller report. The other soft-edge rejections are conservative and consistent with the titles/body summaries, and nothing appears overstated." + "feedback": "The summary is well grounded in the packet: the only accepted soft edge is an identical-title pair (issue:45310 / issue:45478), and the rest of the verdicts are conservatively rejected based on clearly different titles/subsystems. No overstatement is apparent." }, "evaluator_used": true, "retried": false, @@ -7777,24 +7734,23 @@ "cluster_id": "cluster-15354-390", "nodes": [ "issue:25251", + "issue:29127", "issue:29942", "issue:30064", "issue:32090", - "issue:35141", - "issue:36010", - "issue:37428", - "issue:40444", + "issue:33357", + "issue:34567", + "issue:39692", "issue:42915", "issue:42994", "issue:43065", "issue:43066", "issue:43278", "issue:43381", - "issue:43412", "issue:43421", - "issue:43526", - "issue:43550", "issue:43653", + "issue:43723", + "issue:43756", "issue:43873", "issue:43976", "issue:43994", @@ -7807,33 +7763,26 @@ "issue:44462", "issue:44466", "issue:44479", - "issue:44493", + "issue:44554", + "issue:44610", + "issue:44734", "issue:44743", "issue:44857", "issue:44871", "issue:44977", - "issue:45083", + "issue:45103", "issue:45198", - "issue:45245", + "issue:45229", "issue:45372", + "issue:45406", "issue:45412", "issue:45440", - "issue:45459", "issue:45491", "issue:45520", - "issue:45563", "issue:45588", "issue:45823" ], "soft_pairs": [ - "issue:40444|issue:43526", - "issue:43550|issue:45083", - "issue:43412|issue:45588", - "issue:45245|issue:45563", - "issue:29942|issue:35141", - "issue:43873|issue:44493", - "issue:36010|issue:37428", - "issue:45372|issue:45459", "issue:43066|issue:44462", "issue:45588|issue:45823", "issue:44857|issue:45588", @@ -7842,215 +7791,230 @@ "issue:25251|issue:32090", "issue:43065|issue:45412", "issue:43653|issue:44743", - "issue:43976|issue:45440", "issue:44451|issue:45520", + "issue:43976|issue:45440", "issue:44186|issue:45198", "issue:42915|issue:42994", "issue:43994|issue:45412", - "issue:44361|issue:45198", "issue:43421|issue:45491", + "issue:44361|issue:45198", "issue:44871|issue:44977", "issue:44265|issue:45198", "issue:44206|issue:44479", "issue:29942|issue:30064", - "issue:43065|issue:43994" + "issue:43065|issue:43994", + "issue:44734|issue:45406", + "issue:33357|issue:39692", + "issue:29127|issue:34567", + "issue:44610|issue:45412", + "issue:45103|issue:45372", + "issue:43873|issue:45229", + "issue:43756|issue:45440", + "issue:43723|issue:44554", + "issue:45372|issue:45406" ], - "prepared_review_unit_hash": "c3567a4ea3948c2da9d057ac31818db75f90e705c929e75cbe152e5bdf3fb095", + "prepared_review_unit_hash": "f147da53eb0df96a8806bb958cd0d589d5944266765abf8cc5e3aad6491c9e9e", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 28, - "serialized_chars": 36117, - "estimated_input_tokens": 9030, - "estimated_eval_tokens": 18316 + "soft_pair_count": 29, + "serialized_chars": 36446, + "estimated_input_tokens": 9112, + "estimated_eval_tokens": 18480 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is highly heterogeneous: it mixes unrelated tokenizer, vision, quantization, export, and attention regressions. None of the soft pairs looks like the same underlying bug/change, so I reject all soft edges and do not pick a canonical issue or PR.", - "confidence": 0.89, - "canonical_issue_reason": "No single issue is a reliable canonical representative because the items span many unrelated bugs and subsystems rather than one duplicated report.", - "canonical_pr_reason": "No pull requests are present in the cluster.", - "best_issue_reason": "None of the issues is clearly more central than the others; the cluster does not have a coherent shared problem domain.", - "best_pr_reason": "No pull requests are present in the cluster.", + "summary": "The items are mostly unrelated tokenizer/model regressions that only look superficially similar by subsystem. No soft pair looks like the same underlying bug or change closely enough to merge.", + "confidence": 0.82, + "canonical_issue_reason": "issue:44462 is the clearest standalone bug report: it describes a concrete AutoTokenizer loading regression with a specific repository-level failure mode.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44462 is the most actionable and user-facing report in the set, with a focused code path and a broad impact on tokenizer loading.", + "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:40444", - "right": "issue:43526", + "left": "issue:43066", + "right": "issue:44462", "accept": false, - "reason": "Both are vision-related, but one is a Qwen2.5-VL iterable-dataset failure and the other is a BeitImageProcessorFast label-reduction bug; different code paths and failures." + "reason": "Both involve tokenizer loading in v5, but one is a decoder-type mismatch and the other is AutoTokenizer ignoring tokenizer.json; different failure modes and likely different fixes." }, { - "left": "issue:43550", - "right": "issue:45083", + "left": "issue:45588", + "right": "issue:45823", "accept": false, - "reason": "A torch.compile SDPA failure in Bamba-9B-v2 is unrelated to qwen3_omni_moe feature-extractor length handling." + "reason": "One is a flash-attention sink-less crash, the other is a Gemma4 PLE device-map mismatch; different code paths and symptoms." }, { - "left": "issue:43412", + "left": "issue:44857", "right": "issue:45588", "accept": false, - "reason": "Gemma3n executorch export issues and a flash_attention integration crash on s_aux=None are different bugs in different paths." + "reason": "LwDetrImageLoss AMP/CUDA crash is unrelated to flash_attention.py s_aux handling." }, { - "left": "issue:45245", - "right": "issue:45563", + "left": "issue:44448", + "right": "issue:44466", "accept": false, - "reason": "Category-cardinality RuntimeError and a stale paged-generate warning are unrelated." + "reason": "Pegasus output differences and lm_head.weight serialization inconsistencies are distinct regressions with different surfaces." }, { - "left": "issue:29942", - "right": "issue:35141", + "left": "issue:43278", + "right": "issue:43381", "accept": false, - "reason": "Flash Attention 2 test failures and token-embedding resize/post_init reinitialization are different regressions." + "reason": "Eval-mode dtype drift and gradient-checkpointing-in-eval are separate training/eval issues, not the same bug." }, { - "left": "issue:43873", - "right": "issue:44493", + "left": "issue:25251", + "right": "issue:32090", "accept": false, - "reason": "Quantization offloading behavior and unexpected position-id keys are not the same underlying issue." + "reason": "Pipeline top_k nesting and Trainer NoneType broadcast are unrelated." }, { - "left": "issue:36010", - "right": "issue:37428", + "left": "issue:43065", + "right": "issue:45412", "accept": false, - "reason": "Both are import errors, but they involve different symbols, modules, and fixes." + "reason": "Dummy Conv2d in Sam3PixelDecoder and RT-DETR memory leaks are different problems." }, { - "left": "issue:45372", - "right": "issue:45459", + "left": "issue:43653", + "right": "issue:44743", "accept": false, - "reason": "Gemma4 processor loading failure from a missing mistral_common import is unrelated to protobuf exception handling in tokenizers." + "reason": "Tokenizer special-token registration and Qwen3.5 recurrent state reset are unrelated." }, { - "left": "issue:43066", - "right": "issue:44462", + "left": "issue:44451", + "right": "issue:45520", "accept": false, - "reason": "A wrong decoder type in v5 and AutoTokenizer ignoring tokenizer.json are distinct tokenizer-loading/serialization problems." + "reason": "Tokenizer loading failure for a model repo and a flash_attn import KeyError on Python 3.13 are different issues." }, { - "left": "issue:45588", - "right": "issue:45823", + "left": "issue:43976", + "right": "issue:45440", "accept": false, - "reason": "A flash_attention crash on sink-less models and a Gemma4 PLE device-mismatch forward bug are unrelated." + "reason": "Python-version compatibility and DeepseekV3MoE behavioral divergence are not the same bug." }, { - "left": "issue:44857", - "right": "issue:45588", + "left": "issue:44186", + "right": "issue:45198", "accept": false, - "reason": "LwDetrImageLoss AMP/CUDA crash and flash_attention s_aux=None failure are different code paths." + "reason": "LayoutLMv2Tokenizer NER/padding crash and Wav2Vec2 save/tokenization failure are different tokenizer/model paths." }, { - "left": "issue:44448", - "right": "issue:44466", + "left": "issue:42915", + "right": "issue:42994", "accept": false, - "reason": "Both are v4/v5 regression reports, but one concerns model outputs and the other serialization of lm_head.weight; not the same bug." + "reason": "FineGrainedFP8Config failure for Qwen3Moe and quantized model saving failure are distinct quantization bugs." }, { - "left": "issue:43278", - "right": "issue:43381", + "left": "issue:43994", + "right": "issue:45412", "accept": false, - "reason": "Embedding dtype drift in eval and gradient-checkpointing being unsupported in eval mode are separate evaluation issues." + "reason": "SigLIP2 inference mismatch and RT-DETR memory release are unrelated." }, { - "left": "issue:25251", - "right": "issue:32090", + "left": "issue:43421", + "right": "issue:45491", "accept": false, - "reason": "Pipeline top_k nesting behavior and Trainer _gpu_broadcast_one NoneType errors are unrelated." + "reason": "Runtime post-processor updates for special tokens and Gemma3 NaN embeddings are different tokenizer/model behaviors." }, { - "left": "issue:43065", - "right": "issue:45412", + "left": "issue:44361", + "right": "issue:45198", "accept": false, - "reason": "A dummy Conv2d in Sam3PixelDecoder and RT-DETR memory not being released are different problems." + "reason": "MLukeTokenizer AttributeError and Wav2Vec2 save/tokenization failure do not share a concrete code-path problem." }, { - "left": "issue:43653", - "right": "issue:44743", + "left": "issue:44871", + "right": "issue:44977", "accept": false, - "reason": "BigBirdTokenizer special-token registration and Qwen3_5 recurrent-state reset behavior are unrelated." + "reason": "Gemma eos_token_id config mismatch and Qwen3.5 flash-attention generation regression are unrelated." }, { - "left": "issue:43976", - "right": "issue:45440", + "left": "issue:44265", + "right": "issue:45198", "accept": false, - "reason": "Python version compatibility and DeepseekV3MoE divergence from remote implementation are unrelated." + "reason": "torch.export failures with torch_compilable_check and Wav2Vec2 save/tokenization problems are different areas." }, { - "left": "issue:44451", - "right": "issue:45520", + "left": "issue:44206", + "right": "issue:44479", "accept": false, - "reason": "A model-loading issue for ScandiBERT and a Python 3.13 flash_attn import KeyError are not the same bug." + "reason": "Feature-extractor center-arg crash and Qwen VL video regression are unrelated." }, { - "left": "issue:44186", - "right": "issue:45198", + "left": "issue:29942", + "right": "issue:30064", "accept": false, - "reason": "LayoutLMv2 tokenizer crashes on NER padding/truncation and Wav2Vec2 save_pretrained/tokenization failure are separate tokenizer issues." + "reason": "Flash Attention 2 test failures and void segmentation map processing are different bugs." }, { - "left": "issue:42915", - "right": "issue:42994", + "left": "issue:43065", + "right": "issue:43994", "accept": false, - "reason": "Qwen3Moe failing with FineGrainedFP8Config and quantized model saving failing are related to quantization in general, but not the same concrete defect." + "reason": "Sam3PixelDecoder dummy Conv2d and SigLIP2 incorrect outputs are not the same change." }, { - "left": "issue:43994", - "right": "issue:45412", + "left": "issue:44734", + "right": "issue:45406", "accept": false, - "reason": "SigLIP2 nonsensical outputs and RT-DETR memory retention are unrelated." + "reason": "KV-cache continuation tensor indexing in transformers serve and Gemma4Processor missing _tokenizer are different failures." }, { - "left": "issue:44361", - "right": "issue:45198", + "left": "issue:33357", + "right": "issue:39692", "accept": false, - "reason": "MLukeTokenizer AttributeError and Wav2Vec2 save_pretrained/tokenization failure are different model/tokenizer bugs." + "reason": "MacOS bus error for community CLIP and SigLIP2 doc example errors are separate issues." }, { - "left": "issue:43421", - "right": "issue:45491", + "left": "issue:29127", + "right": "issue:34567", "accept": false, - "reason": "Runtime post-processor updates for special tokens and Gemma3 NaN embeddings on mixed-length batching are unrelated." + "reason": "LayoutLMv3 box-clarity error and TrainerState token-count tracking are unrelated." }, { - "left": "issue:44871", - "right": "issue:44977", + "left": "issue:44610", + "right": "issue:45412", "accept": false, - "reason": "Gemma eos_token_id inconsistency and Qwen3.5 flash-attention generation failure are different issues." + "reason": "OmDet-Turbo processor size mismatch and RT-DETR memory leak are different bugs." }, { - "left": "issue:44265", - "right": "issue:45198", + "left": "issue:45103", + "right": "issue:45372", "accept": false, - "reason": "torch.export compatibility with torch_compilable_check and Wav2Vec2 save_pretrained/tokenization failures are unrelated." + "reason": "auto_docstring crash under future annotations and Gemma4 processor import failure are unrelated." }, { - "left": "issue:44206", - "right": "issue:44479", + "left": "issue:43873", + "right": "issue:45229", "accept": false, - "reason": "Unsupported center arg in a feature extractor and a Qwen video-input regression are different failures." + "reason": "Quantization/offloading behavior and Gemma4 multi-GPU OOM are different problems." }, { - "left": "issue:29942", - "right": "issue:30064", + "left": "issue:43756", + "right": "issue:45440", "accept": false, - "reason": "Flash Attention 2 test failures and void segmentation map processing failure are unrelated." + "reason": "Smollm3 RoPE-layer discrepancy and DeepseekV3MoE divergence are unrelated model-architecture issues." }, { - "left": "issue:43065", - "right": "issue:43994", + "left": "issue:43723", + "right": "issue:44554", + "accept": false, + "reason": "AutoTokenizer loading regression and an MPS attention correctness issue are different code paths." + }, + { + "left": "issue:45372", + "right": "issue:45406", "accept": false, - "reason": "Sam3PixelDecoder dummy Conv2d and SigLIP2 bad outputs are not the same bug." + "reason": "Both mention Gemma4, but one is an import-time dependency failure and the other is a serve-time missing attribute; not the same underlying bug." } ] }, @@ -8078,276 +8042,291 @@ "issue:29942", "issue:32090", "issue:33357", - "issue:34567", + "issue:35141", "issue:36010", - "issue:39692", + "issue:38175", "issue:41720", "issue:42915", "issue:43262", "issue:43278", + "issue:43316", "issue:43329", "issue:43334", "issue:43381", "issue:43441", + "issue:43452", + "issue:43525", "issue:43526", "issue:43531", "issue:43575", + "issue:43646", "issue:43653", "issue:43701", - "issue:43723", - "issue:43756", "issue:43824", - "issue:43873", "issue:43931", + "issue:44077", "issue:44186", "issue:44206", "issue:44279", + "issue:44387", "issue:44442", "issue:44464", - "issue:44554", - "issue:44610", - "issue:44734", + "issue:44743", + "issue:44811", "issue:44857", + "issue:44964", "issue:44977", "issue:45072", - "issue:45103", "issue:45229", "issue:45245", - "issue:45372", - "issue:45406", - "issue:45412", "issue:45440", "issue:45491", + "issue:45584", "issue:45588", "issue:45593", + "issue:45803", "issue:45834" ], "soft_pairs": [ - "issue:44734|issue:45406", - "issue:33357|issue:39692", - "issue:29127|issue:34567", - "issue:44610|issue:45412", - "issue:45103|issue:45372", - "issue:43756|issue:45440", - "issue:43873|issue:45229", - "issue:43723|issue:44554", - "issue:45372|issue:45406", "issue:43278|issue:43575", - "issue:43653|issue:44442", "issue:43381|issue:43701", - "issue:45440|issue:45593", + "issue:43526|issue:45834", + "issue:43653|issue:44442", "issue:43278|issue:43329", "issue:41720|issue:45229", + "issue:45440|issue:45593", "issue:29942|issue:36010", "issue:43334|issue:43531", "issue:32090|issue:33357", "issue:44977|issue:45245", "issue:43824|issue:44279", "issue:43526|issue:44186", - "issue:43526|issue:45834", "issue:43526|issue:44857", - "issue:43441|issue:45588", "issue:42915|issue:43931", + "issue:43441|issue:45588", "issue:44464|issue:45491", "issue:43262|issue:44206", - "issue:44442|issue:45072" + "issue:44442|issue:45072", + "issue:44743|issue:44811", + "issue:43575|issue:43701", + "issue:43646|issue:44077", + "issue:43452|issue:45588", + "issue:29127|issue:35141", + "issue:44442|issue:45803", + "issue:43575|issue:44387", + "issue:44977|issue:45584", + "issue:33357|issue:38175", + "issue:43316|issue:43525", + "issue:44964|issue:45440" ], - "prepared_review_unit_hash": "d9e752e4252f52f3bc31b0cf5a81ba55e1a0c279899187a212bfc22f26c6817b", + "prepared_review_unit_hash": "ec8e76295e4957adb3b6026f01330a623c48aee97e6d3627f374b079e463f00b", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 28, - "serialized_chars": 35549, - "estimated_input_tokens": 8888, - "estimated_eval_tokens": 18032 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36641, + "estimated_input_tokens": 9161, + "estimated_eval_tokens": 18578 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is not a real duplicate cluster: the issues span unrelated models, tokenizers, training/runtime paths, and docs examples. All soft pairs should be rejected; 43873 is only a weak canonical anchor because it is the broadest, most active open issue.", - "confidence": 0.88, - "canonical_issue_reason": "Issue 43873 is the broadest and most active open item, but only as a weak anchor; the overall set is heterogeneous and not a true duplicate family.", + "summary": "The candidate pairs are mostly unrelated issues across different models, components, and failure modes. I would reject all soft edges; none look like the same underlying bug or change.", + "confidence": 0.97, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "43873 has the highest generality and discussion activity, so it is the least-bad representative if a single issue must be chosen.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44734", - "right": "issue:45406", + "left": "issue:43278", + "right": "issue:43575", "accept": false, - "reason": "Different failures: KV-cache continuation tensor indexing in serve vs Gemma4 processor initialization missing _tokenizer." + "reason": "Different problems: dtype drift in eval vs a tensor-parallel OOM while loading a large Qwen model." }, { - "left": "issue:33357", - "right": "issue:39692", + "left": "issue:43381", + "right": "issue:43701", "accept": false, - "reason": "Different artifacts and symptoms: MacOS bus error with a community CLIP model vs SigLIP2 docs example/model-processor mismatch and quantization errors." + "reason": "One is gradient checkpointing in eval mode; the other is a resume_from_checkpoint key mismatch. No shared code-path bug." }, { - "left": "issue:29127", - "right": "issue:34567", + "left": "issue:43526", + "right": "issue:45834", "accept": false, - "reason": "Unrelated bugs: LayoutLMv3 error messaging for bad boxes vs TrainerState num_input_tokens_seen not updating." + "reason": "BeitImageProcessorFast label reduction bug vs Kosmos2.5 OCR long-input index error; distinct processors and failures." }, { - "left": "issue:44610", - "right": "issue:45412", + "left": "issue:43653", + "right": "issue:44442", "accept": false, - "reason": "Different code paths: OmDet-Turbo processor image size mismatch vs RT-DETR memory not being released on deletion." + "reason": "BigBirdTokenizer special-token registration issue vs FastSpeech2ConformerTokenizer loading failure; unrelated tokenization bugs." }, { - "left": "issue:45103", - "right": "issue:45372", + "left": "issue:43278", + "right": "issue:43329", "accept": false, - "reason": "Different root causes: auto_docstring annotations crash vs Gemma4 loading breaking on a missing mistral_common import." + "reason": "Embedding dtype mismatch is unrelated to the multimodal token-count video-branch undefined variable bug." }, { - "left": "issue:43756", - "right": "issue:45440", + "left": "issue:41720", + "right": "issue:45229", "accept": false, - "reason": "Both concern model implementation differences, but they are for different models and different mechanisms; not the same underlying bug." + "reason": "Different models and symptoms: Qwen3 auto device mapping assert vs Gemma4 multi-GPU CUDA OOM." }, { - "left": "issue:43873", - "right": "issue:45229", + "left": "issue:45440", + "right": "issue:45593", "accept": false, - "reason": "Both involve memory/resource issues, but one is quantization/offloading behavior and the other is multi-GPU OOM for a specific model." + "reason": "DeepSeekV3MoE implementation divergence vs D-FINE auxiliary-loss handling; no common underlying change." }, { - "left": "issue:43723", - "right": "issue:44554", + "left": "issue:29942", + "right": "issue:36010", "accept": false, - "reason": "Different failures: tokenizer loading regression vs MPS attention correctness when value head dim differs from query." + "reason": "Flash Attention 2 test failures are not the same as a GenerationMixin import error." }, { - "left": "issue:45372", - "right": "issue:45406", + "left": "issue:43334", + "right": "issue:43531", "accept": false, - "reason": "Gemma4-related, but one is an import-time dependency break and the other is a serve-time missing processor attribute." + "reason": "Missing pad_token_id on Qwen3-VL config is unrelated to sliding_window behavior in Qwen3-MoE." }, { - "left": "issue:43278", - "right": "issue:43575", + "left": "issue:32090", + "right": "issue:33357", "accept": false, - "reason": "Different problems: dtype drift during evaluate vs tensor-parallel load OOM for a large Qwen2 model." + "reason": "Trainer broadcast TypeError and MacOS CLIP bus error are different runtime failures in different paths." }, { - "left": "issue:43653", - "right": "issue:44442", + "left": "issue:44977", + "right": "issue:45245", "accept": false, - "reason": "Both tokenizer-related, but one is a special-token registration bug and the other is AutoTokenizer loading a different tokenizer class." + "reason": "Flash-attention generation issue vs category-cardinality limit error; no shared bug." }, { - "left": "issue:43381", - "right": "issue:43701", + "left": "issue:43824", + "right": "issue:44279", "accept": false, - "reason": "Different training-state behaviors: eval-mode gradient checkpointing restriction vs resume_from_checkpoint key mismatch." + "reason": "Specific missing Qwen2.5-VL symbol import vs a broad dependency issue; not the same failure." }, { - "left": "issue:45440", - "right": "issue:45593", + "left": "issue:43526", + "right": "issue:44186", "accept": false, - "reason": "Different model implementations and bug types: DeepseekV3MoE divergence vs D-FINE auxiliary losses missing when denoising is off." + "reason": "Different tokenizer/processor crashes with different inputs and root causes." }, { - "left": "issue:43278", - "right": "issue:43329", + "left": "issue:43526", + "right": "issue:44857", "accept": false, - "reason": "Different areas: evaluation dtype mismatch vs multimodal token counting video-branch undefined names." + "reason": "BEiT label reduction bug is unrelated to LwDetrImageLoss AMP/CUDA crash." }, { - "left": "issue:41720", - "right": "issue:45229", + "left": "issue:42915", + "right": "issue:43931", "accept": false, - "reason": "Different model/runtime failures: Qwen3 auto device mapping assertion on A800 vs Gemma4 multi-GPU OOM." + "reason": "FineGrainedFP8Config failure for Qwen3Moe vs weight-shape mismatch loading Qwen3-VL; distinct issues." }, { - "left": "issue:29942", - "right": "issue:36010", + "left": "issue:43441", + "right": "issue:45588", "accept": false, - "reason": "Flash Attention test failures and a GenerationMixin import error are unrelated regression classes." + "reason": "Ministral FlashAttention regression and sink-less-models s_aux None crash are separate FlashAttention-related bugs." }, { - "left": "issue:43334", - "right": "issue:43531", + "left": "issue:44464", + "right": "issue:45491", "accept": false, - "reason": "Both are Qwen3-family issues, but one is a loading AttributeError and the other is a sliding_window behavior bug." + "reason": "Compiled chunked generation inconsistency is not the same as Gemma3 NaN embeddings from sliding-window/all-padding windows." }, { - "left": "issue:32090", - "right": "issue:33357", + "left": "issue:43262", + "right": "issue:44206", "accept": false, - "reason": "Different runtime layers and symptoms: Trainer broadcast NoneType error vs MacOS bus error with a CLIP model." + "reason": "Audio chat-template sampling-rate default bug vs LasrFeatureExtractor unsupported argument crash; different components." }, { - "left": "issue:44977", - "right": "issue:45245", + "left": "issue:44442", + "right": "issue:45072", "accept": false, - "reason": "Different bugs: flash-attention generation instability vs category cardinality limit in a separate model/input path." + "reason": "FastSpeech2ConformerTokenizer load failure vs dtype mismatch in SwitchTransformers/TimmWrapperModel; unrelated." }, { - "left": "issue:43824", - "right": "issue:44279", + "left": "issue:44743", + "right": "issue:44811", "accept": false, - "reason": "A specific missing class import is not the same as a broad dependency issue with transformers." + "reason": "Qwen3.5 recurrent-state reset bug is not the same as Whisper batch_decode skip_special_tokens handling." }, { - "left": "issue:43526", - "right": "issue:44186", + "left": "issue:43575", + "right": "issue:43701", "accept": false, - "reason": "Different processors/tokenizers and different failure modes: reduce_labels behavior vs LayoutLMv2Tokenizer crashes on NER/padding." + "reason": "Loading OOM for a large Qwen model is unrelated to resume checkpoint key mismatches." }, { - "left": "issue:43526", - "right": "issue:45834", + "left": "issue:43646", + "right": "issue:44077", "accept": false, - "reason": "BeitImageProcessorFast label reduction and Kosmos2.5 long-OCR index errors are unrelated." + "reason": "Transformers 5 custom model init break is broader than the patchtsmixer post_init policy issue; not the same concrete bug." }, { - "left": "issue:43526", - "right": "issue:44857", + "left": "issue:43452", + "right": "issue:45588", "accept": false, - "reason": "Different image-processing bug vs mixed-precision CUDA loss crash." + "reason": "Tokenizer/model loading with gguf_file is unrelated to an s_aux=None flash_attention crash." }, { - "left": "issue:43441", - "right": "issue:45588", + "left": "issue:29127", + "right": "issue:35141", "accept": false, - "reason": "Both touch flash attention, but they affect different models and different code paths; not mergeable as one fix." + "reason": "LayoutLMv3 error-message clarity issue vs embedding reinitialization in post_init; different behavior and code paths." }, { - "left": "issue:42915", - "right": "issue:43931", + "left": "issue:44442", + "right": "issue:45803", "accept": false, - "reason": "Different model-loading failures: FineGrainedFP8Config issue vs Qwen3-VL weight-shape mismatch." + "reason": "Tokenizer loading failure vs bare-except swallowing errors in FuyuBatchFeature; no common underlying bug." }, { - "left": "issue:44464", - "right": "issue:45491", + "left": "issue:43575", + "right": "issue:44387", "accept": false, - "reason": "Different inference bugs: compiled-forward chunked generation inconsistency vs Gemma3 NaNs from sliding-window/all-padding behavior." + "reason": "OOM while loading a model with tensor parallelism is distinct from increased CUDA reserved memory under int4 quantization." }, { - "left": "issue:43262", - "right": "issue:44206", + "left": "issue:44977", + "right": "issue:45584", "accept": false, - "reason": "Audio chat-template sampling-rate default mismatch is unrelated to a feature extractor passing an unsupported center argument." + "reason": "Qwen3.5 flash-attention generation bug is unrelated to Whisper empty-transcription generation after align_special_tokens." }, { - "left": "issue:44442", - "right": "issue:45072", + "left": "issue:33357", + "right": "issue:38175", "accept": false, - "reason": "Tokenizer loading and bf16 dtype mismatches are different subsystems with different fixes." + "reason": "MacOS bus error on CLIP is not the same as zero probabilities on siglip2-base-patch16-224." + }, + { + "left": "issue:43316", + "right": "issue:43525", + "accept": false, + "reason": "Both mention config API issues, but they are different models and missing fields; not the same bug." + }, + { + "left": "issue:44964", + "right": "issue:45440", + "accept": false, + "reason": "Phi-4 multimodal loading regression is unrelated to DeepSeekV3MoE implementation divergence." } ] }, @@ -8378,59 +8357,49 @@ "issue:33357", "issue:34567", "issue:34689", - "issue:35141", - "issue:38175", + "issue:36010", "issue:39692", + "issue:41628", "issue:42907", "issue:43316", "issue:43381", - "issue:43452", "issue:43493", - "issue:43525", + "issue:43540", "issue:43550", - "issue:43575", "issue:43611", - "issue:43646", - "issue:43701", + "issue:43643", + "issue:43720", "issue:43761", "issue:43827", + "issue:43856", "issue:43873", "issue:43931", "issue:44077", "issue:44079", "issue:44188", - "issue:44387", + "issue:44190", "issue:44442", "issue:44479", + "issue:44496", + "issue:44514", "issue:44568", "issue:44743", - "issue:44811", + "issue:44855", + "issue:44871", + "issue:44877", "issue:44898", - "issue:44964", - "issue:44977", + "issue:44913", + "issue:45137", "issue:45216", "issue:45290", - "issue:45440", + "issue:45372", "issue:45479", "issue:45491", - "issue:45584", - "issue:45588", + "issue:45656", "issue:45698", - "issue:45759", - "issue:45803" + "issue:45759" ], "soft_pairs": [ - "issue:44743|issue:44811", - "issue:43575|issue:43701", - "issue:43452|issue:45588", - "issue:43646|issue:44077", - "issue:44442|issue:45803", - "issue:29127|issue:35141", - "issue:43575|issue:44387", - "issue:44977|issue:45584", - "issue:33357|issue:38175", - "issue:44964|issue:45440", - "issue:43316|issue:43525", "issue:43761|issue:44079", "issue:44479|issue:45290", "issue:28218|issue:29127", @@ -8438,206 +8407,238 @@ "issue:43931|issue:45216", "issue:28218|issue:32090", "issue:33290|issue:34567", - "issue:43761|issue:44188", "issue:34689|issue:43611", "issue:39692|issue:45491", "issue:44442|issue:44898", + "issue:43761|issue:44188", "issue:43381|issue:43873", "issue:43493|issue:43827", "issue:43550|issue:44743", + "issue:44568|issue:45479", "issue:43316|issue:45759", - "issue:44568|issue:45479" + "issue:41628|issue:45372", + "issue:43643|issue:44913", + "issue:43720|issue:44442", + "issue:32090|issue:33290", + "issue:44190|issue:44496", + "issue:43873|issue:44871", + "issue:34689|issue:36010", + "issue:43381|issue:43856", + "issue:44077|issue:44479", + "issue:44855|issue:45137", + "issue:33290|issue:45656", + "issue:43316|issue:44877", + "issue:29127|issue:33357", + "issue:43540|issue:44514" ], - "prepared_review_unit_hash": "d6ff464fa2f551ad3639951ffd027c6f6ffb2ee083bf014c6443d29ec40ca5ed", + "prepared_review_unit_hash": "70db5139c0ea59200a2f037a331eebd06a05e5d0aed6a497c43b5629835ca808", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 27, - "serialized_chars": 35419, - "estimated_input_tokens": 8855, - "estimated_eval_tokens": 17966 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 37030, + "estimated_input_tokens": 9258, + "estimated_eval_tokens": 18772 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This is a heterogeneous cluster of mostly unrelated Transformers issues; the only commonality is broad runtime/model-loading breakage across different subsystems. No soft pair looks like the same underlying bug or change, so all soft edges are rejected.", - "confidence": 0.9, - "canonical_issue_reason": "issue:43873 is the strongest representative by activity and inbound references, and it sits in the broadest recurring theme here (runtime/memory/quantization regressions).", + "summary": "These items are mostly unrelated Transformers bugs spanning tokenization, config/loading, training, and docs. None of the soft pairs look like the same concrete bug, so I would not merge any of them.", + "confidence": 0.83, + "canonical_issue_reason": "No single canonical issue stands out; the cluster is heterogeneous and the soft links are weak.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43873 is open, active, and has the most external interest, making it the best single issue to anchor this noisy cluster despite the weak overall topical coherence.", + "best_issue_reason": "issue:45698 is the most broadly representative load/save-pretrained regression among the set, so it is the best anchor if one issue must be chosen.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44743", - "right": "issue:44811", + "left": "issue:43761", + "right": "issue:44079", "accept": false, - "reason": "Different bugs: recurrent-state reset in Qwen modular code vs Whisper batch_decode skipping special tokens." + "reason": "Different failures: CLIPVisionModel hidden_states regression vs ModelOutput key assignment when a value was previously None." }, { - "left": "issue:43575", - "right": "issue:43701", + "left": "issue:44479", + "right": "issue:45290", "accept": false, - "reason": "Different failure modes: tensor-parallel OOM on load vs resume_from_checkpoint key mismatch." + "reason": "Video-input regression and chat-template tool-call crash are separate code paths and different bugs." }, { - "left": "issue:43452", - "right": "issue:45588", + "left": "issue:28218", + "right": "issue:29127", "accept": false, - "reason": "Unrelated subsystems: gguf / AutoTokenizer-AutoModel loading vs flash_attention crash on sink-less models." + "reason": "Tokenizer spacing after added tokens is unrelated to LayoutLMv3 error-message clarity." }, { - "left": "issue:43646", - "right": "issue:44077", + "left": "issue:42907", + "right": "issue:45698", "accept": false, - "reason": "Both touch initialization, but one is a general v5 custom model init breakage and the other is a patchtsmixer-specific post_init policy issue." + "reason": "Different save/load problems: dequantized model saving vs wrong custom module loaded after save_pretrained." }, { - "left": "issue:44442", - "right": "issue:45803", + "left": "issue:43931", + "right": "issue:45216", "accept": false, - "reason": "Different tokenizer bugs: FastSpeech2ConformerTokenizer loading vs a bare except swallowing errors in FuyuBatchFeature.convert_to_tensors()." + "reason": "Qwen3-VL weight-shape mismatch and Qwen3.5 checkpoint save corruption are different model-loading issues." }, { - "left": "issue:29127", - "right": "issue:35141", + "left": "issue:28218", + "right": "issue:32090", "accept": false, - "reason": "Completely different areas: LayoutLMv3 error messaging vs embedding reinitialization after resize_token_embeddings." + "reason": "Tokenizer behavior bug vs Trainer/_gpu_broadcast_one NoneType error." }, { - "left": "issue:43575", - "right": "issue:44387", + "left": "issue:33290", + "right": "issue:34567", "accept": false, - "reason": "Both are memory-related, but one is TP load OOM and the other is increased reserved memory under int4 quantization." + "reason": "DeepSpeed+AdaFactor OOM and TrainerState token counter not updating are unrelated." }, { - "left": "issue:44977", - "right": "issue:45584", + "left": "issue:34689", + "right": "issue:43611", "accept": false, - "reason": "Different generation regressions: Qwen3.5 flash-attention issue vs Whisper empty-transcription/alignment failure." + "reason": "Model loading break for Llama 3.2 Vision is not the same as the base_model_prefix loading regression." }, { - "left": "issue:33357", - "right": "issue:38175", + "left": "issue:39692", + "right": "issue:45491", "accept": false, - "reason": "Different models and symptoms: MacOS bus error in CLIP vs zero probabilities in SigLIP2." + "reason": "Documentation/example errors for SigLIP2 are unrelated to Gemma3 NaN embeddings in attention." }, { - "left": "issue:44964", - "right": "issue:45440", + "left": "issue:44442", + "right": "issue:44898", "accept": false, - "reason": "Different model families and code paths: Phi-4 multimodal loading vs DeepSeekV3MoE implementation divergence." + "reason": "AutoTokenizer loading failure and Perceiver non-default-resolution failure are separate bugs." }, { - "left": "issue:43316", - "right": "issue:43525", + "left": "issue:43761", + "right": "issue:44188", "accept": false, - "reason": "Both are config API discrepancies, but they are distinct attributes on different config classes." + "reason": "Hidden-states return bug is unrelated to attention kernel divergence under torch.compile." }, { - "left": "issue:43761", - "right": "issue:44079", + "left": "issue:43381", + "right": "issue:43873", "accept": false, - "reason": "Related to outputs/hidden states, but not the same bug: one is CLIPVision hidden_states omission, the other is ModelOutput key assignment with None values." + "reason": "Gradient-checkpointing eval-mode restriction and quantization offloading issues are different problems." }, { - "left": "issue:44479", - "right": "issue:45290", + "left": "issue:43493", + "right": "issue:43827", "accept": false, - "reason": "Different regressions: video-input handling for Qwen models vs chat template crashes on tool-call assistant messages." + "reason": "SigLIP2 implementation discrepancy and docs still referencing pipeline() are unrelated." }, { - "left": "issue:28218", - "right": "issue:29127", + "left": "issue:43550", + "right": "issue:44743", "accept": false, - "reason": "Tokenizer spacing bug vs LayoutLMv3 error clarity issue; no shared underlying defect." + "reason": "torch.compile SDPA failure in Bamba-9B-v2 is not the same as recurrent states resetting in modular_qwen3_5.py." }, { - "left": "issue:42907", - "right": "issue:45698", + "left": "issue:44568", + "right": "issue:45479", "accept": false, - "reason": "Saving dequantized models and loading the wrong custom module are distinct save/load issues." + "reason": "Tokenizer add_special_tokens regression and zero-loss sequence-classification bug do not share the same code path." }, { - "left": "issue:43931", - "right": "issue:45216", + "left": "issue:43316", + "right": "issue:45759", "accept": false, - "reason": "Different save/load problems: weight-shape mismatch on model load vs incorrect checkpoint produced by save_pretrained." + "reason": "Both involve config/model APIs, but one is a Gemma3TextConfig discrepancy and the other is Qwen composite-config unwrapping." }, { - "left": "issue:28218", - "right": "issue:32090", + "left": "issue:41628", + "right": "issue:45372", "accept": false, - "reason": "Tokenizer added-space bug is unrelated to Trainer/_gpu_broadcast_one NoneType error." + "reason": "AutoImageProcessor import failure and mistral_common ReasoningEffort import failure are different import regressions." }, { - "left": "issue:33290", - "right": "issue:34567", + "left": "issue:43643", + "right": "issue:44913", "accept": false, - "reason": "OOM with Adafactor+DeepSpeed is unrelated to TrainerState.num_input_tokens_seen not updating." + "reason": "trust_remote_code missing fields and GPTNeoX rotary_pct resetting on reload are distinct config bugs." }, { - "left": "issue:43761", - "right": "issue:44188", + "left": "issue:43720", + "right": "issue:44442", "accept": false, - "reason": "One is a hidden_states output bug; the other is a torch.compile branching divergence in attention kernels." + "reason": "BitNet packed-weight loading and FastSpeech2ConformerTokenizer loading failure are unrelated loader issues." }, { - "left": "issue:34689", - "right": "issue:43611", + "left": "issue:32090", + "right": "issue:33290", "accept": false, - "reason": "Both concern loading regressions, but they stem from different breakages and model/config paths." + "reason": "Trainer NoneType broadcast error and DeepSpeed AdaFactor OOM are different training/runtime failures." }, { - "left": "issue:39692", - "right": "issue:45491", + "left": "issue:44190", + "right": "issue:44496", "accept": false, - "reason": "Docs example errors are unrelated to Gemma3 NaN embeddings in mixed-length batching." + "reason": "Local dataset loading in an example script is unrelated to an unrecognized-model/config model_type error." }, { - "left": "issue:44442", - "right": "issue:44898", + "left": "issue:43873", + "right": "issue:44871", + "accept": false, + "reason": "Quantization/offloading behavior and Gemma-3 eos_token_id mismatch are different issues." + }, + { + "left": "issue:34689", + "right": "issue:36010", "accept": false, - "reason": "Different vision/tokenizer loading bug vs Perceiver interpolation failure at non-default resolution." + "reason": "Llama 3.2 Vision loading break is not the same as the GenerationMixin import error." }, { "left": "issue:43381", - "right": "issue:43873", + "right": "issue:43856", "accept": false, - "reason": "Gradient checkpointing in eval mode is unrelated to quantization/offloading behavior." + "reason": "Gradient checkpointing eval-mode bug and Qwen3 MoE memory inefficiency are separate concerns." }, { - "left": "issue:43493", - "right": "issue:43827", + "left": "issue:44077", + "right": "issue:44479", "accept": false, - "reason": "Implementation-vs-JAX discrepancy for SigLIP2 is unrelated to stale pipeline docs after v5 removals." + "reason": "patchtsmixer post_init API rule and video-input regression affect different components." }, { - "left": "issue:43550", - "right": "issue:44743", + "left": "issue:44855", + "right": "issue:45137", + "accept": false, + "reason": "Python 3.13 import/torch.jit parsing error is unrelated to DeepSpeed ZeRO3 deque underflow." + }, + { + "left": "issue:33290", + "right": "issue:45656", "accept": false, - "reason": "Different code paths: torch.compile+SDPA failure vs recurrent state reset with cache in modular Qwen3.5." + "reason": "Both mention DeepSpeed, but one is OOM with AdaFactor and the other is duplicate optimizer stepping." }, { "left": "issue:43316", - "right": "issue:45759", + "right": "issue:44877", "accept": false, - "reason": "Both involve config APIs, but one is a Gemma3TextConfig inconsistency and the other is Qwen multimodal text_config unwrapping." + "reason": "Gemma3TextConfig API mismatch and strict config preventing granite_speech loading are different config-loading problems." }, { - "left": "issue:44568", - "right": "issue:45479", + "left": "issue:29127", + "right": "issue:33357", "accept": false, - "reason": "Tokenizer special-token regression is unrelated to degenerate zero-loss sequence classification behavior." + "reason": "LayoutLMv3 error-message clarity and CLIP bus error on macOS are unrelated." + }, + { + "left": "issue:43540", + "right": "issue:44514", + "accept": false, + "reason": "Video-input processing failure in Qwen3OmniMoe is different from batched chat-template padding crash in Qwen2_5_VLProcessor." } ] }, @@ -8663,15 +8664,15 @@ "nodes": [ "issue:25251", "issue:28282", - "issue:29127", - "issue:32090", "issue:33290", - "issue:33357", "issue:34689", - "issue:36010", - "issue:41628", + "issue:35141", + "issue:36331", + "issue:41720", "issue:41950", "issue:42175", + "issue:42617", + "issue:43065", "issue:43232", "issue:43295", "issue:43316", @@ -8679,262 +8680,270 @@ "issue:43388", "issue:43404", "issue:43441", + "issue:43452", "issue:43475", - "issue:43540", "issue:43550", + "issue:43575", "issue:43606", - "issue:43643", + "issue:43646", + "issue:43673", "issue:43701", - "issue:43720", "issue:43742", + "issue:43761", "issue:43825", - "issue:43856", - "issue:43873", + "issue:43931", + "issue:44060", "issue:44077", "issue:44162", - "issue:44190", - "issue:44442", + "issue:44242", + "issue:44464", "issue:44479", "issue:44496", - "issue:44514", + "issue:44534", + "issue:44617", + "issue:44743", "issue:44792", - "issue:44855", "issue:44871", - "issue:44877", "issue:44913", + "issue:44936", "issue:45127", - "issue:45137", "issue:45200", - "issue:45372", "issue:45584", - "issue:45656" + "issue:45698" ], "soft_pairs": [ - "issue:41628|issue:45372", - "issue:43720|issue:44442", - "issue:43643|issue:44913", - "issue:32090|issue:33290", - "issue:44190|issue:44496", - "issue:43873|issue:44871", - "issue:34689|issue:36010", - "issue:43381|issue:43856", - "issue:44077|issue:44479", - "issue:44855|issue:45137", - "issue:33290|issue:45656", - "issue:43316|issue:44877", - "issue:43540|issue:44514", - "issue:29127|issue:33357", "issue:43381|issue:43742", "issue:42175|issue:43316", - "issue:43404|issue:43441", "issue:33290|issue:34689", + "issue:43404|issue:43441", "issue:44162|issue:44792", "issue:25251|issue:28282", "issue:43232|issue:43388", - "issue:41950|issue:43475", "issue:43295|issue:43825", - "issue:45127|issue:45200", + "issue:41950|issue:43475", "issue:44871|issue:45584", + "issue:45127|issue:45200", "issue:43550|issue:43701", "issue:43606|issue:43701", - "issue:43295|issue:44871" - ], - "prepared_review_unit_hash": "c6e21f144ab8c2d19b4cb2627867956fa51024691a6ba278bb040c831ea6ab1b", - "component_budget": { - "node_count": 390, - "item_count": 390, + "issue:43295|issue:44871", + "issue:43065|issue:44617", + "issue:33290|issue:35141", + "issue:43761|issue:44479", + "issue:33290|issue:36331", + "issue:43673|issue:44743", + "issue:44936|issue:45698", + "issue:43452|issue:44496", + "issue:43575|issue:43742", + "issue:43646|issue:44913", + "issue:42617|issue:43575", + "issue:43761|issue:44242", + "issue:41720|issue:43575", + "issue:44077|issue:44534", + "issue:43931|issue:44060", + "issue:44464|issue:44871" + ], + "prepared_review_unit_hash": "a7bbec2d8ef31a89541061c3cbd84fe5e4ea2b5e5034c6e4e7ae6c7a62bb0f85", + "component_budget": { + "node_count": 390, + "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 28, - "serialized_chars": 35646, - "estimated_input_tokens": 8912, - "estimated_eval_tokens": 18080 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36313, + "estimated_input_tokens": 9079, + "estimated_eval_tokens": 18414 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is highly heterogeneous: it mixes unrelated import/config/loading, training/DeepSpeed, and multimodal pipeline regressions. I found no safe duplicate merge among the soft edges; the closest thing to a representative issue is a processor/tokenizer regression, but it does not cover the cluster as a whole.", - "confidence": 0.81, - "canonical_issue_reason": "No single issue cleanly represents this cluster as a true duplicate set. If one must be chosen as the closest anchor, issue 43295 is the most concrete user-facing regression, but it only matches a small slice of the set.", + "summary": "These issues are broadly heterogeneous and do not collapse into one duplicate cluster. Most pairs share only a subsystem or release theme, not the same concrete bug or change, so all soft edges should be rejected.", + "confidence": 0.96, + "canonical_issue_reason": "issue:43295 is the clearest high-signal regression report in the set, but the overall cluster is too diverse for a true canonical duplicate anchor.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43295 is the strongest standalone representative because it describes a specific regression with a clear failure mode and reproduction context; the rest of the items are too diverse to serve as one duplicate umbrella.", + "best_issue_reason": "issue:43295 is the best representative issue: it is concrete, reproducible, and has a well-scoped regression description. It is not a duplicate of the others.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:41628", - "right": "issue:45372", + "left": "issue:43381", + "right": "issue:43742", "accept": false, - "reason": "Both are import errors, but they involve different symbols, dependencies, and code paths: AutoImageProcessor vs mistral_common ReasoningEffort/Gemma 4 loading." + "reason": "Different failures: eval-mode gradient checkpointing vs model load key error." }, { - "left": "issue:43720", - "right": "issue:44442", + "left": "issue:42175", + "right": "issue:43316", "accept": false, - "reason": "One is a BitNet/accelerate packed-weights loading bug; the other is AutoTokenizer failing to resolve a tokenizer class. Similar theme, different failure." + "reason": "Unrelated topics: optional backend packaging vs Gemma3 config API mismatch." }, { - "left": "issue:43643", - "right": "issue:44913", + "left": "issue:33290", + "right": "issue:34689", "accept": false, - "reason": "Both concern config persistence, but one is missing fields with trust_remote_code and the other is GPTNeoX rotary_pct not surviving reload." + "reason": "Different code paths and symptoms: deepspeed/Adafactor OOM vs model loading regression." }, { - "left": "issue:32090", - "right": "issue:33290", + "left": "issue:43404", + "right": "issue:43441", "accept": false, - "reason": "Both touch trainer/DeepSpeed, but the symptoms are unrelated: NoneType broadcast error vs Adafactor OOM." + "reason": "Both touch Mistral-family models, but one is tied-weights initialization and the other is FlashAttention runtime failure." }, { - "left": "issue:44190", - "right": "issue:44496", + "left": "issue:44162", + "right": "issue:44792", "accept": false, - "reason": "Dataset loading in an example script is unrelated to an unrecognized model/config missing model_type." + "reason": "Completely different models and failures: ESM2 breakage vs Janus test regression." }, { - "left": "issue:43873", - "right": "issue:44871", + "left": "issue:25251", + "right": "issue:28282", "accept": false, - "reason": "Quantization/offload memory behavior is a different bug class from Gemma eos_token_id inconsistency." + "reason": "Pipeline output shape bug vs missing PyTorch ImportError; not the same issue." }, { - "left": "issue:34689", - "right": "issue:36010", + "left": "issue:43232", + "right": "issue:43388", "accept": false, - "reason": "A model-loading regression for Llama 3.2 Vision is not the same as an import failure for GenerationMixin." + "reason": "Generation kwargs update after sync_gpus is unrelated to gather_for_metrics label handling." }, { - "left": "issue:43381", - "right": "issue:43856", + "left": "issue:43295", + "right": "issue:43825", "accept": false, - "reason": "Gradient checkpointing in eval mode and Qwen3 MoE memory inefficiency are distinct training/runtime issues." + "reason": "Both are v5-related pipeline regressions, but one is tokenizer/processor API breakage and the other is an error-message wording issue." }, { - "left": "issue:44077", - "right": "issue:44479", + "left": "issue:41950", + "right": "issue:43475", "accept": false, - "reason": "A PatchTSMixer post_init API restriction is unrelated to a Qwen video-input regression." + "reason": "Different video/SAM bugs: wrong processor lookup vs missing encoder attribute." }, { - "left": "issue:44855", - "right": "issue:45137", + "left": "issue:44871", + "right": "issue:45584", "accept": false, - "reason": "Python 3.13 torch.jit parsing/IndentationError is unrelated to a DeepSpeed ZeRO3 deque pop failure." + "reason": "Different generation edge cases: Gemma eos-token config mismatch vs Whisper empty-transcription failure." }, { - "left": "issue:33290", - "right": "issue:45656", + "left": "issue:45127", + "right": "issue:45200", "accept": false, - "reason": "Both mention DeepSpeed optimizers, but one is an OOM with Adafactor and the other is optimizer.step being invoked twice." + "reason": "Unrelated model-finetuning issues: LoRA merge collapse vs Gemma4 mm token defaults." }, { - "left": "issue:43316", - "right": "issue:44877", + "left": "issue:43550", + "right": "issue:43701", "accept": false, - "reason": "These are both config-related, but one is an API discrepancy in Gemma3TextConfig and the other is strict config blocking granite_speech loading." + "reason": "torch.compile/SDPA OOM is unrelated to resume_from_checkpoint key mismatch." }, { - "left": "issue:43540", - "right": "issue:44514", + "left": "issue:43606", + "right": "issue:43701", "accept": false, - "reason": "Both are Qwen multimodal issues, but one is video-input processing in Qwen3OmniMoe and the other is batched apply_chat_template crashing with padding=False." + "reason": "CPU offload device mismatch and checkpoint key mismatch are different bugs." }, { - "left": "issue:29127", - "right": "issue:33357", + "left": "issue:43295", + "right": "issue:44871", "accept": false, - "reason": "LayoutLMV3 error-message clarity and a MacOS bus error on CLIP are unrelated." + "reason": "Both are config/regression reports, but they affect different APIs and symptoms." }, { - "left": "issue:43381", - "right": "issue:43742", + "left": "issue:43065", + "right": "issue:44617", "accept": false, - "reason": "Eval-mode checkpointing and a MobileLLM loading KeyError are different bugs." + "reason": "Dummy Conv2d placeholder issue vs SAM3 video OOM; not the same underlying bug." }, { - "left": "issue:42175", - "right": "issue:43316", + "left": "issue:33290", + "right": "issue:35141", "accept": false, - "reason": "Packaging/backend dependency omission is unrelated to a Gemma3 config API mismatch." + "reason": "Optimizer OOM and embedding reinitialization are unrelated." }, { - "left": "issue:43404", - "right": "issue:43441", + "left": "issue:43761", + "right": "issue:44479", "accept": false, - "reason": "Weight tying in Mistral3 and FlashAttention failure in Ministral-3 affect different model paths." + "reason": "CLIP hidden_states regression is unrelated to Qwen VL video-input regression." }, { "left": "issue:33290", - "right": "issue:34689", + "right": "issue:36331", "accept": false, - "reason": "DeepSpeed/Adafactor OOM is not the same problem as Llama 3.2 Vision model loading breaking in 4.46.2." + "reason": "OOM in deepspeed/Adafactor vs Trainer signature TypeError; different layers." }, { - "left": "issue:44162", - "right": "issue:44792", + "left": "issue:43673", + "right": "issue:44743", "accept": false, - "reason": "ESM2 regression and a janus test failure are unrelated model-specific issues." + "reason": "Both involve cache/state, but one is GenerationMixin missing cache in v5 and the other is Qwen recurrent state reset logic." }, { - "left": "issue:25251", - "right": "issue:28282", + "left": "issue:44936", + "right": "issue:45698", "accept": false, - "reason": "Top-k nested-list output in pipeline is unrelated to AutoModel requiring PyTorch at import time." + "reason": "Trainer evaluate-after-train failure is unrelated to loading the wrong custom module." }, { - "left": "issue:43232", - "right": "issue:43388", + "left": "issue:43452", + "right": "issue:44496", "accept": false, - "reason": "Generation kwargs syncing after sync_gpus and metric-gathering label truncation are different runtime bugs." + "reason": "Tokenizer/model gguf_file breakage is different from missing model_type config errors." }, { - "left": "issue:41950", - "right": "issue:43475", + "left": "issue:43575", + "right": "issue:43742", "accept": false, - "reason": "Both are vision/video-adjacent, but one is a pipeline processor lookup bug and the other is a missing Sam3VisionEncoderOutput attribute." + "reason": "Large-model tensor-parallel OOM is unrelated to MobileLLM load key errors." }, { - "left": "issue:43295", - "right": "issue:43825", + "left": "issue:43646", + "right": "issue:44913", "accept": false, - "reason": "Processor/tokenizer regression and a misleading pipeline error message about translation tasks are distinct issues." + "reason": "Custom model init breakage and GPTNeoX rotary_pct reload bug are different code paths." }, { - "left": "issue:45127", - "right": "issue:45200", + "left": "issue:42617", + "right": "issue:43575", "accept": false, - "reason": "LoRA merge with extended vocabulary/tied embeddings is unrelated to Gemma 4 mm_token_type_ids defaulting." + "reason": "3d_parallel.py execution problem is not the same as tensor-parallel OOM on model load." }, { - "left": "issue:44871", - "right": "issue:45584", + "left": "issue:43761", + "right": "issue:44242", "accept": false, - "reason": "Gemma eos_token_id mismatch and Whisper empty-transcription failure after align_special_tokens are different bugs." + "reason": "Vision-model hidden-state regression is unrelated to load-balancing loss omission." }, { - "left": "issue:43550", - "right": "issue:43701", + "left": "issue:41720", + "right": "issue:43575", "accept": false, - "reason": "torch.compile/SDPA failure in Bamba is unrelated to a resume_from_checkpoint key mismatch." + "reason": "cudaErrorAssert on Qwen3 auto device mapping is different from OOM during tensor-parallel loading." }, { - "left": "issue:43606", - "right": "issue:43701", + "left": "issue:44077", + "right": "issue:44534", "accept": false, - "reason": "CPU offload device mismatch and checkpoint key mismatch are different code paths and symptoms." + "reason": "PatchTSMixer post_init policy and non-persistent buffer junk are separate v5 issues." }, { - "left": "issue:43295", + "left": "issue:43931", + "right": "issue:44060", + "accept": false, + "reason": "Model weight shape mismatch and tied-weights warning are different loading/config problems." + }, + { + "left": "issue:44464", "right": "issue:44871", "accept": false, - "reason": "Processor.tokenizer/image passing regression does not match Gemma's eos_token_id configuration inconsistency." + "reason": "Compiled-forward chunked generation inconsistency is unrelated to Gemma eos_token_id configuration." } ] }, @@ -8958,28 +8967,25 @@ "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-390", "nodes": [ - "issue:33290", - "issue:35141", - "issue:36331", "issue:41720", - "issue:42617", "issue:43065", + "issue:43116", + "issue:43295", "issue:43335", - "issue:43452", - "issue:43575", - "issue:43646", - "issue:43673", - "issue:43742", + "issue:43479", + "issue:43540", + "issue:43550", + "issue:43644", + "issue:43650", "issue:43761", "issue:43827", "issue:43906", - "issue:43931", + "issue:43976", "issue:43994", - "issue:44060", "issue:44077", + "issue:44112", "issue:44190", - "issue:44242", - "issue:44464", + "issue:44220", "issue:44479", "issue:44496", "issue:44521", @@ -8988,265 +8994,274 @@ "issue:44617", "issue:44734", "issue:44737", - "issue:44743", "issue:44792", "issue:44855", - "issue:44871", + "issue:44877", "issue:44913", - "issue:44936", + "issue:44938", "issue:44964", "issue:44977", "issue:45127", "issue:45245", + "issue:45276", "issue:45290", "issue:45357", + "issue:45375", "issue:45381", + "issue:45542", "issue:45584", "issue:45588", "issue:45600", - "issue:45698", - "issue:45803" + "issue:45803", + "issue:45834" ], "soft_pairs": [ - "issue:43065|issue:44617", - "issue:43761|issue:44479", - "issue:43673|issue:44743", - "issue:33290|issue:35141", - "issue:33290|issue:36331", - "issue:44936|issue:45698", - "issue:43452|issue:44496", - "issue:43646|issue:44913", - "issue:43575|issue:43742", - "issue:42617|issue:43575", - "issue:43761|issue:44242", - "issue:41720|issue:43575", - "issue:44077|issue:44534", - "issue:43931|issue:44060", - "issue:44464|issue:44871", "issue:44479|issue:44734", "issue:44617|issue:45584", "issue:43827|issue:43994", - "issue:43906|issue:45290", "issue:44792|issue:44977", - "issue:43065|issue:44610", + "issue:43906|issue:45290", "issue:44534|issue:44913", - "issue:44190|issue:44964", + "issue:43065|issue:44610", "issue:41720|issue:45245", + "issue:44190|issue:44964", "issue:44792|issue:45600", "issue:44737|issue:45803", "issue:44855|issue:45588", "issue:44521|issue:45381", "issue:45127|issue:45357", - "issue:43335|issue:44855" + "issue:44938|issue:45542", + "issue:43335|issue:44855", + "issue:43976|issue:44855", + "issue:44077|issue:44877", + "issue:43761|issue:45834", + "issue:43644|issue:44913", + "issue:44496|issue:45803", + "issue:43550|issue:44190", + "issue:43540|issue:44734", + "issue:43650|issue:44220", + "issue:45276|issue:45584", + "issue:44112|issue:45600", + "issue:43335|issue:44190", + "issue:43116|issue:44190", + "issue:43295|issue:45276", + "issue:45245|issue:45584", + "issue:43479|issue:45375" ], - "prepared_review_unit_hash": "b1190f4b804dc823bcfe667b9a5215840e663ca051532759d3d0683f67c3d4df", + "prepared_review_unit_hash": "d86657ae7a7a68960f8125b8ca1e566d5fa972cd8857fcd10989e4a385c34f6a", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 30, - "serialized_chars": 36816, - "estimated_input_tokens": 9204, - "estimated_eval_tokens": 18664 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "serialized_chars": 36434, + "estimated_input_tokens": 9109, + "estimated_eval_tokens": 18474 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is loose and mostly composed of unrelated issue reports across model loading, generation, config, and model-family-specific regressions. I do not see any soft edge that is clearly the same underlying bug or change, so all candidate duplicates should stay separate.", - "confidence": 0.84, - "canonical_issue_reason": "issue:44521 is the strongest cluster anchor: it is open, framework-level, and has the most direct external references around a reproducible multimodal chat-template bug, making it the best representative issue in this otherwise heterogeneous set.", + "summary": "No soft pair appears to describe the same underlying bug or change closely enough to merge. The set is mostly unrelated issues with some superficial overlap in subsystem keywords (e.g. multimodal, pipeline, config, CI).", + "confidence": 0.97, + "canonical_issue_reason": "issue:44521 is the strongest representative issue in the set: it is active, well-scoped, has multiple inbound references, and clearly describes a reproducible multimodal chat-template bug.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44521 is the most suitable single issue to surface because it is broad, actionable, and better connected than the other candidates; the rest are mostly model-specific or symptom-specific one-offs.", + "best_issue_reason": "issue:44521 is the best overall issue to keep as a representative entry because it is specific, actionable, and appears to be the most central/open problem among the listed items.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43065", - "right": "issue:44617", + "left": "issue:44479", + "right": "issue:44734", "accept": false, - "reason": "Same model family, but one is about a dummy Conv2d in Sam3PixelDecoder and the other is a CUDA OOM in Sam3Video; different code paths and failure modes." + "reason": "Both mention video/serving behavior, but one is a multimodal video-input regression and the other is a KV-cache tensor-indexing crash in serve; different code paths and failure modes." }, { - "left": "issue:43761", - "right": "issue:44479", + "left": "issue:44617", + "right": "issue:45584", "accept": false, - "reason": "Different models and symptoms: CLIPVision hidden_states regression versus Qwen/VL video-input regression. Not the same underlying bug." + "reason": "CUDA OOM in Sam3Video is unrelated to Whisper empty-transcription generation failure after token alignment." }, { - "left": "issue:43673", - "right": "issue:44743", + "left": "issue:43827", + "right": "issue:43994", "accept": false, - "reason": "Both involve cache behavior, but one is a GenerationMixin/chunked_prefill regression and the other is recurrent states resetting in modular_qwen3_5; distinct defects." + "reason": "One is documentation cleanup after pipeline removals; the other is a model/pipeline behavior bug for SigLIP2. Same word \"pipeline\" only, not same issue." }, { - "left": "issue:33290", - "right": "issue:35141", + "left": "issue:44792", + "right": "issue:44977", "accept": false, - "reason": "OOM with Adafactor/DeepSpeed is unrelated to token-embedding resizing and post_init reinitialization when tie_word_embedding is False." + "reason": "Janus image-generation test failure and Qwen3.5 flash-attention generation bug are different models and different failure mechanisms." }, { - "left": "issue:33290", - "right": "issue:36331", + "left": "issue:43906", + "right": "issue:45290", "accept": false, - "reason": "Optimizer OOM and a CustomTrainer signature TypeError are unrelated bugs." + "reason": "A reproduction issue for an external report is not enough to equate it with a specific apply_chat_template crash on tool-call assistant messages." }, { - "left": "issue:44936", - "right": "issue:45698", + "left": "issue:44534", + "right": "issue:44913", "accept": false, - "reason": "trainer.evaluate() failing after train is a training-loop issue, while from_pretrained loading the wrong custom module after save_pretrained is a serialization/loading issue." + "reason": "Non-persistent buffer initialization junk and GPTNeoXConfig rotary_pct reload behavior are separate config/runtime bugs." }, { - "left": "issue:43452", - "right": "issue:44496", + "left": "issue:43065", + "right": "issue:44610", "accept": false, - "reason": "Both are loading-related, but gguf_file breakage for AutoTokenizer/AutoModel and a missing model_type in config.json are different failure classes." + "reason": "Dummy Conv2d in Sam3PixelDecoder and OmDet-Turbo processor size mismatch are unrelated vision-model problems." }, { - "left": "issue:43646", - "right": "issue:44913", + "left": "issue:41720", + "right": "issue:45245", "accept": false, - "reason": "A broad Transformers v5 custom-model init regression is not the same as GPTNeoXConfig rotary_pct losing persistence on reload." + "reason": "Qwen3 auto device-map cudaErrorAssert and category-count limit 2^24 are different errors with no shared code path." }, { - "left": "issue:43575", - "right": "issue:43742", + "left": "issue:44190", + "right": "issue:44964", "accept": false, - "reason": "Qwen2-57B-A14B-Instruct tensor-parallel OOM and MobileLLM-125M key-error loading are distinct load-time failures." + "reason": "Local dataset loading in an example script and loading a Phi-4 multimodal model are unrelated failure reports." }, { - "left": "issue:42617", - "right": "issue:43575", + "left": "issue:44792", + "right": "issue:45600", "accept": false, - "reason": "run_image_classification_no_trainer.py failing to run is unrelated to OOM when loading Qwen2-57B-A14B-Instruct with tensor parallelism." + "reason": "A Janus generation test and stale auto_mappings references for Sam3LiteText are different subsystems and different bugs." }, { - "left": "issue:43761", - "right": "issue:44242", + "left": "issue:44737", + "right": "issue:45803", "accept": false, - "reason": "CLIPVision hidden_states regression and missing load-balancing loss when output_router_logits=False are different model and loss-path bugs." + "reason": "CPU device placement bug in XLNet relative positions is unrelated to a bare except swallowing errors in Fuyu tensor conversion." }, { - "left": "issue:41720", - "right": "issue:43575", + "left": "issue:44855", + "right": "issue:45588", "accept": false, - "reason": "Both mention model loading/resource pressure, but Qwen3 auto device mapping cudaErrorAssert and Qwen2-57B tensor-parallel OOM are not the same bug." + "reason": "Python 3.13 import parsing failure in DebertaV2 and flash-attention sink-less crash are unrelated." }, { - "left": "issue:44077", - "right": "issue:44534", + "left": "issue:44521", + "right": "issue:45381", "accept": false, - "reason": "patchtsmixer post_init policy and non-persistent buffers being filled with junk are different regressions, even if both touch initialization." + "reason": "assistant_masks being all-zero for multimodal inputs is not the same concrete bug as wrong vision_position_ids in qwen2.5-vl video input handling." }, { - "left": "issue:43931", - "right": "issue:44060", + "left": "issue:45127", + "right": "issue:45357", "accept": false, - "reason": "One is a Qwen3-VL weight-shape mismatch on load; the other is a tied-weights warning incorrectly linking embed_tokens.weight to dt_bias. Related area, different bug." + "reason": "LoRA merge collapse with extended vocab and incorrect visual encoder keys on save_pretrained are different Qwen-related issues, not the same bug." }, { - "left": "issue:44464", - "right": "issue:44871", + "left": "issue:44938", + "right": "issue:45542", "accept": false, - "reason": "Chunked generation inconsistency with compiled forward is unrelated to Gemma-3 eos_token_id config mismatch." + "reason": "Python 3.14 import/load failure and tensorboard-only TensorFlow backend error are unrelated environment/package issues." }, { - "left": "issue:44479", - "right": "issue:44734", + "left": "issue:43335", + "right": "issue:44855", "accept": false, - "reason": "A video-input regression in Qwen multimodal models is not the same as a serve /v1/responses KV-cache continuation tensor-indexing crash." + "reason": "SwitchTransformers sparse-layer construction and DebertaV2 import parsing are unrelated." }, { - "left": "issue:44617", - "right": "issue:45584", + "left": "issue:43976", + "right": "issue:44855", "accept": false, - "reason": "Sam3Video CUDA OOM and Whisper empty-transcription failure after align_special_tokens are unrelated bugs." + "reason": "Python-version compatibility regression and a JIT/decorator parsing issue are not the same defect." }, { - "left": "issue:43827", - "right": "issue:43994", + "left": "issue:44077", + "right": "issue:44877", "accept": false, - "reason": "Docs still referencing pipeline() and SigLIP2 producing nonsensical outputs via AutoModel/pipeline are not the same underlying issue." + "reason": "Optional post_init in patchtsmixer config and strict config blocking granite_speech loading are different config-validation problems." }, { - "left": "issue:43906", - "right": "issue:45290", + "left": "issue:43761", + "right": "issue:45834", "accept": false, - "reason": "An isolated reproduction of a prior issue is not the same as a crash in apply_chat_template with tool calls and no content." + "reason": "CLIPVisionModel hidden_states regression and Kosmos2.5 long-OCR index error are unrelated model bugs." }, { - "left": "issue:44792", - "right": "issue:44977", + "left": "issue:43644", + "right": "issue:44913", "accept": false, - "reason": "Failed janus image-generation test and Qwen3.5 flash-attention generation bug are different models and different failure surfaces." + "reason": "Non-persistent buffers filled with junk and GPTNeoX rotary_pct reset on reload are different failure classes." }, { - "left": "issue:43065", - "right": "issue:44610", + "left": "issue:44496", + "right": "issue:45803", "accept": false, - "reason": "Dummy Conv2d in Sam3PixelDecoder is unrelated to OmDet-Turbo processor producing 640px inputs instead of 224px." + "reason": "Unrecognized model_type for a specific model repo and a bare except in Fuyu tensor conversion are unrelated." }, { - "left": "issue:44534", - "right": "issue:44913", + "left": "issue:43550", + "right": "issue:44190", "accept": false, - "reason": "Non-persistent buffers being filled with junk and GPTNeoX rotary_pct not persisting on reload are both config/state bugs, but not the same one." + "reason": "torch.compile/SDPA failure in Bamba and dataset loading in an example script are not the same underlying issue." }, { - "left": "issue:44190", - "right": "issue:44964", + "left": "issue:43540", + "right": "issue:44734", "accept": false, - "reason": "A local dataset loading failure in a training script is unrelated to loading microsoft/Phi-4-multimodal-instruct with transformers." + "reason": "Qwen3OmniMoe video-input ValueError and serve KV-cache continuation indexing crash affect different paths and models." }, { - "left": "issue:41720", - "right": "issue:45245", + "left": "issue:43650", + "right": "issue:44220", "accept": false, - "reason": "Qwen3 auto device mapping cudaErrorAssert and the 2^24 category-limit RuntimeError are completely different problems." + "reason": "Generic placeholder issue and an fbank feature extraction bug are unrelated." }, { - "left": "issue:44792", + "left": "issue:45276", + "right": "issue:45584", + "accept": false, + "reason": "Gemma4 embedding resize mismatch and Whisper empty-transcription generation failure are different model-specific bugs." + }, + { + "left": "issue:44112", "right": "issue:45600", "accept": false, - "reason": "Janus image-generation test failure and stale auto_mappings references to removed Sam3LiteText configs are unrelated." + "reason": "A stale GraniteSpeech CI test and broken auto_mappings references for removed Sam3LiteText configs are different CI failures." }, { - "left": "issue:44737", - "right": "issue:45803", + "left": "issue:43335", + "right": "issue:44190", "accept": false, - "reason": "XLNet CPU placement regression and FuyuBatchFeature's bare except swallowing errors are different code paths and bugs." + "reason": "SwitchTransformers config bug and image-classification example local dataset loading bug are unrelated." }, { - "left": "issue:44855", - "right": "issue:45588", + "left": "issue:43116", + "right": "issue:44190", "accept": false, - "reason": "Python 3.13 IndentationError in DebertaV2 import and flash_attention AttributeError on s_aux=None are unrelated." + "reason": "Text classification example always empty results and image classification local dataset loading are different example-script issues." }, { - "left": "issue:44521", - "right": "issue:45381", + "left": "issue:43295", + "right": "issue:45276", "accept": false, - "reason": "Both are multimodal/template-adjacent regressions, but all-zero assistant masks and wrong vision_position_ids are distinct symptoms and likely distinct fixes." + "reason": "Processor/tokenizer API regression and Gemma4 embedding resize behavior do not describe the same code path." }, { - "left": "issue:45127", - "right": "issue:45357", + "left": "issue:45245", + "right": "issue:45584", "accept": false, - "reason": "LoRA merge collapse with extended vocabulary and Qwen3.5 save_pretrained writing incorrect visual encoder keys are different save/merge issues." + "reason": "Category-count limit RuntimeError and Whisper empty transcription failure are unrelated." }, { - "left": "issue:43335", - "right": "issue:44855", + "left": "issue:43479", + "right": "issue:45375", "accept": false, - "reason": "SwitchTransformers sparse-layer creation with num_sparse_encoder_layers=0 has nothing in common with the DebertaV2 Python 3.13 import parse error." + "reason": "Incorrect default config initialization when None is passed and missing deepstack_visual_indexes in strict config are separate config bugs." } ] }, @@ -9274,296 +9289,290 @@ "issue:38175", "issue:38617", "issue:41628", + "issue:41950", + "issue:42175", + "issue:42907", "issue:43065", - "issue:43116", "issue:43295", - "issue:43335", + "issue:43299", + "issue:43388", "issue:43404", - "issue:43479", - "issue:43540", - "issue:43550", - "issue:43644", - "issue:43650", - "issue:43761", - "issue:43976", - "issue:44077", + "issue:43441", + "issue:43526", + "issue:43531", + "issue:43643", + "issue:43673", + "issue:43688", + "issue:43854", + "issue:43901", + "issue:44016", "issue:44112", "issue:44186", - "issue:44190", "issue:44220", "issue:44246", + "issue:44279", + "issue:44336", "issue:44464", "issue:44466", "issue:44496", "issue:44561", "issue:44683", "issue:44734", - "issue:44743", - "issue:44855", - "issue:44877", "issue:44913", "issue:44933", - "issue:44938", + "issue:44964", "issue:45003", + "issue:45042", "issue:45216", - "issue:45245", - "issue:45276", + "issue:45335", "issue:45362", - "issue:45375", "issue:45406", "issue:45446", - "issue:45542", "issue:45563", "issue:45584", "issue:45600", - "issue:45632", - "issue:45803" + "issue:45632" ], "soft_pairs": [ - "issue:44938|issue:45542", - "issue:43550|issue:44190", - "issue:43976|issue:44855", - "issue:44077|issue:44877", - "issue:44496|issue:45803", - "issue:43644|issue:44913", - "issue:43761|issue:44743", - "issue:43540|issue:44734", - "issue:43650|issue:44220", - "issue:44112|issue:45600", - "issue:45276|issue:45584", - "issue:43335|issue:44190", - "issue:43116|issue:44190", - "issue:43295|issue:45276", - "issue:45245|issue:45584", - "issue:43479|issue:45375", - "issue:44933|issue:45362", "issue:36246|issue:41628", + "issue:44933|issue:45362", "issue:44464|issue:45563", - "issue:44186|issue:44734", "issue:43404|issue:45216", + "issue:44186|issue:44734", "issue:44734|issue:45632", "issue:44683|issue:45446", "issue:44561|issue:45632", - "issue:38175|issue:43065", "issue:44466|issue:44913", + "issue:38175|issue:43065", "issue:44246|issue:45003", "issue:36246|issue:38617", - "issue:45406|issue:45632" + "issue:43643|issue:44496", + "issue:45406|issue:45632", + "issue:45563|issue:45584", + "issue:41950|issue:44016", + "issue:44964|issue:45600", + "issue:43388|issue:43688", + "issue:42907|issue:43441", + "issue:44112|issue:44964", + "issue:43295|issue:45335", + "issue:43854|issue:44964", + "issue:44016|issue:44220", + "issue:44496|issue:45042", + "issue:43673|issue:44336", + "issue:43299|issue:45216", + "issue:43531|issue:45600", + "issue:43526|issue:43901", + "issue:42175|issue:44279", + "issue:45335|issue:45584" ], - "prepared_review_unit_hash": "087c4488a0c1eb0e4f60404e3e20a53b0c058c8ad18915d6fe4253728c4ce3f8", + "prepared_review_unit_hash": "6a20e8f7a6092f273e5bc0e4614408b970ec4f9920a9526b7badeea82762cac1", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 29, - "serialized_chars": 36474, - "estimated_input_tokens": 9119, - "estimated_eval_tokens": 18494 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36122, + "estimated_input_tokens": 9031, + "estimated_eval_tokens": 18318 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "All soft pairs are false positives: they share broad Transformers themes (imports, configs, multimodal, caching, CI) but each describes a distinct failure mode, model, or code path. No safe duplicate merges here.", - "confidence": 0.95, - "canonical_issue_reason": "No canonical issue: the items are unrelated bug reports rather than one duplicate cluster.", - "canonical_pr_reason": "No pull requests were provided.", - "best_issue_reason": "issue:44734 is the strongest standalone report: it has a specific failing endpoint (/v1/responses), a clear symptom (KV cache continuation crash), and a concrete code-path clue (wrong tensor indexing).", + "summary": "The set is heterogeneous: the soft-similar pairs mostly share broad keywords (imports, generation, model loading, save/load, vision, trust_remote_code) but not the same concrete bug or fix. I would not merge any of the suggested pairs as duplicates.", + "confidence": 0.94, + "canonical_issue_reason": "issue:41628 is the cleanest broad user-facing import regression in the set, but there is no true duplicate cluster here.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:41628 is the best overall anchor if one must pick a representative, though it still does not subsume the other reports.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44938", - "right": "issue:45542", + "left": "issue:36246", + "right": "issue:41628", "accept": false, - "reason": "Different problems: Python 3.14 load failure vs TensorBoard-only-without-TF backend error." + "reason": "Both are import errors, but for different missing symbols and different code paths; not the same bug." }, { - "left": "issue:43550", - "right": "issue:44190", + "left": "issue:44933", + "right": "issue:45362", "accept": false, - "reason": "Unrelated: torch.compile/SDPA failure in Bamba vs local dataset loading in an image-classification example." + "reason": "Different failures: missing image-utils import vs Qwen3.5 chat crash." }, { - "left": "issue:43976", - "right": "issue:44855", + "left": "issue:44464", + "right": "issue:45563", "accept": false, - "reason": "Both are Python-version issues, but one is package support/release compatibility and the other is a DebertaV2 import parse/indentation error." + "reason": "One is a generation correctness bug, the other a stale warning; not the same change." }, { - "left": "issue:44077", - "right": "issue:44877", + "left": "issue:43404", + "right": "issue:45216", "accept": false, - "reason": "Both touch config handling, but one is a model-specific post_init constraint and the other is strict config loading for granite_speech." + "reason": "Both involve tied weights/serialization, but they are different models and different failure modes." }, { - "left": "issue:44496", - "right": "issue:45803", + "left": "issue:44186", + "right": "issue:44734", "accept": false, - "reason": "Unrelated: unrecognized OLMo model config vs a bare-except bug in FuyuBatchFeature tensor conversion." + "reason": "Tokenizer padding/NER crash versus serve KV-cache indexing crash; unrelated code paths." }, { - "left": "issue:43644", - "right": "issue:44913", + "left": "issue:44734", + "right": "issue:45632", "accept": false, - "reason": "Different bugs: non-persistent buffer serialization junk vs GPTNeoX rotary_pct not persisting on reload." + "reason": "Serve cache indexing bug and trust_remote_code cache-path collision are separate problems." }, { - "left": "issue:43761", - "right": "issue:44743", + "left": "issue:44683", + "right": "issue:45446", "accept": false, - "reason": "Both involve forward-state behavior, but CLIP hidden_states omission and Qwen recurrent state reset are separate model-specific defects." + "reason": "Both touch flex_attention, but one is a runtime failure on torch 2.9 and the other is a version-check/import issue." }, { - "left": "issue:43540", - "right": "issue:44734", + "left": "issue:44561", + "right": "issue:45632", "accept": false, - "reason": "Different code paths: Qwen3OmniMoe video input validation vs serve KV-cache continuation indexing." + "reason": "Different trust_remote_code/cache behaviors; not the same defect." }, { - "left": "issue:43650", - "right": "issue:44220", + "left": "issue:44466", + "right": "issue:44913", "accept": false, - "reason": "A data-request issue and an audio feature extraction bug are not the same underlying problem." + "reason": "Serialization of tied weights and GPTNeoX config reload are unrelated bugs." }, { - "left": "issue:44112", - "right": "issue:45600", + "left": "issue:38175", + "right": "issue:43065", "accept": false, - "reason": "Both are CI breakages, but one is a stale GraniteSpeech device-override test and the other is outdated auto_mappings references." + "reason": "Different vision-model issues with no shared concrete failure path." }, { - "left": "issue:45276", - "right": "issue:45584", + "left": "issue:44246", + "right": "issue:45003", "accept": false, - "reason": "Different models and symptoms: Gemma4 embedding resize propagation vs Whisper empty-transcription generation after token alignment." + "reason": "Import slowness is a performance issue; unsafe sys.modules access is a different implementation bug." }, { - "left": "issue:43335", - "right": "issue:44190", + "left": "issue:36246", + "right": "issue:38617", "accept": false, - "reason": "SwitchTransformers sparse-layer construction and example-script dataset loading are unrelated." + "reason": "Both are ImportErrors, but for different missing APIs and modules." }, { - "left": "issue:43116", - "right": "issue:44190", + "left": "issue:43643", + "right": "issue:44496", "accept": false, - "reason": "Both reference example scripts, but one is multi-label classification output handling and the other is local dataset loading." + "reason": "One is missing fields when using trust_remote_code; the other is a missing model_type in config." }, { - "left": "issue:43295", - "right": "issue:45276", + "left": "issue:45406", + "right": "issue:45632", "accept": false, - "reason": "Custom processor.tokenizer/image passing regression is unrelated to Gemma4 embedding resize behavior." + "reason": "Gemma4Processor _tokenizer crash is unrelated to the local-model cache-path collision." }, { - "left": "issue:45245", + "left": "issue:45563", "right": "issue:45584", "accept": false, - "reason": "Completely different failures: category-count limit vs Whisper empty transcription handling." + "reason": "A stale warning and an empty-transcription generation failure are not the same bug." }, { - "left": "issue:43479", - "right": "issue:45375", + "left": "issue:41950", + "right": "issue:44016", "accept": false, - "reason": "Both are multimodal config bugs, but they concern different models and different fields/defaulting behavior." + "reason": "Pipeline image-processor lookup bug versus a notebook syntax error." }, { - "left": "issue:44933", - "right": "issue:45362", + "left": "issue:44964", + "right": "issue:45600", "accept": false, - "reason": "Nonexistent image_utils import and Qwen3.5 chat crash are distinct issues." + "reason": "Model-loading regression and auto_mappings CI breakage are separate issues." }, { - "left": "issue:36246", - "right": "issue:41628", + "left": "issue:43388", + "right": "issue:43688", "accept": false, - "reason": "Both are import errors, but for different symbols and modules: Qwen2_5_VLImageProcessor vs AutoImageProcessor." + "reason": "Different training/evaluation bugs: dropped labels versus auxiliary-loss normalization." }, { - "left": "issue:44464", - "right": "issue:45563", + "left": "issue:42907", + "right": "issue:43441", "accept": false, - "reason": "Chunked generation with compiled forward and a stale num_return_sequences warning are unrelated generation issues." + "reason": "Saving dequantized checkpoints and FlashAttention load failure are different model-specific regressions." }, { - "left": "issue:44186", - "right": "issue:44734", + "left": "issue:44112", + "right": "issue:44964", "accept": false, - "reason": "Tokenizer NER/padding crash is unrelated to serve-side KV-cache continuation indexing." + "reason": "CI stale-test failure is unrelated to Phi-4 multimodal loading." }, { - "left": "issue:43404", - "right": "issue:45216", + "left": "issue:43295", + "right": "issue:45335", "accept": false, - "reason": "Both involve weights/tied serialization, but one is Mistral3 lm_head tying and the other is Qwen3.5 save_pretrained checkpoint correctness." + "reason": "Processor/tokenizer regression and t5gemma embedding resize bug are distinct code paths." }, { - "left": "issue:44734", - "right": "issue:45632", + "left": "issue:43854", + "right": "issue:44964", "accept": false, - "reason": "Serve KV-cache crash and trust_remote_code cache-path collision are different subsystems and failure modes." + "reason": "Both are model-loading problems, but for different models and different root causes." }, { - "left": "issue:44683", - "right": "issue:45446", + "left": "issue:44016", + "right": "issue:44220", "accept": false, - "reason": "Flex attention on torch>=2.9 and an incorrect version check for AuxRequest import are separate flex_attention bugs." + "reason": "Notebook syntax error versus audio feature extraction bug." }, { - "left": "issue:44561", - "right": "issue:45632", + "left": "issue:44496", + "right": "issue:45042", "accept": false, - "reason": "Trust_remote_code API removal breakage and local cache-path collision are unrelated." + "reason": "Unrecognized model config and PIL/torchvision dependency regression are unrelated." }, { - "left": "issue:38175", - "right": "issue:43065", + "left": "issue:43673", + "right": "issue:44336", "accept": false, - "reason": "Different model correctness bugs: SIGLIP2 zero probabilities vs Sam3PixelDecoder dummy Conv2d." + "reason": "Generation cache regression and ANSI logging output issue are unrelated." }, { - "left": "issue:44466", - "right": "issue:44913", + "left": "issue:43299", + "right": "issue:45216", "accept": false, - "reason": "Inconsistent lm_head.weight serialization by device is unrelated to GPTNeoX rotary_pct reload behavior." + "reason": "Different Qwen-related regressions: model loading versus save_pretrained checkpoint correctness." }, { - "left": "issue:44246", - "right": "issue:45003", + "left": "issue:43531", + "right": "issue:45600", "accept": false, - "reason": "Import-time slowness and unsafe sys.modules access may be adjacent, but they are not the same bug." + "reason": "Sliding-window behavior in Qwen3-MoE and removed Sam3LiteText configs are unrelated." }, { - "left": "issue:36246", - "right": "issue:38617", + "left": "issue:43526", + "right": "issue:43901", "accept": false, - "reason": "Different missing imports from different modules; no shared underlying defect." + "reason": "Image processor label reduction bug versus documentation mismatch." }, { - "left": "issue:45406", - "right": "issue:45632", + "left": "issue:42175", + "right": "issue:44279", "accept": false, - "reason": "Gemma4Processor missing _tokenizer and trust_remote_code cache-path collision are unrelated." + "reason": "Dependency/package-install issue and vague dependency issue are not the same concrete bug." }, { - "left": "issue:45245", + "left": "issue:45335", "right": "issue:45584", "accept": false, - "reason": "Category-cardinality runtime error and Whisper empty-transcription failure do not match." - }, - { - "left": "issue:43761", - "right": "issue:45276", - "accept": false, - "reason": "Hidden-state return regression in CLIPVisionModel and Gemma4 embedding resize propagation are different bugs." + "reason": "Decoder embedding resize bug and Whisper empty-transcription failure are separate." } ] }, @@ -9587,9 +9596,11 @@ "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-390", "nodes": [ + "issue:32090", + "issue:35141", + "issue:38175", + "issue:39692", "issue:41950", - "issue:42175", - "issue:42907", "issue:43295", "issue:43299", "issue:43381", @@ -9597,12 +9608,8 @@ "issue:43441", "issue:43479", "issue:43525", - "issue:43526", - "issue:43531", "issue:43577", - "issue:43643", - "issue:43673", - "issue:43688", + "issue:43650", "issue:43824", "issue:43827", "issue:43854", @@ -9611,49 +9618,34 @@ "issue:44016", "issue:44062", "issue:44075", - "issue:44112", - "issue:44220", "issue:44242", "issue:44279", - "issue:44336", + "issue:44297", "issue:44351", "issue:44368", + "issue:44462", "issue:44496", + "issue:44617", + "issue:44683", + "issue:44779", "issue:44933", - "issue:44964", + "issue:44987", "issue:45020", - "issue:45042", + "issue:45081", "issue:45200", "issue:45216", "issue:45278", - "issue:45335", "issue:45357", "issue:45405", - "issue:45563", - "issue:45584", + "issue:45542", "issue:45593", "issue:45600", + "issue:45712", "issue:45759", - "issue:45823" + "issue:45823", + "issue:45834" ], "soft_pairs": [ - "issue:43643|issue:44496", - "issue:45563|issue:45584", - "issue:41950|issue:44016", - "issue:44964|issue:45600", - "issue:43388|issue:43688", - "issue:42907|issue:43441", - "issue:44112|issue:44964", - "issue:43673|issue:44336", - "issue:43854|issue:44964", - "issue:43295|issue:45335", - "issue:44016|issue:44220", - "issue:44496|issue:45042", - "issue:43299|issue:45216", - "issue:43531|issue:45600", - "issue:43526|issue:43901", - "issue:42175|issue:44279", - "issue:45335|issue:45584", "issue:44075|issue:44368", "issue:43381|issue:45593", "issue:43299|issue:45357", @@ -9668,228 +9660,218 @@ "issue:43479|issue:43525", "issue:43577|issue:45216", "issue:43824|issue:44933", - "issue:41950|issue:45823" + "issue:41950|issue:45823", + "issue:44683|issue:45542", + "issue:43299|issue:43854", + "issue:44279|issue:45405", + "issue:39692|issue:43901", + "issue:38175|issue:44617", + "issue:32090|issue:35141", + "issue:44462|issue:45081", + "issue:41950|issue:43650", + "issue:43295|issue:44779", + "issue:44297|issue:44462", + "issue:43976|issue:44279", + "issue:45600|issue:45712", + "issue:43976|issue:44987", + "issue:43441|issue:45834" ], - "prepared_review_unit_hash": "12efc491e19a9a7d25c34105d723b2b15b1d567b9ab0a88b9f6cc7731eadd812", + "prepared_review_unit_hash": "c95be6db3523bd269f3dbd828c872f44040358db89e5f490f1db6d3b8020674d", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 32, - "serialized_chars": 37273, - "estimated_input_tokens": 9319, - "estimated_eval_tokens": 18894 + "soft_pair_count": 29, + "serialized_chars": 36498, + "estimated_input_tokens": 9125, + "estimated_eval_tokens": 18506 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is dominated by unrelated Transformers regressions around model loading/imports, config handling, processor behavior, and a few training/inference edge cases. The issues are broadly version-regression themed, but the concrete root causes differ too much to collapse them into one duplicate group.", - "confidence": 0.78, - "canonical_issue_reason": "issue:45020 is the best umbrella anchor: it explicitly frames the broader class of recent-version breakages around remote/custom-code model loading, which matches many of the other import/load regression reports in this set better than the narrower model-specific tickets.", + "summary": "These issues are mostly broad Transformers regressions and docs/model-loading bugs, but the soft pairs do not describe the same underlying defect closely enough to merge as duplicates. I would treat this cluster as largely non-duplicate and keep a broad umbrella issue only as a loose organizer, not a canonical duplicate.", + "confidence": 0.91, + "canonical_issue_reason": "issue:45020 is the broadest representative report in the set, covering recent-version breakage for remote-code models. It is the best umbrella candidate, though it is not a true duplicate of the others.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45020 is the strongest global representative because it is broad, clearly articulated, and open, making it a better cluster entry point than the more generic or highly model-specific issues.", + "best_issue_reason": "issue:45020 is the most general user-facing regression report and can serve as the cluster\u2019s loose anchor.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43643", - "right": "issue:44496", - "accept": false, - "reason": "Both are loading/config failures, but one is missing fields with trust_remote_code and the other is an unrecognized model type; different concrete bugs." - }, - { - "left": "issue:45563", - "right": "issue:45584", - "accept": false, - "reason": "One is a stale warning in generation, the other is an empty-transcription failure in Whisper; not the same code path." - }, - { - "left": "issue:41950", - "right": "issue:44016", - "accept": false, - "reason": "Video-classification processor lookup and a notebook syntax error are unrelated." - }, - { - "left": "issue:44964", - "right": "issue:45600", + "left": "issue:44075", + "right": "issue:44368", "accept": false, - "reason": "Both touch model-loading infrastructure, but they target different models and different failure modes (multimodal load vs auto-mapping CI breakage)." + "reason": "Different bugs: unused SGD args vs a tie_word_embeddings warning during Qwen3.5 LoRA fine-tuning." }, { - "left": "issue:43388", - "right": "issue:43688", + "left": "issue:43381", + "right": "issue:45593", "accept": false, - "reason": "Training/metrics loss issues in different subsystems; no shared underlying bug." + "reason": "Different code paths: gradient checkpointing in eval mode vs D-FINE auxiliary losses with denoising disabled." }, { - "left": "issue:42907", - "right": "issue:43441", + "left": "issue:43299", + "right": "issue:45357", "accept": false, - "reason": "Same model family, but saving dequantized weights and FlashAttention loading are separate problems." + "reason": "Both are Qwen-related, but one is a model-loading regression and the other is a save_pretrained serialization bug." }, { - "left": "issue:44112", - "right": "issue:44964", + "left": "issue:44496", + "right": "issue:45759", "accept": false, - "reason": "A CI device-override test failure is unrelated to a Phi-4 model loading bug." + "reason": "Different problems: tokenizer file selection vs from_config unwrapping of composite multimodal configs." }, { - "left": "issue:43673", - "right": "issue:44336", + "left": "issue:43901", + "right": "issue:44496", "accept": false, - "reason": "Generation cache behavior and ANSI formatting in loading_report are unrelated." + "reason": "Docs mismatch for return_all_scores is unrelated to tokenizer loading behavior." }, { - "left": "issue:43854", - "right": "issue:44964", + "left": "issue:44351", + "right": "issue:45278", "accept": false, - "reason": "Both are model load failures, but they affect different models with no shared root cause shown." + "reason": "Both mention imports, but one is a specific missing symbol and the other is a broad post-upgrade import breakage report." }, { - "left": "issue:43295", - "right": "issue:45335", + "left": "issue:44242", + "right": "issue:45200", "accept": false, - "reason": "One is processor/tokenizer API regression, the other is embedding resize behavior in T5Gemma; different paths." + "reason": "Unrelated training-loss bug vs Gemma 4 text-only fine-tuning token-type defaulting." }, { "left": "issue:44016", - "right": "issue:44220", + "right": "issue:44062", "accept": false, - "reason": "Notebook syntax error and audio feature extraction bug are unrelated." + "reason": "Notebook syntax error and AddedToken argument handling are separate failures." }, { - "left": "issue:44496", - "right": "issue:45042", + "left": "issue:43388", + "right": "issue:43827", "accept": false, - "reason": "Unrecognized-model/config issue versus an image-processor torchvision dependency regression." + "reason": "Metric gathering drops tuple labels; docs still referencing pipeline() is a separate documentation issue." }, { - "left": "issue:43299", - "right": "issue:45216", + "left": "issue:43976", + "right": "issue:45405", "accept": false, - "reason": "Both are Qwen-related regressions, but one is loading and the other is save_pretrained checkpoint serialization; not mergeable as one fix." + "reason": "Python compatibility issue vs unreleased dependency bump; not the same defect." }, { - "left": "issue:43531", - "right": "issue:45600", + "left": "issue:41950", + "right": "issue:45020", "accept": false, - "reason": "Sliding-window behavior in Qwen3-MoE and removed config references in auto_mappings are different bugs." + "reason": "Video-classification processor lookup is a pipeline-specific bug, not the remote_code regression described in 45020." }, { - "left": "issue:43526", - "right": "issue:43901", + "left": "issue:43479", + "right": "issue:43525", "accept": false, - "reason": "Processor label reduction bug and documentation mismatch for text classification are not the same underlying issue." + "reason": "Different config initialization/attribute bugs in unrelated model classes." }, { - "left": "issue:42175", - "right": "issue:44279", + "left": "issue:43577", + "right": "issue:45216", "accept": false, - "reason": "Package extras/backend dependency composition versus a general dependency issue; too vague to unify." + "reason": "BLIP2 dtype loading issue vs Qwen3.5 save_pretrained regression are distinct." }, { - "left": "issue:45335", - "right": "issue:45584", + "left": "issue:43824", + "right": "issue:44933", "accept": false, - "reason": "Embedding resize regression and Whisper empty-output failure are unrelated." + "reason": "Different missing-import problems affecting different modules/symbols." }, { - "left": "issue:44075", - "right": "issue:44368", + "left": "issue:41950", + "right": "issue:45823", "accept": false, - "reason": "Optimizer argument handling and a tied-embeddings warning are different concerns." + "reason": "Pipeline processor lookup and Gemma4 PLE device mismatch are unrelated issues." }, { - "left": "issue:43381", - "right": "issue:45593", + "left": "issue:44683", + "right": "issue:45542", "accept": false, - "reason": "Gradient checkpointing in eval mode and D-FINE auxiliary-loss behavior are unrelated." + "reason": "Compiled flex_attention on torch>=2.9 is unrelated to the tensorboard/tensorflow backend issue." }, { "left": "issue:43299", - "right": "issue:45357", - "accept": false, - "reason": "Same broad model family, but save_pretrained serialization bugs on different versions and paths; not the same bug." - }, - { - "left": "issue:44496", - "right": "issue:45759", + "right": "issue:43854", "accept": false, - "reason": "Both involve config/model resolution, but one is an unrecognized remote model and the other is unwrap logic for composite multimodal configs." + "reason": "Both are model-loading failures, but they involve different models and failure modes." }, { - "left": "issue:43901", - "right": "issue:44496", + "left": "issue:44279", + "right": "issue:45405", "accept": false, - "reason": "Docs wording for a pipeline is unrelated to a model-loading failure." + "reason": "Generic dependency issue vs PEFT version floor bump; no shared underlying bug." }, { - "left": "issue:44351", - "right": "issue:45278", + "left": "issue:39692", + "right": "issue:43901", "accept": false, - "reason": "Both mention import failures, but 45278 is a broad symptom report while 44351 is a specific missing export; not enough evidence of one defect." + "reason": "Doc example errors for SigLIP2 are unrelated to text-classification pipeline docs." }, { - "left": "issue:44242", - "right": "issue:45200", + "left": "issue:38175", + "right": "issue:44617", "accept": false, - "reason": "Router-logit loss handling and Gemma4 token-type defaults are separate training bugs." + "reason": "Unexpected probabilities in SigLIP2 is unrelated to Sam3Video OOM." }, { - "left": "issue:44016", - "right": "issue:44062", + "left": "issue:32090", + "right": "issue:35141", "accept": false, - "reason": "Notebook syntax error and AddedToken keyword collision are unrelated." + "reason": "Trainer GPU broadcast TypeError and embedding reinitialization after resize are different bugs." }, { - "left": "issue:43388", - "right": "issue:43827", + "left": "issue:44462", + "right": "issue:45081", "accept": false, - "reason": "Metric label truncation and stale docs references are entirely different categories." + "reason": "AutoTokenizer ignoring tokenizer.json and Mistral regex patch failing on backend_tokenizer are separate tokenizer-loading defects." }, { - "left": "issue:43976", - "right": "issue:45405", + "left": "issue:41950", + "right": "issue:43650", "accept": false, - "reason": "Python version compatibility and a PEFT minimum-version bump are not the same bug." + "reason": "A real pipeline bug vs a non-informative issue title; no duplicate evidence." }, { - "left": "issue:41950", - "right": "issue:45020", + "left": "issue:43295", + "right": "issue:44779", "accept": false, - "reason": "Both are regressions, but one is pipeline processor selection and the other is remote_code model loading; too broad to merge." + "reason": "Custom model code regression around processor.tokenizer/images-to-tokenizer differs from Deepseek tokenizer incorrect results." }, { - "left": "issue:43479", - "right": "issue:43525", + "left": "issue:44297", + "right": "issue:44462", "accept": false, - "reason": "Different config classes, different missing/default fields, and different failure modes." + "reason": "Tokenizer class metadata written on save vs AutoTokenizer ignoring tokenizer.json are related to tokenizers but not the same bug." }, { - "left": "issue:43577", - "right": "issue:45216", + "left": "issue:45600", + "right": "issue:45712", "accept": false, - "reason": "BLIP2 dtype propagation and Qwen3.5 checkpoint serialization are unrelated." + "reason": "Stale auto_mappings entries and leftover dummy classes are separate cleanup/CI failures." }, { - "left": "issue:43824", - "right": "issue:44933", + "left": "issue:43976", + "right": "issue:44987", "accept": false, - "reason": "Both are import errors, but they refer to different missing symbols in different modules." + "reason": "Python/dependency compatibility vs loading a specific model under 5.1.0 are not the same underlying issue." }, { - "left": "issue:41950", - "right": "issue:45823", + "left": "issue:43441", + "right": "issue:45834", "accept": false, - "reason": "Video-classification processor lookup and Gemma4 device placement mismatch are unrelated issues." + "reason": "FlashAttention compatibility for Ministral-3 and an OCR index error in Kosmos2.5 are unrelated." } ] }, @@ -9913,31 +9895,36 @@ "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-390", "nodes": [ - "issue:32090", - "issue:35141", - "issue:38175", - "issue:39692", - "issue:41950", + "issue:42491", "issue:42994", "issue:43065", - "issue:43295", + "issue:43122", + "issue:43262", "issue:43299", "issue:43317", "issue:43441", "issue:43450", + "issue:43525", + "issue:43643", "issue:43650", "issue:43653", + "issue:43673", "issue:43723", + "issue:43761", "issue:43784", - "issue:43854", + "issue:43881", "issue:43901", - "issue:43976", + "issue:43994", "issue:44016", "issue:44162", + "issue:44188", "issue:44261", "issue:44263", "issue:44279", + "issue:44291", "issue:44297", + "issue:44336", + "issue:44361", "issue:44462", "issue:44466", "issue:44521", @@ -9949,266 +9936,241 @@ "issue:44779", "issue:44898", "issue:44987", - "issue:45081", "issue:45276", "issue:45290", "issue:45325", "issue:45397", - "issue:45405", "issue:45542", "issue:45593", - "issue:45600", - "issue:45712", - "issue:45823", - "issue:45834" + "issue:45823" ], "soft_pairs": [ - "issue:44683|issue:45542", - "issue:43299|issue:43854", - "issue:44279|issue:45405", - "issue:39692|issue:43901", - "issue:32090|issue:35141", - "issue:38175|issue:44617", - "issue:41950|issue:43650", - "issue:44462|issue:45081", - "issue:43295|issue:44779", - "issue:44297|issue:44462", - "issue:43976|issue:44279", - "issue:45600|issue:45712", "issue:44521|issue:45325", - "issue:43976|issue:44987", "issue:44462|issue:44779", - "issue:43441|issue:45834", - "issue:44261|issue:44263", "issue:43450|issue:44279", "issue:42994|issue:43317", + "issue:44261|issue:44263", "issue:44466|issue:45276", "issue:43065|issue:44898", "issue:43441|issue:44683", - "issue:44623|issue:45397", "issue:43650|issue:45290", - "issue:44623|issue:44749", "issue:43723|issue:44162", + "issue:44623|issue:44749", + "issue:44623|issue:45397", "issue:43653|issue:45593", "issue:44671|issue:44779", "issue:43784|issue:45542", "issue:44016|issue:45823", - "issue:44987|issue:45542" + "issue:44987|issue:45542", + "issue:44361|issue:45593", + "issue:43901|issue:43994", + "issue:43122|issue:43650", + "issue:44016|issue:44291", + "issue:43262|issue:44521", + "issue:43673|issue:43761", + "issue:43525|issue:43881", + "issue:44188|issue:44336", + "issue:43525|issue:43643", + "issue:44297|issue:45397", + "issue:43450|issue:44617", + "issue:42491|issue:43299" ], - "prepared_review_unit_hash": "190b3313a6292969cc51a28456c3c840852bde0b3c5175d232b1cb353174fed3", + "prepared_review_unit_hash": "1d7de83c187260c67fbbce4bad31886ef6cae4041632796c8d7732532ed2c8fc", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 31, - "serialized_chars": 36944, - "estimated_input_tokens": 9236, - "estimated_eval_tokens": 18728 + "soft_pair_count": 29, + "serialized_chars": 36286, + "estimated_input_tokens": 9072, + "estimated_eval_tokens": 18400 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly a loose collection of Transformer v5-era regressions across tokenizers, model loading, processors, quantization, and docs; the soft edges are largely superficial similarity rather than true duplicates.", - "confidence": 0.39, - "canonical_issue_reason": "Issue 44462 is the best representative of the shared tokenizer-loading regression theme: it is concrete, user-facing, and broad enough to anchor several nearby tokenizer-related similarities.", + "summary": "The set is heterogeneous, and none of the soft pairs look like true duplicates. The closest shared theme is a family of v5/Qwen3-MoE loading regressions, but the candidate pairs still differ in concrete code path and symptom.", + "confidence": 0.43, + "canonical_issue_reason": "issue:43299 is the clearest standalone regression report: it pins the breakage to v5.0.0.dev0 and a specific Qwen3VL MoE loading path, making it the best canonical issue target among the set.", "canonical_pr_reason": null, - "best_issue_reason": "44462 is the strongest issue candidate for triage because it describes a clear, actionable loading bug with a broad surface area; however, the cluster is heterogeneous, so it should be treated as a representative rather than a true umbrella duplicate.", + "best_issue_reason": "issue:43299 is the strongest representative issue: specific version regression, clear failure mode, and a concrete model-loading path that is likely to attract related reports.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44683", - "right": "issue:45542", - "accept": false, - "reason": "Unrelated bugs: flash attention compilation on torch>=2.9 vs a TensorBoard/TensorFlow dependency/backend error." - }, - { - "left": "issue:43299", - "right": "issue:43854", + "left": "issue:44521", + "right": "issue:45325", "accept": false, - "reason": "Both are model-loading failures, but they involve different models and failure modes; no shared code path is evident." + "reason": "Different bugs: multimodal assistant masks are all zero vs still-image temporal position scaling in Qwen2.5-VL." }, { - "left": "issue:44279", - "right": "issue:45405", + "left": "issue:44462", + "right": "issue:44779", "accept": false, - "reason": "A generic dependency issue is not the same as a specific PEFT version bump to an unreleased package." + "reason": "AutoTokenizer ignoring tokenizer.json is a loading bug; Deepseek tokenizer incorrect results is a tokenizer behavior bug." }, { - "left": "issue:39692", - "right": "issue:43901", + "left": "issue:43450", + "right": "issue:44279", "accept": false, - "reason": "Both mention docs, but they target different examples and different behaviors; not the same bug." + "reason": "Video batched-shape bug and a generic dependency issue are unrelated failure modes." }, { - "left": "issue:32090", - "right": "issue:35141", + "left": "issue:42994", + "right": "issue:43317", "accept": false, - "reason": "Trainer GPU broadcast TypeError is unrelated to token-embedding resizing and post_init reinitialization." + "reason": "Quantized model saving failure is not the same as dequantized model loading with gpu+cpu offload." }, { - "left": "issue:38175", - "right": "issue:44617", + "left": "issue:44261", + "right": "issue:44263", "accept": false, - "reason": "Different models and different problems: unexpected zero probabilities vs CUDA OOM." + "reason": "MLA q_a_layernorm epsilon precision issue is unrelated to torch.split return values in GlmMoeDsaIndexer." }, { - "left": "issue:41950", - "right": "issue:43650", + "left": "issue:44466", + "right": "issue:45276", "accept": false, - "reason": "A pipeline processor lookup bug is unrelated to the placeholder issue in 43650." + "reason": "lm_head.weight serialization inconsistency and Gemma4 embedding resize propagation are different bugs." }, { - "left": "issue:44462", - "right": "issue:45081", + "left": "issue:43065", + "right": "issue:44898", "accept": false, - "reason": "Both are tokenizer-related, but one is repository tokenizer resolution and the other is a Mistral regex-patching crash; different code paths." + "reason": "Dummy Conv2d in Sam3PixelDecoder and Perceiver non-default-resolution failure are different model-path issues." }, { - "left": "issue:43295", - "right": "issue:44779", + "left": "issue:43441", + "right": "issue:44683", "accept": false, - "reason": "Processor API regression and DeepSeek tokenizer output corruption are distinct issues despite both being v5 regressions." + "reason": "Both mention attention, but one is Ministral-3 FlashAttention compatibility and the other is compiled flex_attention on torch>=2.9." }, { - "left": "issue:44297", - "right": "issue:44462", + "left": "issue:43650", + "right": "issue:45290", "accept": false, - "reason": "Tokenizer save serialization mismatch is not the same as AutoTokenizer ignoring repository tokenizer.json." + "reason": "The placeholder title issue is unrelated to apply_chat_template crashing on tool-call messages without content." }, { - "left": "issue:43976", - "right": "issue:44279", + "left": "issue:43723", + "right": "issue:44162", "accept": false, - "reason": "A Python-version compatibility break is not the same as a general dependency issue." + "reason": "Tokenizer loading in v5 and ESM2 model breakage are different subsystems and symptoms." }, { - "left": "issue:45600", - "right": "issue:45712", + "left": "issue:44623", + "right": "issue:44749", "accept": false, - "reason": "Both are repo/CI hygiene problems, but they touch different files and different failure mechanisms." + "reason": "Missing files on processor.save_pretrained and slower filtering after upgrade are unrelated." }, { - "left": "issue:44521", - "right": "issue:45325", + "left": "issue:44623", + "right": "issue:45397", "accept": false, - "reason": "Both are multimodal, but assistant mask generation and temporal position-id scaling are different bugs." + "reason": "processor.save_pretrained missing files is not the same as gemma-4 zero3 from_pretrained failure." }, { - "left": "issue:43976", - "right": "issue:44987", + "left": "issue:43653", + "right": "issue:45593", "accept": false, - "reason": "Both are broad v5 regressions, but they affect different environments and loading paths." + "reason": "BigBirdTokenizer special-token registration and D-FINE auxiliary-loss behavior are unrelated." }, { - "left": "issue:44462", + "left": "issue:44671", "right": "issue:44779", "accept": false, - "reason": "Tokenizer repository-resolution bug and DeepSeek tokenizer incorrect results are different concrete problems." - }, - { - "left": "issue:43441", - "right": "issue:45834", - "accept": false, - "reason": "FlashAttention failure for Ministral-3 is unrelated to Kosmos2.5 OCR long-input indexing." - }, - { - "left": "issue:44261", - "right": "issue:44263", - "accept": false, - "reason": "A missing config epsilon in MLA layernorm is unrelated to torch.split return handling in GlmMoeDsaIndexer." + "reason": "CamemBERT masked-LM prediction errors and Deepseek tokenizer errors are different model families and bugs." }, { - "left": "issue:43450", - "right": "issue:44279", + "left": "issue:43784", + "right": "issue:45542", "accept": false, - "reason": "Video processor batching shape bug is unrelated to a generic dependency issue." + "reason": "Import-time NameError in sentence-transformers and a TensorBoard/TensorFlow backend issue are different dependency failures." }, { - "left": "issue:42994", - "right": "issue:43317", + "left": "issue:44016", + "right": "issue:45823", "accept": false, - "reason": "Quantized model saving failure and dequantized model loading/offload failure are different phases and different bugs." + "reason": "Notebook syntax error and Gemma4 device-mismatch forward bug do not share a concrete code path." }, { - "left": "issue:44466", - "right": "issue:45276", + "left": "issue:44987", + "right": "issue:45542", "accept": false, - "reason": "Both mention tied/output weights, but one is serialization behavior and the other is resize_token_embeddings not updating Gemma4 outputs; not clearly the same fix." + "reason": "Loading physical-intelligence/fast on transformers>=5.1 and undefined tf backend are unrelated." }, { - "left": "issue:43065", - "right": "issue:44898", + "left": "issue:44361", + "right": "issue:45593", "accept": false, - "reason": "Dummy Conv2d in Sam3PixelDecoder is unrelated to Perceiver non-default resolution failures." + "reason": "MLukeTokenizer task AttributeError and D-FINE loss handling are different areas." }, { - "left": "issue:43441", - "right": "issue:44683", + "left": "issue:43901", + "right": "issue:43994", "accept": false, - "reason": "Different attention-kernel failures with different models/code paths; not mergeable as one fix." + "reason": "Docs mismatch for return_all_scores is unrelated to SigLIP2 producing nonsensical outputs." }, { - "left": "issue:44623", - "right": "issue:45397", + "left": "issue:43122", + "right": "issue:43650", "accept": false, - "reason": "Missing processor save files is unrelated to Gemma4 zero3 from_pretrained loading." + "reason": "Tokenizer version drift and the unrelated placeholder issue are not duplicates." }, { - "left": "issue:43650", - "right": "issue:45290", + "left": "issue:44016", + "right": "issue:44291", "accept": false, - "reason": "Placeholder text issue is unrelated to apply_chat_template crashing on tool-call assistant messages." + "reason": "Notebook syntax error is unrelated to init_empty_weights receiving an unexpected argument." }, { - "left": "issue:44623", - "right": "issue:44749", + "left": "issue:43262", + "right": "issue:44521", "accept": false, - "reason": "Processor save-pretrained missing files is unrelated to a performance regression in data filtering." + "reason": "Both involve chat templates, but one is audio sampling-rate defaults and the other is multimodal assistant masks." }, { - "left": "issue:43723", - "right": "issue:44162", + "left": "issue:43673", + "right": "issue:43761", "accept": false, - "reason": "Both are loading regressions, but they concern different models and unrelated code paths." + "reason": "Chunked-prefill cache missing and CLIPVisionModel hidden_states omission are different code paths." }, { - "left": "issue:43653", - "right": "issue:45593", + "left": "issue:43525", + "right": "issue:43881", "accept": false, - "reason": "BigBirdTokenizer special-token registration and D-FINE auxiliary-loss behavior are unrelated." + "reason": "Missing pad_token_id on Llama4Config and glm-4v-9b loading failure are not the same bug." }, { - "left": "issue:44671", - "right": "issue:44779", + "left": "issue:43525", + "right": "issue:43643", "accept": false, - "reason": "CamemBERT masked-LM prediction drift and DeepSeek tokenizer corruption are different model-specific regressions." + "reason": "A missing config attribute on Llama4Config is not the same as trust_remote_code returning incomplete AutoConfig fields." }, { - "left": "issue:43784", - "right": "issue:45542", + "left": "issue:44297", + "right": "issue:45397", "accept": false, - "reason": "Import-time NameError in sentence-transformers is unrelated to a TensorBoard/TensorFlow packaging issue." + "reason": "Tokenizer save metadata mismatch and gemma-4 zero3 loading failure are unrelated." }, { - "left": "issue:44016", - "right": "issue:45823", + "left": "issue:43450", + "right": "issue:44617", "accept": false, - "reason": "Notebook syntax error and Gemma4 device-mismatch forward bug are unrelated." + "reason": "Incorrect batched video shapes and CUDA OOM in Sam3Video are different failure modes." }, { - "left": "issue:44987", - "right": "issue:45542", + "left": "issue:42491", + "right": "issue:43299", "accept": false, - "reason": "A model-loading failure is not the same as a TensorBoard/TensorFlow installation error." + "reason": "They are related by Qwen3/MoE loading regression themes, but the concrete failures differ enough that they should not be merged as duplicates." } ] }, @@ -10237,297 +10199,310 @@ "issue:36246", "issue:41628", "issue:41950", - "issue:42491", "issue:42757", - "issue:43122", - "issue:43262", - "issue:43299", + "issue:43232", "issue:43352", - "issue:43450", - "issue:43525", - "issue:43643", - "issue:43650", + "issue:43526", + "issue:43596", "issue:43673", - "issue:43761", "issue:43824", - "issue:43881", "issue:43901", "issue:43976", - "issue:43994", - "issue:44016", - "issue:44188", + "issue:44162", "issue:44220", "issue:44242", "issue:44246", - "issue:44291", "issue:44295", - "issue:44297", "issue:44336", "issue:44351", - "issue:44361", "issue:44373", "issue:44485", "issue:44496", - "issue:44521", "issue:44561", "issue:44589", - "issue:44617", + "issue:44749", + "issue:44779", "issue:44857", "issue:44871", + "issue:44877", "issue:44964", + "issue:44987", + "issue:45003", + "issue:45200", "issue:45250", + "issue:45292", "issue:45362", "issue:45375", "issue:45397", - "issue:45593" + "issue:45459", + "issue:45561", + "issue:45563", + "issue:45584", + "issue:45593", + "issue:45701", + "issue:45759" ], "soft_pairs": [ - "issue:44361|issue:45593", - "issue:43901|issue:43994", - "issue:43122|issue:43650", - "issue:44016|issue:44291", - "issue:44297|issue:45397", - "issue:44188|issue:44336", - "issue:43673|issue:43761", - "issue:43262|issue:44521", - "issue:43525|issue:43881", - "issue:43525|issue:43643", - "issue:43450|issue:44617", - "issue:42491|issue:43299", "issue:44589|issue:45362", - "issue:44336|issue:44373", "issue:41628|issue:43976", "issue:43901|issue:44246", + "issue:44336|issue:44373", "issue:44242|issue:45593", "issue:43352|issue:45250", "issue:16998|issue:22355", "issue:44295|issue:45397", "issue:44246|issue:44496", "issue:41950|issue:44220", - "issue:44336|issue:44485", "issue:36246|issue:42757", "issue:36246|issue:44351", + "issue:44336|issue:44485", "issue:43673|issue:44561", "issue:43824|issue:43976", "issue:43976|issue:44964", "issue:44246|issue:44871", "issue:44242|issue:44857", - "issue:45362|issue:45375" + "issue:45362|issue:45375", + "issue:44162|issue:45200", + "issue:44779|issue:45292", + "issue:44295|issue:44749", + "issue:44877|issue:45375", + "issue:45292|issue:45584", + "issue:45292|issue:45701", + "issue:45561|issue:45563", + "issue:44987|issue:45459", + "issue:43901|issue:45003", + "issue:45375|issue:45759", + "issue:43232|issue:44336", + "issue:36246|issue:43596", + "issue:43526|issue:45003", + "issue:44496|issue:45003" ], - "prepared_review_unit_hash": "884a11067081ee16a10b400b5323550cefb8986e561f09848cf64b62b2945c00", + "prepared_review_unit_hash": "c4de05efbd22b3d964970fcb88b14b0001fe82faee546258bd16421f41eaad00", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 31, - "serialized_chars": 36671, - "estimated_input_tokens": 9168, - "estimated_eval_tokens": 18592 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 33, + "serialized_chars": 36703, + "estimated_input_tokens": 9176, + "estimated_eval_tokens": 18608 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is a grab bag of unrelated regressions, import errors, model-specific loading failures, and docs/issues. None of the soft pairs look like the same concrete bug or change, so I would not merge any of them as duplicates.", - "confidence": 0.9, - "canonical_issue_reason": "issue:44521 is the strongest representative issue: it is a concrete, reproducible multimodal chat-template bug with active discussion and a clear user-facing failure mode.", + "summary": "This cluster is mostly a grab bag of unrelated Transformers bug reports, with a few surface-level overlaps around imports, configs, generation, and model-specific regressions. None of the soft edges look like true duplicates of the same underlying fix.", + "confidence": 0.86, + "canonical_issue_reason": "issue:43824 is the clearest representative of the recurring top-level import/export regression theme and has the strongest user impact/engagement among the import-error reports.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44521 is the best global anchor because it is specific, actionable, and tied to a core library workflow rather than a question or a documentation-only report.", + "best_issue_reason": "issue:43824 is the best single issue to anchor the cluster because it is concrete, high-signal, and broadly representative of the import failure complaints.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44361", - "right": "issue:45593", + "left": "issue:44589", + "right": "issue:45362", + "accept": false, + "reason": "Different failures: Float8 storage lookup vs a Qwen chat runtime crash." + }, + { + "left": "issue:41628", + "right": "issue:43976", "accept": false, - "reason": "Different models, different symptoms, and different code paths; not the same bug." + "reason": "ImportError for AutoImageProcessor is unrelated to the Python-version compatibility regression." }, { "left": "issue:43901", - "right": "issue:43994", + "right": "issue:44246", "accept": false, - "reason": "Docs mismatch for text-classification is unrelated to a bad AutoModel/pipeline output regression." + "reason": "Docs mismatch for return_all_scores is not the same as intermittent slow imports." }, { - "left": "issue:43122", - "right": "issue:43650", + "left": "issue:44336", + "right": "issue:44373", "accept": false, - "reason": "Tokenizer behavior regression vs unrelated placeholder issue text; no shared underlying change." + "reason": "ANSI output bug and docstring typo are unrelated." }, { - "left": "issue:44016", - "right": "issue:44291", + "left": "issue:44242", + "right": "issue:45593", "accept": false, - "reason": "Notebook syntax error and init_empty_weights TypeError are unrelated." + "reason": "Both mention losses, but they are different model-specific loss bugs." }, { - "left": "issue:44297", - "right": "issue:45397", + "left": "issue:43352", + "right": "issue:45250", "accept": false, - "reason": "Tokenizer save metadata mismatch is unrelated to gemma-4 zero3 loading failure." + "reason": "General Flash Attention support complaint vs a specific model limitation." }, { - "left": "issue:44188", - "right": "issue:44336", + "left": "issue:16998", + "right": "issue:22355", "accept": false, - "reason": "Torch.compile attention-kernel divergence and ANSI reporting output are unrelated." + "reason": "Model_max_length question is unrelated to missing transformers.onnx." }, { - "left": "issue:43673", - "right": "issue:43761", + "left": "issue:44295", + "right": "issue:45397", "accept": false, - "reason": "Generation cache regression and CLIP hidden_states regression affect different code paths." + "reason": "position_ids buffer access bug is unrelated to ZeRO-3 from_pretrained loading." }, { - "left": "issue:43262", - "right": "issue:44521", + "left": "issue:44246", + "right": "issue:44496", "accept": false, - "reason": "Both mention apply_chat_template, but one is audio sampling-rate defaults and the other is assistant mask generation; different bugs." + "reason": "Slow import and unrecognized model config are different root causes." }, { - "left": "issue:43525", - "right": "issue:43881", + "left": "issue:41950", + "right": "issue:44220", "accept": false, - "reason": "Different model-loading failures with no clear shared root cause." + "reason": "Video pipeline image-processor lookup is unrelated to _torch_extract_fbank_features." }, { - "left": "issue:43525", - "right": "issue:43643", + "left": "issue:36246", + "right": "issue:42757", "accept": false, - "reason": "A missing config field in one model is not the same as trust_remote_code dropping fields generally." + "reason": "Different missing imports in different modules." }, { - "left": "issue:43450", - "right": "issue:44617", + "left": "issue:36246", + "right": "issue:44351", "accept": false, - "reason": "Batched video-shape bug and video OOM are distinct failure modes." + "reason": "Qwen2_5_VL export issue is distinct from HybridCache import failure." }, { - "left": "issue:42491", - "right": "issue:43299", + "left": "issue:44336", + "right": "issue:44485", "accept": false, - "reason": "Both involve Qwen3 MoE variants, but the reported failures are different enough that they are not clearly the same concrete bug." + "reason": "Loading-report ANSI codes and GLM-5 RoPE implementation are unrelated." }, { - "left": "issue:44589", - "right": "issue:45362", + "left": "issue:43673", + "right": "issue:44561", "accept": false, - "reason": "Float8 storage import failure is unrelated to a Qwen3.5 chat crash." + "reason": "Generation cache regression is not the same as the removed helper breaking trust_remote_code models." }, { - "left": "issue:44336", - "right": "issue:44373", + "left": "issue:43824", + "right": "issue:43976", "accept": false, - "reason": "Loading_report ANSI output and a docstring issue are unrelated." + "reason": "Missing exported symbol and Python support regression are different issues." }, { - "left": "issue:41628", - "right": "issue:43976", + "left": "issue:43976", + "right": "issue:44964", "accept": false, - "reason": "Missing export import error and Python version compatibility are different issues." + "reason": "Python 3.9+ incompatibility is unrelated to loading a specific multimodal model." }, { - "left": "issue:43901", - "right": "issue:44246", + "left": "issue:44246", + "right": "issue:44871", "accept": false, - "reason": "Documentation mismatch and import latency are unrelated." + "reason": "Import slowness and eos_token_id config inconsistency are unrelated." }, { "left": "issue:44242", - "right": "issue:45593", + "right": "issue:44857", "accept": false, - "reason": "Both mention losses, but they are for different models and different loss conditions." + "reason": "Load-balancing loss omission is not the same as the float16 AMP crash." }, { - "left": "issue:43352", - "right": "issue:45250", + "left": "issue:45362", + "right": "issue:45375", "accept": false, - "reason": "A model explicitly lacking Flash Attention 2 support is not the same as a generic Flash Attention 2 issue." + "reason": "Qwen chat crash and missing config field are different bugs." }, { - "left": "issue:16998", - "right": "issue:22355", + "left": "issue:44162", + "right": "issue:45200", + "accept": false, + "reason": "ESM2 breakage and Gemma 4 token-type defaulting are unrelated." + }, + { + "left": "issue:44779", + "right": "issue:45292", "accept": false, - "reason": "Model_max_length question and missing transformers.onnx module are unrelated." + "reason": "Tokenizer regression and resize_token_embeddings output mismatch are different code paths." }, { "left": "issue:44295", - "right": "issue:45397", + "right": "issue:44749", "accept": false, - "reason": "Position_ids buffer access and gemma-4 zero3 loading are unrelated." + "reason": "IndexError on position_ids is unrelated to the post-upgrade filtering slowdown." }, { - "left": "issue:44246", - "right": "issue:44496", + "left": "issue:44877", + "right": "issue:45375", "accept": false, - "reason": "Import slowness and unrecognized model config are different problems." + "reason": "Strict granite_speech config loading and missing Qwen deepstack fields are different models/issues." }, { - "left": "issue:41950", - "right": "issue:44220", + "left": "issue:45292", + "right": "issue:45584", "accept": false, - "reason": "Video-classification processor selection and audio feature extraction are unrelated subsystems." + "reason": "Embedding resize bug is unrelated to Whisper empty-transcription generation failure." }, { - "left": "issue:44336", - "right": "issue:44485", + "left": "issue:45292", + "right": "issue:45701", "accept": false, - "reason": "ANSI rendering noise and GLM-5 RoPE implementation are unrelated." + "reason": "Embedding resize bug is unrelated to tokenizer changes across versions." }, { - "left": "issue:36246", - "right": "issue:42757", + "left": "issue:45561", + "right": "issue:45563", "accept": false, - "reason": "Both are import errors, but they involve different missing symbols from different packages." + "reason": "pytest-xdist race on captured_info.txt is unrelated to a stale generation warning." }, { - "left": "issue:36246", - "right": "issue:44351", + "left": "issue:44987", + "right": "issue:45459", "accept": false, - "reason": "Two separate missing imports in different transformer releases; not the same bug." + "reason": "Model-loading failure and tokenizer error masking are different problems." }, { - "left": "issue:43673", - "right": "issue:44561", + "left": "issue:43901", + "right": "issue:45003", "accept": false, - "reason": "Generation cache missing and removal of is_torch_fx_available are distinct regressions." + "reason": "A docs issue is not the same as unsafe sys.modules access in modeling_utils." }, { - "left": "issue:43824", - "right": "issue:43976", + "left": "issue:45375", + "right": "issue:45759", "accept": false, - "reason": "Missing Qwen2.5-VL export and Python 3.9/3.10 compatibility are unrelated." + "reason": "Missing config field and text_config unwrapping are different multimodal/model-loading bugs." }, { - "left": "issue:43976", - "right": "issue:44964", + "left": "issue:43232", + "right": "issue:44336", "accept": false, - "reason": "Interpreter-version incompatibility and a specific multimodal model load failure are unrelated." + "reason": "Generation kwargs handling and ANSI report output are unrelated." }, { - "left": "issue:44246", - "right": "issue:44871", + "left": "issue:36246", + "right": "issue:43596", "accept": false, - "reason": "Import latency and eos_token_id configuration mismatch are unrelated." + "reason": "Missing Qwen export and deepspeed/BertModel IndexError are unrelated." }, { - "left": "issue:44242", - "right": "issue:44857", + "left": "issue:43526", + "right": "issue:45003", "accept": false, - "reason": "Router-logit load balancing and LwDetrImageLoss AMP crash are different bugs." + "reason": "BeitImageProcessorFast label reduction bug is unrelated to sys.modules access." }, { - "left": "issue:45362", - "right": "issue:45375", + "left": "issue:44496", + "right": "issue:45003", "accept": false, - "reason": "Both are Qwen3.5-related, but one is a chat crash and the other is a config field being dropped; not the same concrete issue." + "reason": "Unrecognized model config is unrelated to unsafe sys.modules access." } ] }, @@ -10551,70 +10526,56 @@ "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-390", "nodes": [ - "issue:36246", + "issue:28282", + "issue:30990", "issue:42886", + "issue:42994", "issue:43065", "issue:43232", "issue:43257", "issue:43262", "issue:43408", + "issue:43452", "issue:43475", - "issue:43526", + "issue:43482", "issue:43540", - "issue:43596", + "issue:43643", + "issue:43646", "issue:43653", "issue:43673", - "issue:43901", + "issue:43827", "issue:43931", "issue:44060", "issue:44077", "issue:44162", "issue:44246", - "issue:44295", - "issue:44336", + "issue:44297", + "issue:44361", "issue:44368", "issue:44466", - "issue:44496", + "issue:44623", "issue:44734", "issue:44749", - "issue:44779", - "issue:44877", + "issue:44869", + "issue:44933", "issue:44977", - "issue:44987", "issue:44995", "issue:45003", "issue:45137", "issue:45200", "issue:45229", - "issue:45292", + "issue:45310", "issue:45335", - "issue:45375", + "issue:45356", "issue:45397", "issue:45459", "issue:45561", "issue:45563", - "issue:45584", "issue:45588", "issue:45600", - "issue:45656", - "issue:45701", - "issue:45759" + "issue:45656" ], "soft_pairs": [ - "issue:44162|issue:45200", - "issue:44295|issue:44749", - "issue:44877|issue:45375", - "issue:44779|issue:45292", - "issue:45292|issue:45584", - "issue:45561|issue:45563", - "issue:45292|issue:45701", - "issue:44987|issue:45459", - "issue:43232|issue:44336", - "issue:45375|issue:45759", - "issue:43901|issue:45003", - "issue:36246|issue:43596", - "issue:43526|issue:45003", - "issue:44496|issue:45003", "issue:43257|issue:45137", "issue:43065|issue:43408", "issue:44995|issue:45200", @@ -10622,237 +10583,238 @@ "issue:42886|issue:45229", "issue:43475|issue:43540", "issue:44466|issue:45335", - "issue:45397|issue:45656", "issue:44995|issue:45588", "issue:43653|issue:44162", "issue:44368|issue:44977", "issue:44368|issue:45563", + "issue:45397|issue:45656", "issue:44060|issue:44077", - "issue:43673|issue:44734", "issue:45003|issue:45561", + "issue:43673|issue:44734", "issue:45137|issue:45600", - "issue:43931|issue:44368" + "issue:43931|issue:44368", + "issue:44869|issue:45356", + "issue:44933|issue:45459", + "issue:44297|issue:44623", + "issue:43646|issue:44162", + "issue:43232|issue:43673", + "issue:44361|issue:44749", + "issue:43673|issue:43827", + "issue:43452|issue:45003", + "issue:28282|issue:30990", + "issue:44623|issue:45656", + "issue:42994|issue:43482", + "issue:43475|issue:43643", + "issue:44749|issue:45310" ], - "prepared_review_unit_hash": "c80b29307ff74249e8134302a8a6a3a14a0b3cde58df1768a34612f9bb83d180", + "prepared_review_unit_hash": "cd2b6cc462cd565efdae892a81ea1645a257fed9036e8e0e29dba8156e43951e", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 31, - "serialized_chars": 37187, - "estimated_input_tokens": 9297, - "estimated_eval_tokens": 18850 + "soft_pair_count": 30, + "serialized_chars": 36631, + "estimated_input_tokens": 9158, + "estimated_eval_tokens": 18572 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These issues are mostly unrelated model- or subsystem-specific regressions. The only strong duplicate-like pair is the two resize_token_embeddings reports, where one is the generic bug and the other is a T5Gemma-specific manifestation.", - "confidence": 0.78, - "canonical_issue_reason": "`issue:45292` is the cleanest, most general report of the resize_token_embeddings regression and can subsume the T5Gemma-specific follow-up.", + "summary": "The cluster is a loose collection of unrelated Transformers bug reports, mostly one-off regressions across different subsystems. The soft pairs are only superficially similar by broad topic and do not look like the same underlying bug/change.", + "confidence": 0.93, + "canonical_issue_reason": "issue:44466 is the best representative if one must choose: it describes a concrete, broadly impactful v5 regression around tied-weight serialization, with clearer generality than the more model-specific reports.", "canonical_pr_reason": null, - "best_issue_reason": "`issue:45292` is the most canonical issue candidate: concise, concrete, and broad enough to represent the shared embedding-resize bug.", + "best_issue_reason": "issue:44466 is the strongest single issue to anchor the cluster because it is a well-scoped, reproducible v5 regression with broad downstream impact; the rest are mostly narrower or unrelated failures.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44162", - "right": "issue:45200", + "left": "issue:43257", + "right": "issue:45137", "accept": false, - "reason": "Different models and failures: ESM2 is broken vs Gemma 4 text-only token-type defaults." + "reason": "Different failures: Qwen3 MOE weight conversion/loading vs DeepSpeed ZeRO3 deque underflow. No shared code path." }, { - "left": "issue:44295", - "right": "issue:44749", + "left": "issue:43065", + "right": "issue:43408", "accept": false, - "reason": "Different bug classes: position_ids buffer access vs general post-upgrade slowdown." + "reason": "Both SAM3-related, but one is a dummy Conv2d design complaint and the other is a model-type/config mismatch warning." }, { - "left": "issue:44877", - "right": "issue:45375", + "left": "issue:44995", + "right": "issue:45200", "accept": false, - "reason": "Both are config-related, but one is strict loading failure and the other is silent field dropping in a different Qwen config." + "reason": "Stale cache/indexer crash vs Gemma4 text-only mm_token_type_ids defaulting. Unrelated mechanisms." }, { - "left": "issue:44779", - "right": "issue:45292", + "left": "issue:43262", + "right": "issue:44246", "accept": false, - "reason": "Tokenizer regression vs embedding-resize propagation; not the same underlying bug." + "reason": "Audio processor sampling-rate default bug vs intermittent slow import. No common underlying defect." }, { - "left": "issue:45292", - "right": "issue:45584", + "left": "issue:42886", + "right": "issue:45229", "accept": false, - "reason": "Embedding resize bug and Whisper empty-transcription generation failure are unrelated." + "reason": "Offline tokenizer cache loading regression vs multi-GPU Gemma4 OOM. Different symptom and root cause." }, { - "left": "issue:45561", - "right": "issue:45563", + "left": "issue:43475", + "right": "issue:43540", "accept": false, - "reason": "xdist file-race bug vs stale warning in paged generate; different code paths." + "reason": "Both video/SAM3/Qwen3Omni-adjacent, but the concrete attribute error and video input ValueError are different bugs." }, { - "left": "issue:45292", - "right": "issue:45701", + "left": "issue:44466", + "right": "issue:45335", "accept": false, - "reason": "Embedding update bug vs broad tokenization changes across versions; too general and not the same issue." + "reason": "Both involve embeddings/tied weights, but one is serialization inconsistency and the other is resize_token_embeddings not propagating to decoder.embed_tokens." }, { - "left": "issue:44987", - "right": "issue:45459", + "left": "issue:44995", + "right": "issue:45588", "accept": false, - "reason": "Model loading failure vs tokenizer error masking with protobuf absent; different failure mechanisms." + "reason": "Stale indexer cache crash vs flash_attention s_aux=None AttributeError. Not the same failure mode." }, { - "left": "issue:43232", - "right": "issue:44336", + "left": "issue:43653", + "right": "issue:44162", "accept": false, - "reason": "Generation kwargs/update bug vs ANSI-color output in loading_report; unrelated." + "reason": "Tokenizer special-token decode bug vs broad ESM2 breakage. Too different to merge." }, { - "left": "issue:45375", - "right": "issue:45759", + "left": "issue:44368", + "right": "issue:44977", "accept": false, - "reason": "Different config handling bugs: missing field dropped vs text_config not unwrapped in from_config." + "reason": "Warning about tie_word_embeddings in Qwen3.5 fine-tuning vs flash-attention generation bug. Different concrete issue." }, { - "left": "issue:43901", - "right": "issue:45003", + "left": "issue:44368", + "right": "issue:45563", "accept": false, - "reason": "Docs mismatch vs unsafe sys.modules access; not duplicates." + "reason": "Tie_word_embeddings warning vs stale num_return_sequences warning in paged generate. Only both are warnings." }, { - "left": "issue:36246", - "right": "issue:43596", + "left": "issue:45397", + "right": "issue:45656", "accept": false, - "reason": "ImportError for a missing class and a DeepSpeed/BertModel index error are unrelated." + "reason": "Gemma-4 zero3 from_pretrained failure and optimizer.step called twice under deepspeed are separate training/runtime bugs." }, { - "left": "issue:43526", - "right": "issue:45003", + "left": "issue:44060", + "right": "issue:44077", "accept": false, - "reason": "Beit label reduction bug vs sys.modules safety issue; different subsystems." + "reason": "Incorrect tied-weights warning in Qwen3-Next vs patchtsmixer post_init policy change. Not the same code path." }, { - "left": "issue:44496", - "right": "issue:45003", + "left": "issue:45003", + "right": "issue:45561", "accept": false, - "reason": "Unrecognized model config vs sys.modules access; distinct bugs." + "reason": "sys.modules access bug in modeling_utils vs pytest-xdist race on captured_info.txt. Different layers entirely." }, { - "left": "issue:43257", - "right": "issue:45137", + "left": "issue:43673", + "right": "issue:44734", "accept": false, - "reason": "Both involve DeepSpeed, but one is MOE weight conversion and the other is a ZeRO3 deque underflow." + "reason": "Generation cache missing in v5 chunked_prefill vs serve KV-cache continuation tensor indexing crash. Both generation-related but distinct bugs." }, { - "left": "issue:43065", - "right": "issue:43408", + "left": "issue:45137", + "right": "issue:45600", "accept": false, - "reason": "SAM3 pixel-decoder implementation detail vs model-type warning on loading; not the same bug." + "reason": "DeepSpeed ZeRO3 deque error vs auto_mappings referencing removed Sam3LiteText configs. One is runtime, the other CI/config cleanup." }, { - "left": "issue:44995", - "right": "issue:45200", + "left": "issue:43931", + "right": "issue:44368", "accept": false, - "reason": "Stale cache on second forward pass vs Gemma 4 token-type defaults; unrelated." + "reason": "Qwen3-VL weight-shape mismatch vs Qwen3.5 tie_word_embeddings warning. Same family only at a very broad level." }, { - "left": "issue:43262", - "right": "issue:44246", + "left": "issue:44869", + "right": "issue:45356", "accept": false, - "reason": "Audio sampling-rate default bug vs intermittent slow import; different areas." + "reason": "Whisper timestamp decode crash vs Kimi-K2.5 tokenizer regression. Different models and failure surfaces." }, { - "left": "issue:42886", - "right": "issue:45229", + "left": "issue:44933", + "right": "issue:45459", "accept": false, - "reason": "Offline tokenizer cache load failure vs multi-GPU CUDA OOM; not the same issue." + "reason": "Missing/nonexistent image_utils import vs protobuf exception masking tokenizer errors. Both import-path related but not the same bug." }, { - "left": "issue:43475", - "right": "issue:43540", + "left": "issue:44297", + "right": "issue:44623", "accept": false, - "reason": "SAM3 missing attribute and Qwen3OmniMoe video-input ValueError are different model bugs." + "reason": "Tokenizer.save_pretrained writes wrong tokenizer_class vs processor.save_pretrained missing files. Related persistence area, but different artifacts and fixes." }, { - "left": "issue:44466", - "right": "issue:45335", + "left": "issue:43646", + "right": "issue:44162", "accept": false, - "reason": "Tied-weight serialization inconsistency vs resize_token_embeddings not updating decoder embeddings; related theme but different concrete failures." + "reason": "Custom model initialization breaking in Transformers 5.0.0 vs ESM2 breakage. The latter is model-specific and not clearly the same regression." }, { - "left": "issue:45397", - "right": "issue:45656", + "left": "issue:43232", + "right": "issue:43673", "accept": false, - "reason": "Gemma-4 ZeRO3 loading bug vs double optimizer step under DeepSpeed; unrelated." + "reason": "Post-sync_gpus generation kwargs update issue vs missing GenerationMixin cache in chunked_prefill. Different generation internals." }, { - "left": "issue:44995", - "right": "issue:45588", - "accept": false, - "reason": "Stale indexer cache vs flash-attention crash on s_aux=None; different code paths." - }, - { - "left": "issue:43653", - "right": "issue:44162", - "accept": false, - "reason": "Tokenizer special-token registration bug vs ESM2 model breakage; not duplicates." - }, - { - "left": "issue:44368", - "right": "issue:44977", + "left": "issue:44361", + "right": "issue:44749", "accept": false, - "reason": "Tied-embedding warning vs Qwen3.5 flash-attention generation failure; unrelated." + "reason": "MLukeTokenizer AttributeError on tasks vs Chinese report of slower filtering after upgrade. Not the same bug." }, { - "left": "issue:44060", - "right": "issue:44077", + "left": "issue:43673", + "right": "issue:43827", "accept": false, - "reason": "Qwen3-Next tied-weights warning vs patchtsmixer post_init policy; different concerns." + "reason": "Generation cache regression vs docs still referencing removed pipeline(). One is runtime code, the other documentation cleanup." }, { - "left": "issue:43673", - "right": "issue:44734", + "left": "issue:43452", + "right": "issue:45003", "accept": false, - "reason": "Both mention cache, but one is chunked_prefill GenerationMixin cache and the other is serve KV-continuation indexing; not the same bug." + "reason": "gguf_file breaks tokenizer/model loading vs unsafe sys.modules access. Both loading-related, but not the same concrete defect." }, { - "left": "issue:45003", - "right": "issue:45561", + "left": "issue:28282", + "right": "issue:30990", "accept": false, - "reason": "sys.modules access bug vs xdist race condition; unrelated." + "reason": "PyTorch missing ImportError for AutoModel vs Sentence Transformers getting stuck loading. Different environments and symptoms." }, { - "left": "issue:45137", - "right": "issue:45600", + "left": "issue:44623", + "right": "issue:45656", "accept": false, - "reason": "ZeRO3 deque underflow vs removed Sam3LiteText config references in auto_mappings; different failures." + "reason": "Missing files on processor.save_pretrained vs deepspeed optimizer step called twice. No shared underlying bug." }, { - "left": "issue:43931", - "right": "issue:44368", + "left": "issue:42994", + "right": "issue:43482", "accept": false, - "reason": "Qwen3-VL weight-shape mismatch vs tied-embedding warning; unrelated." + "reason": "Quantized model saving failure vs Qwen2.5-GGUF loading failure in v5. Save vs load path; not mergeable." }, { - "left": "issue:44368", - "right": "issue:45563", + "left": "issue:43475", + "right": "issue:43643", "accept": false, - "reason": "Different generation/tied-weights warning issues; no shared concrete bug." + "reason": "SAM3 video encoder output missing attribute vs AutoConfig trust_remote_code missing fields. Different model/config layers." }, { - "left": "issue:44060", - "right": "issue:45335", + "left": "issue:44749", + "right": "issue:45310", "accept": false, - "reason": "Qwen3-Next tied-weights warning vs embedding resize propagation bug; not the same code-path problem." + "reason": "Performance regression after upgrade vs Qwen3.5 MOE from_pretrained error in transformers>=5.4.0. Not the same failure." } ] }, @@ -10876,8 +10838,8 @@ "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-390", "nodes": [ - "issue:28282", "issue:30990", + "issue:35141", "issue:36010", "issue:41628", "issue:42175", @@ -10885,313 +10847,285 @@ "issue:42371", "issue:42673", "issue:42831", + "issue:42898", "issue:42994", "issue:43232", "issue:43377", - "issue:43452", "issue:43475", - "issue:43482", "issue:43525", - "issue:43643", - "issue:43673", "issue:43704", + "issue:43784", "issue:43824", - "issue:43827", + "issue:43901", "issue:44038", + "issue:44188", "issue:44222", "issue:44242", - "issue:44297", "issue:44351", - "issue:44361", + "issue:44496", + "issue:44568", "issue:44623", "issue:44661", "issue:44749", - "issue:44869", + "issue:44792", "issue:44933", - "issue:45003", + "issue:44964", "issue:45081", "issue:45092", "issue:45103", + "issue:45137", "issue:45200", "issue:45230", "issue:45310", - "issue:45356", "issue:45375", "issue:45381", "issue:45397", - "issue:45459", "issue:45478", + "issue:45561", + "issue:45600", "issue:45656", - "issue:45712" + "issue:45712", + "issue:45812" ], "soft_pairs": [ - "issue:44933|issue:45459", - "issue:44869|issue:45356", - "issue:44297|issue:44623", - "issue:44361|issue:44749", - "issue:43232|issue:43673", - "issue:43673|issue:43827", - "issue:44623|issue:45656", - "issue:43452|issue:45003", - "issue:28282|issue:30990", - "issue:44749|issue:45310", - "issue:44749|issue:45656", - "issue:42994|issue:43482", - "issue:43475|issue:43643", "issue:42371|issue:45092", - "issue:45230|issue:45397", - "issue:44038|issue:44623", + "issue:44749|issue:45656", "issue:43475|issue:45381", + "issue:44038|issue:44623", + "issue:45230|issue:45397", "issue:41628|issue:44933", "issue:45081|issue:45103", - "issue:45375|issue:45478", "issue:42994|issue:43525", + "issue:45375|issue:45478", "issue:42673|issue:43704", "issue:43475|issue:44661", "issue:45310|issue:45375", - "issue:42831|issue:44222", "issue:41628|issue:44351", + "issue:42831|issue:44222", "issue:42222|issue:45200", "issue:44222|issue:45310", "issue:42994|issue:43824", - "issue:44038|issue:45310", "issue:42175|issue:45712", "issue:36010|issue:41628", - "issue:43377|issue:44242" + "issue:43377|issue:44242", + "issue:44038|issue:45310", + "issue:44496|issue:45561", + "issue:44964|issue:45137", + "issue:45561|issue:45600", + "issue:43901|issue:45561", + "issue:30990|issue:35141", + "issue:42898|issue:44568", + "issue:43232|issue:44792", + "issue:43232|issue:44188", + "issue:42898|issue:45812", + "issue:43784|issue:43824" ], - "prepared_review_unit_hash": "8c128aa92a2df1eb0e3bb9cfb18c21387b849344742839a01903c52f1d82f495", + "prepared_review_unit_hash": "3b6fa28564806d2a8ba76cbebd0623c2a4459456cbf8464b6da6a4e5f8691454", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 33, - "serialized_chars": 36891, - "estimated_input_tokens": 9223, - "estimated_eval_tokens": 18702 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36919, + "estimated_input_tokens": 9230, + "estimated_eval_tokens": 18716 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is heterogeneous and mostly false-positive similarity: import/export regressions, tokenizer/save/load bugs, generation/cache issues, FP8/quantization, and model-specific breakages. I did not find any soft pair that clearly describes the same underlying bug or change, so none were merged.", - "confidence": 0.66, - "canonical_issue_reason": "issue:41628 is the cleanest representative of a concrete, user-facing import/export regression; it is better scoped than the broader or more model-specific reports.", + "summary": "Mostly a heterogeneous bundle of unrelated Transformers issues, but not a single unique duplicate island: there are at least two duplicate-like mini-clusters, the Qwen3ForCausalLM VRAM leak pair (42673/43704) and the identical-titled Qwen3.5 Moe from_pretrained error pair (45310/45478). The remaining soft-edge candidates still look distinct, so this is largely separate bugs with a couple of clear duplicates.", + "confidence": 0.84, + "canonical_issue_reason": "Issue 42673 is a strong anchor because it has an exact duplicate counterpart (43704) and a specific, self-contained VRAM leak report. It is still one of the clearest representatives even though the cluster also contains another duplicate-like Qwen3.5 Moe pair elsewhere.", "canonical_pr_reason": null, - "best_issue_reason": "issue:41628 is the most straightforward and actionable bug report in the set, with a clear failure mode and a package-level symptom.", + "best_issue_reason": "42673 is the best single issue representative because it is concrete, well-scoped, and backed by an exact duplicate report. It is not the only duplicate-like topic in the packet, but it remains the cleanest canonical issue.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44933", - "right": "issue:45459", - "accept": false, - "reason": "Both mention import-related failures, but one is a nonexistent image_utils import and the other masks tokenizer errors when protobuf is absent; different code paths." - }, - { - "left": "issue:44869", - "right": "issue:45356", - "accept": false, - "reason": "Both involve tokenization/decoding, but they are different model-specific regressions with different symptoms and fixes." - }, - { - "left": "issue:44297", - "right": "issue:44623", - "accept": false, - "reason": "Save_pretrained is shared, but one is tokenizer_class metadata and the other is missing processor files; not the same bug." - }, - { - "left": "issue:44361", - "right": "issue:44749", - "accept": false, - "reason": "These are unrelated: MLukeTokenizer task handling versus a performance regression when filtering data." - }, - { - "left": "issue:43232", - "right": "issue:43673", - "accept": false, - "reason": "Both touch generation internals, but one is sync_gpus kwargs handling and the other is chunked_prefill cache behavior; not one concrete issue." - }, - { - "left": "issue:43673", - "right": "issue:43827", + "left": "issue:42371", + "right": "issue:45092", "accept": false, - "reason": "Generation cache regression versus docs still referencing pipeline(); different artifacts and different fixes." + "reason": "Different problems: TF32 settings guidance vs an InternVL2/meta-init incompatibility." }, { - "left": "issue:44623", + "left": "issue:44749", "right": "issue:45656", "accept": false, - "reason": "Processor.save_pretrained missing files is unrelated to a deepspeed double optimizer-step bug." + "reason": "Unrelated bugs: tokenizer/filtering slowdown vs optimizer step being called twice under DeepSpeed." }, { - "left": "issue:43452", - "right": "issue:45003", + "left": "issue:43475", + "right": "issue:45381", "accept": false, - "reason": "GGUF/from_pretrained loading breakage is not the same as unsafe sys.modules access in modeling_utils." + "reason": "Both are vision-related, but they describe different model/code-path failures and different symptoms." }, { - "left": "issue:28282", - "right": "issue:30990", + "left": "issue:44038", + "right": "issue:44623", "accept": false, - "reason": "PyTorch-missing ImportError and sentence-transformers loading hang are different failure modes." + "reason": "Different issues: Qwen3-VL-Moe loading vs processor.save_pretrained missing files." }, { - "left": "issue:44749", - "right": "issue:45310", + "left": "issue:45230", + "right": "issue:45397", "accept": false, - "reason": "A Chinese performance regression report versus a Qwen3.5 MoE from_pretrained error; no shared concrete bug." + "reason": "No shared underlying bug is evident; generic bug report vs Gemma-4 ZeRO3 loading failure." }, { - "left": "issue:44749", - "right": "issue:45656", + "left": "issue:41628", + "right": "issue:44933", "accept": false, - "reason": "Filtering slowdown and deepspeed optimizer double-step are unrelated." + "reason": "Both are import errors, but they involve different missing symbols and likely different fixes." }, { - "left": "issue:42994", - "right": "issue:43482", + "left": "issue:45081", + "right": "issue:45103", "accept": false, - "reason": "Quantized model saving failed versus GGUF loading failed; save-side and load-side issues are distinct." + "reason": "Tokenizer backend crash and auto-docstring future-annotations crash are unrelated." }, { - "left": "issue:43475", - "right": "issue:43643", + "left": "issue:42994", + "right": "issue:43525", "accept": false, - "reason": "SAM3 output attribute error and missing fields from trust_remote_code config are different object-construction problems." + "reason": "Different failures: quantized model saving vs missing pad_token_id on Llama4Config." }, { - "left": "issue:42371", - "right": "issue:45092", + "left": "issue:45375", + "right": "issue:45478", "accept": false, - "reason": "TF32 API warning/setting guidance is unrelated to meta-init incompatibility for old remote-code checkpoints." + "reason": "Same model family, but one is a missing config field and the other is a generic from_pretrained error; not enough evidence they're the same bug." }, { - "left": "issue:45230", - "right": "issue:45397", - "accept": false, - "reason": "A generic bug report is not the same as a Gemma-4 zero3 from_pretrained failure." + "left": "issue:42673", + "right": "issue:43704", + "accept": true, + "reason": "Same title and same VRAM leak symptom for Qwen3ForCausalLM; this looks like the same underlying issue." }, { - "left": "issue:44038", - "right": "issue:44623", + "left": "issue:42831", + "right": "issue:44222", "accept": false, - "reason": "Qwen3-VL-Moe/v5 bug versus processor.save_pretrained missing files; different subsystems." + "reason": "Both mention FP8, but one is an accuracy issue and the other is a save_pretrained failure." }, { - "left": "issue:43475", - "right": "issue:45381", + "left": "issue:42222", + "right": "issue:45200", "accept": false, - "reason": "Different vision/video bugs in different model families; no shared failing code path." + "reason": "Different model families and different bugs: VitPose breakage vs Gemma 4 token-type defaults." }, { - "left": "issue:41628", - "right": "issue:44933", + "left": "issue:44222", + "right": "issue:45310", "accept": false, - "reason": "Both are import-related, but one is a top-level export missing for AutoImageProcessor and the other is a nonexistent image_utils import; different missing symbols." + "reason": "Different bugs: FP8 save_pretrained failure vs Qwen3.5-Moe from_pretrained error." }, { - "left": "issue:45081", - "right": "issue:45103", + "left": "issue:42994", + "right": "issue:43824", "accept": false, - "reason": "Tokenizer regex patch crash versus auto_docstring crash under future annotations; unrelated failures." + "reason": "Unrelated: quantized saving failure vs missing Qwen2.5-VL import." }, { - "left": "issue:45375", - "right": "issue:45478", + "left": "issue:42175", + "right": "issue:45712", "accept": false, - "reason": "Both involve Qwen3.5 MoE, but one is a missing config field and the other is a from_pretrained error; not enough evidence of the same bug." + "reason": "Different concerns: backend dependency packaging vs leftover dummy classes in repo checks." }, { - "left": "issue:42994", - "right": "issue:43525", + "left": "issue:36010", + "right": "issue:41628", "accept": false, - "reason": "Quantized saving failure and missing pad_token_id on Llama4Config are different issues." + "reason": "Both are import errors, but they concern different missing APIs and likely different root causes." }, { - "left": "issue:42673", - "right": "issue:43704", + "left": "issue:43377", + "right": "issue:44242", "accept": false, - "reason": "Same title text, but the later report is a separate issue instance; no evidence they are the same underlying bug from the provided metadata." + "reason": "Different model behaviors: batched-vs-single mismatch vs router loss calculation." }, { - "left": "issue:43475", - "right": "issue:44661", + "left": "issue:44038", + "right": "issue:45310", "accept": false, - "reason": "SAM3 video attribute error and add-new-model-like tokenizer mapping failure are unrelated." + "reason": "Related model family, but the titles point to different generations/version-specific load errors." }, { - "left": "issue:45310", - "right": "issue:45375", + "left": "issue:44496", + "right": "issue:45561", "accept": false, - "reason": "Both are Qwen-related, but one is a from_pretrained error and the other is a missing config field silently dropped by strict validation." + "reason": "Completely unrelated: model auto-detection failure vs xdist file-race in testing utils." }, { - "left": "issue:42831", - "right": "issue:44222", + "left": "issue:44964", + "right": "issue:45137", "accept": false, - "reason": "FP8 accuracy degradation and FP8 save_pretrained failure are distinct problems." + "reason": "Different subsystems and symptoms: multimodal model loading vs DeepSpeed ZeRO3 deque error." }, { - "left": "issue:41628", - "right": "issue:44351", + "left": "issue:45561", + "right": "issue:45600", "accept": false, - "reason": "Both are import errors, but they refer to different missing symbols and likely different exports." + "reason": "Testing race condition vs CI breakage from stale auto_mappings references; not the same bug." }, { - "left": "issue:42222", - "right": "issue:45200", + "left": "issue:43901", + "right": "issue:45561", "accept": false, - "reason": "Vitpose breakage and Gemma-4 mm_token_type_ids handling are unrelated model-specific bugs." + "reason": "Docs/behavior mismatch for pipeline output vs xdist file race are unrelated." }, { - "left": "issue:44222", - "right": "issue:45310", + "left": "issue:30990", + "right": "issue:35141", "accept": false, - "reason": "FP8 save_pretrained for MoE versus a Qwen3.5 Moe from_pretrained error; different code paths." + "reason": "Sentence Transformers loading hang and embedding reinit are unrelated regressions." }, { - "left": "issue:42994", - "right": "issue:43824", + "left": "issue:42898", + "right": "issue:44568", "accept": false, - "reason": "Quantized model saving versus missing Qwen2_5_VLForConditionalGeneration import are separate loading/saving issues." + "reason": "Both are tokenizer regressions, but they affect different behaviors and different code paths." }, { - "left": "issue:44038", - "right": "issue:45310", + "left": "issue:43232", + "right": "issue:44792", "accept": false, - "reason": "Both mention Qwen3.5/Qwen3-VL, but the failure modes are different and model-specific." + "reason": "Generation kwargs bug vs Janus image-generation test failure; no clear shared underlying defect." }, { - "left": "issue:42175", - "right": "issue:45712", + "left": "issue:43232", + "right": "issue:44188", "accept": false, - "reason": "TensorFlow backend packaging and dummy_pt_objects cleanup are related to packaging, but not the same concrete bug or change." + "reason": "Different issues in generation/attention internals; not the same concrete bug." }, { - "left": "issue:36010", - "right": "issue:41628", + "left": "issue:42898", + "right": "issue:45812", "accept": false, - "reason": "Different missing imports: GenerationMixin versus AutoImageProcessor; not the same regression." + "reason": "Both are tokenization regressions, but one is cleanup-space behavior and the other is wrong token IDs for Granite models." }, { - "left": "issue:43377", - "right": "issue:44242", + "left": "issue:43784", + "right": "issue:43824", "accept": false, - "reason": "MIMI batching/padding-mask correctness and load-balancing loss omission are unrelated model-training issues." + "reason": "Both are import regressions, but they are for different missing symbols and different packages/models." } ] }, - "evaluator_result": null, - "evaluator_used": false, - "retried": false, - "accepted_nontrivial_soft_edge": false, + "evaluator_result": { + "accept": false, + "feedback": "The summary overstates uniqueness: the packet contains another obvious duplicate-like pair with identical titles, issue:45310 and issue:45478 (`[BUG] transformers>=5.4.0, Qwen3.5 Moe from_pretrained error`), so it is not grounded to say 42673/43704 is the only clear duplicate-like pair. The rest of the soft-edge rejections are generally conservative, but the omission makes the canonicality claim too strong." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -11208,41 +11142,44 @@ "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-390", "nodes": [ + "issue:28282", "issue:30333", - "issue:30990", "issue:33290", + "issue:34689", "issue:35141", "issue:36331", + "issue:41628", "issue:42175", + "issue:42757", "issue:42831", "issue:42898", "issue:43232", "issue:43278", "issue:43479", "issue:43723", - "issue:43784", - "issue:43824", + "issue:43873", "issue:43874", - "issue:43901", "issue:43976", "issue:44060", "issue:44079", "issue:44188", "issue:44206", "issue:44222", + "issue:44263", "issue:44295", "issue:44297", "issue:44373", "issue:44448", - "issue:44496", + "issue:44484", "issue:44568", "issue:44623", "issue:44734", "issue:44779", - "issue:44792", "issue:44869", "issue:44933", + "issue:44945", "issue:44964", + "issue:44977", "issue:45092", "issue:45103", "issue:45125", @@ -11250,287 +11187,285 @@ "issue:45310", "issue:45356", "issue:45405", - "issue:45561", - "issue:45600", "issue:45656", "issue:45712", - "issue:45812" + "issue:45834" ], "soft_pairs": [ - "issue:44496|issue:45561", - "issue:45561|issue:45600", - "issue:44964|issue:45137", - "issue:43901|issue:45561", - "issue:30990|issue:35141", - "issue:42898|issue:44568", - "issue:43232|issue:44792", - "issue:43232|issue:44188", - "issue:42898|issue:45812", "issue:44188|issue:44373", - "issue:44623|issue:45310", - "issue:43784|issue:43824", "issue:43278|issue:45137", + "issue:44623|issue:45310", "issue:44734|issue:45103", "issue:30333|issue:33290", "issue:43723|issue:44568", "issue:44060|issue:45125", "issue:42898|issue:45356", "issue:43874|issue:45092", - "issue:45405|issue:45712", "issue:42898|issue:44779", + "issue:45405|issue:45712", "issue:42898|issue:44448", + "issue:43479|issue:44079", "issue:44188|issue:44964", "issue:44295|issue:45656", - "issue:43479|issue:44079", "issue:44933|issue:45712", "issue:42175|issue:44933", - "issue:44222|issue:44297", - "issue:44297|issue:45656", "issue:43976|issue:44933", + "issue:44222|issue:44297", "issue:43479|issue:44869", + "issue:44297|issue:45656", + "issue:44206|issue:45103", "issue:42831|issue:44623", "issue:44222|issue:44623", - "issue:44206|issue:45103", - "issue:30333|issue:36331" + "issue:30333|issue:36331", + "issue:41628|issue:42757", + "issue:43232|issue:45834", + "issue:30333|issue:34689", + "issue:43723|issue:44977", + "issue:43873|issue:44945", + "issue:44222|issue:44484", + "issue:28282|issue:30333", + "issue:44297|issue:45310", + "issue:30333|issue:35141", + "issue:44263|issue:45092" ], - "prepared_review_unit_hash": "23fbe17b8006e89b1090fd9b846fce5bbd53bfea1e3ef7529e327b1a8e55b11d", + "prepared_review_unit_hash": "76abcf35ebffda7a534fa5b9c3807424c1a65dcf782c86990b5c78496d69880f", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { - "node_count": 47, - "item_count": 47, + "node_count": 48, + "item_count": 48, "soft_pair_count": 35, - "serialized_chars": 37774, - "estimated_input_tokens": 9444, - "estimated_eval_tokens": 19144 + "serialized_chars": 38117, + "estimated_input_tokens": 9530, + "estimated_eval_tokens": 19316 }, - "overflow_policy": "truncate_then_skip", - "trimmed": false, - "aggressively_trimmed": false, - "split": true, - "analyst_result": { - "summary": "This cluster is mostly a grab bag of unrelated Transformers issues across tokenization, model loading, generation, DeepSpeed, multimodal processors, docs, and test infra. I do not see any soft pair that clearly describes the same underlying bug or change, so all candidate merges should be rejected.", - "confidence": 0.93, - "canonical_issue_reason": "Issue 45812 is the most concrete and actionable bug report in the set: it describes a specific silent regression in AutoTokenizer affecting Granite models with a clear failure mode and scope.", - "canonical_pr_reason": null, - "best_issue_reason": "Issue 45812 is a strong representative issue because it is specific, reproducible, and user-facing, with a narrowly defined tokenizer regression rather than a broad or speculative report.", - "best_pr_reason": null, - "soft_edge_verdicts": [ - { - "left": "issue:44496", - "right": "issue:45561", - "accept": false, - "reason": "Different failures: unrecognized model config vs pytest-xdist race in captured_info.txt." - }, - { - "left": "issue:45561", - "right": "issue:45600", - "accept": false, - "reason": "Test harness race condition is unrelated to auto_mappings referencing removed configs." - }, - { - "left": "issue:44964", - "right": "issue:45137", - "accept": false, - "reason": "Phi-4 multimodal loading failure is unrelated to DeepSpeed ZeRO3 deque underflow." - }, - { - "left": "issue:43901", - "right": "issue:45561", - "accept": false, - "reason": "Docs mismatch for TextClassificationPipeline is unrelated to xdist file race." - }, - { - "left": "issue:30990", - "right": "issue:35141", - "accept": false, - "reason": "Sentence Transformers loading hang and token embedding resize reinit are different code paths." - }, - { - "left": "issue:42898", - "right": "issue:44568", - "accept": false, - "reason": "Both are tokenizer regressions, but one is cleanup-space behavior and the other is special-token insertion for a specific tokenizer." - }, - { - "left": "issue:43232", - "right": "issue:44792", - "accept": false, - "reason": "Generation sync_gpus kwargs bug is unrelated to a janus image-generation test failure." - }, - { - "left": "issue:43232", - "right": "issue:44188", - "accept": false, - "reason": "One is generation kwargs updating; the other is attention-kernel divergence under torch.compile." - }, - { - "left": "issue:42898", - "right": "issue:45812", - "accept": false, - "reason": "Both concern tokenization, but one is cleanup-space behavior and the other is wrong token IDs for Granite models." - }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a heterogeneous mix of unrelated Transformers bugs and regressions. The soft similarities are driven by shared vocabulary around v5, loading, tokenizers, and training rather than the same underlying defect. No PRs are present.", + "confidence": 0.94, + "canonical_issue_reason": "issue:30333 is the most connected node in this set and is broad enough to serve as the cluster anchor, though it is not a true duplicate of the others.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:30333 is the best representative issue for the cluster because it has the highest soft-edge connectivity and a broad training/workflow scope.", + "best_pr_reason": null, + "soft_edge_verdicts": [ { "left": "issue:44188", "right": "issue:44373", "accept": false, - "reason": "Attention-kernel branching bug is unrelated to a docstring typo for position_ids." - }, - { - "left": "issue:44623", - "right": "issue:45310", - "accept": false, - "reason": "Processor save_pretrained missing files is unrelated to Qwen3.5 MoE from_pretrained failure." + "reason": "Attention-kernel branching under torch.compile is unrelated to a docstring typo for position_ids." }, { - "left": "issue:43784", - "right": "issue:43824", + "left": "issue:43278", + "right": "issue:45137", "accept": false, - "reason": "Import-time NameError in sentence-transformers is unrelated to missing Qwen2.5 VL class export." + "reason": "Embedding dtype drift in evaluation is not the same bug as a DeepSpeed ZeRO3 deque IndexError." }, { - "left": "issue:43278", - "right": "issue:45137", + "left": "issue:44623", + "right": "issue:45310", "accept": false, - "reason": "Embedding dtype drift in evaluate is unrelated to DeepSpeed ZeRO3 deque errors." + "reason": "Missing processor save files and a Qwen3.5 MoE from_pretrained failure are different code paths." }, { "left": "issue:44734", "right": "issue:45103", "accept": false, - "reason": "Serve KV-cache indexing crash is unrelated to auto_docstring annotation handling." + "reason": "KV-cache continuation indexing in serve is unrelated to an auto_docstring annotations crash." }, { "left": "issue:30333", "right": "issue:33290", "accept": false, - "reason": "MLflow training-job reporting and adafactor OOM in DeepSpeed are unrelated problems." + "reason": "MLflow reporting on failed jobs and adafactor OOM in DeepSpeed are distinct training issues." }, { "left": "issue:43723", "right": "issue:44568", "accept": false, - "reason": "Tokenizer loading in v5 and missing BOS/EOS on add_special_tokens are distinct tokenizer regressions." + "reason": "Tokenizer loading in v5 and missing add_special_tokens behavior are separate tokenizer regressions." }, { "left": "issue:44060", "right": "issue:45125", "accept": false, - "reason": "These are separate Qwen3 MoE issues: tied-weights warning vs missing tensor-parallel plan." + "reason": "A tied-weights warning in Qwen3-Next is not the same as missing _tp_plan in Qwen3_5Moe." }, { "left": "issue:42898", "right": "issue:45356", "accept": false, - "reason": "Different tokenizer regressions affecting different models and failure modes." + "reason": "These are different tokenizer regressions affecting different models and failure modes." }, { "left": "issue:43874", "right": "issue:45092", "accept": false, - "reason": "Missing image-patch method in GLM46V is unrelated to old InternVL2 meta-init incompatibility." + "reason": "A missing image-patch method and meta-init incompatibility are unrelated multimodal loading bugs." + }, + { + "left": "issue:42898", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer-related, but they describe different regressions in different tokenizers/models." }, { "left": "issue:45405", "right": "issue:45712", "accept": false, - "reason": "PEFT version pinning issue is unrelated to leftover dummy classes in repo checks." + "reason": "A PEFT version pin issue is unrelated to leftover dummy classes in the repo." }, { "left": "issue:42898", - "right": "issue:44779", + "right": "issue:44448", "accept": false, - "reason": "Cleanup-space behavior change is unrelated to Deepseek tokenizer output regression." + "reason": "These concern different output/behavior regressions and are not the same underlying tokenizer bug." }, { - "left": "issue:42898", - "right": "issue:44448", + "left": "issue:43479", + "right": "issue:44079", "accept": false, - "reason": "Tokenizer cleanup-space regression is unrelated to Pegasus CNN/DM output differences." + "reason": "Phi4 multimodal config initialization and ModelOutput key assignment are different None-handling bugs." }, { "left": "issue:44188", "right": "issue:44964", "accept": false, - "reason": "Attention-kernel divergence under compile is unrelated to Phi-4 multimodal model loading." + "reason": "Attention kernel divergence and Phi-4 multimodal loading failure do not share a concrete code path." }, { "left": "issue:44295", "right": "issue:45656", "accept": false, - "reason": "Position_ids buffer read bug is unrelated to optimizer stepping twice under DeepSpeed." - }, - { - "left": "issue:43479", - "right": "issue:44079", - "accept": false, - "reason": "Phi-4 multimodal config init bug is unrelated to ModelOutput key assignment." + "reason": "Reading position_ids after buffer registration is unrelated to DeepSpeed calling optimizer.step twice." }, { "left": "issue:44933", "right": "issue:45712", "accept": false, - "reason": "Missing image_utils import is unrelated to leftover dummy classes causing repo checks to fail." + "reason": "A missing image_utils import and dummy-class cleanup are different repository maintenance issues." }, { "left": "issue:42175", "right": "issue:44933", "accept": false, - "reason": "Backend packaging omission is unrelated to a removed image_utils import." + "reason": "Missing tensorflow backend in extras and a nonexistent image_utils import are separate import problems." + }, + { + "left": "issue:43976", + "right": "issue:44933", + "accept": false, + "reason": "Python version support regression and a missing image_utils symbol are not the same defect." }, { "left": "issue:44222", "right": "issue:44297", "accept": false, - "reason": "FP8 MoE save_pretrained bug and tokenizer save_pretrained class-name bug are different features." + "reason": "FP8 save_pretrained behavior and tokenizer_class metadata mismatch affect different save paths." }, { - "left": "issue:44297", - "right": "issue:45656", + "left": "issue:43479", + "right": "issue:44869", "accept": false, - "reason": "Tokenizer config serialization issue is unrelated to DeepSpeed optimizer double-step." + "reason": "Phi4 config defaults and Whisper word timestamp decoding crash are unrelated." }, { - "left": "issue:43976", - "right": "issue:44933", + "left": "issue:44297", + "right": "issue:45656", "accept": false, - "reason": "Python version compatibility issue is unrelated to missing import from image_utils." + "reason": "Tokenizer config mismatch is unrelated to DeepSpeed double optimizer steps." }, { - "left": "issue:43479", - "right": "issue:44869", + "left": "issue:44206", + "right": "issue:45103", "accept": false, - "reason": "Phi-4 multimodal config initialization is unrelated to Whisper timestamp decode crash." + "reason": "Unsupported center argument in LasrFeatureExtractor is unrelated to the auto_docstring annotations crash." }, { "left": "issue:42831", "right": "issue:44623", "accept": false, - "reason": "FineGrainedFP8 accuracy issue is unrelated to processor.save_pretrained missing files." + "reason": "FineGrainedFP8 accuracy issues are not the same as missing files in processor.save_pretrained." }, { "left": "issue:44222", "right": "issue:44623", "accept": false, - "reason": "FP8 MoE save_pretrained and processor save_pretrained missing files are separate save/export bugs." + "reason": "FP8 MoE save issues and processor file export issues touch different save code paths." }, { - "left": "issue:44206", - "right": "issue:45103", + "left": "issue:30333", + "right": "issue:36331", + "accept": false, + "reason": "Failed-job MLflow reporting and compute_loss signature changes are separate trainer issues." + }, + { + "left": "issue:41628", + "right": "issue:42757", "accept": false, - "reason": "LasrFeatureExtractor center-arg regression is unrelated to auto_docstring annotation crashes." + "reason": "These are both import errors, but for different symbols and dependency breakages." + }, + { + "left": "issue:43232", + "right": "issue:45834", + "accept": false, + "reason": "Generation kwargs updates after sync_gpus are unrelated to Kosmos2.5 OCR index errors." }, { "left": "issue:30333", - "right": "issue:36331", + "right": "issue:34689", + "accept": false, + "reason": "MLflow reporting on failure is unrelated to a model-loading regression for Llama 3.2 Vision." + }, + { + "left": "issue:43723", + "right": "issue:44977", + "accept": false, + "reason": "Tokenizer load failures and flash-attention generation issues are different bugs." + }, + { + "left": "issue:43873", + "right": "issue:44945", + "accept": false, + "reason": "Quantization/offloading behavior and pipeline-parallel output mismatch are different runtime issues." + }, + { + "left": "issue:44222", + "right": "issue:44484", + "accept": false, + "reason": "FP8 save_pretrained MoE behavior is unrelated to the max_shard_size default question." + }, + { + "left": "issue:28282", + "right": "issue:30333", + "accept": false, + "reason": "PyTorch import availability and MLflow reporting on failed training jobs are unrelated." + }, + { + "left": "issue:44297", + "right": "issue:45310", "accept": false, - "reason": "MLflow job-reporting failure and CustomTrainer compute_loss signature mismatch are unrelated training bugs." + "reason": "Tokenizer_class metadata mismatch and Qwen3.5 MoE from_pretrained failure are different problems." + }, + { + "left": "issue:30333", + "right": "issue:35141", + "accept": false, + "reason": "MLflow job reporting and embedding reinitialization in post_init are unrelated." + }, + { + "left": "issue:44263", + "right": "issue:45092", + "accept": false, + "reason": "GlmMoeDsaIndexer split semantics and InternVL2 meta-init compatibility are different bugs." } ] }, @@ -11556,16 +11491,16 @@ "nodes": [ "issue:22355", "issue:28282", - "issue:30333", "issue:30990", - "issue:34689", - "issue:35141", + "issue:33357", "issue:38175", "issue:39401", "issue:41628", + "issue:42371", "issue:42757", "issue:42831", "issue:42886", + "issue:42907", "issue:42994", "issue:43066", "issue:43232", @@ -11573,30 +11508,30 @@ "issue:43576", "issue:43644", "issue:43723", + "issue:43756", "issue:43784", "issue:43824", - "issue:43873", "issue:44038", - "issue:44222", + "issue:44060", + "issue:44117", "issue:44261", "issue:44263", "issue:44295", - "issue:44297", "issue:44360", "issue:44373", "issue:44483", - "issue:44484", "issue:44485", "issue:44514", "issue:44568", "issue:44623", + "issue:44704", "issue:44871", "issue:44913", "issue:44945", - "issue:44977", "issue:45092", "issue:45103", "issue:45278", + "issue:45290", "issue:45310", "issue:45357", "issue:45406", @@ -11604,21 +11539,12 @@ "issue:45753" ], "soft_pairs": [ - "issue:41628|issue:42757", - "issue:44297|issue:45310", - "issue:30333|issue:34689", - "issue:43723|issue:44977", - "issue:43873|issue:44945", - "issue:44222|issue:44484", - "issue:44263|issue:45092", - "issue:28282|issue:30333", - "issue:30333|issue:35141", "issue:44483|issue:45406", "issue:44263|issue:44360", - "issue:44373|issue:44485", - "issue:44295|issue:44623", "issue:44514|issue:45103", + "issue:44373|issue:44485", "issue:43479|issue:43644", + "issue:44295|issue:44623", "issue:44261|issue:45092", "issue:45092|issue:45357", "issue:43723|issue:44871", @@ -11627,236 +11553,224 @@ "issue:42886|issue:42994", "issue:41628|issue:43824", "issue:22355|issue:28282", - "issue:42831|issue:45310", "issue:39401|issue:44568", + "issue:42831|issue:45310", "issue:44263|issue:44373", "issue:44945|issue:45753", "issue:42831|issue:44038", "issue:42757|issue:45278", "issue:43576|issue:43784", "issue:42886|issue:43066", - "issue:43232|issue:45593" + "issue:43232|issue:45593", + "issue:42371|issue:44263", + "issue:43756|issue:44060", + "issue:44117|issue:44704", + "issue:30990|issue:33357", + "issue:42907|issue:44945", + "issue:44704|issue:45290" ], - "prepared_review_unit_hash": "07cac3b403e6da2ef43bfc87bf9abdcbb3c6ff45010e2f58cbea6a5dc1d08cc4", + "prepared_review_unit_hash": "1ea5f8c2bea51c34c555464996d409cdfe66948f4e6b73b648ab69352a275f2d", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 32, - "serialized_chars": 36863, - "estimated_input_tokens": 9216, - "estimated_eval_tokens": 18688 + "soft_pair_count": 29, + "serialized_chars": 36004, + "estimated_input_tokens": 9001, + "estimated_eval_tokens": 18258 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These items are mostly heterogeneous, with no soft pair looking like the same concrete bug/change. The closest matches are only broad subsystem overlaps (imports, tokenizers, save/load, quantization), but not true duplicates. I\u2019d use the broad v5 import-regression report as the best issue representative.", - "confidence": 0.67, - "canonical_issue_reason": "Issue 45278 is the broadest, most representative active report in this set: it summarizes widespread import failures after upgrading to Transformers 5.5.0, which is the kind of umbrella issue that can collect related reports.", + "summary": "The cluster is highly heterogeneous; the soft pairs mostly share only subsystem-level similarity (imports, tokenizers, save/load, multimodal, generation) but not the same concrete bug. No soft pair is a safe duplicate merge candidate.", + "confidence": 0.72, + "canonical_issue_reason": "issue:45278 is the broadest umbrella-style report in the set: it describes many import errors after upgrading to v5.5.0, so it is the most representative issue for this mixed regression cluster.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45278 has the widest scope among the candidates and is phrased as a general regression rather than a model-specific edge case, making it the best single issue to anchor the cluster.", + "best_issue_reason": "issue:45278 is the strongest cluster anchor because it is open, broad, and directly captures a large class of upgrade-related import failures rather than a single narrow symptom.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:41628", - "right": "issue:42757", - "accept": false, - "reason": "Both are import errors, but they involve different missing symbols and different dependency boundaries; not the same bug." - }, - { - "left": "issue:44297", - "right": "issue:45310", - "accept": false, - "reason": "Tokenizer config save/load metadata mismatch vs Qwen3.5 from_pretrained failure; different code paths and symptoms." - }, - { - "left": "issue:30333", - "right": "issue:34689", - "accept": false, - "reason": "MLflow reporting after failed training vs model loading regression; unrelated failures." - }, - { - "left": "issue:43723", - "right": "issue:44977", - "accept": false, - "reason": "General tokenizer loading issue vs Qwen3.5 flash-attention generation bug; different concrete problems." - }, - { - "left": "issue:43873", - "right": "issue:44945", - "accept": false, - "reason": "Quantization/offloading behavior vs pipeline-parallel output correctness; not the same underlying bug." - }, - { - "left": "issue:44222", - "right": "issue:44484", - "accept": false, - "reason": "FP8 save_pretrained bug vs a question about max_shard_size defaults; not duplicates." - }, - { - "left": "issue:44263", - "right": "issue:45092", - "accept": false, - "reason": "DSA indexer torch.split behavior vs meta-init incompatibility for old InternVL2 checkpoints; different issues." - }, - { - "left": "issue:28282", - "right": "issue:30333", - "accept": false, - "reason": "Missing PyTorch import dependency vs MLflow reporting after failed jobs; unrelated." - }, - { - "left": "issue:30333", - "right": "issue:35141", - "accept": false, - "reason": "Training-job reporting vs embedding reinitialization on resize; different layers of the stack." - }, { "left": "issue:44483", "right": "issue:45406", "accept": false, - "reason": "Chat/completions request handling vs Gemma4Processor attribute crash; different endpoints and bugs." + "reason": "Different failures: chat/completions request validation vs Gemma4Processor missing _tokenizer during serve startup." }, { "left": "issue:44263", "right": "issue:44360", "accept": false, - "reason": "Same broad DSA area, but one is about torch.split return values and the other about a missing ReLU; not the same change." + "reason": "Unrelated bugs in the same general area; one is torch.split return handling, the other is a missing ReLU in a DSA indexer." }, { - "left": "issue:44373", - "right": "issue:44485", + "left": "issue:44514", + "right": "issue:45103", "accept": false, - "reason": "Docstring issue vs RoPE implementation bug; clearly different." + "reason": "Batched chat template crash is unrelated to the auto_docstring AttributeError from future annotations." }, { - "left": "issue:44295", - "right": "issue:44623", + "left": "issue:44373", + "right": "issue:44485", "accept": false, - "reason": "Buffer registration/readback bug vs processor save_pretrained missing files; different subsystems." + "reason": "A docstring mistake is not the same bug as the GLM-5 RoPE implementation issue." }, { - "left": "issue:44514", - "right": "issue:45103", + "left": "issue:43479", + "right": "issue:43644", "accept": false, - "reason": "Qwen2_5_VL chat template batching crash vs auto_docstring annotation crash; unrelated." + "reason": "Config defaulting when None and non-persistent buffer junk are different code paths and symptoms." }, { - "left": "issue:43479", - "right": "issue:43644", + "left": "issue:44295", + "right": "issue:44623", "accept": false, - "reason": "Default multimodal config initialization vs junk-filled non-persistent buffers; not the same bug." + "reason": "Registering position_ids as a buffer is unrelated to processor.save_pretrained missing files." }, { "left": "issue:44261", "right": "issue:45092", "accept": false, - "reason": "Precision/config epsilon issue in MLA vs checkpoint meta-init incompatibility; different root causes." + "reason": "LayerNorm epsilon precision mismatch and remote-code meta-init incompatibility are distinct problems." }, { "left": "issue:45092", "right": "issue:45357", "accept": false, - "reason": "Old InternVL2 meta-init incompatibility vs incorrect visual encoder keys on save_pretrained; different code paths." + "reason": "Meta-initialization incompatibility for old checkpoints is not the same as incorrect visual encoder keys on save_pretrained." }, { "left": "issue:43723", "right": "issue:44871", "accept": false, - "reason": "General tokenizer loading failure vs Gemma eos_token_id inconsistency; both tokenizer-related but not the same defect." + "reason": "Tokenizer loading regression and eos_token_id config inconsistency are different issues." }, { "left": "issue:30990", "right": "issue:38175", "accept": false, - "reason": "Sentence-transformers loading stall vs unexpected zero probabilities in SigLIP2; unrelated." + "reason": "Sentence-Transformers loading stall and zero-probabilities on SigLIP2 are unrelated behaviors." }, { "left": "issue:43479", "right": "issue:44913", "accept": false, - "reason": "Config defaulting when None vs GPTNeoX rotary_pct not persisting on reload; different configuration bugs." + "reason": "Different model config bugs: Phi4 multimodal defaults vs GPTNeoX rotary_pct reload." }, { "left": "issue:42886", "right": "issue:42994", "accept": false, - "reason": "Offline cache tokenizer load failure vs quantized model saving failure; different operations and symptoms." + "reason": "Offline tokenizer cache loading and quantized model saving are separate failure modes." }, { "left": "issue:41628", "right": "issue:43824", "accept": false, - "reason": "Both are import errors, but for different missing transformer exports and different model families; not a duplicate." + "reason": "Both are import errors, but they concern different missing exports and likely different fixes." }, { "left": "issue:22355", "right": "issue:28282", "accept": false, - "reason": "Missing transformers.onnx module vs missing PyTorch dependency for AutoModel; unrelated import failures." + "reason": "onnx module import failure is not the same as missing PyTorch for AutoModel." }, { - "left": "issue:42831", - "right": "issue:45310", + "left": "issue:39401", + "right": "issue:44568", "accept": false, - "reason": "FineGrainedFP8 accuracy issue vs Qwen3.5 from_pretrained error; different bugs." + "reason": "Wrong offset_mapping and BOS/EOS insertion behavior are distinct tokenizer bugs." }, { - "left": "issue:39401", - "right": "issue:44568", + "left": "issue:42831", + "right": "issue:45310", "accept": false, - "reason": "Tokenizer offset_mapping bug vs add_special_tokens BOS/EOS omission; both tokenizer issues but not the same underlying behavior." + "reason": "FineGrainedFP8 accuracy and Qwen3.5 MoE from_pretrained errors are unrelated." }, { "left": "issue:44263", "right": "issue:44373", "accept": false, - "reason": "DSA indexer runtime behavior vs a wrong docstring; not comparable as duplicates." + "reason": "A runtime tensor split bug is not a docstring typo." }, { "left": "issue:44945", "right": "issue:45753", "accept": false, - "reason": "Pipeline parallelism output correctness vs a Qwen3_5 image-specific infinite loop; unrelated model/runtime bugs." + "reason": "Pipeline parallelism output corruption and an image-specific infinite loop are different LLM-generation problems." }, { "left": "issue:42831", "right": "issue:44038", "accept": false, - "reason": "FineGrainedFP8 accuracy regression vs Qwen3-VL-Moe bug; different concrete failures." + "reason": "FineGrainedFP8 accuracy regression and Qwen3-VL-Moe loading bug are not the same issue." }, { "left": "issue:42757", "right": "issue:45278", "accept": false, - "reason": "Specific missing is_offline_mode import vs a broad set of import errors after upgrade; related theme, but not the same concrete bug." + "reason": "A single missing huggingface_hub symbol and a broad multi-import regression after upgrade are related only at subsystem level, not the same bug." }, { "left": "issue:43576", "right": "issue:43784", "accept": false, - "reason": "Broken transformers env command vs sentence-transformers import NameError; different code paths." + "reason": "The env command regression and the sentence-transformers import NameError are separate failures." }, { "left": "issue:42886", "right": "issue:43066", "accept": false, - "reason": "Offline tokenizer cache load failure vs wrong tokenizer decoder type in v5; different problems." + "reason": "Offline cache loading failure and wrong tokenizer decoder type are different tokenizer regressions." }, { "left": "issue:43232", "right": "issue:45593", "accept": false, - "reason": "Generation kwargs update bug vs D-FINE auxiliary-loss behavior; unrelated." + "reason": "Generation kwargs handling after sync_gpus and D-FINE auxiliary loss behavior are unrelated." + }, + { + "left": "issue:42371", + "right": "issue:44263", + "accept": false, + "reason": "TF32 settings API guidance and torch.split return handling do not share the same code-path bug." + }, + { + "left": "issue:43756", + "right": "issue:44060", + "accept": false, + "reason": "RoPE layer dropping in Smollm3 is not the same as an incorrect tied-weights warning in Qwen3-Next." + }, + { + "left": "issue:44117", + "right": "issue:44704", + "accept": false, + "reason": "TOKENIZER_MAPPING_NAMES returning None and AutoProcessor kwargs forwarding are different from_pretrained plumbing bugs." + }, + { + "left": "issue:30990", + "right": "issue:33357", + "accept": false, + "reason": "Loading stall in Sentence-Transformers is unrelated to a bus error on MacOS with a community CLIP model." + }, + { + "left": "issue:42907", + "right": "issue:44945", + "accept": false, + "reason": "Quantized model saving failure and pipeline-parallelism output corruption are different behaviors." + }, + { + "left": "issue:44704", + "right": "issue:45290", + "accept": false, + "reason": "AutoProcessor cached_file kwargs forwarding is unrelated to assistant-message chat template crashes with tool calls." } ] }, @@ -11880,14 +11794,16 @@ "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-390", "nodes": [ + "issue:22355", + "issue:28218", "issue:29127", "issue:30990", - "issue:33357", "issue:36296", "issue:39401", "issue:41628", - "issue:42371", + "issue:42757", "issue:42907", + "issue:43066", "issue:43116", "issue:43122", "issue:43232", @@ -11895,16 +11811,13 @@ "issue:43452", "issue:43475", "issue:43723", - "issue:43756", "issue:43784", "issue:43824", "issue:43937", + "issue:43992", "issue:44038", - "issue:44060", - "issue:44117", "issue:44222", "issue:44261", - "issue:44263", "issue:44295", "issue:44297", "issue:44351", @@ -11917,265 +11830,286 @@ "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:45290", + "issue:45446", + "issue:45478", "issue:45600" ], "soft_pairs": [ - "issue:42371|issue:44263", - "issue:44117|issue:44704", - "issue:43756|issue:44060", - "issue:30990|issue:33357", - "issue:42907|issue:44945", - "issue:44704|issue:45290", - "issue:44295|issue:44297", "issue:43122|issue:44514", "issue:43232|issue:45245", "issue:43784|issue:45600", "issue:43723|issue:44779", + "issue:44295|issue:44297", "issue:42907|issue:43937", - "issue:44261|issue:44373", - "issue:43723|issue:44442", "issue:41628|issue:45278", + "issue:43723|issue:44442", "issue:43408|issue:43475", + "issue:44261|issue:44373", "issue:44360|issue:44485", "issue:43122|issue:44521", - "issue:43232|issue:44743", "issue:44625|issue:44829", "issue:43116|issue:45200", "issue:29127|issue:30990", "issue:42907|issue:44964", - "issue:44038|issue:44297", "issue:43122|issue:44779", - "issue:44038|issue:44295", + "issue:44038|issue:44297", "issue:42907|issue:43452", "issue:39401|issue:44488", "issue:36296|issue:43116", - "issue:44038|issue:44222", + "issue:44038|issue:44295", "issue:43824|issue:44351", - "issue:39401|issue:44521" + "issue:44038|issue:44222", + "issue:39401|issue:44521", + "issue:45216|issue:45478", + "issue:42757|issue:44351", + "issue:43066|issue:44779", + "issue:22355|issue:28218", + "issue:42907|issue:44222", + "issue:43992|issue:44704", + "issue:43122|issue:44977", + "issue:43784|issue:45446", + "issue:43937|issue:44485" ], - "prepared_review_unit_hash": "31195dcd1eab70b57c175ac13922474e725cc22d638aef908c6940a213c2319f", + "prepared_review_unit_hash": "03524216562f09dad81a299959fac2f3becdc71175c9603e5e19af2ef5c29c21", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { "node_count": 47, "item_count": 47, - "soft_pair_count": 32, - "serialized_chars": 36386, - "estimated_input_tokens": 9097, - "estimated_eval_tokens": 18450 + "soft_pair_count": 34, + "serialized_chars": 36838, + "estimated_input_tokens": 9210, + "estimated_eval_tokens": 18676 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is mostly heterogeneous transformer bugs rather than one duplicate cluster. The only plausible soft duplicate is a tokenizer-loading regression in v5 (43723 \u2194 44442); the rest are too different in model, subsystem, or failure mode.", - "confidence": 0.68, - "canonical_issue_reason": "No single true canonical issue spans the whole set. If forced to anchor the closest duplicate subgroup, issue 43723 is the best candidate because it is the broadest report of a v5 AutoTokenizer loading regression.", + "summary": "Most candidate pairs are only superficially similar (shared model family, tokenizer, import, or save/load wording) and do not look like the same underlying bug. The only reasonably strong duplicate pair is the AutoTokenizer loading regression in v5 (43723/44442).", + "confidence": 0.46, + "canonical_issue_reason": "Issue 43723 is the broadest and most representative report of the tokenizer-loading regression in v5; it cleanly captures the shared AutoTokenizer.from_pretrained failure mode.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43723 is the most general, symptom-focused tokenizer-loading regression among the items, so it is the best canonical anchor for the one likely duplicate subgroup.", + "best_issue_reason": "Issue 43723 is the best umbrella issue because it describes the underlying AutoTokenizer loading problem at a higher level, while 44442 is a specific instance of that failure.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:42371", - "right": "issue:44263", - "accept": false, - "reason": "TF32 settings guidance and a torch.split return-value bug are unrelated subsystems and symptoms." - }, - { - "left": "issue:44117", - "right": "issue:44704", - "accept": false, - "reason": "TOKENIZER_MAPPING_NAMES returning None is a tokenizer registry bug; cached_file kwargs forwarding is a processor loading bug." - }, - { - "left": "issue:43756", - "right": "issue:44060", - "accept": false, - "reason": "Different model-specific problems: missing RoPE layers vs an incorrect tied-weights warning." - }, - { - "left": "issue:30990", - "right": "issue:33357", - "accept": false, - "reason": "A loading hang and a Mac bus error are different failure modes on different models." - }, - { - "left": "issue:42907", - "right": "issue:44945", - "accept": false, - "reason": "Saving dequantized models and pipeline-parallel output correctness are not the same code-path problem." - }, - { - "left": "issue:44704", - "right": "issue:45290", - "accept": false, - "reason": "Processor kwargs propagation and chat-template tool-call crashes are distinct issues." - }, - { - "left": "issue:44295", - "right": "issue:44297", - "accept": false, - "reason": "Reading a buffer-backed position_ids tensor and tokenizer_class metadata mismatch are unrelated." - }, { "left": "issue:43122", "right": "issue:44514", "accept": false, - "reason": "Tokenizer behavior change across versions and batched chat-template crashes are different bugs." + "reason": "Both are tokenizer-related, but one is about changed tokenization across versions and the other is a batched chat-template crash. Different failure modes and likely different fixes." }, { "left": "issue:43232", "right": "issue:45245", "accept": false, - "reason": "Generation kwarg handling after sync_gpus and a category-count limit error do not match." + "reason": "Unrelated bugs: generation state handling after sync_gpus versus a category-count limit error." }, { "left": "issue:43784", "right": "issue:45600", "accept": false, - "reason": "Sentence-transformers import NameError and broken Sam3LiteText mappings are separate import/regression reports." + "reason": "Different problems: sentence-transformers import NameError versus stale auto_mappings references to removed SAM3 configs." }, { "left": "issue:43723", "right": "issue:44779", "accept": false, - "reason": "Both involve tokenizers in v5, but one is a loading failure and the other is incorrect tokenization output." + "reason": "Both mention tokenizer regressions in v5, but one is a loading failure and the other is incorrect tokenizer output for Deepseek. Not clearly the same concrete defect." + }, + { + "left": "issue:44295", + "right": "issue:44297", + "accept": false, + "reason": "Position_ids buffer access error and tokenizer_class metadata mismatch are unrelated." }, { "left": "issue:42907", "right": "issue:43937", "accept": false, - "reason": "Dequantized save failures and invalid GenerationConfig errors are different problems." + "reason": "Different model-specific issues: dequantized save_pretrained failure versus invalid GenerationConfig for GLM-5." }, { - "left": "issue:44261", - "right": "issue:44373", + "left": "issue:41628", + "right": "issue:45278", "accept": false, - "reason": "A precision/config bug in q_a_layernorm and a wrong docstring for position_ids are unrelated." + "reason": "The second is a broad report of many import errors; it is too vague to treat as the same specific AutoImageProcessor import bug." }, { "left": "issue:43723", "right": "issue:44442", "accept": true, - "reason": "Both describe AutoTokenizer.from_pretrained loading failures in v5; 44442 looks like a model-specific instance of the same loader regression." + "reason": "Both describe the same AutoTokenizer.from_pretrained loading regression in v5; 44442 is a concrete tokenizer example of the broader issue in 43723." }, { - "left": "issue:41628", - "right": "issue:45278", + "left": "issue:43408", + "right": "issue:43475", "accept": false, - "reason": "A missing exported symbol and broad post-upgrade import errors are too general to treat as the same concrete bug." + "reason": "Same model family, but one is a config/type warning and the other is a missing attribute in encoder output. Different code paths." }, { - "left": "issue:43408", - "right": "issue:43475", + "left": "issue:44261", + "right": "issue:44373", "accept": false, - "reason": "SAM3 model-type warning and a missing fpn_position_embeddings attribute are different SAM3 issues." + "reason": "MLA norm precision/config issue and a wrong docstring for position_ids are unrelated." }, { "left": "issue:44360", "right": "issue:44485", "accept": false, - "reason": "The DSA indexer ReLU discussion and the GLM-5 RoPE implementation bug are unrelated." + "reason": "No meaningful overlap: DSA indexer ReLU versus GLM-5 RoPE implementation." }, { "left": "issue:43122", "right": "issue:44521", "accept": false, - "reason": "Tokenizer regression and all-zero assistant masks in multimodal chat templates are different manifestations." - }, - { - "left": "issue:43232", - "right": "issue:44743", - "accept": false, - "reason": "Generation state handling after sync_gpus and recurrent-state reset in modular_qwen3_5 are distinct code paths." + "reason": "Both concern tokenization/chat-template behavior, but one is a tokenizer-version difference and the other is assistant_mask generation for multimodal inputs." }, { "left": "issue:44625", "right": "issue:44829", "accept": false, - "reason": "num_labels propagation in Qwen3.5 and flash_attention_3 training degeneration are not the same bug." + "reason": "Different subsystems: Qwen3.5 num_labels propagation versus flash_attention_3 training degeneration." }, { "left": "issue:43116", "right": "issue:45200", "accept": false, - "reason": "Example-script multi-label output failure and Gemma 4 token-type defaults are separate issues." + "reason": "An example script returning empty multi-label results is unrelated to Gemma 4 mm_token_type_ids defaults." }, { "left": "issue:29127", "right": "issue:30990", "accept": false, - "reason": "LayoutLMv3 error-message clarity and Sentence Transformers loading hang are unrelated." + "reason": "LayoutLMv3 error-message clarity and Sentence Transformers loading stall are unrelated." }, { "left": "issue:42907", "right": "issue:44964", "accept": false, - "reason": "Dequantized save failure and Phi-4 multimodal load failure are different model-level bugs." + "reason": "Different bugs: quantized dequantized save failure versus loading a specific multimodal model." + }, + { + "left": "issue:43122", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer regressions in v5, but they affect different models and symptoms; not enough to \u0441\u0447\u0438\u0442\u0430\u0442\u044c them the same bug." }, { "left": "issue:44038", "right": "issue:44297", "accept": false, - "reason": "Qwen3-VL-Moe breakage and tokenizer save metadata mismatch are not the same underlying issue." + "reason": "Qwen3-VL-Moe bug and tokenizer save_pretrained metadata mismatch are unrelated." }, { - "left": "issue:43122", - "right": "issue:44779", + "left": "issue:39401", + "right": "issue:44488", + "accept": false, + "reason": "Wrong offset_mapping and failing to load cjvt/sleng-bert are distinct tokenizer issues." + }, + { + "left": "issue:36296", + "right": "issue:43116", "accept": false, - "reason": "A tokenizer regression and Deepseek tokenizer incorrect results are both tokenizer-related, but not the same concrete failure." + "reason": "Tensor parallel training bug versus empty results in an example script are unrelated." }, { "left": "issue:44038", - "right": "issue:44222", + "right": "issue:44295", "accept": false, - "reason": "Qwen3-VL-Moe bugs and FP8 save_pretrained moe bugs are different concrete problems." + "reason": "No clear shared failure mode: Qwen3-VL-Moe issue versus position_ids buffer error." }, { "left": "issue:43824", "right": "issue:44351", "accept": false, - "reason": "Missing Qwen2_5_VLForConditionalGeneration and missing HybridCache exports are distinct import errors; do not merge just because both are import failures." + "reason": "Both are import errors, but for different symbols and likely different root causes." + }, + { + "left": "issue:44038", + "right": "issue:44222", + "accept": false, + "reason": "Both mention MoE, but the issues are about different model families and different save/load paths." }, { "left": "issue:39401", - "right": "issue:44488", + "right": "issue:44521", "accept": false, - "reason": "Wrong offset_mapping in Qwen3 tokenizer and a model-loading failure for cjvt/sleng-bert are unrelated." + "reason": "Wrong offset mapping and all-zero assistant masks are different tokenizer behaviors." }, { - "left": "issue:36296", - "right": "issue:43116", + "left": "issue:45216", + "right": "issue:45478", "accept": false, - "reason": "Tensor-parallel training and multi-label example-script output are different bug classes." + "reason": "Both involve Qwen3.5 and version 5.4+, but one is save_pretrained output correctness and the other is from_pretrained loading; too different to merge." }, { - "left": "issue:39401", - "right": "issue:44521", + "left": "issue:42757", + "right": "issue:44351", + "accept": false, + "reason": "Different import failures from different packages and symbols." + }, + { + "left": "issue:43066", + "right": "issue:44779", + "accept": false, + "reason": "Tokenizer decoder type mismatch and Deepseek incorrect results may be related at a high level, but the concrete problems are not clearly the same." + }, + { + "left": "issue:22355", + "right": "issue:28218", + "accept": false, + "reason": "Completely unrelated: missing transformers.onnx module versus added-token spacing behavior." + }, + { + "left": "issue:42907", + "right": "issue:44222", + "accept": false, + "reason": "Both concern saving quantized/MoE models, but they are model-specific and do not obviously share one concrete bug." + }, + { + "left": "issue:43992", + "right": "issue:44704", + "accept": false, + "reason": "UMT5 weight loading and AutoProcessor cached_file kwargs are unrelated." + }, + { + "left": "issue:43122", + "right": "issue:44977", + "accept": false, + "reason": "Tokenization regression versus flash-attention generation failure are unrelated." + }, + { + "left": "issue:43784", + "right": "issue:45446", + "accept": false, + "reason": "sentence-transformers import failure and flex_attention version check bug are unrelated." + }, + { + "left": "issue:43937", + "right": "issue:44485", "accept": false, - "reason": "Tokenizer offset-mapping corruption and zero assistant masks in multimodal apply_chat_template are different issues." + "reason": "GLM-5 GenerationConfig validation and GLM-5 RoPE implementation are different issues." } ] }, "evaluator_result": { "accept": true, - "feedback": "The analysis is well-grounded in the packet and stays conservative on the soft-edge calls. The lone accepted pair, issue:43723 \u2194 issue:44442, is supported by both titles describing AutoTokenizer loading failures in v5. The remaining verdicts generally avoid overclaiming duplicate status across clearly different subsystems or failure modes. No PR-pair mergeability issue applies here." + "feedback": "The summary is conservative and grounded in the packet. The only accepted duplicate pair, issue:43723 vs issue:44442, is supported by the titles as the same AutoTokenizer.from_pretrained loading failure class. The remaining soft-edge rejections are appropriately cautious and do not overstate evidence." }, "evaluator_used": true, "retried": false, @@ -12197,47 +12131,47 @@ "cluster_id": "cluster-15354-390", "nodes": [ "issue:22355", - "issue:28218", "issue:29127", "issue:33453", "issue:38617", "issue:39401", + "issue:41628", "issue:42222", "issue:42371", - "issue:42757", + "issue:42673", "issue:42831", - "issue:42907", "issue:43064", - "issue:43066", "issue:43116", - "issue:43122", "issue:43381", + "issue:43421", "issue:43441", "issue:43450", "issue:43493", "issue:43673", - "issue:43784", "issue:43825", "issue:43827", "issue:43874", "issue:43937", "issue:43976", "issue:43986", - "issue:43992", "issue:44038", "issue:44075", "issue:44117", "issue:44222", - "issue:44351", - "issue:44485", - "issue:44704", + "issue:44291", + "issue:44410", "issue:44779", + "issue:44829", "issue:44936", "issue:44945", "issue:44977", + "issue:45071", + "issue:45072", + "issue:45081", "issue:45083", "issue:45216", "issue:45278", + "issue:45310", "issue:45405", "issue:45446", "issue:45478", @@ -12246,15 +12180,6 @@ "issue:45753" ], "soft_pairs": [ - "issue:45216|issue:45478", - "issue:42757|issue:44351", - "issue:43066|issue:44779", - "issue:22355|issue:28218", - "issue:42907|issue:44222", - "issue:43992|issue:44704", - "issue:43122|issue:44977", - "issue:43784|issue:45446", - "issue:43937|issue:44485", "issue:42222|issue:43441", "issue:42371|issue:43874", "issue:43976|issue:45446", @@ -12272,233 +12197,228 @@ "issue:39401|issue:44779", "issue:33453|issue:39401", "issue:44117|issue:45588", - "issue:22355|issue:29127", - "issue:43827|issue:45446", - "issue:43381|issue:44945", - "issue:43937|issue:44977", - "issue:45405|issue:45446", - "issue:43450|issue:43986" - ], - "prepared_review_unit_hash": "2ffcc3414d5763dc574eef5bd9a7ec0ee6e36ec848d299bf38a3f37685943cb4", - "component_budget": { - "node_count": 390, - "item_count": 390, - "soft_pair_count": 1471, - "serialized_chars": 757026, - "estimated_input_tokens": 189257, - "estimated_eval_tokens": 378770 - }, - "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 32, - "serialized_chars": 36737, - "estimated_input_tokens": 9185, - "estimated_eval_tokens": 18626 - }, - "overflow_policy": "truncate_then_skip", - "trimmed": false, - "aggressively_trimmed": false, - "split": true, - "analyst_result": { - "summary": "This cluster is broadly heterogeneous, with many unrelated Transformers v5 regressions, import errors, tokenizer bugs, and model-specific failures. No soft pair is a clear duplicate; the best representative issue is the broad import-regression report (#45278).", - "confidence": 0.41, - "canonical_issue_reason": "#45278 is the broadest and most umbrella-like issue in the set (\u201cmany import errors after update\u201d), so it is the most plausible canonical bucket for near-duplicates in this noisy cluster.", - "canonical_pr_reason": null, - "best_issue_reason": "#45278 is the most generally applicable report and the best representative of the overall v5 upgrade/import-regression theme, even though the cluster is not truly cohesive.", - "best_pr_reason": null, - "soft_edge_verdicts": [ - { - "left": "issue:45216", - "right": "issue:45478", - "accept": false, - "reason": "Same model family, but one is a save_pretrained checkpoint issue and the other is a from_pretrained/load error; not the same concrete bug." - }, - { - "left": "issue:42757", - "right": "issue:44351", - "accept": false, - "reason": "Both are import errors, but they involve different missing symbols from different packages and different code paths." - }, - { - "left": "issue:43066", - "right": "issue:44779", - "accept": false, - "reason": "Both concern tokenizer behavior in v5, but one is decoder-type selection and the other is Deepseek output correctness; too different to merge." - }, - { - "left": "issue:22355", - "right": "issue:28218", - "accept": false, - "reason": "Completely different problems: ONNX module import vs extra whitespace after added tokens." - }, - { - "left": "issue:42907", - "right": "issue:44222", - "accept": false, - "reason": "Both touch model saving, but one is dequantized Ministral/Devstral saving and the other is FP8 MoE save_pretrained; not the same bug." - }, - { - "left": "issue:43992", - "right": "issue:44704", - "accept": false, - "reason": "One is a specific encoder weight-loading omission, the other is AutoProcessor not forwarding kwargs; different layers and failures." - }, - { - "left": "issue:43122", - "right": "issue:44977", - "accept": false, - "reason": "Tokenizer regression vs flash-attention generation failure; no shared concrete code path." - }, - { - "left": "issue:43784", - "right": "issue:45446", - "accept": false, - "reason": "Both are import/version-related crashes, but they are unrelated dependency checks and missing imports in different modules." - }, - { - "left": "issue:43937", - "right": "issue:44485", - "accept": false, - "reason": "Same model family, but invalid GenerationConfig and RoPE implementation are distinct bugs." - }, + "issue:22355|issue:29127", + "issue:43381|issue:44945", + "issue:43827|issue:45446", + "issue:43937|issue:44977", + "issue:45405|issue:45446", + "issue:43450|issue:43986", + "issue:44117|issue:45081", + "issue:42673|issue:45072", + "issue:39401|issue:43421", + "issue:38617|issue:41628", + "issue:44410|issue:45310", + "issue:44829|issue:45216", + "issue:44291|issue:45071" + ], + "prepared_review_unit_hash": "fdd12d30987d8f53a20444edbb2d8f6e0e350af7de367ed94fe78897b47420aa", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36490, + "estimated_input_tokens": 9123, + "estimated_eval_tokens": 18502 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These are mostly unrelated single-issue reports across different subsystems; I do not see a real duplicate cluster. All soft edges should be rejected. The broadest issue is the open import-regression report 45278, but it still does not subsume the rest.", + "confidence": 0.93, + "canonical_issue_reason": "No single canonical issue stands out because the set is heterogeneous. If a broad umbrella is needed, 45278 is the closest, but it only covers import errors after upgrading to 5.5.0, not the other bugs here.", + "canonical_pr_reason": null, + "best_issue_reason": "453? No PRs are present. Among the issues, 45278 is the most general representative because it describes a broad import-regression class, but it is still not a true duplicate target for the other items.", + "best_pr_reason": null, + "soft_edge_verdicts": [ { "left": "issue:42222", "right": "issue:43441", "accept": false, - "reason": "Different model families and different failure modes: broken vitpose models vs Ministral-3 flash-attention failure." + "reason": "Different models and failures: vitpose model breakage vs Ministral FlashAttention error." }, { "left": "issue:42371", "right": "issue:43874", "accept": false, - "reason": "TF32 API guidance vs a missing image-processor method; unrelated issues." + "reason": "TF32 API guidance vs missing image-patch method in GLM46V are unrelated." }, { "left": "issue:43976", "right": "issue:45446", "accept": false, - "reason": "Version-compatibility complaints, but one is a Python version support issue and the other is a PyTorch version check bug." + "reason": "Python version support mismatch vs an AuxRequest PyTorch version check bug." }, { "left": "issue:43493", "right": "issue:45753", "accept": false, - "reason": "Different multimodal models and different symptoms; no evidence of the same underlying bug." + "reason": "SigLIP2 implementation discrepancy vs Qwen3.5 image infinite loop are different bugs." }, { "left": "issue:42831", "right": "issue:45753", "accept": false, - "reason": "FineGrainedFP8 accuracy issue and Qwen3_5 image infinite loop are unrelated." + "reason": "FineGrainedFP8 accuracy issue and Qwen3.5 infinite loop are unrelated." }, { "left": "issue:44075", "right": "issue:44936", "accept": false, - "reason": "Optimizer-argument handling vs post-train evaluate failure; not the same defect." + "reason": "SGD args not applied vs trainer.evaluate() failing after train() are separate trainer issues." }, { "left": "issue:43116", "right": "issue:43825", "accept": false, - "reason": "Example-script multi-label output bug vs pipeline() error-message/docs inconsistency; different surfaces and causes." + "reason": "Multi-label classification example bug vs pipeline translation error message are different code paths." }, { "left": "issue:44038", "right": "issue:45478", "accept": false, - "reason": "Both involve Qwen MoE and v5, but one is a broad bug report and the other is a specific from_pretrained regression; not clearly the same code-path issue." + "reason": "Qwen3-VL-Moe issue vs Qwen3.5 Moe from_pretrained error involve different model families." }, { "left": "issue:44222", "right": "issue:45478", "accept": false, - "reason": "MoE-related but one is FP8 save_pretrained and the other is a load/from_pretrained failure; different operations." + "reason": "FP8 save_pretrained moe bug vs from_pretrained loading error are not the same symptom or path." }, { "left": "issue:43116", "right": "issue:43493", "accept": false, - "reason": "Classification example output vs SigLIP2 implementation discrepancy; unrelated." + "reason": "Example-script multi-label bug and SigLIP2 discrepancy are unrelated." }, { "left": "issue:43937", "right": "issue:45563", "accept": false, - "reason": "GenerationConfig validity vs a stale warning in paged generate; different bugs." + "reason": "Invalid GenerationConfig vs stale num_return_sequences warning are different generation issues." }, { "left": "issue:43064", "right": "issue:43673", "accept": false, - "reason": "Trainer/FSDP optimizer-state corruption vs missing GenerationMixin cache in chunked prefill; unrelated subsystems." + "reason": "FSDP2/PEFT optimizer-state corruption vs chunked_prefill cache absence are unrelated." }, { "left": "issue:45083", "right": "issue:45446", "accept": false, - "reason": "A qwen3_omni_moe helper-function behavior issue vs a flex_attention version-check bug; no shared code path." + "reason": "Feature-extraction output-length behavior vs a PyTorch version check bug do not match." }, { "left": "issue:38617", "right": "issue:45278", "accept": false, - "reason": "#45278 is a broad import-regression umbrella, but #38617 is a specific missing symbol import; not enough to treat as the same underlying bug." + "reason": "Specific missing import of layer_type_validation is not clearly the same as the broader 'many import errors' report." }, { "left": "issue:39401", "right": "issue:44779", "accept": false, - "reason": "Both are tokenizer correctness regressions, but they affect different model families and different behaviors." + "reason": "Qwen3 tokenizer offset_mapping bug vs Deepseek tokenizer regression are different tokenizer models and failures." }, { "left": "issue:33453", "right": "issue:39401", "accept": false, - "reason": "Tokenizer loading regression vs wrong offset_mapping; related domain but not the same concrete failure." + "reason": "Generic tokenizer-loading regression vs Qwen3 offset_mapping bug are not the same underlying defect." }, { "left": "issue:44117", "right": "issue:45588", "accept": false, - "reason": "Tokenizer mapping fallback bug vs flash_attention crash on s_aux=None; unrelated." + "reason": "TOKENIZER_MAPPING_NAMES None handling and flash_attention s_aux=None crash are unrelated." }, { "left": "issue:22355", "right": "issue:29127", "accept": false, - "reason": "No relation beyond both being issues; completely different components and symptoms." + "reason": "onnx import failure vs LayoutLMv3 error-message clarity are completely different issues." }, { - "left": "issue:43827", - "right": "issue:45446", + "left": "issue:43381", + "right": "issue:44945", "accept": false, - "reason": "Docs/pipeline-removal issue vs flex_attention version-check bug; unrelated." + "reason": "Gradient checkpointing eval-mode restriction vs incorrect pipeline-parallel LLM output are separate bugs." }, { - "left": "issue:43381", - "right": "issue:44945", + "left": "issue:43827", + "right": "issue:45446", "accept": false, - "reason": "Gradient checkpointing eval-mode restriction vs incorrect output under pipeline parallelism; different training/inference problems." + "reason": "Docs still referencing pipeline() vs a version-check bug are different kinds of problems." }, { "left": "issue:43937", "right": "issue:44977", "accept": false, - "reason": "Different model-specific generation problems with no shared concrete implementation failure." + "reason": "Invalid GenerationConfig vs Qwen3.5 flash-attention generation failure are not the same bug." }, { "left": "issue:45405", "right": "issue:45446", "accept": false, - "reason": "PEFT minimum-version packaging issue vs PyTorch version check bug; different dependencies and failure modes." + "reason": "Released PEFT version mismatch and AuxRequest version check are unrelated dependency issues." }, { "left": "issue:43450", "right": "issue:43986", "accept": false, - "reason": "Video processor batch shape bug vs AutoProcessor crash without torchvision; both video-related but not the same bug." + "reason": "Batched video processor shape bug vs torchvision-missing crash are different video-processing failures." + }, + { + "left": "issue:44117", + "right": "issue:45081", + "accept": false, + "reason": "Tokenizer mapping fallback bug vs Mistral regex patch crash are separate tokenizer internals." + }, + { + "left": "issue:42673", + "right": "issue:45072", + "accept": false, + "reason": "VRAM leak in multi-threaded Qwen3.5 use vs bfloat16 dtype mismatch in CI are unrelated." + }, + { + "left": "issue:39401", + "right": "issue:43421", + "accept": false, + "reason": "Tokenizer offset_mapping regression vs runtime special-token post-processor update feature are different tokenizer behaviors." + }, + { + "left": "issue:38617", + "right": "issue:41628", + "accept": false, + "reason": "Missing layer_type_validation import and missing AutoImageProcessor import are different import regressions." + }, + { + "left": "issue:44410", + "right": "issue:45310", + "accept": false, + "reason": "Qwen3next projection omission vs Qwen3.5 Moe from_pretrained error are different model bugs." + }, + { + "left": "issue:44829", + "right": "issue:45216", + "accept": false, + "reason": "FlashAttention 3 training degeneration vs save_pretrained checkpoint regression are unrelated." + }, + { + "left": "issue:44291", + "right": "issue:45071", + "accept": false, + "reason": "init_empty_weights argument error vs PretrainedConfig type-checking breakage are distinct v5 compatibility issues." } ] }, @@ -12523,7 +12443,6 @@ "cluster_id": "cluster-15354-390", "nodes": [ "issue:38617", - "issue:39401", "issue:41628", "issue:42175", "issue:42222", @@ -12534,22 +12453,24 @@ "issue:43066", "issue:43097", "issue:43122", + "issue:43335", "issue:43408", - "issue:43421", "issue:43441", + "issue:43452", "issue:43577", "issue:43742", "issue:43874", "issue:43906", "issue:43931", "issue:43937", + "issue:43976", + "issue:43986", "issue:44038", "issue:44075", "issue:44117", "issue:44220", "issue:44261", "issue:44263", - "issue:44291", "issue:44410", "issue:44483", "issue:44484", @@ -12557,12 +12478,11 @@ "issue:44493", "issue:44496", "issue:44829", + "issue:44945", "issue:44964", "issue:44977", + "issue:44987", "issue:45071", - "issue:45072", - "issue:45081", - "issue:45216", "issue:45278", "issue:45310", "issue:45459", @@ -12572,18 +12492,11 @@ "issue:45656" ], "soft_pairs": [ - "issue:44117|issue:45081", - "issue:42673|issue:45072", - "issue:39401|issue:43421", - "issue:38617|issue:41628", - "issue:44410|issue:45310", - "issue:44829|issue:45216", - "issue:44291|issue:45071", "issue:42222|issue:45542", "issue:44484|issue:45310", "issue:42175|issue:42222", - "issue:43937|issue:44496", "issue:43408|issue:43742", + "issue:43937|issue:44496", "issue:44483|issue:45464", "issue:44075|issue:45656", "issue:44964|issue:45278", @@ -12595,243 +12508,236 @@ "issue:44410|issue:45478", "issue:44484|issue:45478", "issue:42222|issue:45459", - "issue:44263|issue:44485", "issue:43097|issue:44493", + "issue:44263|issue:44485", "issue:43441|issue:44829", "issue:43012|issue:43408", "issue:41628|issue:45071", "issue:45071|issue:45542", - "issue:42371|issue:42831", "issue:42673|issue:44977", + "issue:42371|issue:42831", "issue:42673|issue:43906", - "issue:43931|issue:44038" + "issue:43931|issue:44038", + "issue:43986|issue:44484", + "issue:43335|issue:45071", + "issue:44117|issue:44987", + "issue:43097|issue:43452", + "issue:43976|issue:44945" ], - "prepared_review_unit_hash": "bbe176138eb06c257ac83c911d90e9ef865d038b159890a0bc44461864254b08", + "prepared_review_unit_hash": "a82fc3732cd1b0501e7d653ad3f1838a48ca67adde492c99bd3a567d0b734d33", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 33, - "serialized_chars": 37454, - "estimated_input_tokens": 9364, - "estimated_eval_tokens": 18984 + "soft_pair_count": 31, + "serialized_chars": 36711, + "estimated_input_tokens": 9178, + "estimated_eval_tokens": 18612 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is a heterogeneous mix of unrelated Transformers regressions and feature requests. The soft pairs mostly share only broad subsystem keywords (tokenizers, imports, Qwen, flash-attention, GLM, dtype), not the same concrete bug or change, so I reject all soft matches.", - "confidence": 0.96, - "canonical_issue_reason": null, + "summary": "The cluster is broad and mostly noisy: most pairs are only loosely related Transformers v5 regressions or model-loading failures, not exact duplicates. I would keep them split; issue 45278 is the broadest representative of the import/regression subset.", + "confidence": 0.61, + "canonical_issue_reason": "Issue 45278 is the broadest umbrella in this set for version-upgrade import/regression breakage, whereas the others are mostly narrower model-specific failures.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the broadest umbrella-style regression report in the set, so it is the best representative issue, but it still does not truly canonically cover the rest of the cluster.", + "best_issue_reason": "45278 is the most representative single issue to anchor the cluster because it captures the widest release-regression surface.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:44117", - "right": "issue:45081", - "accept": false, - "reason": "Both are tokenizer-adjacent failures, but one is a missing mapping/None-handling problem and the other is a Mistral regex/backend_tokenizer crash." - }, - { - "left": "issue:42673", - "right": "issue:45072", - "accept": false, - "reason": "Different bug classes: a multithreaded VRAM leak versus a bfloat16 dtype mismatch in inference." - }, - { - "left": "issue:39401", - "right": "issue:43421", - "accept": false, - "reason": "Both involve tokenizers, but offset_mapping corruption is not the same as post-processor not updating after runtime special-token changes." - }, - { - "left": "issue:38617", - "right": "issue:41628", - "accept": false, - "reason": "Different import failures for different symbols; no indication they stem from the same code path." - }, - { - "left": "issue:44410", - "right": "issue:45310", - "accept": false, - "reason": "One is missing projections in qwen3next; the other is a Qwen3.5 Moe from_pretrained load error." - }, - { - "left": "issue:44829", - "right": "issue:45216", - "accept": false, - "reason": "Flash-attention training degradation and save_pretrained checkpoint corruption are distinct problems." - }, - { - "left": "issue:44291", - "right": "issue:45071", - "accept": false, - "reason": "Unexpected _is_hf_initialized handling and PretrainedConfig type-checking are unrelated regressions." - }, { "left": "issue:42222", "right": "issue:45542", "accept": false, - "reason": "VitPose model breakage is unrelated to the TensorFlow backend being absent from a torch-only install." + "reason": "Different failures: vitpose model breakage vs missing TensorFlow backend." }, { "left": "issue:44484", "right": "issue:45310", "accept": false, - "reason": "A save_pretrained shard-size question does not match a Qwen3.5 Moe loading failure." + "reason": "Unrelated topics: save_pretrained shard size question vs Qwen3.5 loading error." }, { "left": "issue:42175", "right": "issue:42222", "accept": false, - "reason": "Package dependency/backend installation issue versus a broken model implementation; not the same bug." + "reason": "TF installation/backend packaging issue vs vitpose model-specific breakage." }, { - "left": "issue:43937", - "right": "issue:44496", + "left": "issue:43408", + "right": "issue:43742", "accept": false, - "reason": "GenerationConfig validation and missing model_type in config.json are different loader failures." + "reason": "Different model/config warnings; one is SAM type mismatch, the other a MobileLLM key error." }, { - "left": "issue:43408", - "right": "issue:43742", + "left": "issue:43937", + "right": "issue:44496", "accept": false, - "reason": "A model-type warning between sam3 variants is unrelated to a MobileLLM key error." + "reason": "Both are load-time ValueErrors, but for different model/config problems." }, { "left": "issue:44483", "right": "issue:45464", "accept": false, - "reason": "Same endpoint family, but a general request rejection is not the same as a streaming-inference failure on Qwen3.5-0.8B." + "reason": "Chat/completions API request handling is unrelated to streaming inference on Qwen3.5." }, { "left": "issue:44075", "right": "issue:45656", "accept": false, - "reason": "Both mention optimizers, but ignored SGD args and double optimizer.step() under deepspeed are different defects." + "reason": "Optimizer SGD args issue is not the same as deepspeed calling step twice." }, { "left": "issue:44964", "right": "issue:45278", "accept": false, - "reason": "Specific Phi-4 multimodal load failure versus a broad multi-import regression report; not the same underlying issue." + "reason": "Different breakages: multimodal model loading vs broad import errors after upgrade." }, { "left": "issue:43012", "right": "issue:43577", "accept": false, - "reason": "One is a warning about float32 precision during compile; the other is incorrect dtype propagation when loading Blip2." + "reason": "Precision warning on compile is unrelated to Blip2 dtype propagation." }, { "left": "issue:43066", "right": "issue:43122", "accept": false, - "reason": "Tokenizer decoder-type mismatch and changed tokenization behavior are related only at a high level, not the same concrete bug." + "reason": "Related tokenizer regressions, but not clearly the same concrete defect." }, { "left": "issue:42371", "right": "issue:44261", "accept": false, - "reason": "TF32 settings API guidance and MLA rms_norm_eps precision mismatch are unrelated." + "reason": "TF32 control warning is unrelated to MLA q_a_layernorm epsilon precision mismatch." }, { "left": "issue:43874", "right": "issue:44261", "accept": false, - "reason": "Missing image-patch counting support is not the same as a layernorm epsilon precision issue." + "reason": "Image-patch API missing method is unrelated to MLA layernorm epsilon handling." }, { "left": "issue:38617", "right": "issue:44220", "accept": false, - "reason": "ImportError for a missing symbol and an audio feature-extraction bug are different code paths." + "reason": "Different import/helper failures: configuration_utils symbol missing vs fbank feature extraction." }, { "left": "issue:44410", "right": "issue:45478", "accept": false, - "reason": "Different Qwen model families and different failure modes; no single shared bug." + "reason": "Missing qkv/gate projections in qwen3next is not the same as Qwen3.5 MoE from_pretrained failure." }, { "left": "issue:44484", "right": "issue:45478", "accept": false, - "reason": "Shard-size behavior and Qwen3.5 Moe from_pretrained loading are unrelated." + "reason": "save_pretrained shard-size question is unrelated to Qwen3.5 MoE loading errors." }, { "left": "issue:42222", "right": "issue:45459", "accept": false, - "reason": "VitPose breakage is unrelated to tokenizer errors hidden by protobuf exception handling." + "reason": "vitpose model breakage is unrelated to protobuf-hidden tokenizer errors." }, { - "left": "issue:44263", - "right": "issue:44485", + "left": "issue:43097", + "right": "issue:44493", "accept": false, - "reason": "A torch.split return-value issue in GLM-MoE indexing is not the same as the GLM-5 RoPE implementation question." + "reason": "Removed config flag vs unexpected key/position-id warnings are different issues." }, { - "left": "issue:43097", - "right": "issue:44493", + "left": "issue:44263", + "right": "issue:44485", "accept": false, - "reason": "A removed config helper and unexpected position-id keys are separate regressions." + "reason": "torch.split return-value issue is unrelated to GLM-5 RoPE implementation." }, { "left": "issue:43441", "right": "issue:44829", "accept": false, - "reason": "Both mention flash-attention, but one is a model-specific failure and the other is a training-quality regression." + "reason": "Ministral FlashAttention failure and FA3 degenerate training are different code-path problems." }, { "left": "issue:43012", "right": "issue:43408", "accept": false, - "reason": "Different warnings for different models and different causes." + "reason": "Precision-warning compile issue is unrelated to SAM model-type warning." }, { "left": "issue:41628", "right": "issue:45071", "accept": false, - "reason": "Importing AutoImageProcessor and PretrainedConfig type checking are unrelated issues." + "reason": "AutoImageProcessor import failure is not the same as PretrainedConfig type-checking breakage." }, { "left": "issue:45071", "right": "issue:45542", "accept": false, - "reason": "Type-checking regression has no connection to TensorFlow backend installation behavior." + "reason": "Config type-checking regression and missing TF backend are unrelated." }, { - "left": "issue:42371", - "right": "issue:42831", + "left": "issue:42673", + "right": "issue:44977", "accept": false, - "reason": "TF32 API settings and FineGrainedFP8 accuracy are distinct performance/precision topics." + "reason": "VRAM leak in dataloader threads is unrelated to flash-attention generation issues." }, { - "left": "issue:42673", - "right": "issue:44977", + "left": "issue:42371", + "right": "issue:42831", "accept": false, - "reason": "VRAM leak in multithreaded Qwen3ForCausalLM and flash-attention generation problems are different bugs." + "reason": "TF32 behavior settings and FineGrainedFP8 accuracy are different precision concerns." }, { "left": "issue:42673", "right": "issue:43906", "accept": false, - "reason": "No concrete evidence that the isolated reproduction of issue 38071 is the same VRAM leak problem." + "reason": "VRAM leak report is unrelated to an isolated reproduction of another issue." }, { "left": "issue:43931", "right": "issue:44038", "accept": false, - "reason": "Weight-shape mismatch for Qwen3-VL-30B is not the same as the Qwen3.5/Qwen3-VL-Moe issue." + "reason": "Weight-shape mismatch for Qwen3-VL differs from Qwen3.5/VL-Moe bug report." + }, + { + "left": "issue:43986", + "right": "issue:44484", + "accept": false, + "reason": "AutoProcessor torchvision crash is unrelated to save_pretrained shard sizing." + }, + { + "left": "issue:43335", + "right": "issue:45071", + "accept": false, + "reason": "SwitchTransformers sparse-layer config bug is unrelated to PretrainedConfig type checking." + }, + { + "left": "issue:44117", + "right": "issue:44987", + "accept": false, + "reason": "Tokenizer mapping None bug is unrelated to fast model loading failure." + }, + { + "left": "issue:43097", + "right": "issue:43452", + "accept": false, + "reason": "Removed encoder-decoder tie flag is unrelated to gguf_file loading failures." + }, + { + "left": "issue:43976", + "right": "issue:44945", + "accept": false, + "reason": "Python version support issue is unrelated to pipeline-parallelism output corruption." } ] }, @@ -12859,13 +12765,16 @@ "issue:42617", "issue:42673", "issue:42757", + "issue:42886", + "issue:43012", "issue:43064", "issue:43066", "issue:43097", - "issue:43335", + "issue:43208", + "issue:43381", "issue:43408", - "issue:43452", "issue:43502", + "issue:43550", "issue:43577", "issue:43825", "issue:43873", @@ -12873,7 +12782,6 @@ "issue:43901", "issue:43906", "issue:43931", - "issue:43976", "issue:43986", "issue:43992", "issue:44038", @@ -12890,9 +12798,7 @@ "issue:44655", "issue:44704", "issue:44829", - "issue:44945", "issue:44964", - "issue:44987", "issue:45071", "issue:45103", "issue:45245", @@ -12904,13 +12810,8 @@ "issue:45588" ], "soft_pairs": [ - "issue:43986|issue:44484", - "issue:44117|issue:44987", - "issue:43335|issue:45071", - "issue:43097|issue:43452", - "issue:43976|issue:44945", - "issue:43874|issue:44263", "issue:43408|issue:44368", + "issue:43874|issue:44263", "issue:44829|issue:45245", "issue:38617|issue:42757", "issue:43064|issue:44315", @@ -12918,229 +12819,251 @@ "issue:38617|issue:44351", "issue:44062|issue:44117", "issue:42673|issue:43577", - "issue:44704|issue:45103", "issue:43097|issue:45588", "issue:44038|issue:44410", + "issue:44704|issue:45103", "issue:44964|issue:45071", "issue:43931|issue:44410", - "issue:44261|issue:44485", "issue:44964|issue:45341", + "issue:44261|issue:44485", "issue:43502|issue:43992", "issue:43986|issue:44117", "issue:43097|issue:43873", "issue:43066|issue:43906", - "issue:45341|issue:45561", "issue:43986|issue:45290", + "issue:45341|issue:45561", "issue:43986|issue:45372", - "issue:43986|issue:45341", "issue:43097|issue:43901", + "issue:43986|issue:45341", "issue:42617|issue:45341", "issue:43825|issue:44655", "issue:43992|issue:44484", - "issue:45341|issue:45588" + "issue:45341|issue:45588", + "issue:43012|issue:43550", + "issue:43012|issue:44368", + "issue:42886|issue:43381", + "issue:43208|issue:43550" ], - "prepared_review_unit_hash": "0813b3a0ae7c98e6694039745e719b7307619cd3a745f79851a6dd999488c7a8", + "prepared_review_unit_hash": "209d8ab379a1e7607f46e7921cf0b7cf2f6eac99a2d75575c84baf22132515ff", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { "node_count": 47, "item_count": 47, - "soft_pair_count": 34, - "serialized_chars": 37409, - "estimated_input_tokens": 9353, - "estimated_eval_tokens": 18962 + "soft_pair_count": 33, + "serialized_chars": 37026, + "estimated_input_tokens": 9257, + "estimated_eval_tokens": 18770 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These issues are mostly unrelated Transformers bugs with only superficial overlap around v5, loading, and import paths. None of the soft pairs look like the same underlying bug or change, so all candidate merges are rejected.", - "confidence": 0.92, - "canonical_issue_reason": "Issue 43097 is the most umbrella-like v5 regression report in this set, with broad downstream impact and enough generality to serve as the best representative anchor among the listed issues.", + "summary": "These items do not look like a duplicate cluster; they span many unrelated transformer bugs across imports, tokenizer loading, model config, training, and processor paths. I rejected all soft-edge pairs because none appear to be the same underlying bug or change.", + "confidence": 0.94, + "canonical_issue_reason": "issue:43873 is the best issue anchor here: it is open, has the most discussion/inbound attention, and describes a concrete user-facing regression with clear impact.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43986 is the most concrete and actionable standalone bug report here, with a specific crash path and clear reproduction-oriented framing, even though it is not a duplicate of the others.", + "best_issue_reason": "issue:43873 is the strongest standalone issue to keep as the cluster representative because it is active, substantive, and broadly scoped compared with the other narrowly targeted reports.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:43986", - "right": "issue:44484", - "accept": false, - "reason": "Video-model crash without torchvision vs a save_pretrained shard-size question; different bug classes." - }, - { - "left": "issue:44117", - "right": "issue:44987", - "accept": false, - "reason": "Tokenizer-mapping None bug vs a model-loading failure for a specific repo; no shared root cause." - }, - { - "left": "issue:43335", - "right": "issue:45071", - "accept": false, - "reason": "Config construction bug in SwitchTransformers vs PretrainedConfig type-checking regression; unrelated." - }, - { - "left": "issue:43097", - "right": "issue:43452", - "accept": false, - "reason": "Removed tie_embeddings warning/regression vs gguf tokenizer/model loading breakage; not the same issue." - }, - { - "left": "issue:43976", - "right": "issue:44945", - "accept": false, - "reason": "Python compatibility problem vs incorrect pipeline-parallel outputs; different failure modes." - }, - { - "left": "issue:43874", - "right": "issue:44263", - "accept": false, - "reason": "Missing image-patch API vs torch.split return handling in a different model component." - }, { "left": "issue:43408", "right": "issue:44368", "accept": false, - "reason": "sam3 model-type warning vs tie_word_embeddings warning in Qwen fine-tuning; only superficial warning overlap." + "reason": "Both are warnings, but they concern different models and different causes: sam3 tracker type mismatch vs tie_word_embeddings config advice." + }, + { + "left": "issue:43874", + "right": "issue:44263", + "accept": false, + "reason": "Different GLM bugs: missing image-patch method in a processor vs unexpected torch.split return handling." }, { "left": "issue:44829", "right": "issue:45245", "accept": false, - "reason": "Flash-attention training degeneration vs large-category runtime limit; unrelated." + "reason": "Unrelated failures: flash_attention_3 training degeneration vs a category-count limit error." }, { "left": "issue:38617", "right": "issue:42757", "accept": false, - "reason": "Different ImportError targets from different packages and code paths." + "reason": "Both are ImportErrors, but they are for different missing symbols from different modules." }, { "left": "issue:43064", "right": "issue:44315", "accept": false, - "reason": "FSDP/PEFT optimizer-state bug vs Liger Kernel application issue; not the same concrete path." + "reason": "Different training-path problems: optimizer state corruption on nonzero ranks vs Liger Kernel not being applied with model_init." }, { "left": "issue:44410", "right": "issue:45375", "accept": false, - "reason": "Missing Qwen3Next projections vs missing Qwen3_5MoeVision config field; different model/config defects." + "reason": "Both are Qwen-related, but one is missing attention projections and the other is a missing config field silently dropped." }, { "left": "issue:38617", "right": "issue:44351", "accept": false, - "reason": "Importing different missing symbols from different modules; no evidence of one underlying breakage." + "reason": "Different missing exports: layer_type_validation vs HybridCache." }, { "left": "issue:44062", "right": "issue:44117", "accept": false, - "reason": "AddedToken keyword collision vs tokenizer mapping assumption failure; unrelated tokenizer bugs." + "reason": "Tokenizer-related, but one is an AddedToken constructor conflict and the other is TOKENIZER_MAPPING_NAMES returning None." }, { "left": "issue:42673", "right": "issue:43577", "accept": false, - "reason": "VRAM leak in multi-threaded dataloaders vs dtype not propagating on load; different symptoms and paths." - }, - { - "left": "issue:44704", - "right": "issue:45103", - "accept": false, - "reason": "cached_file kwargs forwarding vs auto_docstring annotation crash; unrelated internals." + "reason": "Unrelated model issues: VRAM leak across dataloader threads vs dtype not propagating in BLIP-2 loading." }, { "left": "issue:43097", "right": "issue:45588", "accept": false, - "reason": "Config flag removal/warning vs flash_attention None-aux crash; not the same bug." + "reason": "Different code paths: removed config behavior in v5 vs a flash_attention crash on sink-less models." }, { "left": "issue:44038", "right": "issue:44410", "accept": false, - "reason": "Qwen3-VL-Moe bug vs Qwen3Next layer projection omission; different model families and defects." + "reason": "Both mention Qwen, but one is a broader v5/Qwen3-VL-Moe issue and the other is a specific Qwen3Next layer-projection bug." + }, + { + "left": "issue:44704", + "right": "issue:45103", + "accept": false, + "reason": "Different subsystems: AutoProcessor kwargs forwarding vs auto_docstring parsing with future annotations." }, { "left": "issue:44964", "right": "issue:45071", "accept": false, - "reason": "Model load failure for Phi-4 multimodal vs config type-checking regression; no common code path." + "reason": "A model loading failure is not the same as a generic PretrainedConfig type-checking regression." }, { "left": "issue:43931", "right": "issue:44410", "accept": false, - "reason": "Qwen VL weight-shape mismatch vs missing projections in Qwen3Next; distinct load vs architecture issues." + "reason": "Different Qwen model failures: weight-shape mismatch vs missing projections in a different architecture." }, { - "left": "issue:44261", - "right": "issue:44485", + "left": "issue:44964", + "right": "issue:45341", "accept": false, - "reason": "MLA layernorm epsilon precision issue vs GLM-5 RoPE implementation discussion; not duplicates." + "reason": "A model load regression is unrelated to a testing_utils bug." }, { - "left": "issue:44964", - "right": "issue:45341", + "left": "issue:44261", + "right": "issue:44485", "accept": false, - "reason": "Model loading failure vs a testing utility bug; completely different areas." + "reason": "Different numerical/model issues: missing rms_norm_eps precision error vs RoPE implementation discussion." }, { "left": "issue:43502", "right": "issue:43992", "accept": false, - "reason": "local_files_only network calls vs missing embed token weights on load; different loading bugs." + "reason": "Offline/local_files_only request leakage is unrelated to a missing embed_tokens.weight load issue." }, { "left": "issue:43986", "right": "issue:44117", "accept": false, - "reason": "Video-model torchvision crash vs tokenizer mapping None; unrelated failures." + "reason": "Different failures: video AutoProcessor needing torchvision vs tokenizer mapping assumptions." }, { "left": "issue:43097", "right": "issue:43873", "accept": false, - "reason": "tie_embeddings config removal vs quantization/offloading issue; only broad v5-era overlap." + "reason": "No shared bug: one is a v5 API/config removal warning, the other is a quantization offloading bug." }, { "left": "issue:43066", "right": "issue:43906", "accept": false, - "reason": "Tokenizer decoder type warning vs reproduction of another issue; not the same concrete problem." + "reason": "The titles point to different tokenizer problems; the reproduction issue is not enough to equate them." + }, + { + "left": "issue:43986", + "right": "issue:45290", + "accept": false, + "reason": "Video processor import/loading failure is unrelated to chat-template tool-call crashes." }, { "left": "issue:45341", "right": "issue:45561", "accept": false, - "reason": "Different testing-utils bugs: captured_info helper issue vs xdist race on captured_info.txt." + "reason": "A generic testing_utils bug is not the same as the xdist race on captured_info.txt." + }, + { + "left": "issue:43986", + "right": "issue:45372", + "accept": false, + "reason": "Different dependency/import failures: missing torchvision vs missing ReasoningEffort from mistral_common." + }, + { + "left": "issue:43097", + "right": "issue:43901", + "accept": false, + "reason": "Config removal and docstring warning changes are unrelated to a docs-behavior mismatch in TextClassificationPipeline." + }, + { + "left": "issue:42617", + "right": "issue:45341", + "accept": false, + "reason": "A 3d_parallel.py execution failure is unrelated to a testing_utils bug." }, { "left": "issue:43825", "right": "issue:44655", "accept": false, - "reason": "Pipeline docs mismatch vs inability to save Pipeline objects; different symptoms and fixes." + "reason": "Different pipeline issues: incorrect translation-task messaging vs save_pretrained serialization of Pipeline objects." }, { "left": "issue:43992", "right": "issue:44484", "accept": false, - "reason": "Missing embed_tokens.weight on load vs shard-size question; unrelated." + "reason": "Missing encoder weights during load is unrelated to the max_shard_size default question." }, { "left": "issue:45341", "right": "issue:45588", "accept": false, - "reason": "Testing utility bug vs flash_attention crash on None auxiliary output; different code paths." + "reason": "Testing utilities and flash_attention are different code paths with different failures." + }, + { + "left": "issue:43012", + "right": "issue:43550", + "accept": false, + "reason": "A precision-warning regression is not the same as a torch.compile SDPA training failure." + }, + { + "left": "issue:43012", + "right": "issue:44368", + "accept": false, + "reason": "These are different warnings with different root causes and model contexts." + }, + { + "left": "issue:42886", + "right": "issue:43381", + "accept": false, + "reason": "Offline tokenizer cache loading is unrelated to gradient checkpointing in eval mode." + }, + { + "left": "issue:43208", + "right": "issue:43550", + "accept": false, + "reason": "xLSTM small-model training bugs and Bamba SDPA compile failure are different model-specific problems." } ] }, @@ -13168,7 +13091,6 @@ "issue:36683", "issue:38617", "issue:42757", - "issue:42886", "issue:42907", "issue:42994", "issue:43012", @@ -13177,13 +13099,12 @@ "issue:43208", "issue:43299", "issue:43352", - "issue:43381", + "issue:43441", "issue:43475", "issue:43502", "issue:43525", "issue:43526", "issue:43531", - "issue:43550", "issue:43618", "issue:43756", "issue:43761", @@ -13194,12 +13115,12 @@ "issue:43906", "issue:43937", "issue:43976", + "issue:43992", "issue:44038", "issue:44220", "issue:44230", "issue:44242", "issue:44263", - "issue:44368", "issue:44380", "issue:44483", "issue:44485", @@ -13208,16 +13129,14 @@ "issue:44683", "issue:45216", "issue:45290", + "issue:45310", "issue:45341", "issue:45381", "issue:45440", + "issue:45479", "issue:45753" ], "soft_pairs": [ - "issue:43012|issue:43550", - "issue:43012|issue:44368", - "issue:43208|issue:43550", - "issue:42886|issue:43381", "issue:42907|issue:45753", "issue:42907|issue:44655", "issue:43531|issue:45341", @@ -13225,9 +13144,9 @@ "issue:44483|issue:44514", "issue:43012|issue:44683", "issue:42757|issue:43824", - "issue:44038|issue:44230", "issue:43618|issue:43761", "issue:38617|issue:43502", + "issue:44038|issue:44230", "issue:44483|issue:45290", "issue:43299|issue:43867", "issue:44483|issue:45381", @@ -13243,19 +13162,23 @@ "issue:43756|issue:44485", "issue:44263|issue:45440", "issue:36683|issue:43525", - "issue:43906|issue:45753", "issue:43618|issue:45216", + "issue:43906|issue:45753", "issue:36683|issue:44242", "issue:36683|issue:43881", "issue:43299|issue:45753", - "issue:43352|issue:43976" + "issue:43352|issue:43976", + "issue:43992|issue:45310", + "issue:43441|issue:44380", + "issue:43352|issue:44380", + "issue:44380|issue:45479" ], - "prepared_review_unit_hash": "0bfb4674e1e3139d15900aebe6f19b2095b9e91c895376e3bf4fe81a68075026", + "prepared_review_unit_hash": "a936051c6890f59a08921674ffe62bff5fb1f1aa01521141659656d1386d7240", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, @@ -13263,7 +13186,7 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 35, - "serialized_chars": 37730, + "serialized_chars": 37731, "estimated_input_tokens": 9433, "estimated_eval_tokens": 19122 }, @@ -13272,222 +13195,222 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is heterogeneous; the soft pairs mostly share only broad subsystem or symptom-level similarity, not the same concrete bug/change. I would not merge any of the proposed soft edges.", - "confidence": 0.96, - "canonical_issue_reason": "No single issue is a defensible canonical for this set; the items are unrelated regressions, import errors, model-specific failures, and API behavior changes.", + "summary": "This cluster is heterogeneous: import errors, model config/weight-loading regressions, save_pretrained issues, attention/backend bugs, and chat/pipeline behavior changes. None of the soft pairs look like the same underlying bug or change, so they should stay separate.", + "confidence": 0.97, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:42886 is the strongest standalone representative because it is a narrow, reproducible regression with a clear trigger (HF_HUB_OFFLINE=1) and expected behavior.", + "best_issue_reason": "If a single issue had to represent the cluster, issue 42907 is the clearest self-contained bug report, but it is not a duplicate center for the rest of the items.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:43012", - "right": "issue:43550", - "accept": false, - "reason": "Different problems: a bfloat16 compile warning versus a Bamba SDPA/torch.compile failure." - }, - { - "left": "issue:43012", - "right": "issue:44368", - "accept": false, - "reason": "Unrelated symptoms: precision warning versus a tie_word_embeddings warning in a fine-tuning workflow." - }, - { - "left": "issue:43208", - "right": "issue:43550", - "accept": false, - "reason": "Different model families and different failures; no shared concrete code path." - }, - { - "left": "issue:42886", - "right": "issue:43381", - "accept": false, - "reason": "Offline cache loading bug versus gradient checkpointing in eval mode; unrelated behavior." - }, { "left": "issue:42907", "right": "issue:45753", "accept": false, - "reason": "One is about saving dequantized models, the other about an image-specific infinite loop." + "reason": "Different bugs: quantized/dequantized model saving vs an image-specific Qwen3.5 generation loop." }, { "left": "issue:42907", "right": "issue:44655", "accept": false, - "reason": "Both involve saving, but one is quantized/dequantized model saving and the other is Pipeline.save_pretrained." + "reason": "Both involve saving, but one is about dequantized model saving and the other about Pipeline.save_pretrained; different code paths." }, { "left": "issue:43531", "right": "issue:45341", "accept": false, - "reason": "Sliding window handling in Qwen3-MoE is unrelated to a testing_utils bug." + "reason": "Unrelated: Qwen3-MoE sliding_window bug vs a testing_utils.py issue." }, { "left": "issue:43208", "right": "issue:43526", "accept": false, - "reason": "Different xLSTM training bugs versus a BeitImageProcessorFast label-reduction bug." + "reason": "Different models and failures: xLSTM training bugs vs BeitImageProcessorFast reduce_labels behavior." }, { "left": "issue:44483", "right": "issue:44514", "accept": false, - "reason": "Chat completions API rejection and batched chat template crash are different request-path bugs." + "reason": "Different layers and symptoms: OpenAI-style /v1/chat/completions rejection vs Qwen2_5_VLProcessor chat template crash." }, { "left": "issue:43012", "right": "issue:44683", "accept": false, - "reason": "Precision warning versus compiled flex_attention failure; not the same bug." + "reason": "Both mention compilation/precision, but one is a PyTorch warning on bfloat16 compile and the other is a torch>=2.9 flex_attention failure." }, { "left": "issue:42757", "right": "issue:43824", "accept": false, - "reason": "Both are import errors, but they are missing different symbols from different modules." - }, - { - "left": "issue:44038", - "right": "issue:44230", - "accept": false, - "reason": "Qwen3-VL MoE loading bug versus fp8 support request for a related but distinct model/configuration." + "reason": "Both are import errors, but for different symbols from different packages/modules." }, { "left": "issue:43618", "right": "issue:43761", "accept": false, - "reason": "Both are CLIP regressions, but one affects attentions and the other hidden_states; different concrete failures." + "reason": "Same broad CLIP area, but different regressions: attentions missing vs hidden_states=None." }, { "left": "issue:38617", "right": "issue:43502", "accept": false, - "reason": "An import failure in configuration_utils is unrelated to local_files_only network requests." + "reason": "Different problems: import failure for layer_type_validation vs network requests despite local_files_only=True." + }, + { + "left": "issue:44038", + "right": "issue:44230", + "accept": false, + "reason": "Different bug classes: Qwen3-VL-Moe loading breakage vs fp8 inference support request/feature." }, { "left": "issue:44483", "right": "issue:45290", "accept": false, - "reason": "Different chat-related crashes with different inputs and failure points." + "reason": "Different APIs: /v1/chat/completions request handling vs tokenizer chat-template crash with tool calls." }, { "left": "issue:43299", "right": "issue:43867", "accept": false, - "reason": "Both are loading failures, but one is Qwen3VL MoE model loading and the other is a sorted state_dict load error." + "reason": "Both are loading failures, but one is Qwen3.5-VL-MoE-specific and the other is a generic state_dict sorting issue." }, { "left": "issue:44483", "right": "issue:45381", "accept": false, - "reason": "Chat completion request handling and Qwen2.5-VL video position IDs are separate bugs." + "reason": "Unrelated: chat/completions request acceptance vs Qwen2.5-VL video position_ids bug." }, { "left": "issue:43064", "right": "issue:44380", "accept": false, - "reason": "Distributed optimizer-state corruption is unrelated to GPT2 attention scaling being ignored by SDPA/FlashAttention." + "reason": "Different subsystems: distributed training optimizer state bug vs GPT2 attention scaling ignored under SDPA/FlashAttention." }, { "left": "issue:43901", "right": "issue:44655", "accept": false, - "reason": "Docs mismatch for return_all_scores is unrelated to Pipeline.save_pretrained behavior." + "reason": "Docs mismatch for return_all_scores vs inability to save Pipeline objects; not the same bug." }, { "left": "issue:36683", "right": "issue:43475", "accept": false, - "reason": "Different attribute errors on different model configs/outputs; not the same underlying bug." + "reason": "Both are missing-attribute errors, but they affect different model configs/outputs and different fields." }, { "left": "issue:43867", "right": "issue:45216", "accept": false, - "reason": "Both touch serialization/loading, but one is a sorted state_dict load issue and the other is a save_pretrained regression for Qwen3.5." + "reason": "Related to saving/loading, but one is a load failure with sorted state_dict and the other is a save_pretrained regression for Qwen3.5." }, { "left": "issue:42994", "right": "issue:44655", "accept": false, - "reason": "Both concern saving, but one is quantized model saving and the other is saving Pipeline objects." + "reason": "Both involve saving, but quantized model saving failure and pipeline save_pretrained are distinct code paths." }, { "left": "issue:43352", "right": "issue:43937", "accept": false, - "reason": "A Flash Attention support limitation for Nemotron is not the same as GLM-5 GenerationConfig validation failure." + "reason": "Different failures: FlashAttention unsupported for Nemotron vs invalid GenerationConfig for GLM-5." }, { "left": "issue:43066", "right": "issue:45381", "accept": false, - "reason": "Tokenizer decoder type mismatch and video vision_position_ids are different regressions." + "reason": "Unrelated tokenizer-decoder typing issue vs Qwen2.5-VL video input position_ids bug." }, { "left": "issue:36010", "right": "issue:42757", "accept": false, - "reason": "Both are import errors, but they concern different symbols and different modules; too broad to merge." + "reason": "Both are import errors, but for unrelated symbols from different packages." }, { "left": "issue:44220", "right": "issue:44655", "accept": false, - "reason": "Audio feature extraction issue versus Pipeline.save_pretrained; unrelated code paths." + "reason": "Audio feature extraction bug vs saving Pipeline objects; no shared underlying defect." }, { "left": "issue:43756", "right": "issue:44485", "accept": false, - "reason": "RoPE layer mismatch in Smollm3 is unrelated to GLM-5 RoPE implementation discussion." + "reason": "Different model-specific RoPE/implementation problems; not the same bug." }, { "left": "issue:44263", "right": "issue:45440", "accept": false, - "reason": "A torch.split indexing issue is unrelated to DeepseekV3MoE divergence from remote implementation." + "reason": "Different model families and code paths: GlmMoeDsaIndexer split handling vs DeepseekV3MoE divergence." }, { "left": "issue:36683", "right": "issue:43525", "accept": false, - "reason": "Both are missing-attribute errors, but on different configs and different attributes." + "reason": "Both are missing config attributes, but they are different models and different missing fields." }, { - "left": "issue:43906", - "right": "issue:45753", + "left": "issue:43618", + "right": "issue:45216", "accept": false, - "reason": "A reproduction of an older issue is unrelated to a Qwen3.5 image-specific infinite loop." + "reason": "CLIP attentions regression and Qwen3.5 checkpoint corruption are unrelated." }, { - "left": "issue:43618", - "right": "issue:45216", + "left": "issue:43906", + "right": "issue:45753", "accept": false, - "reason": "CLIP output regression and Qwen3.5 save_pretrained regression are unrelated." + "reason": "A reproduction of a prior issue is not the same bug as a Qwen3.5 image-specific infinite loop." }, { "left": "issue:36683", "right": "issue:44242", "accept": false, - "reason": "Gemma3Config vocab_size and MoE load-balancing loss are unrelated bugs." + "reason": "Gemma3Config attribute error vs MoE load-balancing loss omission; different defects." }, { "left": "issue:36683", "right": "issue:43881", "accept": false, - "reason": "Gemma3Config missing vocab_size and glm-4v-9b loading failure are different issues." + "reason": "Both are model-loading/config issues, but for different models and failures." }, { "left": "issue:43299", "right": "issue:45753", "accept": false, - "reason": "Qwen3VL MoE loading and an image-triggered infinite loop are different failure modes." + "reason": "Different Qwen3-related problems: MoE loading breakage vs generation infinite loop on a specific image." }, { "left": "issue:43352", "right": "issue:43976", "accept": false, - "reason": "Flash Attention 2 support for one model is unrelated to a Python version compatibility problem." + "reason": "FlashAttention support issue vs Python version compatibility problem; unrelated." + }, + { + "left": "issue:43992", + "right": "issue:45310", + "accept": false, + "reason": "Different from_pretrained failures on different models and versions." + }, + { + "left": "issue:43441", + "right": "issue:44380", + "accept": false, + "reason": "Both involve attention backends, but one is a Ministral FlashAttention failure and the other is GPT2 attention scaling being ignored." + }, + { + "left": "issue:43352", + "right": "issue:44380", + "accept": false, + "reason": "Unrelated backend/attention bugs affecting different models and failure modes." + }, + { + "left": "issue:44380", + "right": "issue:45479", + "accept": false, + "reason": "GPT2 attention scaling bug and zero-loss sequence-classification bug are unrelated." } ] }, @@ -13516,12 +13439,12 @@ "issue:36296", "issue:36683", "issue:41669", + "issue:42548", "issue:42890", "issue:43010", "issue:43064", "issue:43097", "issue:43352", - "issue:43441", "issue:43502", "issue:43575", "issue:43618", @@ -13536,40 +13459,37 @@ "issue:44117", "issue:44222", "issue:44246", + "issue:44351", "issue:44355", "issue:44360", "issue:44380", "issue:44484", + "issue:44485", "issue:44492", "issue:44655", + "issue:44749", "issue:44855", "issue:44857", "issue:44938", "issue:44964", "issue:44977", "issue:45125", - "issue:45310", "issue:45341", "issue:45357", "issue:45375", "issue:45440", "issue:45478", - "issue:45479", "issue:45561", "issue:45588", "issue:45600" ], "soft_pairs": [ - "issue:43992|issue:45310", - "issue:43441|issue:44380", - "issue:43352|issue:44380", - "issue:44380|issue:45479", "issue:43867|issue:45375", "issue:41669|issue:44246", - "issue:43064|issue:44492", "issue:43618|issue:44380", - "issue:43352|issue:45478", + "issue:43064|issue:44492", "issue:44355|issue:44855", + "issue:43352|issue:45478", "issue:36683|issue:44117", "issue:42890|issue:45561", "issue:43097|issue:43352", @@ -13585,258 +13505,259 @@ "issue:43618|issue:44857", "issue:43618|issue:45588", "issue:43618|issue:44977", - "issue:42890|issue:44964", "issue:44655|issue:44938", "issue:43901|issue:44938", + "issue:42890|issue:44964", "issue:42890|issue:44112", "issue:42890|issue:45600", "issue:43502|issue:44062", "issue:43010|issue:44075", "issue:42890|issue:45341", - "issue:44222|issue:45125" + "issue:44222|issue:45125", + "issue:42548|issue:44351", + "issue:43502|issue:44485", + "issue:44355|issue:44749", + "issue:45125|issue:45478" ], - "prepared_review_unit_hash": "d831f6e17c6b296d9f12be13caf32b68eaa6bc5e6c3a45016437e787c8a3e134", + "prepared_review_unit_hash": "3200ac9c6afe46eda2e2016bdb0a71a0c0738dfb946f0503f36025378c13beeb", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { - "node_count": 47, - "item_count": 47, + "node_count": 48, + "item_count": 48, "soft_pair_count": 34, - "serialized_chars": 36916, - "estimated_input_tokens": 9229, - "estimated_eval_tokens": 18714 + "serialized_chars": 37423, + "estimated_input_tokens": 9356, + "estimated_eval_tokens": 18968 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous issue reports. The only soft-duplicate candidate I\u2019d accept is the import-time slowdown pair, where one issue identifies a likely root cause and the other reports the same slow `import transformers` symptom.", - "confidence": 0.66, - "canonical_issue_reason": "Issue 41669 is the stronger canonical: it identifies the concrete cause (`import *` in model modules) behind the import-time slowdown, while the paired issue only reports the broader symptom.", + "summary": "This cluster is a loose grab bag of unrelated issues across loading, training, testing, and model-specific regressions. None of the soft pairs look safe to merge as true duplicates.", + "confidence": 0.95, + "canonical_issue_reason": "issue:43867 is a clear, concrete core loading failure and the most broadly representative user-facing bug among this set.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 41669 is the best issue anchor for the cluster because it is the most specific, actionable description of the only apparent duplicate pair and captures the underlying regression more clearly than the symptom-only report.", + "best_issue_reason": "issue:43867 is a strong standalone issue to anchor the cluster because it describes a specific model-loading error with likely broad impact.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:43992", - "right": "issue:45310", - "accept": false, - "reason": "Both are `from_pretrained` failures, but they involve different models and different missing pieces; not the same concrete bug." - }, - { - "left": "issue:43441", - "right": "issue:44380", - "accept": false, - "reason": "Both mention FlashAttention, but one is model support for Ministral and the other is GPT-2 attention scaling behavior; different code paths." - }, - { - "left": "issue:43352", - "right": "issue:44380", - "accept": false, - "reason": "Unsupported FlashAttention for Nemotron is a different problem from GPT-2 attention scaling being ignored." - }, - { - "left": "issue:44380", - "right": "issue:45479", - "accept": false, - "reason": "These are unrelated: one is attention backend config handling, the other is a classification loss degeneracy issue." - }, { "left": "issue:43867", "right": "issue:45375", "accept": false, - "reason": "A generic load-state_dict issue is not the same as a missing config field being dropped by strict serialization." + "reason": "Sorted state_dict loading error is unrelated to missing Qwen3.5 vision config fields." }, { "left": "issue:41669", "right": "issue:44246", - "accept": true, - "reason": "Both describe `import transformers` being slow; 41669 points to a plausible root cause for the same import-time regression." - }, - { - "left": "issue:43064", - "right": "issue:44492", "accept": false, - "reason": "Distributed optimizer-state corruption and a cache-strategy typo are unrelated bugs." + "reason": "Both mention import performance, but one is about removing import * and the other is an intermittent slowdown with different root cause." }, { "left": "issue:43618", "right": "issue:44380", "accept": false, - "reason": "CLIP attentions not being assigned is unrelated to GPT-2 attention scaling under SDPA/FlashAttention." + "reason": "Different models and different bugs: missing CLIPOutput attentions vs GPT2 attention scaling ignored in backend paths." }, { - "left": "issue:43352", - "right": "issue:45478", + "left": "issue:43064", + "right": "issue:44492", "accept": false, - "reason": "These are different model-specific issues; one is unsupported FlashAttention, the other is a Qwen3.5 MoE load failure." + "reason": "FSDP2/PEFT optimizer-state corruption is unrelated to a cache-strategy typo." }, { "left": "issue:44355", "right": "issue:44855", "accept": false, - "reason": "Running compiled Python files and a Python 3.13 `@torch.jit.script` parsing failure are different failure modes." + "reason": "Both are import-time failures, but one concerns compiled Python files generally and the other is a Python 3.13 torch.jit.script parsing issue." + }, + { + "left": "issue:43352", + "right": "issue:45478", + "accept": false, + "reason": "Nemotron Flash Attention 2 support and Qwen3.5 MoE from_pretrained errors are different model-specific problems." }, { "left": "issue:36683", "right": "issue:44117", "accept": false, - "reason": "A missing `vocab_size` attribute in one config is not the same as `TOKENIZER_MAPPING_NAMES` returning `None`." + "reason": "A missing config attribute is not the same as TOKENIZER_MAPPING_NAMES returning None during from_pretrained." }, { "left": "issue:42890", "right": "issue:45561", "accept": false, - "reason": "Seed-related test flakiness and an xdist race on a captured-info file are different testing issues." + "reason": "SamHQ seeding flakiness and xdist race on captured_info.txt are different test failures." }, { "left": "issue:43097", "right": "issue:43352", "accept": false, - "reason": "A removed config flag and FlashAttention support for Nemotron are unrelated." + "reason": "Removed tie_embeddings behavior is unrelated to Flash Attention support errors." }, { "left": "issue:43867", "right": "issue:45357", "accept": false, - "reason": "Load-time state_dict ordering problems are not the same as incorrect keys being saved for Qwen3.5 vision encoders." + "reason": "Loading a sorted state_dict and saving incorrect visual encoder keys are different serialization bugs." }, { "left": "issue:43976", "right": "issue:44938", "accept": false, - "reason": "Both are Python-version compatibility complaints, but they target different versions and different loading failures." + "reason": "These are separate Python-version compatibility failures with no shared code-path evidence." }, { "left": "issue:43992", "right": "issue:45478", "accept": false, - "reason": "Different models and different missing/loading behavior; not a duplicate." + "reason": "UMT5Encoder missing embed_tokens.weight and Qwen3.5 MoE from_pretrained failure are unrelated model-loading bugs." }, { "left": "issue:44360", "right": "issue:45440", "accept": false, - "reason": "A DSA indexer math bug is unrelated to DeepseekV3MoE diverging from its remote implementation." + "reason": "A missing ReLU in the DSA indexer is unrelated to DeepseekV3MoE diverging from remote implementation." }, { "left": "issue:43064", "right": "issue:44655", "accept": false, - "reason": "Optimizer-state corruption in training is unrelated to saving Pipeline objects." + "reason": "Optimizer-state corruption during training is not the same as Pipeline.save_pretrained failing." }, { "left": "issue:36296", "right": "issue:43575", "accept": false, - "reason": "Tensor-parallel training state corruption and TP-related OOM during model loading are different problems." + "reason": "Tensor-parallel training bug and TP OOM while loading a large model are different problems." }, { "left": "issue:44077", "right": "issue:44380", "accept": false, - "reason": "A `post_init` policy change for patchtsmixer is unrelated to GPT-2 attention backend behavior." + "reason": "A patchtsmixer post_init policy change is unrelated to GPT2 attention scaling under SDPA/FlashAttention." }, { "left": "issue:43867", "right": "issue:44484", "accept": false, - "reason": "State-dict load ordering and the default `max_shard_size` in `save_pretrained` are unrelated." + "reason": "Sorted state_dict loading failure is not the same as a question about the default max_shard_size in save_pretrained." }, { "left": "issue:28282", "right": "issue:33453", "accept": false, - "reason": "PyTorch-not-found import error and tokenizer-loading regression are different failure classes." + "reason": "PyTorch-missing ImportError and tokenizer-loading regression are different failure modes." }, { "left": "issue:43618", "right": "issue:44857", "accept": false, - "reason": "Missing CLIP attentions and an AMP/CUDA crash in LwDetrImageLoss are unrelated." + "reason": "Missing CLIPOutput attentions is unrelated to LwDetrImageLoss crashing under float16 AMP." }, { "left": "issue:43618", "right": "issue:45588", "accept": false, - "reason": "Both mention flash attention only indirectly; the concrete failures and affected code paths differ." + "reason": "CLIPOutput attentions regression is unrelated to flash_attention.py crashing on s_aux=None." }, { "left": "issue:43618", "right": "issue:44977", "accept": false, - "reason": "CLIP attention output behavior is unrelated to Qwen3.5 generation issues under flash-attention." - }, - { - "left": "issue:42890", - "right": "issue:44964", - "accept": false, - "reason": "A flaky SamHQ integration test and a Phi-4 multimodal load failure are unrelated." + "reason": "These concern different models and different flash-attention-related bugs." }, { "left": "issue:44655", "right": "issue:44938", "accept": false, - "reason": "Saving Pipeline objects and Python 3.14 import/load failure are different issues." + "reason": "Pipeline save_pretrained failure is unrelated to Python 3.14 import/load breakage." }, { "left": "issue:43901", "right": "issue:44938", "accept": false, - "reason": "Documentation mismatch for a pipeline parameter is unrelated to a Python 3.14 loading failure." + "reason": "A documentation mismatch in TextClassificationPipeline is not the same as Python 3.14 loading failure." + }, + { + "left": "issue:42890", + "right": "issue:44964", + "accept": false, + "reason": "SamHQ test seeding flakiness is unrelated to Phi-4 multimodal model loading failure." }, { "left": "issue:42890", "right": "issue:44112", "accept": false, - "reason": "Different test failures in different areas; no shared underlying bug is evident." + "reason": "Both are test-related, but one is missing seeding and the other is a stale CI device-override test." }, { "left": "issue:42890", "right": "issue:45600", "accept": false, - "reason": "SamHQ test flakiness and broken auto-mapping references to removed configs are separate CI issues." + "reason": "SamHQ test seeding and auto_mappings references to removed configs are different issues." }, { "left": "issue:43502", "right": "issue:44062", "accept": false, - "reason": "Offline-download behavior and an `AddedToken()` argument error are unrelated." + "reason": "Local_files_only still making API requests and AddedToken duplicate special arg are unrelated." }, { "left": "issue:43010", "right": "issue:44075", "accept": false, - "reason": "A `torch.no_grad` decoration request for cache updates is unrelated to SGD argument handling." + "reason": "Cache update no_grad decoration and SGD args not used are unrelated training/runtime issues." }, { "left": "issue:42890", "right": "issue:45341", "accept": false, - "reason": "A specific seeding-related test failure and a vague testing_utils bug are too different to treat as the same bug." + "reason": "SamHQ seeding flakiness is not the same as a generic bug in testing_utils.py." }, { "left": "issue:44222", "right": "issue:45125", "accept": false, - "reason": "Both mention Qwen3.5 MoE, but one is FP8 save_pretrained behavior and the other is tensor-parallel planning; different fixes." + "reason": "FP8 save_pretrained for MoE and missing _tp_plan for Qwen3_5Moe are different code paths." + }, + { + "left": "issue:42548", + "right": "issue:44351", + "accept": false, + "reason": "Cannot import PreTrainedModel and cannot import HybridCache are different missing-export problems." + }, + { + "left": "issue:43502", + "right": "issue:44485", + "accept": false, + "reason": "Local_files_only network requests and GLM-5 RoPE implementation are unrelated." + }, + { + "left": "issue:44355", + "right": "issue:44749", + "accept": false, + "reason": "Compiled Python import errors and a data-filtering slowdown after upgrade are not the same bug." + }, + { + "left": "issue:45125", + "right": "issue:45478", + "accept": false, + "reason": "Both involve Qwen3.5 MoE, but one is missing tensor-parallel plan support and the other is a from_pretrained regression." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The cluster summary is grounded in the packet, and the one accepted soft edge is conservative enough: 41669 and 44246 both concern slow `import transformers`, with 41669 plausibly identifying a root cause for that same import-time regression. The other pairwise rejects also stay appropriately cautious." - }, - "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 }, @@ -13879,33 +13800,29 @@ "issue:44222", "issue:44230", "issue:44261", + "issue:44273", "issue:44315", "issue:44351", "issue:44355", "issue:44360", "issue:44368", "issue:44387", - "issue:44485", "issue:44556", "issue:44623", "issue:44655", - "issue:44749", "issue:44908", "issue:44961", + "issue:45003", "issue:45071", "issue:45125", "issue:45230", "issue:45278", "issue:45375", "issue:45468", - "issue:45478", + "issue:45542", "issue:45656" ], "soft_pairs": [ - "issue:42548|issue:44351", - "issue:43502|issue:44485", - "issue:44355|issue:44749", - "issue:45125|issue:45478", "issue:30990|issue:31795", "issue:45125|issue:45375", "issue:44387|issue:44556", @@ -13917,10 +13834,10 @@ "issue:44315|issue:44360", "issue:43502|issue:44961", "issue:42831|issue:43874", - "issue:44222|issue:44230", "issue:30333|issue:36296", - "issue:44355|issue:44655", "issue:44355|issue:45071", + "issue:44355|issue:44655", + "issue:44222|issue:44230", "issue:43827|issue:44961", "issue:33453|issue:34689", "issue:43010|issue:45656", @@ -13941,180 +13858,158 @@ "issue:41628|issue:44355", "issue:36296|issue:43526", "issue:44261|issue:44360", + "issue:44273|issue:45003", + "issue:44273|issue:45542", "issue:44623|issue:45230" ], - "prepared_review_unit_hash": "33c7f8e105cc15d1258506d56c930c141fc262e9133a9769a83538690b402848", + "prepared_review_unit_hash": "83117f6a01803c198e801d79f1f56d1e58f0e7ca4c27932488d4df3555f67695", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { "node_count": 47, "item_count": 47, - "soft_pair_count": 40, - "serialized_chars": 38567, - "estimated_input_tokens": 9642, - "estimated_eval_tokens": 19540 + "soft_pair_count": 38, + "serialized_chars": 37903, + "estimated_input_tokens": 9476, + "estimated_eval_tokens": 19208 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is mostly heterogeneous, with a loose theme around v5 import/loading regressions. I did not find any true duplicate soft-edge pairs; most are different symbols, model families, or unrelated bugs. The broadest representative issue is the open 5.x import-regression report.", - "confidence": 0.83, - "canonical_issue_reason": "issue:45278 is the best umbrella issue because it broadly captures the main recurring theme in this cluster: multiple import/load breakages after upgrading to Transformers 5.5.0.", + "summary": "These issues are mostly related by broad Transformers v5 regression themes, but they describe different concrete failures: import/export breakages, tokenizer/model loading, quantization, training, docs, and CLI behavior. I do not see any soft pair that is clearly the same underlying bug/change.", + "confidence": 0.84, + "canonical_issue_reason": "issue:45278 is the broadest and most representative open report of the upgrade/import-regression class, covering multiple failures after moving from 4.57.0 to 5.5.0.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the most representative and reusable issue for this cluster since it is broad, current, and adjacent to several other import-regression reports.", + "best_issue_reason": "issue:45278 is the best single issue to anchor this cluster because it is explicit, broad, and closest to the repeated v5 import/loading regressions seen across the set.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:42548", - "right": "issue:44351", - "accept": false, - "reason": "Both are import errors, but they are missing different symbols (`PreTrainedModel` vs `HybridCache`) and likely stem from separate export paths." - }, - { - "left": "issue:43502", - "right": "issue:44485", - "accept": false, - "reason": "One is about `local_files_only=True` still making network requests; the other is a GLM-5 RoPE implementation discussion." - }, - { - "left": "issue:44355", - "right": "issue:44749", - "accept": false, - "reason": "These are unrelated symptoms: compiled-Python-file errors versus a data-filtering slowdown after upgrade." - }, - { - "left": "issue:45125", - "right": "issue:45478", - "accept": false, - "reason": "Same model family, but different concrete failures: missing `_tp_plan` for tensor parallelism versus a generic `from_pretrained` error." - }, { "left": "issue:30990", "right": "issue:31795", "accept": false, - "reason": "Loading hang for Sentence Transformers is not the same as documentation confusion about `input_ids` and `past_key_values`." + "reason": "Different problems: a loading hang in Sentence Transformers vs docs confusion about forward args." }, { "left": "issue:45125", "right": "issue:45375", "accept": false, - "reason": "Both mention Qwen3.5 MoE, but one is a tensor-parallel plan issue and the other is a missing config field being dropped." + "reason": "Both touch Qwen3.5 MoE, but one is tensor-parallel plan support and the other is a config field being dropped by strict parsing." }, { "left": "issue:44387", "right": "issue:44556", "accept": false, - "reason": "Int4 quantization OOM and checkpoint reload compatibility are different failures with different code paths." + "reason": "Int4 quantization OOM is a runtime memory regression; checkpoint reload after upgrade is a separate loading failure." }, { "left": "issue:43010", "right": "issue:45278", "accept": false, - "reason": "One is a cache `update()` no-grad issue; the other is a broad import-regression report." + "reason": "Cache/layer no_grad behavior is unrelated to the broad import-error regression report." }, { "left": "issue:30333", "right": "issue:33453", "accept": false, - "reason": "MLflow job status reporting and tokenizer loading regression are unrelated." + "reason": "MLFlow reporting after failed training is unrelated to tokenizer loading regression." }, { "left": "issue:43723", "right": "issue:44556", "accept": false, - "reason": "Tokenizer loading in v5 and reloading old checkpoints are both load-related but not the same bug." + "reason": "Tokenizer loading in v5 and checkpoint reload after upgrade are different loading paths and likely different bugs." }, { "left": "issue:43010", "right": "issue:44368", "accept": false, - "reason": "Cache update decoration and a tie-word-embeddings warning are different behaviors." + "reason": "No-grad cache updates and a tie_word_embeddings warning are unrelated." }, { "left": "issue:43502", "right": "issue:44222", "accept": false, - "reason": "`local_files_only` network calls and FP8 MoE save-pretrained behavior are unrelated." + "reason": "Local_files_only network leakage and FP8 save_pretrained moE are different code paths." }, { "left": "issue:44315", "right": "issue:44360", "accept": false, - "reason": "Liger-kernel application in `model_init` is unrelated to a DSA indexer missing ReLU." + "reason": "Applying Liger Kernel via model_init is unrelated to a DSA indexer ReLU omission." }, { "left": "issue:43502", "right": "issue:44961", "accept": false, - "reason": "`local_files_only` API calls and the placeholder 'racoon' issue do not match." + "reason": "API calls despite local_files_only and an unrelated placeholder issue are not the same bug." }, { "left": "issue:42831", "right": "issue:43874", "accept": false, - "reason": "FineGrainedFP8 accuracy and a missing image-patch helper in GLM46V are different bugs." + "reason": "FineGrainedFP8 accuracy drift and a missing image-patch-count method are different issues." }, { - "left": "issue:44222", - "right": "issue:44230", + "left": "issue:30333", + "right": "issue:36296", "accept": false, - "reason": "Both involve FP8/MoE, but one is about saving models and the other about inference support." + "reason": "MLFlow failure reporting and tensor-parallel training are unrelated." }, { - "left": "issue:30333", - "right": "issue:36296", + "left": "issue:44355", + "right": "issue:45071", "accept": false, - "reason": "MLflow job reporting and tensor-parallel training are unrelated." + "reason": "Compiled Python file errors and PretrainedConfig type checking are different regressions." }, { "left": "issue:44355", "right": "issue:44655", "accept": false, - "reason": "Compiled-file execution errors and saving Pipeline objects are different failures." + "reason": "Compiled-file execution errors are unrelated to saving Pipeline objects." }, { - "left": "issue:44355", - "right": "issue:45071", + "left": "issue:44222", + "right": "issue:44230", "accept": false, - "reason": "Compiled-file errors do not match the `PretrainedConfig` type-checking regression." + "reason": "Save_pretrained on FP8 MoE and FP8 inference support are different change requests." }, { "left": "issue:43827", "right": "issue:44961", "accept": false, - "reason": "Docs still referencing `pipeline()` and the unrelated 'racoon' issue are not duplicates." + "reason": "Docs still referencing pipeline() and a placeholder issue are unrelated." }, { "left": "issue:33453", "right": "issue:34689", "accept": false, - "reason": "Tokenizer-loading regression and Llama 3.2 Vision model-loading breakage are separate model-loading problems." + "reason": "Tokenizer-loading regression and Llama 3.2 model-loading breakage are different failures." }, { "left": "issue:43010", "right": "issue:45656", "accept": false, - "reason": "Cache update no-grad and optimizer stepping twice under deepspeed are different training-loop bugs." + "reason": "Cache update no_grad behavior is unrelated to double optimizer-step calls under deepspeed." }, { "left": "issue:43299", "right": "issue:44556", "accept": false, - "reason": "Qwen3VL MoE loading and old-checkpoint reload compatibility are not the same concrete issue." + "reason": "Qwen3VL MoE model loading and checkpoint reload-after-upgrade are not the same concrete bug." }, { "left": "issue:42757", "right": "issue:43576", "accept": false, - "reason": "Missing `is_offline_mode` import and the `transformers env` command failure are different code paths." + "reason": "Missing huggingface_hub symbol import and the transformers env CLI are different surfaces." }, { "left": "issue:33453", @@ -14126,91 +14021,103 @@ "left": "issue:43576", "right": "issue:45071", "accept": false, - "reason": "Broken `transformers env` command and `PretrainedConfig` type checking are distinct issues." + "reason": "CLI env command breakage and PretrainedConfig type-checking are separate regressions." }, { "left": "issue:43576", "right": "issue:43824", "accept": false, - "reason": "`transformers env` and missing `Qwen2_5_VLForConditionalGeneration` import are different failures." + "reason": "CLI env command breakage and missing Qwen2_5_VL export are different import surfaces." }, { "left": "issue:44961", "right": "issue:45468", "accept": false, - "reason": "The 'racoon' issue is not related to Gemma-4 audio positional encoding." + "reason": "Placeholder racoon issue is unrelated to Gemma4 audio positional encoding." }, { "left": "issue:31795", "right": "issue:38617", "accept": false, - "reason": "Documentation confusion about `forward` arguments is unrelated to an import error for `layer_type_validation`." + "reason": "Docs confusion in model.forward is unrelated to an ImportError for layer_type_validation." }, { "left": "issue:38617", "right": "issue:43576", "accept": false, - "reason": "Different symptoms: missing module import versus the `transformers env` command being broken." + "reason": "ImportError for a missing utility symbol is not the same as the env CLI breakage." }, { "left": "issue:43010", "right": "issue:43976", "accept": false, - "reason": "Cache no-grad and Python-version compatibility are unrelated." + "reason": "No-grad cache update behavior is unrelated to Python version compatibility failure." }, { "left": "issue:41628", "right": "issue:42548", "accept": false, - "reason": "Both are missing imports from `transformers`, but they are different missing symbols and likely separate export regressions." + "reason": "Both are import errors, but for different exported symbols and likely different breakages." }, { "left": "issue:43576", "right": "issue:44351", "accept": false, - "reason": "Broken `transformers env` output and missing `HybridCache` import are unrelated." + "reason": "CLI env command and HybridCache import failure are different issues." }, { "left": "issue:44908", "right": "issue:44961", "accept": false, - "reason": "Scheduler kwargs being ignored has nothing to do with the unrelated 'racoon' issue." + "reason": "Inverse_sqrt scheduler kwargs handling is unrelated to the placeholder issue." }, { "left": "issue:36296", "right": "issue:43901", "accept": false, - "reason": "Tensor-parallel training and text-classification pipeline docs are different topics." + "reason": "Tensor-parallel training bug and documentation of text-classification outputs are unrelated." }, { "left": "issue:43010", "right": "issue:43232", "accept": false, - "reason": "No-grad decoration for cache updates is unrelated to a generation kwargs update bug after `sync_gpus`." + "reason": "Cache/layer update no_grad and generation sync_gpus model-kwargs handling are different code paths." }, { "left": "issue:41628", "right": "issue:44355", "accept": false, - "reason": "Missing `AutoImageProcessor` import and compiled-file execution errors are not the same bug." + "reason": "AutoImageProcessor import failure and compiled Python file errors are unrelated." }, { "left": "issue:36296", "right": "issue:43526", "accept": false, - "reason": "Tensor-parallel training and `reduce_labels` returning only one label are unrelated." + "reason": "Tensor-parallel training and BeitImageProcessorFast label reduction are different bugs." }, { "left": "issue:44261", "right": "issue:44360", "accept": false, - "reason": "A precision error from missing `rms_norm_eps` is unrelated to a missing ReLU in the DSA indexer." + "reason": "MLA q_a_layernorm precision/config issue is unrelated to the DSA indexer ReLU bug." + }, + { + "left": "issue:44273", + "right": "issue:45003", + "accept": false, + "reason": "Lazy loading failure and unsafe sys.modules access are related in theme but not clearly the same concrete bug." + }, + { + "left": "issue:44273", + "right": "issue:45542", + "accept": false, + "reason": "Lazy loading behavior and TensorBoard-without-TF backend handling are separate problems." }, { "left": "issue:44623", "right": "issue:45230", "accept": false, - "reason": "Missing processor save files and a generic bug report are not duplicates." + "reason": "Missing processor save_pretrained files is too specific to merge with a generic bug report." } ] }, @@ -14246,6 +14153,7 @@ "issue:43502", "issue:43519", "issue:43576", + "issue:43606", "issue:43673", "issue:43704", "issue:43827", @@ -14253,6 +14161,7 @@ "issue:44038", "issue:44077", "issue:44246", + "issue:44263", "issue:44273", "issue:44295", "issue:44297", @@ -14271,7 +14180,6 @@ "issue:44861", "issue:44908", "issue:44961", - "issue:45003", "issue:45071", "issue:45092", "issue:45125", @@ -14280,19 +14188,16 @@ "issue:45341", "issue:45468", "issue:45478", - "issue:45542", "issue:45753" ], "soft_pairs": [ - "issue:44273|issue:45003", - "issue:44273|issue:45542", "issue:44393|issue:45753", "issue:43576|issue:44556", "issue:44038|issue:45125", "issue:44393|issue:45071", "issue:41669|issue:43673", - "issue:44373|issue:44961", "issue:44556|issue:45092", + "issue:44373|issue:44961", "issue:44704|issue:44908", "issue:42890|issue:44908", "issue:44246|issue:44273", @@ -14300,29 +14205,29 @@ "issue:43976|issue:44393", "issue:43352|issue:44393", "issue:43576|issue:44908", + "issue:44908|issue:45071", "issue:44297|issue:45230", + "issue:41669|issue:44351", "issue:44295|issue:45230", - "issue:44908|issue:45071", "issue:43673|issue:44492", - "issue:41669|issue:44351", "issue:41669|issue:45341", "issue:44393|issue:45478", "issue:41669|issue:44492", "issue:44315|issue:44829", - "issue:43827|issue:44908", "issue:44077|issue:44861", + "issue:43827|issue:44908", "issue:31795|issue:33453", "issue:41669|issue:44908", "issue:42371|issue:44492", "issue:44655|issue:44861", "issue:43576|issue:44273", "issue:44360|issue:45468", - "issue:45230|issue:45310", - "issue:43827|issue:44492", "issue:44273|issue:44908", + "issue:43827|issue:44492", + "issue:45230|issue:45310", "issue:43519|issue:44485", - "issue:43519|issue:44908", "issue:41669|issue:43704", + "issue:43519|issue:44908", "issue:31795|issue:34689", "issue:31795|issue:37428", "issue:44315|issue:45092", @@ -14331,14 +14236,16 @@ "issue:42371|issue:43704", "issue:43502|issue:43519", "issue:43519|issue:44623", - "issue:43519|issue:43704" + "issue:43519|issue:43704", + "issue:44263|issue:45468", + "issue:43606|issue:45468" ], - "prepared_review_unit_hash": "89244b67ec7b1cc8370e396657507fe2e9dcda471799cd3814dfe0cfe42083b0", + "prepared_review_unit_hash": "109b2890f00cfd2d3e96c25ec4c1965b5eb03a53ba37ea062b2122f300bd2685", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, @@ -14346,315 +14253,309 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 48, - "serialized_chars": 41364, - "estimated_input_tokens": 10341, - "estimated_eval_tokens": 20938 + "serialized_chars": 41368, + "estimated_input_tokens": 10342, + "estimated_eval_tokens": 20940 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a loose grab bag of Transformers issues: a few import/lazy-loading/v5 loading regressions, several unrelated model-specific bugs, and some docs/tests noise. None of the soft-edge pairs look like true duplicates or the same fix.", - "confidence": 0.93, - "canonical_issue_reason": "issue:44273 is the broadest umbrella issue in the import/lazy-loading subset and is the closest thing to a representative user-facing problem here.", + "summary": "This cluster is highly heterogeneous: the soft links are mostly title similarity across unrelated docs, loading regressions, model-specific bugs, and perf issues. I would not merge any of the soft pairs as duplicates.", + "confidence": 0.92, + "canonical_issue_reason": "No clear canonical issue emerges because the items do not share one underlying bug or change; they span distinct subsystems and symptoms.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44273 is the most general, cluster-shaped issue; the rest are narrower regressions or unrelated bugs, so it is the best representative issue if one must be chosen.", + "best_issue_reason": "No single issue is a good global representative here; the set is too broad and inconsistent to center on one bug report.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:44273", - "right": "issue:45003", - "accept": false, - "reason": "Lazy loading failure vs unsafe sys.modules access; different code paths and symptoms." - }, - { - "left": "issue:44273", - "right": "issue:45542", - "accept": false, - "reason": "Lazy loading bug vs undefined TF backend from optional deps; unrelated." - }, { "left": "issue:44393", "right": "issue:45753", "accept": false, - "reason": "Different Qwen3-VL failures: 2D box output error vs image-specific infinite loop." + "reason": "Both are Qwen3 vision-model problems, but one is a 2D bbox hallucination/error and the other is an infinite-loop case on a specific image; different bugs." }, { "left": "issue:43576", "right": "issue:44556", "accept": false, - "reason": "v5 env command breakage vs checkpoint reload incompatibility; not the same bug." + "reason": "One is a broken `transformers env` command and the other is a checkpoint reload regression after upgrading to v5; separate code paths." }, { "left": "issue:44038", "right": "issue:45125", "accept": false, - "reason": "Different Qwen3 model bugs: Qwen3-VL-Moe from_pretrained vs tensor-parallel plan missing." + "reason": "These are both Qwen3-MoE related, but one is a from_pretrained error and the other is a missing tensor-parallel plan; not the same defect." }, { "left": "issue:44393", "right": "issue:45071", "accept": false, - "reason": "Model output bug vs PretrainedConfig type-checking regression; unrelated." + "reason": "A vision-model bbox output bug is unrelated to a `PretrainedConfig` type-checking regression." }, { "left": "issue:41669", "right": "issue:43673", "accept": false, - "reason": "Import-time slowdown from import * vs missing GenerationMixin cache in chunked prefill." + "reason": "Import-star cleanup/perf concerns do not match the chunked_prefill cache regression." }, { - "left": "issue:44373", - "right": "issue:44961", + "left": "issue:44556", + "right": "issue:45092", "accept": false, - "reason": "Wrong docstring vs unrelated placeholder issue; no shared bug." + "reason": "Both involve v5 loading regressions, but one is generic checkpoint reload and the other is remote-code meta-initialization incompatibility for InternVL2." }, { - "left": "issue:44556", - "right": "issue:45092", + "left": "issue:44373", + "right": "issue:44961", "accept": false, - "reason": "Both version-related, but one is checkpoint reload after upgrade and the other is remote-code/meta-init incompatibility." + "reason": "A wrong docstring for `position_ids` is unrelated to a placeholder `racoon` issue." }, { "left": "issue:44704", "right": "issue:44908", "accept": false, - "reason": "AutoProcessor kwargs passthrough vs inverse_sqrt scheduler kwargs; different APIs." + "reason": "Forwarding kwargs to `cached_file` and scheduler `lr_scheduler_kwargs` are unrelated API bugs." }, { "left": "issue:42890", "right": "issue:44908", "accept": false, - "reason": "Test seeding flakiness vs scheduler kwargs bug; unrelated." + "reason": "A flaky integration test due to missing seeds is unrelated to an inverse-sqrt scheduler kwargs regression." }, { "left": "issue:44246", "right": "issue:44273", "accept": false, - "reason": "Both about import/lazy-loading, but one is slow import and the other is broken lazy loading." + "reason": "Import-time slowness and lazy-loading failure are different symptoms without a shared concrete bug." }, { "left": "issue:43408", "right": "issue:44315", "accept": false, - "reason": "sam3 model-type mismatch vs Liger Kernel not applied with model_init; unrelated." + "reason": "A sam3_video/sam3_tracker type mismatch is unrelated to `patchtsmixer` and `model_init`/`post_init` handling." }, { "left": "issue:43976", "right": "issue:44393", "accept": false, - "reason": "Python version incompatibility vs Qwen3-VL bounding-box bug; unrelated." + "reason": "Python version support regression and Qwen3-VL bbox output issues are unrelated." }, { "left": "issue:43352", "right": "issue:44393", "accept": false, - "reason": "Flash Attention 2 support error vs Qwen3-VL output bug; different models and failures." + "reason": "Flash Attention 2 support for Nemotron and a Qwen3-VL output bug are different problems." }, { "left": "issue:43576", "right": "issue:44908", "accept": false, - "reason": "env command breakage vs scheduler kwargs handling; unrelated." + "reason": "A broken CLI env command and scheduler keyword handling are unrelated." }, { - "left": "issue:44297", - "right": "issue:45230", + "left": "issue:44908", + "right": "issue:45071", "accept": false, - "reason": "Tokenizer save_pretrained mismatch vs generic bug report; no evidence of same issue." + "reason": "Scheduler kwargs handling and `PretrainedConfig` type checking do not share the same root cause." }, { - "left": "issue:44295", + "left": "issue:44297", "right": "issue:45230", "accept": false, - "reason": "position_ids buffer error vs generic bug report; unrelated." + "reason": "Tokenizer save metadata mismatch and a vague generic bug report are not enough to establish a duplicate." }, { - "left": "issue:44908", - "right": "issue:45071", + "left": "issue:41669", + "right": "issue:44351", "accept": false, - "reason": "Scheduler kwargs bug vs PretrainedConfig type-checking regression; different code paths." + "reason": "Import-star cleanup/perf work is unrelated to the missing `HybridCache` import failure." }, { - "left": "issue:43673", - "right": "issue:44492", + "left": "issue:44295", + "right": "issue:45230", "accept": false, - "reason": "Chunked prefill cache regression vs typo in cache strategies; unrelated." + "reason": "Position-ids buffer handling and a generic bug report are unrelated." }, { - "left": "issue:41669", - "right": "issue:44351", + "left": "issue:43673", + "right": "issue:44492", "accept": false, - "reason": "Import * slowdown vs HybridCache import failure; same broad area, different concrete bug." + "reason": "Missing cache in chunked_prefill and a typo in cache strategy docs are not the same issue." }, { "left": "issue:41669", "right": "issue:45341", "accept": false, - "reason": "Import-performance issue vs a testing_utils bug; unrelated." + "reason": "Import performance work is unrelated to a small `testing_utils.py` bug." }, { "left": "issue:44393", "right": "issue:45478", "accept": false, - "reason": "Qwen3-VL bounding-box bug vs Qwen3.5 Moe from_pretrained error; different models." + "reason": "A Qwen3-VL bbox output bug and a Qwen3.5 MoE from_pretrained regression are different model failures." }, { "left": "issue:41669", "right": "issue:44492", "accept": false, - "reason": "Import-time slowdown vs cache-strategy typo; unrelated." + "reason": "Import-star cleanup/perf and a cache-strategy typo are unrelated." }, { "left": "issue:44315", "right": "issue:44829", "accept": false, - "reason": "Liger Kernel/model_init issue vs flash_attention_3 degenerate training; distinct failures." + "reason": "`model_init`/`post_init` behavior with Liger Kernel is unrelated to Flash Attention 3 degenerate training." }, { - "left": "issue:43827", - "right": "issue:44908", + "left": "issue:44077", + "right": "issue:44861", "accept": false, - "reason": "Docs still mentioning pipeline() vs scheduler kwargs bug; unrelated." + "reason": "A `post_init` restriction and `_get_tied_weight_keys` crashing on a list are different issues." }, { - "left": "issue:44077", - "right": "issue:44861", + "left": "issue:43827", + "right": "issue:44908", "accept": false, - "reason": "patchtsmixer post_init validation vs tied-weight-key AttributeError; unrelated." + "reason": "Docs still mentioning `pipeline()` and scheduler kwargs are unrelated." }, { "left": "issue:31795", "right": "issue:33453", "accept": false, - "reason": "Forward-doc confusion vs tokenizer loading regression; different layers and bugs." + "reason": "Confusing forward-docs for `input_ids`/`past_key_values` is unrelated to a tokenizer loading regression." }, { "left": "issue:41669", "right": "issue:44908", "accept": false, - "reason": "Import slowdown vs scheduler kwargs bug; unrelated." + "reason": "Import performance and scheduler kwargs handling are unrelated." }, { "left": "issue:42371", "right": "issue:44492", "accept": false, - "reason": "TF32 API guidance issue vs cache-strategy typo; unrelated." + "reason": "TF32 API guidance and cache-strategy typos do not describe the same bug." }, { "left": "issue:44655", "right": "issue:44861", "accept": false, - "reason": "Pipeline save_pretrained failure vs tied-weight-keys crash; different subsystems." + "reason": "Saving Pipeline objects and `_get_tied_weight_keys` AttributeError are unrelated." }, { "left": "issue:43576", "right": "issue:44273", "accept": false, - "reason": "Both touch v5/loading UX, but env command breakage and lazy loading are different bugs." + "reason": "A broken env command and lazy loading not working are different bugs." }, { "left": "issue:44360", "right": "issue:45468", "accept": false, - "reason": "Completely unrelated model/discussion topics." + "reason": "A DSA indexer discussion about ReLU is unrelated to Gemma-4 audio positional encoding." }, { - "left": "issue:45230", - "right": "issue:45310", + "left": "issue:44273", + "right": "issue:44908", "accept": false, - "reason": "Generic bug report provides no concrete overlap with the Qwen3.5 Moe from_pretrained error." + "reason": "Lazy loading behavior and inverse-sqrt scheduler kwargs are unrelated." }, { "left": "issue:43827", "right": "issue:44492", "accept": false, - "reason": "Docs referencing pipeline() vs cache-strategy typo; unrelated." + "reason": "Pipeline-removal docs and cache-strategy typos are unrelated." }, { - "left": "issue:44273", - "right": "issue:44908", + "left": "issue:45230", + "right": "issue:45310", "accept": false, - "reason": "Lazy loading failure vs scheduler kwargs bug; unrelated." + "reason": "The generic bug report is too vague to match the Qwen3.5 MoE from_pretrained regression." }, { "left": "issue:43519", "right": "issue:44485", "accept": false, - "reason": "Qwen3-VL timestamp calculation vs GLM-5 RoPE implementation; unrelated model bugs." + "reason": "Qwen3-VL timestamp calculation and GLM-5 RoPE implementation are different model-specific bugs." }, { - "left": "issue:43519", - "right": "issue:44908", + "left": "issue:41669", + "right": "issue:43704", "accept": false, - "reason": "Timestamp bug vs scheduler kwargs bug; unrelated." + "reason": "Import-star cleanup/perf and a VRAM leak in Qwen3ForCausalLM are unrelated." }, { - "left": "issue:41669", - "right": "issue:43704", + "left": "issue:43519", + "right": "issue:44908", "accept": false, - "reason": "Import slowdown vs VRAM leak in multithreaded dataloaders; different problem." + "reason": "Qwen3VL timestamp math and scheduler kwargs handling are unrelated." }, { "left": "issue:31795", "right": "issue:34689", "accept": false, - "reason": "Docstring confusion vs Llama 3.2 vision loading regression; unrelated." + "reason": "Forward-doc confusion for `input_ids`/`past_key_values` is unrelated to the Llama 3.2 Vision model-loading regression." }, { "left": "issue:31795", "right": "issue:37428", "accept": false, - "reason": "Docstring confusion vs missing flash_attention utility import; unrelated." + "reason": "A documentation issue and a flash-attention import error are unrelated." }, { "left": "issue:44315", "right": "issue:45092", "accept": false, - "reason": "Liger Kernel/model_init bug vs InternVL2 meta-init incompatibility; same general theme, different bugs." + "reason": "`model_init`/Liger Kernel behavior and InternVL2 meta-init incompatibility are different problems." }, { "left": "issue:43704", "right": "issue:44485", "accept": false, - "reason": "VRAM leak in dataloader threads vs GLM-5 RoPE implementation; unrelated." + "reason": "A VRAM leak in Qwen3ForCausalLM is unrelated to GLM-5 RoPE implementation." }, { "left": "issue:44485", "right": "issue:45468", "accept": false, - "reason": "Different model-specific issues: GLM-5 RoPE vs Gemma-4 audio positional encoding." + "reason": "GLM-5 RoPE implementation and Gemma-4 audio positional encoding are unrelated." }, { "left": "issue:42371", "right": "issue:43704", "accept": false, - "reason": "TF32 API guidance vs VRAM leak; unrelated." + "reason": "TF32 API guidance and a Qwen3ForCausalLM VRAM leak are unrelated." }, { "left": "issue:43502", "right": "issue:43519", "accept": false, - "reason": "local_files_only network leakage vs Qwen3VL timestamp miscalculation; unrelated." + "reason": "Unexpected API requests with `local_files_only=True` and Qwen3VL timestamp calculation are different bugs." }, { "left": "issue:43519", "right": "issue:44623", "accept": false, - "reason": "Timestamp calculation bug vs processor save_pretrained missing files; different APIs." + "reason": "Qwen3VL timestamp computation and missing files in `processor.save_pretrained` are unrelated." }, { "left": "issue:43519", "right": "issue:43704", "accept": false, - "reason": "Qwen3VL timestamp bug vs multithreaded VRAM leak; unrelated." + "reason": "Timestamp calculation in Qwen3VL and a VRAM leak in Qwen3ForCausalLM are different defects." }, { - "left": "issue:43519", - "right": "issue:44485", + "left": "issue:44263", + "right": "issue:45468", + "accept": false, + "reason": "A `torch.split()` return-value issue in GlmMoeDsaIndexer is unrelated to Gemma-4 audio positional encoding." + }, + { + "left": "issue:43606", + "right": "issue:45468", "accept": false, - "reason": "Repeated pair: timestamp bug vs GLM-5 RoPE implementation; unrelated." + "reason": "CPU offload device mismatch in Bark is unrelated to Gemma-4 audio positional encoding." } ] }, @@ -14690,11 +14591,9 @@ "issue:43298", "issue:43525", "issue:43572", - "issue:43606", "issue:43704", "issue:44230", "issue:44261", - "issue:44263", "issue:44360", "issue:44623", "issue:44861", @@ -14706,15 +14605,13 @@ "issue:45468" ], "soft_pairs": [ - "issue:44263|issue:45468", - "issue:43606|issue:45468", "issue:44261|issue:45468", "issue:43704|issue:45341", "issue:42913|issue:43066", "issue:44908|issue:44998", "issue:44861|issue:45290", - "issue:43704|issue:44998", "issue:43525|issue:44861", + "issue:43704|issue:44998", "issue:41669|issue:44998", "issue:43572|issue:44861", "issue:43066|issue:44998", @@ -14728,160 +14625,148 @@ "issue:31515|issue:33453", "issue:43298|issue:44230" ], - "prepared_review_unit_hash": "b55dbd18922d0ca7d673764fcb9fd818360d51a07c6b24ebf318fbb0d117461a", + "prepared_review_unit_hash": "0402f14e9110bbbc279ca0ced579c476daaa9a2350bc85290cd379d132406361", "component_budget": { "node_count": 390, "item_count": 390, "soft_pair_count": 1471, - "serialized_chars": 757026, + "serialized_chars": 757027, "estimated_input_tokens": 189257, "estimated_eval_tokens": 378770 }, "budget": { - "node_count": 26, - "item_count": 26, - "soft_pair_count": 21, - "serialized_chars": 20886, - "estimated_input_tokens": 5222, - "estimated_eval_tokens": 10700 + "node_count": 24, + "item_count": 24, + "soft_pair_count": 19, + "serialized_chars": 19156, + "estimated_input_tokens": 4789, + "estimated_eval_tokens": 9834 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly noisy: the soft-similarity links span unrelated topics (model config bugs, tokenizer regressions, training/runtime issues, and generic docs/tooling). None of the suggested soft pairs look like the same underlying bug or change, so all are rejected.", - "confidence": 0.74, - "canonical_issue_reason": "No single canonical issue fits the whole set; the items are too heterogeneous to represent one duplicate family.", + "summary": "This cluster is heterogeneous: the soft-similarity links mostly connect unrelated bugs that only share broad subsystem vocabulary (loading, tokenizer, configs, training). No pair looks like the same underlying issue, so I would not merge any of them as duplicates.", + "confidence": 0.9, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:31515 is the broadest and most connected report in the set, so it is the closest thing to a cluster anchor, but it still only matches a small loading/checkpoint subset.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:44263", - "right": "issue:45468", - "accept": false, - "reason": "Different model-specific bugs in unrelated code paths: DSA indexing vs Gemma4 audio positional encoding." - }, - { - "left": "issue:43606", - "right": "issue:45468", - "accept": false, - "reason": "CPU offload device-mismatch CI bug is unrelated to Gemma4 audio positional encoding." - }, { "left": "issue:44261", "right": "issue:45468", "accept": false, - "reason": "MLA q_a_layernorm epsilon handling and Gemma4AudioRelPositionalEncoding are separate model issues." + "reason": "Both are model/config-related, but they concern different components and failure modes: MLA RMS norm epsilon precision vs Gemma4 audio positional encoding." }, { "left": "issue:43704", "right": "issue:45341", "accept": false, - "reason": "VRAM leak in Qwen3ForCausalLM multi-threading is unrelated to a testing_utils bug." + "reason": "A VRAM leak in Qwen3ForCausalLM is unrelated to a testing_utils bug; no shared code-path or concrete fix target." }, { "left": "issue:42913", "right": "issue:43066", "accept": false, - "reason": "Both involve tokenizers/v5, but one is a general behavior regression and the other is a specific decoder-type mismatch; not clearly the same bug." + "reason": "Both mention tokenizer changes in v5, but one is about behavioral differences across versions and the other about the wrong decoder type; too different to be the same bug." }, { "left": "issue:44908", "right": "issue:44998", "accept": false, - "reason": "Scheduler kwarg handling is unrelated to the irrelevant 'Unemployment' issue." + "reason": "Scheduler kwargs handling and an unrelated placeholder issue are not the same underlying change." }, { "left": "issue:44861", "right": "issue:45290", "accept": false, - "reason": "Tied-weight key extraction crash is unrelated to apply_chat_template tool-call handling." + "reason": "Tied-weight key handling and chat template tool-call crashes affect different code paths and error surfaces." }, { - "left": "issue:43704", - "right": "issue:44998", + "left": "issue:43525", + "right": "issue:44861", "accept": false, - "reason": "Qwen3 VRAM leak and the unrelated 'Unemployment' issue do not match." + "reason": "Missing pad_token_id on Llama4Config is unrelated to _get_tied_weight_keys crashing on list-typed _tied_weights_keys." }, { - "left": "issue:43525", - "right": "issue:44861", + "left": "issue:43704", + "right": "issue:44998", "accept": false, - "reason": "Missing pad_token_id in Llama4Config is unrelated to tied-weight key extraction." + "reason": "No substantive overlap; a memory leak bug is not related to the placeholder issue." }, { "left": "issue:41669", "right": "issue:44998", "accept": false, - "reason": "Import-* performance cleanup is unrelated to the irrelevant 'Unemployment' issue." + "reason": "Import-star performance regression and the placeholder issue are clearly unrelated." }, { "left": "issue:43572", "right": "issue:44861", "accept": false, - "reason": "StableLmConfig pad_token_idx regression is unrelated to tied-weight key extraction." + "reason": "StableLmConfig missing pad_token_idx is a config-field regression, not a tied-weights attribute error." }, { "left": "issue:43066", "right": "issue:44998", "accept": false, - "reason": "Tokenizer decoder-type regression is unrelated to the irrelevant 'Unemployment' issue." + "reason": "Wrong tokenizer decoder type is unrelated to the placeholder issue." }, { "left": "issue:31515", "right": "issue:38617", "accept": false, - "reason": "Slow checkpoint loading and an ImportError for layer_type_validation are different failures." + "reason": "Slow checkpoint loading and an ImportError for layer_type_validation are different failure modes with no shared fix." }, { "left": "issue:44360", "right": "issue:44998", "accept": false, - "reason": "DSA indexer ReLU omission is unrelated to the irrelevant 'Unemployment' issue." + "reason": "A DSA indexer activation-function discussion is unrelated to the placeholder issue." }, { "left": "issue:44230", "right": "issue:44623", "accept": false, - "reason": "FP8 Qwen3/VL inference support and missing processor.save_pretrained files are different problems." + "reason": "FP8 Qwen3-VL/MoE inference support and processor.save_pretrained missing files are distinct feature/bug areas." }, { "left": "issue:30333", "right": "issue:31515", "accept": false, - "reason": "MLFlow reporting on failed training jobs is unrelated to slow from_pretrained checkpoint loading." + "reason": "MLflow job status reporting on training failure is unrelated to slow from_pretrained checkpoint loading." }, { "left": "issue:31515", "right": "issue:36296", "accept": false, - "reason": "Checkpoint loading slowdown is unrelated to tensor parallel training bugs." + "reason": "Slow checkpoint loading and a tensor-parallel training bug are different problems and would not be fixed by one PR." }, { "left": "issue:31515", "right": "issue:31795", "accept": false, - "reason": "A load-speed issue and documentation confusion about inputs/past_key_values are not the same bug." + "reason": "Checkpoint loading performance and documentation confusion about input_ids/past_key_values are not the same underlying issue." }, { "left": "issue:44230", "right": "issue:45310", "accept": false, - "reason": "FP8 support request and a Qwen3.5 MoE from_pretrained error are different code-path failures." + "reason": "Both involve Qwen3/MoE model loading/inference, but one is fp8 support and the other is a from_pretrained regression; too different to merge as duplicates." }, { "left": "issue:31515", "right": "issue:33453", "accept": false, - "reason": "Slow checkpoint loading is not the same as a tokenizer loading regression." + "reason": "Slow checkpoint loading and a tokenizer-loading regression are superficially related but not the same concrete bug." }, { "left": "issue:43298", "right": "issue:44230", "accept": false, - "reason": "Continuous batching missing audio-model support is unrelated to Qwen3/VL FP8 inference support." + "reason": "Continuous batching support for audio models and fp8 Qwen3-VL/Qwen3.5 MoE inference are distinct feature gaps." } ] }, @@ -14911,7 +14796,7 @@ "soft_pairs": [ "issue:26350|issue:33260" ], - "prepared_review_unit_hash": "de1ad279c01f4aead7efa6716b4b57fb4355759620fd8501afe4e8ccb61b484d", + "prepared_review_unit_hash": "9e2a8079ad7609ae8131c254c0c41bdaf0de2012b6182768b2366f97caa9ad84", "component_budget": { "node_count": 2, "item_count": 2, @@ -14933,18 +14818,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are two different community support requests in the same broad theme, but they target separate features and code paths: Flash Attention 2 support vs GGUF support.", + "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 phrasing pattern but describe different feature areas and different underlying changes.", "confidence": 0.98, - "canonical_issue_reason": "Not a duplicate cluster: the issues request different architecture-support features and do not appear to be the same underlying bug or change.", + "canonical_issue_reason": "No canonical issue: the requests target different features (Flash Attention 2 vs GGUF) and are not the same bug or change.", "canonical_pr_reason": null, - "best_issue_reason": "Neither issue is a better duplicate representative; they are separate feature requests rather than one shared problem.", + "best_issue_reason": "Neither issue is a duplicate of the other; if a representative is needed, issue 26350 is slightly more established by discussion activity, but the cluster should really be kept separate.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:26350", "right": "issue:33260", "accept": false, - "reason": "Flash Attention 2 support and GGUF support are distinct features with different implementation paths, so they should not be merged as duplicates." + "reason": "Different requested capabilities and code paths: Flash Attention 2 support vs GGUF support. Similar wording, but not the same underlying change." } ] }, @@ -14981,77 +14866,80 @@ "issue:43834|issue:44365", "issue:44365|issue:44370" ], - "prepared_review_unit_hash": "2bf1ca977a1ceffa3ca94c29db0f4675d57a099e69b04f64dffc802b877ce30d", + "prepared_review_unit_hash": "0724cc51aed38e8269fa5b11920a43d7a35de3cb2dd0e2ddba4f3ab849f2564e", "component_budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 4452, - "estimated_input_tokens": 1113, - "estimated_eval_tokens": 2482 + "serialized_chars": 4455, + "estimated_input_tokens": 1114, + "estimated_eval_tokens": 2484 }, "budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 4452, - "estimated_input_tokens": 1113, - "estimated_eval_tokens": 2482 + "serialized_chars": 4455, + "estimated_input_tokens": 1114, + "estimated_eval_tokens": 2484 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are all highly similar docs-translation issues, but only #27088 is concrete (Turkish). The other three are generic template-style placeholders, so I would not collapse them as the same underlying issue based on the available evidence.", - "confidence": 0.83, - "canonical_issue_reason": "#27088 is the only specific, language-filled report ('Translating docs to Turkish'); the others are placeholder/template variants without enough concrete detail to prove they are the same request.", + "summary": "Three of the issues are near-verbatim duplicates of the same i18n translation template, while the Turkish-specific issue is similar but not clearly the same request. No PRs are present.", + "confidence": 0.73, + "canonical_issue_reason": "issue:43834 is the cleanest representative of the clearly duplicate template trio: it matches the other placeholder issues almost exactly and is the earliest of that set.", "canonical_pr_reason": null, - "best_issue_reason": "#27088 is the best representative issue because it is specific, actionable, and not just a template placeholder.", + "best_issue_reason": "issue:43834 is the best canonical representative because its title/body are essentially identical to the other duplicate template issues and it is the earliest instance.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:27088", "right": "issue:44370", "accept": false, - "reason": "Titles are similar, but one is specific Turkish and the other is a generic placeholder; not enough evidence they are the same translation request." + "reason": "The Turkish-specific title differs from the placeholder template issues; similarity alone is not enough to prove the same underlying request." }, { "left": "issue:27088", "right": "issue:44365", "accept": false, - "reason": "Same broad docs-translation theme, but the placeholder title does not establish the same underlying language or request." + "reason": "Same reason: this is a language-specific issue versus a generic template variant, so the match is too weak to merge confidently." }, { "left": "issue:27088", "right": "issue:43834", "accept": false, - "reason": "The generic template title could refer to any language, so it should not be merged with the specific Turkish issue without clearer matching details." + "reason": "The content is highly similar, but the concrete Turkish issue is not clearly the same underlying request as the generic placeholder issue." }, { "left": "issue:43834", "right": "issue:44370", - "accept": false, - "reason": "Both are template-style translation issues, but the available evidence does not prove they target the same language or exact request." + "accept": true, + "reason": "These two are near-verbatim duplicates with the same generic i18n translation template wording and almost identical body size." }, { "left": "issue:43834", "right": "issue:44365", - "accept": false, - "reason": "Near-identical templates are not enough to treat them as the same issue; the concrete translation target is missing." + "accept": true, + "reason": "Near-identical placeholder issue text; they look like the same underlying template issue." }, { "left": "issue:44365", "right": "issue:44370", - "accept": false, - "reason": "These look like repeated template instances, but there is no concrete evidence they refer to the same underlying translation task." + "accept": true, + "reason": "These are effectively the same issue text/body and clearly duplicate each other." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet: 43834 is the earliest of the three near-identical template issues, the template trio is supported by the identical titles and very high similarity scores, and the Turkish issue is conservatively kept separate. No PRs are present, and the soft-edge verdicts do not overstate the evidence." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -15121,238 +15009,244 @@ "issue:37015|issue:45027", "issue:43837|issue:45177" ], - "prepared_review_unit_hash": "1c93c6037b731821f6ac2f23739edf57c5bc676331b321b8ca222476bd0aad3c", + "prepared_review_unit_hash": "e66e00a9b79eb67d78a35a0d698423c3baecf01753195ccb91c5958b9c760912", "component_budget": { "node_count": 15, "item_count": 15, "soft_pair_count": 35, - "serialized_chars": 20704, - "estimated_input_tokens": 5176, - "estimated_eval_tokens": 10608 + "serialized_chars": 20708, + "estimated_input_tokens": 5177, + "estimated_eval_tokens": 10610 }, "budget": { "node_count": 15, "item_count": 15, "soft_pair_count": 35, - "serialized_chars": 20704, - "estimated_input_tokens": 5176, - "estimated_eval_tokens": 10608 + "serialized_chars": 20708, + "estimated_input_tokens": 5177, + "estimated_eval_tokens": 10610 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is not a duplicate set; it\u2019s a loose family of distinct model-addition requests. The strongest near-neighbors are the Qwen3 audio support issues, but most other items are clearly different models/modalities (vision, OCR, detectors, BERT-like text models, etc.). Similarity appears driven mainly by a shared request template.", - "confidence": 0.96, - "canonical_issue_reason": "If one issue must represent the cluster, issue #43837 is the most central/connected request and is phrased as a broad support proposal. It still isn\u2019t a true umbrella for the rest, but it is the best cluster representative.", + "summary": "This is a loose cluster of model-support requests that share topical wording ('add/support model') but not the same underlying change. None of the soft edges look like true duplicates, so all are rejected. If a single representative issue is needed, the broadest umbrella-style request is the BERT-family/RoPE item.", + "confidence": 0.42, + "canonical_issue_reason": "issue:42738 is the broadest, most umbrella-like request in the set ('BERT-like models with RoPE'), so it best represents the BERT-family subset without being tied to one narrow model name.", "canonical_pr_reason": null, - "best_issue_reason": "Issue #43837 has the highest apparent soft-similarity centrality and sits closest to the only genuinely related subcluster (audio support requests).", + "best_issue_reason": "issue:42738 is the most general and reusable representative among the issues; the others are mostly model-specific requests spanning unrelated modalities and architectures.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:36817", "right": "issue:41211", "accept": false, - "reason": "Different model families: EuroBert vs DEIMv2. Same request pattern, not the same bug/change." + "reason": "Different model families; only the generic 'add model' wording overlaps." }, { "left": "issue:36817", "right": "issue:43671", "accept": false, - "reason": "BERT config addition vs Qwen3-TTS audio support; different modality and code path." + "reason": "EuroBert and Qwen3-TTS are unrelated model requests and code paths." }, { "left": "issue:36817", "right": "issue:36879", "accept": false, - "reason": "EuroBert config vs RF-DETR model; unrelated models despite similar wording." + "reason": "Both are model-add requests, but for different concrete models and domains." }, { "left": "issue:36879", "right": "issue:41211", "accept": false, - "reason": "RF-DETR and DEIMv2 are different architectures and would require different implementations." + "reason": "RF-DETR and DEIMv2 are distinct detection models, not the same change." }, { "left": "issue:36879", "right": "issue:43909", "accept": false, - "reason": "Object detection model vs audio model; not the same underlying change." + "reason": "Object detection vs audio model support; unrelated implementations." }, { "left": "issue:36879", "right": "issue:44121", "accept": false, - "reason": "Detector addition vs weight-sparse transformer architecture request; distinct code paths." + "reason": "Different architectures and product goals; not the same concrete fix." }, { "left": "issue:36879", "right": "issue:43837", "accept": false, - "reason": "RF-DETR and Qwen3-ASR are different model targets and modalities." + "reason": "Different tasks (detection vs ASR) and different model families." }, { "left": "issue:36879", "right": "issue:43671", "accept": false, - "reason": "RF-DETR vision model vs Qwen3-TTS audio support; clearly separate requests." + "reason": "Detection model request vs TTS request; no shared code path." }, { "left": "issue:37015", "right": "issue:43837", "accept": false, - "reason": "NeoBERT text model request vs Qwen3-ASR audio support; not a duplicate." + "reason": "NeoBERT and Qwen3-ASR are unrelated models and modalities." }, { "left": "issue:37015", "right": "issue:44121", "accept": false, - "reason": "NeoBERT and a sparse transformer request are different model additions, not one code-path fix." + "reason": "Different model families; only broad transformer overlap." }, { "left": "issue:37015", "right": "issue:43909", "accept": false, - "reason": "NeoBERT text model vs LFM2.5 Audio model; different domains." + "reason": "BERT-style encoder request vs audio model support." }, { "left": "issue:37015", "right": "issue:42503", "accept": false, - "reason": "NeoBERT and ModernVBERT are different model families; same pattern only." + "reason": "Related naming pattern, but these are separate model additions, not one bug/change." }, { "left": "issue:36879", "right": "issue:37015", "accept": false, - "reason": "RF-DETR and NeoBERT are unrelated model requests with different implementation surfaces." + "reason": "Different specific model requests; no evidence of the same underlying change." }, { "left": "issue:41115", "right": "issue:43837", "accept": false, - "reason": "MiniCPM3 architecture request vs Qwen3-ASR support; distinct underlying changes." + "reason": "MiniCPM3 and Qwen3-ASR address different model support paths." }, { "left": "issue:41115", "right": "issue:44121", "accept": false, - "reason": "MiniCPM3 architecture vs OpenAI weight-sparse transformer; different model implementations." + "reason": "Different model architectures; not mergeable as one PR-style fix." }, { "left": "issue:41115", "right": "issue:42503", "accept": false, - "reason": "MiniCPM3 architecture vs ModernVBERT models; different families, not duplicates." + "reason": "Both are model requests, but for distinct models with separate integration work." }, { "left": "issue:41115", "right": "issue:45027", "accept": false, - "reason": "MiniCPM3 and Voxtral TTS support are different models and modalities." + "reason": "MiniCPM3 vs Voxtral TTS are different model families and tasks." }, { "left": "issue:41211", "right": "issue:43671", "accept": false, - "reason": "DEIMv2 vs Qwen3-TTS; one is a detector-style model request, the other audio TTS support." + "reason": "DEIMv2 and Qwen3-TTS are unrelated requests." }, { "left": "issue:42503", "right": "issue:43837", "accept": false, - "reason": "ModernVBERT models and Qwen3-ASR support are unrelated beyond the general request template." + "reason": "ModernVBERT and Qwen3-ASR are distinct model additions." }, { "left": "issue:42503", "right": "issue:43671", "accept": false, - "reason": "ModernVBERT text/vision model request vs Qwen3-TTS audio support; different code changes." + "reason": "Different families and tasks; no shared concrete implementation." }, { "left": "issue:42503", "right": "issue:42738", "accept": false, - "reason": "ModernVBERT models vs generic BERT-like RoPE support; related theme but not the same concrete issue." + "reason": "ModernVBERT is a specific model request, while 42738 is a broader family-level request." }, { "left": "issue:42738", "right": "issue:45027", "accept": false, - "reason": "BERT-like RoPE support and Voxtral TTS support are different model families and changes." + "reason": "BERT-like RoPE models and Voxtral TTS are different domains." }, { "left": "issue:43671", "right": "issue:43837", "accept": false, - "reason": "Qwen3-TTS and Qwen3-ASR are the closest pair, but they are still distinct speech models with different support paths." + "reason": "Same base family name (Qwen3) but different modalities/tasks: TTS vs ASR." }, { "left": "issue:43671", "right": "issue:45027", "accept": false, - "reason": "Qwen3-TTS vs Voxtral TTS: same modality, but different models and no evidence of one shared fix." + "reason": "Both are TTS-related, but they target different model families and integration paths." }, { "left": "issue:43671", "right": "issue:45177", "accept": false, - "reason": "TTS support request vs DeepSeek-OCR2 model add; different modality and implementation." + "reason": "Speech synthesis vs OCR are unrelated changes." }, { "left": "issue:43671", "right": "issue:44121", "accept": false, - "reason": "Audio TTS support vs sparse transformer architecture request; unrelated change." + "reason": "Different model families and code paths; not the same change." }, { "left": "issue:43837", "right": "issue:45322", "accept": false, - "reason": "Qwen3-ASR audio support vs EUPE perception encoder request; different model and task." + "reason": "ASR support and EUPE are unrelated model requests." }, { "left": "issue:43837", "right": "issue:43909", "accept": false, - "reason": "Qwen3-ASR and LFM2.5 Audio 1.5B are different audio models; not a single duplicate issue." + "reason": "Both are audio-related, but they request different models and tasks." }, { "left": "issue:43909", "right": "issue:44205", "accept": false, - "reason": "LFM2.5 Audio 1.5B vs SAM3-LiteText are different model families and tasks." + "reason": "Audio model request vs segmentation/text model request; unrelated." + }, + { + "left": "issue:43671", + "right": "issue:43909", + "accept": false, + "reason": "Different audio model families and different concrete support work." }, { "left": "issue:44121", "right": "issue:45322", "accept": false, - "reason": "Weight-sparse transformer proposal vs EUPE encoder request; separate architecture changes." + "reason": "OpenAI sparse transformer and EUPE are different architectures with no shared fix." }, { "left": "issue:43837", "right": "issue:44121", "accept": false, - "reason": "Qwen3-ASR support vs sparse transformer proposal; different model targets and code paths." + "reason": "ASR model support and sparse transformer support are unrelated." }, { "left": "issue:43837", "right": "issue:45027", "accept": false, - "reason": "Qwen3-ASR and Voxtral TTS are distinct speech models; not mergeable as one PR/issue." + "reason": "Qwen3-ASR and Voxtral TTS are different speech tasks and model integrations." }, { "left": "issue:37015", "right": "issue:45027", "accept": false, - "reason": "NeoBERT text model request vs Voxtral TTS support; unrelated." + "reason": "NeoBERT and Voxtral TTS are unrelated model families/tasks." }, { "left": "issue:43837", "right": "issue:45177", "accept": false, - "reason": "Qwen3-ASR audio support vs DeepSeek-OCR2 model addition; different modality and implementation." + "reason": "Speech recognition vs OCR; not the same underlying request." } ] }, @@ -15393,12 +15287,12 @@ "issue:43668|issue:44031", "issue:43668|issue:43813" ], - "prepared_review_unit_hash": "7bce94b722d7d8a4d9c0f0789756aac88904616b2638d8f777db3b6e19533900", + "prepared_review_unit_hash": "ce14def5214907f448c730130aa08696445b4647727e2c946cc1cc0b1a7fd98b", "component_budget": { "node_count": 6, "item_count": 6, "soft_pair_count": 8, - "serialized_chars": 6291, + "serialized_chars": 6292, "estimated_input_tokens": 1573, "estimated_eval_tokens": 3402 }, @@ -15406,7 +15300,7 @@ "node_count": 6, "item_count": 6, "soft_pair_count": 8, - "serialized_chars": 6291, + "serialized_chars": 6292, "estimated_input_tokens": 1573, "estimated_eval_tokens": 3402 }, @@ -15415,60 +15309,60 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These issues are only loosely similar by wording; they describe distinct bugs across different models/components, so I would not merge any of the soft pairs as duplicates.", - "confidence": 0.74, - "canonical_issue_reason": "43668 is the most self-contained, narrowly scoped issue here, but it is not actually a duplicate of the others; it is just the clearest representative of the set.", + "summary": "These issues are thematically similar only at a very broad level (model/config/runtime bugs), but they describe distinct bugs in different components and code paths. I do not see any true duplicates in this cluster.", + "confidence": 0.96, + "canonical_issue_reason": "No single duplicate stands out; issue 43668 is the most self-contained and concrete report, so it is the best anchor if one must be chosen.", "canonical_pr_reason": null, - "best_issue_reason": "43668 has the cleanest single-action fix framing (a config type-hint mistake) and is the most concrete issue in the group, making it the best representative issue if one must be chosen.", + "best_issue_reason": "Issue 43668 is the clearest standalone bug report in the set (a specific ModernBERT config typing problem), but the cluster is too heterogeneous for a real canonical duplicate.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:37934", "right": "issue:43668", "accept": false, - "reason": "Different problems: Llama4 norm semantics vs a ModernBERT config type annotation." + "reason": "Different models and different defects: Llama4TextL2Norm/RMS-norm semantics vs ModernBERTConfig type-hint mismatch." }, { "left": "issue:42936", "right": "issue:43240", "accept": false, - "reason": "Both touch loss-related code, but one is about an unused ignore_value and the other about kwargs not being forwarded; not the same bug." + "reason": "Mask2Former ignore_value not being used is unrelated to kwargs not being forwarded into a loss function." }, { "left": "issue:42936", "right": "issue:44031", "accept": false, - "reason": "Mask2Former loss handling and tokenizer regex warnings are unrelated code paths." + "reason": "Mask2Former loss handling and tokenizer regex warnings are unrelated subsystems and bugs." }, { "left": "issue:42936", "right": "issue:43813", "accept": false, - "reason": "Different components and fixes: model loss behavior vs a quantization-string typo." + "reason": "Unused ignore_value in Mask2Former is not the same as a typo in a quantization-operation attribute name." }, { "left": "issue:42936", "right": "issue:43668", "accept": false, - "reason": "No concrete overlap beyond being model issues; one is a loss-parameter bug, the other a config type hint issue." + "reason": "Different component and failure mode: Mask2Former target handling vs ModernBERT config typing." }, { "left": "issue:43240", "right": "issue:43668", "accept": false, - "reason": "Forwarding kwargs to a loss function is unrelated to correcting a config field's type hint." + "reason": "Forwarding kwargs to a loss function is a runtime wiring bug; the other is a config type annotation issue." }, { "left": "issue:43668", "right": "issue:44031", "accept": false, - "reason": "A config typing error is not the same as a tokenizer regex warning regression." + "reason": "A config type hint bug is unrelated to tokenizer regex pattern warnings." }, { "left": "issue:43668", "right": "issue:43813", "accept": false, - "reason": "These are different typo-type issues in different areas, with no shared underlying fix." + "reason": "ModernBERTConfig norm_eps typing and a quantization-operation typo are distinct, non-overlapping issues." } ] }, @@ -15498,12 +15392,12 @@ "soft_pairs": [ "issue:41084|issue:43037" ], - "prepared_review_unit_hash": "c9e9479a23ca8a55240bfc63820206636873fb055beabaa0ecfeb018763b1ee0", + "prepared_review_unit_hash": "5c48b6205293bc4587f63b433d2fab725ed4f1ce19b00dfcdbe2c3be6247370e", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1480, + "serialized_chars": 1479, "estimated_input_tokens": 370, "estimated_eval_tokens": 996 }, @@ -15511,7 +15405,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1480, + "serialized_chars": 1479, "estimated_input_tokens": 370, "estimated_eval_tokens": 996 }, @@ -15520,18 +15414,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two issues do not appear to describe the same underlying bug or change: one asks for block decoding, the other for DeepSeek v3.2 model support.", - "confidence": 0.96, - "canonical_issue_reason": "Issue #43037 is the more concrete feature request, but it is not a duplicate of #41084.", + "summary": "The two issues are not duplicates: one asks for a general \"Set Block Decoding\" capability, while the other requests support for a specific model version (DeepSeek v3.2). They describe different features and likely different implementation work.", + "confidence": 0.95, + "canonical_issue_reason": "No canonical duplicate issue: the titles and likely scopes are too different to treat as the same underlying request.", "canonical_pr_reason": null, - "best_issue_reason": "#43037 is the better representative issue because it states a specific external model-support request, while #41084 is a separate decoding-related ask.", + "best_issue_reason": "Issue 43037 is the better standalone issue because it is more specific and actionable (a concrete model-support request).", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:41084", "right": "issue:43037", "accept": false, - "reason": "Different scopes and code paths: block decoding vs DeepSeek v3.2 support. They do not look like the same bug/change." + "reason": "Different feature requests with no clear shared code-path or identical bug/change; one is about block decoding generally, the other about DeepSeek v3.2 support." } ] }, @@ -15561,12 +15455,12 @@ "soft_pairs": [ "issue:43598|issue:43600" ], - "prepared_review_unit_hash": "e167fde6d97bb04f11d217fc2b1e17fa3479b4786ccf1227aff4293e24988313", + "prepared_review_unit_hash": "10b2486a99e5b29bafe09c4fa0ae9485521586c7b0bd7f8629a172db6ee7cbcd", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1584, + "serialized_chars": 1583, "estimated_input_tokens": 396, "estimated_eval_tokens": 1048 }, @@ -15574,7 +15468,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1584, + "serialized_chars": 1583, "estimated_input_tokens": 396, "estimated_eval_tokens": 1048 }, @@ -15583,18 +15477,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two issues are both about custom trainers in Trainer, but they describe different problems: one is about `remove_unused_column` and configurability, the other about FLOPS estimation for custom trainers. I do not consider them duplicates.", - "confidence": 0.96, - "canonical_issue_reason": "Issue 43598 is the cleaner representative because it states a specific Trainer behavior (`remove_unused_column`) and a concrete customizability concern.", + "summary": "The two issues are only loosely related by Trainer customization, but they describe different problems: one is about `remove_unused_column` behavior, the other about FLOPS estimation for custom trainers.", + "confidence": 0.88, + "canonical_issue_reason": "#43598 is the better anchor if one must be chosen because it is the more direct Trainer customization request; #43600 is a separate accounting/metrics concern rather than the same bug.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43598 is the more focused issue to keep as the representative Trainer customizability report; 43600 is a separate FLOPS-estimation problem.", + "best_issue_reason": "#43598 is the strongest representative issue in this cluster due to its clearer, broader customization focus; #43600 appears orthogonal and should not be treated as a duplicate.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43598", "right": "issue:43600", "accept": false, - "reason": "They share the broad theme of custom trainers, but the underlying bugs are different: one concerns column removal/customizability in Trainer, the other concerns estimating FLOPS. No shared code-path problem is evident." + "reason": "They share a general Trainer/custom trainer theme, but the underlying changes differ: unused-column removal customization vs FLOPS estimation logic. They would not plausibly be merged as one duplicate fix." } ] }, @@ -15624,12 +15518,12 @@ "soft_pairs": [ "issue:43684|issue:44405" ], - "prepared_review_unit_hash": "d89213433c427d935aadb6c88da895cebb3d92dc8fdd7f16a880c32bc86290eb", + "prepared_review_unit_hash": "308762975b97f4f6e474a961da303294953cddc3225a45a725b0802d627a5579", "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 }, @@ -15637,7 +15531,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1612, + "serialized_chars": 1611, "estimated_input_tokens": 403, "estimated_eval_tokens": 1062 }, @@ -15646,18 +15540,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are not duplicates: one requests Qwen3-Omni registration for AutoModel/AutoModelForConditionalGeneration, while the other requests AutoModelForSequenceClassification support for Qwen3.5. They involve different model families and different auto-class APIs.", - "confidence": 0.94, - "canonical_issue_reason": "Issue #43684 is the broader and more central API-registration request, so it is the better canonical issue if one must be chosen.", + "summary": "These are related only at a very broad level (Qwen model AutoModel support), but they target different model families and different heads/tasks, so they do not look like the same bug/change.", + "confidence": 0.93, + "canonical_issue_reason": "Issue 43684 is the broader and more central request: registering Qwen3-Omni with AutoModel/AutoModelForConditionalGeneration. It reads like the more general model-registration gap.", "canonical_pr_reason": null, - "best_issue_reason": "#43684 best represents the broader model registration gap; #44405 is a separate, narrower model-class support request.", + "best_issue_reason": "43684 is the best representative issue for the cluster because it covers the general AutoModel registration problem rather than a narrower task-specific variant.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43684", "right": "issue:44405", "accept": false, - "reason": "Different model families (Qwen3-Omni vs Qwen3.5) and different target APIs (AutoModel/AutoModelForConditionalGeneration vs AutoModelForSequenceClassification); not the same underlying bug." + "reason": "Different underlying requests: Qwen3-Omni registration for AutoModel/AutoModelForConditionalGeneration vs. Qwen3.5 sequence-classification support. They touch different configs and different auto classes, so they are not duplicates." } ] }, @@ -15694,70 +15588,70 @@ "issue:43845|issue:43859", "issue:43846|issue:43859" ], - "prepared_review_unit_hash": "00231f0d479a8781a620b3577ee282a5250009c70c58a8e19246a5870f8106ee", + "prepared_review_unit_hash": "5bd6c832b9dd168e0ae24ca6643a782b2f7cf41e7e424271eeb0ce6561e98aad", "component_budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 4261, - "estimated_input_tokens": 1066, - "estimated_eval_tokens": 2388 + "serialized_chars": 4265, + "estimated_input_tokens": 1067, + "estimated_eval_tokens": 2390 }, "budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 4261, - "estimated_input_tokens": 1066, - "estimated_eval_tokens": 2388 + "serialized_chars": 4265, + "estimated_input_tokens": 1067, + "estimated_eval_tokens": 2390 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster looks like low-signal issue noise: three near-identical closed issues titled \"huggingface \" and one unrelated closed issue titled \"Fett\". The repeated \"huggingface\" issues are the closest match, but there is not enough actual problem description to confidently treat them as the same underlying bug report; the \"Fett\" issue appears separate.", - "confidence": 0.61, - "canonical_issue_reason": "issue:43845 is the best issue representative because it is the earliest of the three identical \"huggingface \" reports and can stand in for that mini-cluster if one must be chosen.", + "summary": "This cluster is dominated by low-information, likely unrelated issues with generic titles; there is no strong evidence of a shared underlying bug. The two identical \"huggingface\" issues are the closest pair, but still too underspecified to confidently treat as duplicates.", + "confidence": 0.41, + "canonical_issue_reason": "Issue 43845 is the best available issue representative because it is one of the repeated \"huggingface\" reports, is earlier than 43846/43859, and is more on-theme than the outlier titled \"Fett\".", "canonical_pr_reason": null, - "best_issue_reason": "issue:43845 is the best overall issue candidate: it is one of the repeated identical titles and is earliest, while issue:43835 does not fit the same apparent topic.", + "best_issue_reason": "43845 is the strongest cluster representative by title similarity and recency among the repeated reports, though the evidence is weak due to the lack of substantive body text.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43835", "right": "issue:43845", "accept": false, - "reason": "Different titles and no shared content beyond weak similarity; no evidence they describe the same bug or change." + "reason": "Titles are different and there is no body/detail evidence showing the same bug." }, { "left": "issue:43835", "right": "issue:43846", "accept": false, - "reason": "\"Fett\" is unrelated to the repeated \"huggingface\" reports; insufficient evidence of a shared underlying issue." + "reason": "Titles are different and there is no body/detail evidence showing the same bug." }, { "left": "issue:43835", "right": "issue:43859", "accept": false, - "reason": "No meaningful overlap besides generic soft similarity; appears to be a different issue." + "reason": "Titles are different and there is no body/detail evidence showing the same bug." }, { "left": "issue:43845", "right": "issue:43846", "accept": false, - "reason": "Titles are identical, but there is no body detail or target evidence to confirm the same underlying bug report, so do not merge." + "reason": "Identical generic titles are not enough; there is no description or issue-target evidence that they report the same underlying problem." }, { "left": "issue:43845", "right": "issue:43859", "accept": false, - "reason": "Very similar placeholder titles, but no substantive description or explicit linkage showing the same issue." + "reason": "Similar generic titles, but insufficient substantive evidence to confirm the same bug." }, { "left": "issue:43846", "right": "issue:43859", "accept": false, - "reason": "Same generic title pattern, but not enough concrete evidence to conclude they are duplicates of the same report." + "reason": "Similar generic titles, but insufficient substantive evidence to confirm the same bug." } ] }, @@ -15798,88 +15692,88 @@ "issue:44572|issue:44937", "issue:44573|issue:44937" ], - "prepared_review_unit_hash": "e7bbcd8b951d2ca0d8ad3044817f16d05da184122403928beede05b8329ab211", + "prepared_review_unit_hash": "c87f2ba32eda7b2a8280a48ef5c544f3771007c9918166364d59f43e8d9521f2", "component_budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 9, - "serialized_chars": 5791, - "estimated_input_tokens": 1448, - "estimated_eval_tokens": 3152 + "serialized_chars": 5785, + "estimated_input_tokens": 1447, + "estimated_eval_tokens": 3150 }, "budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 9, - "serialized_chars": 5791, - "estimated_input_tokens": 1448, - "estimated_eval_tokens": 3152 + "serialized_chars": 5785, + "estimated_input_tokens": 1447, + "estimated_eval_tokens": 3150 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster contains only spammy or generic placeholder issues with no real bug/change details. There is not enough substantive evidence to treat any pair as the same underlying issue.", + "summary": "This cluster is mostly spammy or placeholder issues with no shared concrete bug or change, so there is no real duplicate set here.", "confidence": 0.97, - "canonical_issue_reason": null, + "canonical_issue_reason": "Issue 44418 is the only semi-descriptive title, but the cluster is still too vague and unrelated to treat it as a true canonical duplicate.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 44418 is the only non-placeholder title, but it is still too vague to act as a canonical duplicate target.", + "best_issue_reason": "No issue in this cluster is a good global representative; the items are spam or unrelated prompts, not the same underlying problem.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44371", "right": "issue:44572", "accept": false, - "reason": "Both are just \"\" placeholders; no concrete bug or change is described." + "reason": "Both are spam placeholders; no shared concrete bug or topic." }, { "left": "issue:44371", "right": "issue:44573", "accept": false, - "reason": "Both are just \"\" placeholders; no concrete bug or change is described." + "reason": "Both are spam placeholders, but not the same underlying issue." }, { "left": "issue:44371", "right": "issue:44418", "accept": false, - "reason": "One item is spam and the other is a generic documentation suggestion; no clear shared underlying problem." + "reason": "Spam placeholder vs generic documentation suggestion; unrelated." }, { "left": "issue:44371", "right": "issue:44937", "accept": false, - "reason": "\"\" and \"Check out \\\"Google LLC\\\"\" are unrelated low-signal posts, not the same issue." + "reason": "Spam placeholder vs unrelated \"Google LLC\" prompt; not a duplicate." }, { "left": "issue:44418", "right": "issue:44572", "accept": false, - "reason": "A vague documentation suggestion is not the same underlying item as a spam placeholder." + "reason": "Generic documentation suggestion vs spam placeholder; no common concrete problem." }, { "left": "issue:44418", "right": "issue:44573", "accept": false, - "reason": "A vague documentation suggestion is not the same underlying item as a spam placeholder." + "reason": "Generic documentation suggestion vs spam placeholder; unrelated." }, { "left": "issue:44572", "right": "issue:44573", "accept": false, - "reason": "They share the placeholder title \"\", but there is no evidence of a real common bug/change to dedupe." + "reason": "Both are spam placeholders, but there is no evidence they describe the same bug or change." }, { "left": "issue:44572", "right": "issue:44937", "accept": false, - "reason": "Spam placeholder versus unrelated promotional-looking title; no common issue is evident." + "reason": "Spam placeholder vs unrelated named prompt; not the same issue." }, { "left": "issue:44573", "right": "issue:44937", "accept": false, - "reason": "Spam placeholder versus unrelated promotional-looking title; no common issue is evident." + "reason": "Spam placeholder vs unrelated named prompt; not a duplicate." } ] }, @@ -15909,7 +15803,7 @@ "soft_pairs": [ "issue:45145|issue:45151" ], - "prepared_review_unit_hash": "9ddbcf0b465ec598fb5e394d43695536f3fb1dcfd2cc2aca2da2694a6c50be9a", + "prepared_review_unit_hash": "e6187a3e629fb37e31d3894ec45bde7f84369a3b27ae4f484936f3f088e8578e", "component_budget": { "node_count": 2, "item_count": 2, @@ -15931,28 +15825,28 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These closed issues are highly similar and likely refer to the same proposal, but the packet only exposes title-level similarity plus a soft-similarity signal, not the full bodies. #45145 is the better canonical issue because it was created earlier and already has one inbound reference.", - "confidence": 0.9, - "canonical_issue_reason": "#45145 is the earlier of the two and has an inbound reference, so it is the best representative among these highly similar issues.", + "summary": "The two issues are highly similar and likely related, but the packet does not prove they are exact duplicates. #45145 remains the best canonical issue because it was created first and already has an inbound reference, while #45151 can be treated as a near-match rather than a confirmed duplicate.", + "confidence": 0.78, + "canonical_issue_reason": "#45145 is the better canonical issue because it was created earlier and already has one inbound reference, so it is the more established thread for this topic.", "canonical_pr_reason": null, - "best_issue_reason": "#45145 is the strongest issue to keep as the representative item because it predates #45151 and already has some linkage.", + "best_issue_reason": "#45145 is the best issue representative for the cluster because it is the earliest instance and has the only inbound reference, but the evidence only supports near-duplication, not indistinguishability.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45145", "right": "issue:45151", - "accept": true, - "reason": "The issues have identical titles and a soft-similarity signal, so they likely describe the same underlying proposal. However, the evidence is limited to metadata/title similarity, so this should be treated conservatively as a likely duplicate rather than a proven one." + "accept": false, + "reason": "The available evidence is limited to identical titles, similar body lengths, and a soft_similarity signal. That supports a likely related/near-duplicate relationship, but not a confident conclusion that they are the same underlying issue." } ] }, "evaluator_result": { "accept": false, - "feedback": "The canonical-issue choice is grounded (#45145 is earlier and has one inbound reference), but the duplicate summary overstates the evidence. The packet only shows identical titles and a soft_similarity signal; it does not provide body text, and there is at least one metadata difference (inbound references, discussion activity). Please phrase the relationship more conservatively rather than as a definite duplicate with no differentiating metadata." + "feedback": "The canonical-choice rationale is grounded (earlier creation time and one inbound reference for #45145), but the cluster summary and soft-edge verdict overstate the evidence. The packet only shows identical titles, similar body lengths, and a soft_similarity signal; it does not establish that these issues are exact duplicates or that their substance is indistinguishable. A more conservative verdict would be that they are highly similar and likely related, not definitively the same issue." }, "evaluator_used": true, "retried": true, - "accepted_nontrivial_soft_edge": true, + "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null }, @@ -16029,7 +15923,7 @@ "soft_pairs": [ "issue:45672|issue:45674" ], - "prepared_review_unit_hash": "890dbd0fdb68e3b06e9497e839d856c363107b8050d9b81c43fe936741da6cad", + "prepared_review_unit_hash": "e6c636be2f7ba7a249c6ac36d82d99ade01b30da5e285e0f7bdcc16057073db3", "component_budget": { "node_count": 2, "item_count": 2, @@ -16051,18 +15945,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both issues concern 4-bit inference with bitsandbytes, but they describe different failures: one is a Gemma4 audio-module dtype/finfo TypeError, the other is a BitsAndBytesConfig skip-modules regression that removes the default lm_head exclusion and triggers an AssertionError. They are related by area, not the same bug.", - "confidence": 0.95, - "canonical_issue_reason": "Issue 45674 is the better representative because it states a clearer, more general configuration regression in 4-bit inference with an explicit causal mechanism and likely broader impact.", + "summary": "These two open issues both concern 4-bit inference, but they describe different bugs with different failure points: one is a Gemma4 audio-module `torch.finfo()` TypeError on `uint8` weights, the other is a BitsAndBytesConfig regression where `llm_int8_skip_modules` drops the default `lm_head` exclusion and triggers an AssertionError. They should not be merged as duplicates.", + "confidence": 0.93, + "canonical_issue_reason": "No clear canonical duplicate: the reports describe separate root causes and distinct code paths. If one must be kept as the cluster representative, issue #45674 is slightly better as the more general configuration regression report.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45674 is the strongest standalone report here: it names the concrete failing behavior, the triggering config field, and the affected inference mode.", + "best_issue_reason": "Issue #45674 is the better representative because it states the configuration regression and expected-vs-actual behavior more directly, making it easier to route and triage.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45672", "right": "issue:45674", "accept": false, - "reason": "Same broad 4-bit/bitsandbytes area, but different root causes and symptoms: Gemma4 audio-module torch.finfo on uint8 weights vs. llm_int8_skip_modules clearing the default lm_head exclusion. Not the same underlying bug." + "reason": "Reject: both are 4-bit inference problems, but one is a Gemma4 audio-module `torch.finfo()` type issue on `uint8` weights while the other is an `llm_int8_skip_modules`/`lm_head` exclusion regression causing AssertionError. Different bugs, not one fix." } ] }, @@ -16092,7 +15986,7 @@ "soft_pairs": [ "issue:45762|issue:45763" ], - "prepared_review_unit_hash": "8c64f10158c95dc58d66f1158d5427c3f5d4605f42fe2a3338b96d58c47cecbb", + "prepared_review_unit_hash": "979e58bbff4e03746f2a84f09d1ec77430969d2ad00383a1e10461f512df9c77", "component_budget": { "node_count": 2, "item_count": 2, @@ -16114,18 +16008,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two issues appear unrelated: both are closed, empty-body issues that look like personal-name/date entries rather than the same bug report. I would not cluster them as duplicates.", - "confidence": 0.98, - "canonical_issue_reason": null, + "summary": "These two closed issues do not look like duplicates; they are unrelated name/date entries and appear to be spam or placeholder posts rather than the same bug report.", + "confidence": 0.96, + "canonical_issue_reason": "No single canonical issue is appropriate here because the two issues are not about the same underlying problem.", "canonical_pr_reason": null, - "best_issue_reason": "Neither issue is a strong canonical representative; both are essentially standalone spam/placeholder entries with no technical content to anchor a duplicate set.", + "best_issue_reason": "Neither issue is a good global representative: both are unrelated, content-free entries with no shared technical problem.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45762", "right": "issue:45763", "accept": false, - "reason": "The titles contain different personal names and different dates, with no shared bug description, code area, or issue target; they do not appear to describe the same underlying problem." + "reason": "Different personal-name/date titles with no body, links, or technical context; they do not appear to describe the same bug or change." } ] }, @@ -16155,40 +16049,40 @@ "soft_pairs": [ "issue:45764|issue:45765" ], - "prepared_review_unit_hash": "53f6e19a969e1068ad7c98c35d86bb49a1e848f883916359e664f415cc0d3522", + "prepared_review_unit_hash": "cd93425d808271a24112ee43f8b412cba57e5b8ce9016dbbca69d7eb1d1b7724", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1481, - "estimated_input_tokens": 371, - "estimated_eval_tokens": 998 + "serialized_chars": 1480, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 }, "budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1481, - "estimated_input_tokens": 371, - "estimated_eval_tokens": 998 + "serialized_chars": 1480, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two closed issues look like unrelated low-information reports with different names and dates; there is no evidence they describe the same bug or request.", - "confidence": 0.97, - "canonical_issue_reason": "issue:45764 is slightly more suitable as canonical only because it has the earlier timestamp, but it contains no actionable content.", + "summary": "The two closed issues are unrelated name/date placeholders with no body or shared technical context, so they should not be clustered as duplicates.", + "confidence": 0.99, + "canonical_issue_reason": "Neither issue contains substantive content, and the titles are distinct personal-name/date strings with no evidence of the same problem.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45764 is the best available issue representative by chronology, not by substantive detail.", + "best_issue_reason": "No issue here is meaningfully better as a canonical duplicate target; both are empty and unrelated.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45764", "right": "issue:45765", "accept": false, - "reason": "Titles differ by person/name and date; there is no shared description, target, filename, or other evidence of the same underlying issue." + "reason": "The titles do not describe the same bug or request, and there is no body, linkage, or shared technical context connecting them." } ] }, @@ -16202,7 +16096,7 @@ { "label": "pull_request", "component_index": 1, - "component_count": 27, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16237,8 +16131,8 @@ "pull_request:43424|pull_request:43823", "pull_request:43823|pull_request:45655", "pull_request:43823|pull_request:43995", - "pull_request:43995|pull_request:45213", "pull_request:43995|pull_request:44827", + "pull_request:43995|pull_request:45213", "pull_request:44827|pull_request:45170", "pull_request:44827|pull_request:45795", "pull_request:44827|pull_request:45655", @@ -16247,12 +16141,12 @@ "pull_request:43823|pull_request:45795", "pull_request:43251|pull_request:43254" ], - "prepared_review_unit_hash": "9168ee145853d6467a866b02d1c892f9c28c69d1f94f18832bec19781b0f1559", + "prepared_review_unit_hash": "fd665eb0087351da1f1690706793c539736fa805e7890d8621e6035e839fec27", "component_budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 19, - "serialized_chars": 35205, + "serialized_chars": 35206, "estimated_input_tokens": 8802, "estimated_eval_tokens": 17860 }, @@ -16260,7 +16154,7 @@ "node_count": 13, "item_count": 13, "soft_pair_count": 19, - "serialized_chars": 35205, + "serialized_chars": 35206, "estimated_input_tokens": 8802, "estimated_eval_tokens": 17860 }, @@ -16269,135 +16163,135 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is mostly unrelated PRs. The only genuine duplicate/overlap is the pair of `fixed_cross_entropy` patches, which target the same code path and same issue; all other pairs are just broad topical similarity or shared subsystem noise.", - "confidence": 0.98, + "summary": "The cluster is mostly unrelated PRs grouped by broad subsystem similarity. The only true duplicate is the pair of `fixed_cross_entropy` patches for issue 43240; all other soft links are too coarse and should remain separate.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #43254 is the cleanest representative of the only real overlap: it updates `fixed_cross_entropy` to accept supported kwargs (`weight`, `label_smoothing`) in the same file and for the same issue target as the other patch.", + "canonical_pr_reason": "`pull_request:43251` is a valid canonical anchor for the only real duplicate pair because it is explicitly tied to issue 43240 and makes the same `fixed_cross_entropy` kwargs-forwarding change in `src/transformers/loss/loss_utils.py` as `pull_request:43254`.", "best_issue_reason": null, - "best_pr_reason": "PR #43254 is the best global anchor for the cluster because it is the most directly aligned with the only true duplicate pair and has the clearest, broader description of the fix.", + "best_pr_reason": "`pull_request:43251` is the best cluster PR candidate because it belongs to the only accepted duplicate pair, is issue-linked to 43240, and clearly expresses the cross-entropy kwargs fix in the same file as the matching PR.", "soft_edge_verdicts": [ { "left": "pull_request:39895", "right": "pull_request:43424", "accept": false, - "reason": "Different features: a Videoprism model addition vs an Executorch dynamic-shape test. No shared code-path bug or mergeable single change." + "reason": "VideoPrism model addition and ExecuTorch dynamic-shape test are unrelated changes." }, { "left": "pull_request:41855", "right": "pull_request:43823", "accept": false, - "reason": "Different artifacts: tokenizer API additions for MistralCommon vs adding the MobileLLM model. Similarity is only generic model/tokenizer work." + "reason": "Mistral tokenizer helper methods and a new MobileLLM model are different code paths and fixes." }, { "left": "pull_request:41855", "right": "pull_request:43424", "accept": false, - "reason": "Tokenizer method addition vs Executorch export test; unrelated changes and not the same underlying bug or feature." + "reason": "Tokenizer API additions and exportability tests are not the same underlying change." }, { "left": "pull_request:42668", "right": "pull_request:43823", "accept": false, - "reason": "Processor auto-loading robustness vs adding a new model implementation. Same broad area, but not the same concrete change." + "reason": "Processor robustness work and a new model implementation are unrelated." }, { "left": "pull_request:43251", "right": "pull_request:43823", "accept": false, - "reason": "Cross-entropy kwargs fix vs adding MobileLLM. No overlap in code path or fix intent." + "reason": "Cross-entropy kwargs forwarding and MobileLLM model creation are unrelated." }, { "left": "pull_request:43251", "right": "pull_request:44827", "accept": false, - "reason": "Cross-entropy helper fix vs Mistral4 test/model changes. Different issue and different subsystem behavior." + "reason": "Loss utility kwargs fix and Mistral4 test/model work address different bugs." }, { "left": "pull_request:43424", "right": "pull_request:44827", "accept": false, - "reason": "Executorch dynamic-shape test vs Mistral4 fixes. Both are tests-focused but address unrelated problems." + "reason": "ExecuTorch export tests and Mistral4 fixes are separate changes." }, { "left": "pull_request:43424", "right": "pull_request:43823", "accept": false, - "reason": "Executorch exportability test vs new MobileLLM model. No shared bug or code path." + "reason": "Dynamic-shape export testing and MobileLLM model addition are unrelated." }, { "left": "pull_request:43823", "right": "pull_request:45655", "accept": false, - "reason": "New model addition vs config resolution order fix. Unrelated changes." + "reason": "New MobileLLM model code and config-resolution ordering fix are different changes." }, { "left": "pull_request:43823", "right": "pull_request:43995", "accept": false, - "reason": "New model addition vs Falcon output-capture refactor. Same area of Transformers, but not the same concrete change." + "reason": "MobileLLM model work and Falcon output-interface refactoring are unrelated." }, { "left": "pull_request:43995", - "right": "pull_request:45213", + "right": "pull_request:44827", "accept": false, - "reason": "Falcon refactor vs model-creation skill/docs. The skill PR is tooling/documentation, not the same code-path fix." + "reason": "Falcon refactor and Mistral4 test fixes do not target the same bug or code path." }, { "left": "pull_request:43995", - "right": "pull_request:44827", + "right": "pull_request:45213", "accept": false, - "reason": "Falcon output-interface refactor vs Mistral4 tests. Different models and different changes." + "reason": "Falcon refactoring and the model-creation skill/meta PR are not the same artifact." }, { "left": "pull_request:44827", "right": "pull_request:45170", "accept": false, - "reason": "Mistral4 test/model adjustments vs a layernorm renaming migration. Unrelated patches." + "reason": "Mistral4 test/model fixes and `layrnorm` renaming are separate changes." }, { "left": "pull_request:44827", "right": "pull_request:45795", "accept": false, - "reason": "Mistral4 tests vs docs for audio/video processors. No shared underlying bug or change." + "reason": "Mistral4 fixes and audio/video processor docs are unrelated." }, { "left": "pull_request:44827", "right": "pull_request:45655", "accept": false, - "reason": "Mistral4 changes vs `cls.config` resolution ordering fix. Different code paths and purposes." + "reason": "Mistral4 work and `cls.config` resolution ordering fix are different issues." }, { "left": "pull_request:44827", "right": "pull_request:45213", "accept": false, - "reason": "Model test fixes vs the model-creation skill draft. Not the same artifact type or bug." + "reason": "They both touch modeling-related areas, but the PRs address different problems and should not be merged as duplicates." }, { "left": "pull_request:43823", "right": "pull_request:45213", "accept": false, - "reason": "New model implementation vs tooling/skill scaffolding. Only superficial topic overlap." + "reason": "MobileLLM model implementation and model-creation skill/meta PR are not the same change." }, { "left": "pull_request:43823", "right": "pull_request:45795", "accept": false, - "reason": "New model implementation vs docs updates for audio/video processors. Not the same underlying change." + "reason": "MobileLLM model code and audio/video processor docs are unrelated." }, { "left": "pull_request:43251", "right": "pull_request:43254", "accept": true, - "reason": "Both PRs patch `src/transformers/loss/loss_utils.py` to extend `fixed_cross_entropy` with supported kwargs (`weight`, `label_smoothing`) for the same issue target. They are functionally the same fix and could be merged into one PR." + "reason": "Both PRs change `src/transformers/loss/loss_utils.py` to forward supported kwargs into `nn.functional.cross_entropy` for the same issue 43240, so they are the same underlying fix." } ] }, "evaluator_result": { - "accept": true, - "feedback": "The summary is well grounded in the packet: the only clearly supported duplicate is PRs #43251 and #43254, which both modify `src/transformers/loss/loss_utils.py` for issue target 43240. The rest of the pairwise rejections are conservative and consistent with the evidence (mostly broad topical similarity without shared files or targets)." + "accept": false, + "feedback": "The overall cluster read is mostly grounded, but the canonical PR rationale overstates what the packet shows: there is evidence that 43251 and 43254 are the same fix on the same file/issue, but not that 43251 is the \"more complete/representative\" implementation. That comparative claim is not supported by the diff previews. The soft-edge rejections are otherwise conservative." }, "evaluator_used": true, - "retried": false, + "retried": true, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -16405,7 +16299,7 @@ { "label": "pull_request", "component_index": 2, - "component_count": 27, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16421,7 +16315,7 @@ "soft_pairs": [ "pull_request:40546|pull_request:42781" ], - "prepared_review_unit_hash": "aa50d60bc45291d6729835ea44cc9d75899276b79192dc3c36e0223c6b803e5c", + "prepared_review_unit_hash": "72e0cd2e1c1c2476e54577fc5dca0bc6e5a60b38d8cc219834f27d0842ecd387", "component_budget": { "node_count": 2, "item_count": 2, @@ -16443,18 +16337,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open PRs in the same VibeVoice area, but they are not duplicates: one adds the base VibeVoice model/docs, while the other adds VibeVoice Realtime plus acoustic-tokenizer work and extra generation/runtime changes.", - "confidence": 0.88, + "summary": "Two related but distinct VibeVoice PRs: one for the core model integration, one for a realtime extension with acoustic-tokenizer work. They overlap heavily in shared model/auto-registration files, but they do not look like the same underlying change.", + "confidence": 0.83, "canonical_issue_reason": null, - "canonical_pr_reason": "42781 is the broader and more recent VibeVoice submission, covering realtime support and the acoustic tokenizer in addition to the core model work, so it is the better representative of this cluster.", + "canonical_pr_reason": "PR 40546 is the broader base VibeVoice implementation and reads as the foundational integration; 42781 is a later, narrower realtime follow-up that extends the stack with additional tokenizer/generation work.", "best_issue_reason": null, - "best_pr_reason": "42781 best represents the cluster because it subsumes the base VibeVoice integration and extends it with the realtime/tokenizer stack; 40546 is a narrower earlier model-only PR.", + "best_pr_reason": "PR 40546 is the best representative of the cluster because it covers the primary VibeVoice model bring-up, whereas 42781 is a specialized realtime variant rather than the same change.", "soft_edge_verdicts": [ { "left": "pull_request:40546", "right": "pull_request:42781", "accept": false, - "reason": "Shared VibeVoice files do not mean the same change: 40546 is core VibeVoice model/docs, while 42781 adds VibeVoice Realtime and the acoustic tokenizer with additional generation changes. These are related but not the same concrete fix and would not cleanly merge as one PR." + "reason": "Shared filenames are not enough here: 40546 implements VibeVoice itself, while 42781 adds a realtime flavor and acoustic tokenizer support. They touch related code paths but are not the same concrete change and would not plausibly merge into one PR as duplicates." } ] }, @@ -16468,7 +16362,7 @@ { "label": "pull_request", "component_index": 3, - "component_count": 27, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16484,7 +16378,7 @@ "soft_pairs": [ "pull_request:40755|pull_request:41224" ], - "prepared_review_unit_hash": "590150e26e4f6c24925dc59929a83531271014d5bfc50755f538332100d8e4d7", + "prepared_review_unit_hash": "626103e09780be5f86af888af0a111e4bafc161c45a0c9d4256edd74d38a43df", "component_budget": { "node_count": 2, "item_count": 2, @@ -16506,18 +16400,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two PRs are unrelated feature additions: one adds covariate forecasting for TimesFM, the other adds DINOv3 image classification support. They do not fix the same code path and should not be clustered as duplicates.", + "summary": "These are unrelated feature PRs in different model families: TimesFM covariate forecasting vs. DINOv3 image-classification support. The soft similarity signal is too weak to treat them as the same underlying change.", "confidence": 0.99, "canonical_issue_reason": null, - "canonical_pr_reason": "No single canonical PR: the changes target different models and different features, with no overlapping bug or implementation path.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "PR 41224 is the cleaner representative of its own feature area: a focused DINOv3 image-classification addition with a concrete model/code path.", + "best_pr_reason": "PR 41224 is the more focused, self-contained feature PR, but it is not a duplicate of 40755; the cluster does not have a true canonical PR.", "soft_edge_verdicts": [ { "left": "pull_request:40755", "right": "pull_request:41224", "accept": false, - "reason": "Different components and behaviors: TimesFM covariate forecasting vs. DINOv3 image classification. They are not the same underlying change and could not plausibly be merged into one PR." + "reason": "Different code paths and goals: 40755 adds TimesFM forecasting with covariates, while 41224 adds DINOv3 image-classification support." } ] }, @@ -16531,7 +16425,7 @@ { "label": "pull_request", "component_index": 4, - "component_count": 27, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16594,7 +16488,7 @@ { "label": "pull_request", "component_index": 5, - "component_count": 27, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16612,46 +16506,46 @@ "pull_request:41797|pull_request:45186", "pull_request:45186|pull_request:45630" ], - "prepared_review_unit_hash": "e4c2c41d2ed203152364fe537989e12dcfe1e5965a859355bc479e2cfd646f9c", + "prepared_review_unit_hash": "a513eb7bbac9c979889d9248767be3ff027b4d9aafcefe70506a68ecb8fc56bc", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 10428, - "estimated_input_tokens": 2607, - "estimated_eval_tokens": 5470 + "serialized_chars": 10429, + "estimated_input_tokens": 2608, + "estimated_eval_tokens": 5472 }, "budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 10428, - "estimated_input_tokens": 2607, - "estimated_eval_tokens": 5470 + "serialized_chars": 10429, + "estimated_input_tokens": 2608, + "estimated_eval_tokens": 5472 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are three separate model-addition PRs, not duplicates. They share Transformers integration scaffolding, but each targets a different model family and codepath.", + "summary": "All three pull requests are separate model additions (DeepSeek OCR, Isaac, Kimi2-6) that share Hugging Face model-registration scaffolding but do not fix the same underlying bug or implement the same change.", "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR: DeepSeek OCR, Isaac, and Kimi2-6 are distinct additions with separate configs, processors, models, and tests.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "No single best PR for deduplication; if forced to pick a representative, Kimi2-6 is the broadest integration, but it still addresses a different model than the others.", + "best_pr_reason": "None of these PRs is a duplicate of the others; they target different models and cannot be safely consolidated into one change.", "soft_edge_verdicts": [ { "left": "pull_request:41797", "right": "pull_request:45186", "accept": false, - "reason": "Different model families and different changes: DeepSeek OCR vs Isaac. Shared auto/docs scaffolding is not enough to treat them as the same PR." + "reason": "Different model integrations for DeepSeek OCR vs Isaac. Shared auto-registration/docs/test plumbing is generic boilerplate, not evidence of the same concrete change." }, { "left": "pull_request:45186", "right": "pull_request:45630", "accept": false, - "reason": "Isaac and Kimi2-6 are separate model additions with different files and features. They do not fix the same concrete code-path problem." + "reason": "Different model integrations for Isaac vs Kimi2-6. They overlap only in broad Transformers model-support scaffolding and do not appear mergeable into one PR." } ] }, @@ -16665,7 +16559,7 @@ { "label": "pull_request", "component_index": 6, - "component_count": 27, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16681,7 +16575,7 @@ "soft_pairs": [ "pull_request:42975|pull_request:42976" ], - "prepared_review_unit_hash": "63d4614cc38dac6411b0de51232e02a426697c6a54d24ac5d3cd36da4562f937", + "prepared_review_unit_hash": "69714920e8bac28b0cc36558180747922ef785f93b2ec2fc91756ba5f138984f", "component_budget": { "node_count": 2, "item_count": 2, @@ -16703,18 +16597,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two distinct GitHub Actions maintenance PRs: one is a Node 24 compatibility sweep for workflow actions, the other is a separate bump of Docker/build-related actions to newer versions. They overlap in workflow files but address different dependencies and migration goals.", - "confidence": 0.94, + "summary": "Two unrelated GitHub Actions dependency-upgrade PRs: one for general workflow action compatibility with Node 24, and one specifically upgrading docker/build-push-action. They overlap in workflow files but do not fix the same concrete problem.", + "confidence": 0.95, "canonical_issue_reason": null, - "canonical_pr_reason": "pull_request:42975 is the better canonical PR because it has a clearer, narrower purpose: upgrading workflow actions specifically for Node 24 compatibility across CI/review-related workflows.", + "canonical_pr_reason": "PR 42975 is the better canonical representative because it is the broader, more cohesive workflow-actions compatibility upgrade and touches more of the affected CI surface.", "best_issue_reason": null, - "best_pr_reason": "pull_request:42975 is the strongest representative of the cluster because its title and diff show a concrete compatibility-driven maintenance change; 42976 is a separate version-bump PR focused on Docker/build actions.", + "best_pr_reason": "PR 42975 is the strongest standalone PR in the cluster: it has the clearer overarching goal (Node 24 compatibility) and the widest workflow coverage.", "soft_edge_verdicts": [ { "left": "pull_request:42975", "right": "pull_request:42976", "accept": false, - "reason": "Reject: these are not the same underlying change. 42975 is a broad GitHub Actions upgrade for Node 24 compatibility, while 42976 specifically bumps docker/build-push-action and a few other actions to latest versions. Shared workflow files alone are not enough to merge them as duplicates." + "reason": "They are different dependency bumps with different targets and intents: general GitHub Actions runtime compatibility vs docker/build-push-action upgrade. Shared workflow files are not enough to treat them as the same change." } ] }, @@ -16728,7 +16622,7 @@ { "label": "pull_request", "component_index": 7, - "component_count": 27, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16757,88 +16651,88 @@ "pull_request:44601|pull_request:45838", "pull_request:45490|pull_request:45838" ], - "prepared_review_unit_hash": "5bc024c69eb0b45bbab5ae2b9cd2c007ebc689ad156493d5fc93fb79317db6ce", + "prepared_review_unit_hash": "ad8c8bdae803d7d2c8eae826a7de8701331aaba6773b412a0337dc0a9ad37ab8", "component_budget": { "node_count": 7, "item_count": 7, "soft_pair_count": 9, - "serialized_chars": 23507, - "estimated_input_tokens": 5877, - "estimated_eval_tokens": 12010 + "serialized_chars": 23512, + "estimated_input_tokens": 5878, + "estimated_eval_tokens": 12012 }, "budget": { "node_count": 7, "item_count": 7, "soft_pair_count": 9, - "serialized_chars": 23507, - "estimated_input_tokens": 5877, - "estimated_eval_tokens": 12010 + "serialized_chars": 23512, + "estimated_input_tokens": 5878, + "estimated_eval_tokens": 12012 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "No true duplicates here. The soft edges are only superficial similarity between separate model-addition PRs, plus one unrelated distributed-loading PR; all candidate duplicate links should be rejected.", - "confidence": 0.95, + "summary": "No true duplicates here. The apparent overlaps are mostly shared Hugging Face boilerplate (docs/toctree, auto registries) across unrelated model-addition PRs, plus one separate distributed-loading infra PR.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "No single canonical PR: the cluster mixes unrelated additions for different models/features (Molmo, Molmo2, Lfm2 Audio, CTSM, PP-OCRv6, and pipeline-parallel infra), so there is no shared underlying change.", + "canonical_pr_reason": "No single canonical PR: the shared filenames are generic model-registration/docs scaffolding, while the PRs introduce different models or an unrelated pipeline-parallel loading change.", "best_issue_reason": null, - "best_pr_reason": "If forced to pick one representative, PR 43451 is the most substantial and central model-addition PR, with the broadest implementation footprint and highest review activity.", + "best_pr_reason": "PR 43451 is the strongest standalone representative of a substantive model-addition change, with broad model-specific code and very high review activity, but it is not a duplicate anchor for the others.", "soft_edge_verdicts": [ { "left": "pull_request:42978", "right": "pull_request:43448", "accept": false, - "reason": "Different models (ViT NEPA vs Molmo) and different code paths; same docs/auto registry patterns are not enough to duplicate them." + "reason": "Different models (ViT NEPA vs Molmo); overlap is only docs/auto-registry boilerplate." }, { "left": "pull_request:42978", "right": "pull_request:43451", "accept": false, - "reason": "Different models (ViT NEPA vs Molmo2); overlap is only generic model-registration scaffolding." + "reason": "Different models (ViT NEPA vs Molmo2); shared files reflect generic model registration, not the same bug/change." }, { "left": "pull_request:42978", "right": "pull_request:45490", "accept": false, - "reason": "Different model families (ViT NEPA vs CTSM); similar auto/docs edits do not indicate the same change." + "reason": "Different model additions (ViT NEPA vs CTSM); no shared concrete code-path fix." }, { "left": "pull_request:43448", "right": "pull_request:43451", "accept": false, - "reason": "Molmo and Molmo2 are distinct model additions with separate implementations, tests, and docs." + "reason": "Molmo and Molmo2 are distinct model families/generations; not the same underlying change." }, { "left": "pull_request:43448", "right": "pull_request:45490", "accept": false, - "reason": "Molmo and CTSM are unrelated model additions; shared repo plumbing is too broad to merge as duplicates." + "reason": "Different models (Molmo vs CTSM); only broad subsystem overlap in registration/docs." }, { "left": "pull_request:43451", "right": "pull_request:45490", "accept": false, - "reason": "Molmo2 and CTSM are different models with different architectures and files; not the same underlying change." + "reason": "Different models (Molmo2 vs CTSM); no evidence they fix or add the same concrete code path." }, { "left": "pull_request:43973", "right": "pull_request:45838", "accept": false, - "reason": "Lfm2 Audio model support and PP-OCRv6 text recognition support are unrelated additions." + "reason": "Different domains: audio model support vs OCR/text-recognition model support." }, { "left": "pull_request:44601", "right": "pull_request:45838", "accept": false, - "reason": "Pipeline-parallel loading infrastructure is unrelated to PP-OCRv6 model support; they do not fix the same code-path problem." + "reason": "Infrastructure change for pipeline-parallel loading vs a specific model-support PR; not the same underlying fix." }, { "left": "pull_request:45490", "right": "pull_request:45838", "accept": false, - "reason": "CTSM and PP-OCRv6 are different model families; only broad model-registration files overlap." + "reason": "Different model additions (CTSM vs PP-OCRv6 recognition); shared registry files are insufficient for duplication." } ] }, @@ -16852,7 +16746,7 @@ { "label": "pull_request", "component_index": 8, - "component_count": 27, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16860,63 +16754,85 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-43291-3", + "cluster_id": "cluster-43291-4", "nodes": [ "pull_request:43291", "pull_request:43665", - "pull_request:44815" + "pull_request:44815", + "pull_request:45845" ], "soft_pairs": [ + "pull_request:43291|pull_request:45845", "pull_request:43291|pull_request:43665", "pull_request:43291|pull_request:44815", - "pull_request:43665|pull_request:44815" + "pull_request:43665|pull_request:45845", + "pull_request:43665|pull_request:44815", + "pull_request:44815|pull_request:45845" ], - "prepared_review_unit_hash": "b4a05a0f7a6256d446468512b1e51a158963fff84e2a99bfe82fab38b79c6abb", + "prepared_review_unit_hash": "cf28fb45e1f90ae658ce182dccdf2b3851a509b506d3cce74dbbb5a81a03b932", "component_budget": { - "node_count": 3, - "item_count": 3, - "soft_pair_count": 3, - "serialized_chars": 7093, - "estimated_input_tokens": 1774, - "estimated_eval_tokens": 3804 + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 10176, + "estimated_input_tokens": 2544, + "estimated_eval_tokens": 5344 }, "budget": { - "node_count": 3, - "item_count": 3, - "soft_pair_count": 3, - "serialized_chars": 7093, - "estimated_input_tokens": 1774, - "estimated_eval_tokens": 3804 + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 10176, + "estimated_input_tokens": 2544, + "estimated_eval_tokens": 5344 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are not duplicates: two are test-focused Whisper/vision items, while one is a substantive FP8/model-loading fix. The cluster appears to be a mixed set of unrelated pull requests rather than one underlying change.", - "confidence": 0.95, + "summary": "These are four unrelated pull requests across different models/components; none look like true duplicates. The strongest standalone fix is the FP8 dequant/loading change in 44815.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "pull_request:44815 is the most substantive and concrete change: it fixes model-loading/FP8 code paths with supporting integration updates, rather than only touching tests.", + "canonical_pr_reason": "44815 is the most substantive and representative fix: it changes core FP8/loading code paths and includes related integration/tests, unlike the others which are model-specific or test-only.", "best_issue_reason": null, - "best_pr_reason": "pull_request:44815 is the strongest standalone PR in the set because it addresses a specific code-path bug and includes the broadest coherent fix.", + "best_pr_reason": "44815 is the best overall PR candidate because it addresses a concrete runtime bug in a shared code path and has the clearest production impact.", "soft_edge_verdicts": [ + { + "left": "pull_request:43291", + "right": "pull_request:45845", + "accept": false, + "reason": "Different model families and different bugs: Whisper tokenizer timestamp decoding vs RF-DETR proposal masking/device placement." + }, { "left": "pull_request:43291", "right": "pull_request:43665", "accept": false, - "reason": "Both are test-oriented, but they target different model areas and the diffs do not indicate the same concrete bug or a single mergeable fix." + "reason": "Both touch tests, but they target different models and different issues; 43291 also changes Whisper tokenizer code, while 43665 is just test assertions." }, { "left": "pull_request:43291", "right": "pull_request:44815", "accept": false, - "reason": "Whisper tokenizer/test changes are unrelated to the FP8/model-loading dequantization fix; they do not share a concrete code-path problem." + "reason": "Whisper decode/timestamp handling is unrelated to FP8 dequant/loading logic in 44815." + }, + { + "left": "pull_request:43665", + "right": "pull_request:45845", + "accept": false, + "reason": "Unrelated test-only changes in CLIP/ViT versus an RF-DETR runtime fix." }, { "left": "pull_request:43665", "right": "pull_request:44815", "accept": false, - "reason": "CLIP/ViT test changes and an FP8 dequantization fix are unrelated changes; shared broad testing/cleanup similarity is not enough to treat them as one fix." + "reason": "No shared underlying bug or code path; 43665 is test-focused, while 44815 is a core FP8 integration fix." + }, + { + "left": "pull_request:44815", + "right": "pull_request:45845", + "accept": false, + "reason": "Both are fixes, but for different subsystems and failure modes; they would not plausibly merge into one PR." } ] }, @@ -16930,7 +16846,7 @@ { "label": "pull_request", "component_index": 9, - "component_count": 27, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16946,7 +16862,7 @@ "soft_pairs": [ "pull_request:43488|pull_request:43532" ], - "prepared_review_unit_hash": "c266fb875774090e80f4643194134adf228659a5a328edc4dff187bd1631b8a0", + "prepared_review_unit_hash": "37c71327ccc050fb30237eff2752e524d2d5338529d2d22e551e14defe7c8c2e", "component_budget": { "node_count": 2, "item_count": 2, @@ -16968,18 +16884,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two PRs are both test/demonstration changes, but they target different behaviors and code paths: one is about a bad version format/repo-bot check, the other is about workflow/comment CI behavior and diff display. They should not be clustered as duplicates.", - "confidence": 0.95, + "summary": "Two unrelated open PRs: one is a setup/version/dependency tweak, the other rewires CI/testing workflows. They share a test file path but not the same underlying change.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43488 is the better canonical PR candidate because it is narrower and more self-contained, centered on the version-format/repo-bot check. PR 43532 spans multiple workflows and testing utilities, making it broader and less representative.", + "canonical_pr_reason": "pull_request:43532 is the more substantial PR and best represents the cluster, but the items are not truly duplicates of each other.", "best_issue_reason": null, - "best_pr_reason": "PR 43488 is the best overall PR in the cluster for triage because it has a clearer, single-purpose change and a tighter code path than PR 43532, which is a broader workflow/testing showcase PR.", + "best_pr_reason": "No issue items are present; as a PR representative, pull_request:43532 is the strongest candidate because it contains the broader code/workflow changes.", "soft_edge_verdicts": [ { "left": "pull_request:43488", "right": "pull_request:43532", "accept": false, - "reason": "Different underlying changes: 43488 adjusts packaging/versioning and a Vit test, while 43532 rewrites workflow automation and related test/notification files. Shared Vit test filename is incidental, not evidence of the same fix." + "reason": "Reject: these PRs change different areas and solve different problems. 43488 updates setup/dependency/version metadata, while 43532 modifies GitHub workflows and test utilities; the shared Vit test file is incidental." } ] }, @@ -16993,7 +16909,7 @@ { "label": "pull_request", "component_index": 10, - "component_count": 27, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17009,12 +16925,12 @@ "soft_pairs": [ "pull_request:43612|pull_request:43613" ], - "prepared_review_unit_hash": "d2e5526a4441fd7d16aabf4ea06e230b08b6f82530a6371a2447be3163cb7d92", + "prepared_review_unit_hash": "97a2da92375c51618029bfe7fa5793fe32982cc74f824f6e427ef4972e3b5378", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 6082, + "serialized_chars": 6081, "estimated_input_tokens": 1521, "estimated_eval_tokens": 3298 }, @@ -17022,7 +16938,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 6082, + "serialized_chars": 6081, "estimated_input_tokens": 1521, "estimated_eval_tokens": 3298 }, @@ -17031,18 +16947,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are closely related but distinct feature PRs: one adds a Promptable Concept Segmentation pipeline, the other adds a Promptable Visual Segmentation pipeline. They share infrastructure and docs, but target different tasks and model paths, so they should not be treated as duplicates.", + "summary": "Two separate feature PRs: one adds a Promptable Concept Segmentation pipeline, the other adds a Promptable Visual Segmentation pipeline. They share scaffolding/docs work but target different tasks and model stacks, so they are not duplicates.", "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43613 is the broader representative: it covers a larger set of model integrations and tests, making it the better anchor for this cluster even though it is not a duplicate of 43612.", + "canonical_pr_reason": "No canonical PR: these are distinct feature additions with different pipeline names, docs, and supported model families.", "best_issue_reason": null, - "best_pr_reason": "PR 43613 is the strongest single representative because it has wider code and test coverage across multiple segmentation backends; however, it still addresses a different feature than 43612.", + "best_pr_reason": "43613 is the broader visual-segmentation feature PR and is the better representative if one must be chosen, but it still is not a duplicate of 43612.", "soft_edge_verdicts": [ { "left": "pull_request:43612", "right": "pull_request:43613", "accept": false, - "reason": "Different pipeline features and task targets (concept vs visual segmentation) with different model/test coverage; they are not the same concrete code-path change and would not plausibly be merged into one PR." + "reason": "Different underlying features: concept segmentation vs visual segmentation. The overlapping pipeline/doc/test scaffolding is incidental and not enough to treat them as one mergeable change." } ] }, @@ -17056,7 +16972,7 @@ { "label": "pull_request", "component_index": 11, - "component_count": 27, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17072,7 +16988,7 @@ "soft_pairs": [ "pull_request:43651|pull_request:43663" ], - "prepared_review_unit_hash": "f90ac6a55bf8746821490695e9f48b27f2b679e7e7e9b1947a4f671ad0e2347b", + "prepared_review_unit_hash": "2e6b597885d55abd6d402cbe5185fd647506f9d14cf92dcfaf9826b78968abba", "component_budget": { "node_count": 2, "item_count": 2, @@ -17094,18 +17010,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open PRs touch the same file but implement different Trainer extension points: one changes gradient-accumulation loss scaling, the other changes signature-based column filtering. They are not duplicates.", - "confidence": 0.95, + "summary": "These are two separate trainer.py API-hook PRs: one adjusts gradient-accumulation loss scaling, the other factors out signature-column filtering for overrides. They share a file and theme but not the same underlying change or bug.", + "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": null, + "canonical_pr_reason": "43651 is the cleaner representative PR: it introduces a focused training-step behavior change plus an explicit hook for loss scaling. 43663 addresses a different extension point and is not a duplicate.", "best_issue_reason": null, - "best_pr_reason": "If one must be chosen as the cleaner representative, PR #43651 is the more self-contained change, but it is not a duplicate of #43663; they address different trainer behaviors.", + "best_pr_reason": "43651 is the strongest standalone PR in this cluster because it has a single, concrete behavioral target and a narrowly scoped implementation. 43663 is related only at the subsystem level.", "soft_edge_verdicts": [ { "left": "pull_request:43651", "right": "pull_request:43663", "accept": false, - "reason": "Different code paths and goals in trainer.py: #43651 adds a hook for loss scaling during gradient accumulation, while #43663 adds a hook for signature-column filtering. Shared file alone is not enough to treat them as the same change." + "reason": "Different code paths and semantics: 43651 concerns loss scaling during gradient accumulation, while 43663 concerns how Trainer derives signature columns for filtering inputs. Shared filename alone is not enough to treat them as the same change." } ] }, @@ -17119,7 +17035,7 @@ { "label": "pull_request", "component_index": 12, - "component_count": 27, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17137,7 +17053,7 @@ "pull_request:43656|pull_request:43842", "pull_request:43836|pull_request:43842" ], - "prepared_review_unit_hash": "dcc93991e1bb75d6d07503e429beebbaf9e2ce67cab96665200303aca21999d3", + "prepared_review_unit_hash": "903a6848a51d905611fd58e0b05fdf22a38ea9663aa3c27061080c4e861ff0d7", "component_budget": { "node_count": 3, "item_count": 3, @@ -17159,33 +17075,33 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "PR #43842 is the clearest match for the `TypeAdapter` NameError fix in `src/transformers/cli/serve.py`. PR #43836 appears to be the same underlying annotation/import workaround, while #43656 is a broader annotation-cleanup change and is not evidenced strongly enough to treat as the same bugfix.", - "confidence": 0.89, + "summary": "Three open PRs in transformers/cli/serve.py are all about TypeAdapter/annotation NameErrors, but only one pair looks like the same concrete fix. Two PRs are narrowly about quoting or TYPE_CHECKING-gating TypeAdapter when pydantic is optional; the earlier broad annotation cleanup appears related but not the same change.", + "confidence": 0.82, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #43842 is the most precise fix: it directly addresses the `TypeAdapter` NameError by moving the import under `TYPE_CHECKING` and stringizing the annotation, with the smallest and most explicit diff.", + "canonical_pr_reason": "PR #43842 is the most targeted and minimal fix for the TypeAdapter NameError when pydantic is absent, making it the best representative of the cluster.", "best_issue_reason": null, - "best_pr_reason": "PR #43842 is the best representative because its title and diff both directly describe the runtime `TypeAdapter` name-resolution failure, making it the clearest canonical fix for the cluster.", + "best_pr_reason": "PR #43842 best captures the concrete bug with the smallest, most specific diff and clear issue target.", "soft_edge_verdicts": [ { "left": "pull_request:43656", "right": "pull_request:43842", "accept": false, - "reason": "This diff only shows broader `from __future__ import annotations` / annotation cleanup in `serve.py`; it does not explicitly show the same `TypeAdapter`-focused runtime fix as #43842, so the evidence is too weak to treat them as the same change." + "reason": "Both touch serve.py and mention TypeAdapter, but #43656 is a broader postponed-annotations cleanup while #43842 specifically fixes the pydantic-optional TypeAdapter NameError. Related symptom, not the same underlying change." }, { "left": "pull_request:43836", "right": "pull_request:43842", "accept": true, - "reason": "Both PRs target the same `TypeAdapter` name-resolution problem in `serve.py`, and the shown edits are plausible variants of the same fix: deferring the annotation and typing import to avoid runtime evaluation." + "reason": "These are two variants of the same concrete fix in the same code path: both quote or defer TypeAdapter annotations in serve.py to avoid runtime NameError, and they could plausibly be merged into one PR." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The 43842 assessment is well grounded, but the soft-edge handling is not conservative enough. For 43656, the packet only shows a broader `from __future__ import annotations` / annotation-cleanup diff in `serve.py`; it does not explicitly show the same `TypeAdapter`-focused change that 43842 makes, so claiming it is the same bugfix and mergeable with 43842 is stronger than the provided evidence supports. The 43836 pair is better supported, but one overconfident soft-edge verdict is enough to reject. The summary also slightly overstates by saying all three PRs target the same `TypeAdapter` NameError when only 43842 explicitly shows that in the diff preview." + "accept": true, + "feedback": "The summary is grounded in the packet: #43842 is indeed the smallest and most targeted diff, with an explicit issue target and a direct TypeAdapter/pydantic-absent fix. The soft-edge calls are conservative overall: rejecting #43656 vs #43842 is defensible given the broader annotation cleanup, while accepting #43836 vs #43842 is reasonable because both clearly address the same serve.py TypeAdapter annotation problem and share the same issue target." }, "evaluator_used": true, - "retried": true, + "retried": false, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -17193,7 +17109,7 @@ { "label": "pull_request", "component_index": 13, - "component_count": 27, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17259,7 +17175,7 @@ { "label": "pull_request", "component_index": 14, - "component_count": 27, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 2, "status": "reviewed", @@ -17329,8 +17245,8 @@ "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:44722", "pull_request:44017|pull_request:44073", "pull_request:44068|pull_request:44071", "pull_request:44071|pull_request:44086", @@ -17372,106 +17288,106 @@ "pull_request:44044|pull_request:44154", "pull_request:44024|pull_request:44076" ], - "prepared_review_unit_hash": "62360561d12498d237939c11892f555bfd1d012cce85bdc1edb09628f211eb57", + "prepared_review_unit_hash": "19340dbf0f318e78d43b840f4a1099cc61fc60b2972e369e0044d8422db92a46", "component_budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 77, - "serialized_chars": 84498, - "estimated_input_tokens": 21125, - "estimated_eval_tokens": 42506 + "serialized_chars": 84508, + "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": 76943, + "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 broad standardized output-tracing sweep across unrelated model families. Only the GPT-J/CodeGen duplicates and the GPT-Neo duplicates look like true same-change overlaps; the rest are just similar refactors in different code paths.", - "confidence": 0.87, + "summary": "Mostly a family of model-specific output-tracing refactors, not a single duplicate change. The only strong duplicates are within the GPT-J/GPT-Neo lines; cross-model pairs are generally different code paths and should stay separate.", + "confidence": 0.89, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44722 is the strongest representative of the shared output-tracing refactor work: it directly targets the GPT-J/CodeGen implementation path, is explicit about the standardized decorator approach, and overlaps with the other accepted GPT-J/GPT-Neo duplicates.", + "canonical_pr_reason": "PR 44722 is the most representative GPT-J-family refactor here: it is explicit about the output-tracing migration, touches the same core code path as the other GPT-J variants, and also spans the closely related CodeGen copy.", "best_issue_reason": null, - "best_pr_reason": "PR 44722 is the best single representative for the cluster because it has the clearest concrete implementation of the recurring output-tracing change and the strongest linkage to the duplicate GPT-J work.", + "best_pr_reason": "PR 44722 is the best anchor for the cluster\u2019s dominant theme because it is the broadest and clearest instance of the standardized output-tracing migration in the GPT-J family.", "soft_edge_verdicts": [ { "left": "pull_request:43996", "right": "pull_request:44085", "accept": false, - "reason": "Same high-level theme, but different model families and different concrete code paths." + "reason": "Different model families and different forward paths; same meta theme, not the same concrete change." }, { "left": "pull_request:43996", "right": "pull_request:44044", "accept": false, - "reason": "Different model families; this is not the same bug/change." + "reason": "CVT/FNet output tracing is unrelated to DeBERTa\u2019s attention/output refactor." }, { "left": "pull_request:44066", "right": "pull_request:44085", "accept": true, - "reason": "Both refactor the same GPT-J output-tracing code path, and one is a broader version of the same change." + "reason": "Same GPT-J code path and same decorator-based output-tracing migration; plausibly one combined PR." }, { "left": "pull_request:44007", "right": "pull_request:44072", "accept": false, - "reason": "Both are standardized output refactors, but for different backbone models and not one concrete shared fix." + "reason": "RegNet and EfficientNet are separate model implementations; same pattern, not a duplicate bugfix." }, { "left": "pull_request:44072", "right": "pull_request:44722", "accept": false, - "reason": "Different model families and no shared code path." + "reason": "EfficientNet refactor is unrelated to the GPT-J/CodeGen change." }, { "left": "pull_request:44066", "right": "pull_request:44072", "accept": false, - "reason": "Different models; similarity is only at the refactor pattern level." + "reason": "GPT-J/CodeGen versus EfficientNet are different code paths." }, { "left": "pull_request:44013", "right": "pull_request:44044", "accept": false, - "reason": "Unrelated model implementations despite a shared refactor theme." + "reason": "MobileNetV2 and DeBERTa are unrelated implementations." }, { "left": "pull_request:44066", "right": "pull_request:44086", "accept": false, - "reason": "Different model families and different underlying change." + "reason": "GPT-J/CodeGen refactor and MGP-STR refactor are distinct model changes." }, { "left": "pull_request:44066", "right": "pull_request:44071", "accept": false, - "reason": "GPT-J/CodeGen vs MPT are unrelated code paths." + "reason": "Different models and different refactor targets." }, { "left": "pull_request:44018", "right": "pull_request:44068", "accept": true, - "reason": "Both target the same GPT-Neo output-tracing refactor on the same model family." + "reason": "Both target GPT-Neo output tracing in the same file/model family; this looks like the same underlying migration." }, { "left": "pull_request:44066", "right": "pull_request:44068", "accept": false, - "reason": "GPT-J/CodeGen and GPT-Neo are different code paths." + "reason": "GPT-J/CodeGen and GPT-Neo are separate model code paths." }, { "left": "pull_request:44018", "right": "pull_request:44066", "accept": false, - "reason": "Different model families and not the same concrete change." + "reason": "GPT-Neo versus GPT-J/CodeGen is not the same concrete fix." }, { "left": "pull_request:44019", @@ -17483,7 +17399,7 @@ "left": "pull_request:44086", "right": "pull_request:44722", "accept": false, - "reason": "Different model families; only the refactor style is similar." + "reason": "MGP-STR and GPT-J family changes are different model refactors." }, { "left": "pull_request:44019", @@ -17495,205 +17411,271 @@ "left": "pull_request:44018", "right": "pull_request:44019", "accept": false, - "reason": "Different model families and different output code paths." + "reason": "GPT-Neo and ResNet are different code paths." }, { "left": "pull_request:44019", "right": "pull_request:44071", "accept": false, - "reason": "ResNet and MPT are unrelated concrete changes." + "reason": "ResNet and MPT refactors are unrelated." }, { "left": "pull_request:44068", "right": "pull_request:44116", "accept": false, - "reason": "GPT-Neo and Flaubert/XLM are different code paths." + "reason": "GPT-Neo and Flaubert are different model families." }, { "left": "pull_request:44068", "right": "pull_request:44722", "accept": false, - "reason": "GPT-Neo is a different model family from GPT-J/CodeGen." + "reason": "GPT-Neo and GPT-J/CodeGen are not the same change." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44722", + "accept": false, + "reason": "MPT output tracing is unrelated to GPT-J/CodeGen." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo and Flaubert are different code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo and MGP-STR are unrelated." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44085", + "accept": false, + "reason": "GPT-Neo and GPT-J are different model implementations." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo and MGP-STR are not the same bugfix." }, { "left": "pull_request:44071", "right": "pull_request:44086", "accept": false, - "reason": "Different model families and no shared bug/change." + "reason": "MPT and MGP-STR are unrelated." }, { "left": "pull_request:44059", "right": "pull_request:44086", "accept": false, - "reason": "GPT-2 and MGP-STR are unrelated implementations." + "reason": "GPT2 and MGP-STR touch different model code paths." }, { "left": "pull_request:44085", "right": "pull_request:44086", "accept": false, - "reason": "Both are refactors, but on different model families and different code paths." + "reason": "GPT-J and MGP-STR are unrelated model changes." }, { "left": "pull_request:44059", "right": "pull_request:44722", "accept": false, - "reason": "GPT-2 output tracing is unrelated to GPT-J/CodeGen." + "reason": "GPT2 output tracing is separate from the GPT-J/CodeGen refactor." }, { "left": "pull_request:44098", "right": "pull_request:44101", "accept": false, - "reason": "ViLT and Flaubert/XLM are different concrete changes." + "reason": "ViLT and Flaubert are different implementations." }, { "left": "pull_request:44017", - "right": "pull_request:44722", + "right": "pull_request:44161", "accept": false, - "reason": "SegFormer is unrelated to GPT-J/CodeGen." + "reason": "Segformer and LongT5 are unrelated model refactors." }, { "left": "pull_request:44017", - "right": "pull_request:44161", + "right": "pull_request:44722", "accept": false, - "reason": "Different model families and different output paths." + "reason": "Segformer and GPT-J/CodeGen are different code paths." }, { "left": "pull_request:44017", "right": "pull_request:44073", "accept": false, - "reason": "SegFormer and VisualBERT are not the same underlying fix." + "reason": "Segformer and VisualBert are separate model implementations." }, { "left": "pull_request:44073", "right": "pull_request:44101", "accept": false, - "reason": "Different model families and different code paths." + "reason": "VisualBert and Flaubert are unrelated." }, { - "left": "pull_request:44074", - "right": "pull_request:44101", + "left": "pull_request:44059", + "right": "pull_request:44086", "accept": false, - "reason": "TextNet and Flaubert/XLM are unrelated changes." + "reason": "GPT2 and MGP-STR are different model changes." }, { - "left": "pull_request:44074", + "left": "pull_request:44056", "right": "pull_request:44161", "accept": false, - "reason": "Different models and no shared concrete bug." + "reason": "MPNet and LongT5 are unrelated model refactors." }, { "left": "pull_request:44018", "right": "pull_request:44059", "accept": false, - "reason": "GPT-Neo and GPT-2 are different model implementations." + "reason": "GPT-Neo and GPT2 are different model code paths." }, { "left": "pull_request:44101", "right": "pull_request:44161", "accept": false, - "reason": "Flaubert/XLM and LongT5 are different code paths." + "reason": "Flaubert/XLM and LongT5 are unrelated." }, { "left": "pull_request:43997", "right": "pull_request:44017", "accept": false, - "reason": "RegNet and SegFormer are unrelated model families." + "reason": "RegNet and Segformer are separate models." }, { "left": "pull_request:43997", "right": "pull_request:44056", "accept": false, - "reason": "RegNet and MPNet are different concrete changes." + "reason": "RegNet and MPNet are unrelated." }, { "left": "pull_request:44071", "right": "pull_request:44076", "accept": false, - "reason": "MPT and ImageGPT are unrelated implementations." + "reason": "MPT and ImageGPT are different code paths." }, { - "left": "pull_request:44010", + "left": "pull_request:44074", + "right": "pull_request:44101", + "accept": false, + "reason": "TextNet and Flaubert are unrelated model changes." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44161", + "accept": false, + "reason": "MPNet and LongT5 are different implementations." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44018", + "accept": false, + "reason": "RegNet and GPT-Neo are unrelated." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44129", + "accept": false, + "reason": "MPT and SpeechT5 are different model families." + }, + { + "left": "pull_request:44059", "right": "pull_request:44071", "accept": false, - "reason": "SqueezeBert and MPT are different model code paths." + "reason": "GPT2 and MPT are unrelated refactors." }, { - "left": "pull_request:44010", - "right": "pull_request:44073", + "left": "pull_request:43997", + "right": "pull_request:44074", "accept": false, - "reason": "SqueezeBert and VisualBERT are not the same fix." + "reason": "RegNet and TextNet are separate models." }, { - "left": "pull_request:44018", + "left": "pull_request:43997", "right": "pull_request:44129", "accept": false, - "reason": "GPT-Neo and SpeechT5 are different model families." + "reason": "RegNet and SpeechT5 are unrelated." }, { "left": "pull_request:44010", - "right": "pull_request:44044", + "right": "pull_request:44071", "accept": false, - "reason": "SqueezeBert and DeBERTa are unrelated changes." + "reason": "SqueezeBert and MPT are different code paths." }, { - "left": "pull_request:44044", + "left": "pull_request:44010", + "right": "pull_request:44073", + "accept": false, + "reason": "SqueezeBert and VisualBert are unrelated." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44129", + "accept": false, + "reason": "GPT-Neo and SpeechT5 are different model implementations." + }, + { + "left": "pull_request:43997", "right": "pull_request:44074", "accept": false, - "reason": "DeBERTa and TextNet are different concrete code paths." + "reason": "RegNet and TextNet are unrelated." }, { - "left": "pull_request:44066", - "right": "pull_request:44722", - "accept": true, - "reason": "Same GPT-J/CodeGen output-tracing change; 44722 is the broader combined version." + "left": "pull_request:43997", + "right": "pull_request:44129", + "accept": false, + "reason": "RegNet and SpeechT5 are not the same change." }, { - "left": "pull_request:44085", - "right": "pull_request:44722", - "accept": true, - "reason": "Both cover the same GPT-J tracing refactor and could be merged as one change." + "left": "pull_request:44010", + "right": "pull_request:44018", + "accept": false, + "reason": "SqueezeBert and GPT-Neo are unrelated model code paths." }, { - "left": "pull_request:44085", + "left": "pull_request:44071", "right": "pull_request:44129", "accept": false, - "reason": "GPT-J and SpeechT5 are unrelated changes." + "reason": "MPT and SpeechT5 are different implementations." }, { "left": "pull_request:43996", - "right": "pull_request:44007", + "right": "pull_request:44161", "accept": false, - "reason": "Different model families; only the refactor pattern overlaps." + "reason": "CVT/FNet and LongT5 are unrelated." }, { "left": "pull_request:43996", - "right": "pull_request:44129", + "right": "pull_request:44017", "accept": false, - "reason": "CVT/FNet and SpeechT5 do not share the same concrete fix." + "reason": "CVT/FNet and Segformer are separate model refactors." }, { - "left": "pull_request:44044", - "right": "pull_request:44129", + "left": "pull_request:44010", + "right": "pull_request:44044", "accept": false, - "reason": "DeBERTa and SpeechT5 are different code paths." + "reason": "SqueezeBert and DeBERTa are different code paths." }, { "left": "pull_request:44044", - "right": "pull_request:44154", + "right": "pull_request:44074", "accept": false, - "reason": "DeBERTa and VITS are unrelated model implementations." + "reason": "DeBERTa and TextNet are unrelated." }, { "left": "pull_request:44024", "right": "pull_request:44076", "accept": false, - "reason": "FocalNet and ImageGPT are different concrete changes." + "reason": "FocalNet and ImageGPT are different model implementations." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary stays grounded in the packet: it correctly treats most pairs as theme-level similarity across different model families, while carving out the GPT-J/CodeGen and GPT-Neo overlaps as the only plausible same-change clusters. The accepted soft-edge verdicts are conservative and look mergeable into single PRs for the same bugfix." + "feedback": "The summary is grounded in the packet: it correctly identifies the dominant GPT-J/GPT-Neo output-tracing refactor theme while treating the other model changes as separate code paths. The accepted soft-edge pairs are conservative and match the evidence that those PRs are effectively the same migration within the same model family." }, "evaluator_used": true, "retried": false, @@ -17704,7 +17686,7 @@ { "label": "pull_request", "component_index": 14, - "component_count": 27, + "component_count": 26, "review_unit_index": 2, "review_unit_count": 2, "status": "reviewed", @@ -17728,14 +17710,14 @@ "pull_request:43997|pull_request:44010", "pull_request:44010|pull_request:44129" ], - "prepared_review_unit_hash": "3b555afeb8678382e6a86f4960aaa845619190549f5a1376fedb64059a4e77d7", + "prepared_review_unit_hash": "2ee21b7f52e738f04d1bd9a91078d5d313cfe6d0cef648aa4234bb4af97850cb", "component_budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 77, - "serialized_chars": 84498, - "estimated_input_tokens": 21125, - "estimated_eval_tokens": 42506 + "serialized_chars": 84508, + "estimated_input_tokens": 21127, + "estimated_eval_tokens": 42510 }, "budget": { "node_count": 6, @@ -17750,42 +17732,42 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These PRs form a loose thematic cluster around migrating model forwards to the new standardized output-capture utilities, but they are model-specific refactors rather than the same underlying bug or change. I would not deduplicate any of the soft pairs.", - "confidence": 0.94, + "summary": "This cluster is a set of model-specific refactors to standardized output tracing/capture_outputs across different architectures, not duplicate fixes of the same code-path bug.", + "confidence": 0.86, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44129 is the best representative of the cluster: it has the clearest concrete scope, an explicit issue link, and a substantial diff showing the standardized output-capture migration in one model path.", + "canonical_pr_reason": "PR 44010 is a clean representative of the shared refactor pattern: it updates one model\u2019s forward path to the new standardized output-capture approach without extra cross-cutting scope.", "best_issue_reason": null, - "best_pr_reason": "PR 44129 is the strongest standalone candidate because it is explicitly tied to issue 43979 and cleanly scopes the refactor to SpeechT5 output tracing.", + "best_pr_reason": "PR 44010 is the best cluster representative because it is a straightforward, self-contained example of the output-tracing migration pattern seen across the set.", "soft_edge_verdicts": [ { "left": "pull_request:44073", "right": "pull_request:44074", "accept": false, - "reason": "Same broad refactor pattern, but different models and code paths (VisualBert vs TextNet); they are not the same concrete change and would not be merged as one PR." + "reason": "Both are similar output-tracing refactors, but they touch different models and different code paths; they are not the same underlying change and would not realistically merge into one PR." }, { "left": "pull_request:44056", "right": "pull_request:44073", "accept": false, - "reason": "Both migrate output tracing, but MPNet and VisualBert are separate model implementations with independent edits, so this is not a duplicate change." + "reason": "Shared refactor theme only. MPNet and VisualBert have model-specific tracing implementations, so this is not a duplicate fix/change." }, { "left": "pull_request:44056", "right": "pull_request:44074", "accept": false, - "reason": "Shared utility migration theme only; MPNet and TextNet touch different model logic and are not the same underlying fix." + "reason": "These are separate per-model output-capture migrations, not one concrete bug or code-path fix." }, { "left": "pull_request:43997", "right": "pull_request:44010", "accept": false, - "reason": "Both are per-model output-tracing refactors, but RegNet and SqueezeBert are unrelated code paths and not mergeable into a single PR." + "reason": "RegNet and SqueezeBert are unrelated model implementations; same high-level refactor pattern is not enough to treat them as duplicates." }, { "left": "pull_request:44010", "right": "pull_request:44129", "accept": false, - "reason": "They target different models and different forward signatures; the overlap is only the standardized output-capture pattern, not the same bug or change." + "reason": "Both migrate output tracing, but they are distinct model-specific changes in different files and code paths; not one mergeable PR." } ] }, @@ -17799,7 +17781,7 @@ { "label": "pull_request", "component_index": 15, - "component_count": 27, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17865,256 +17847,274 @@ "pull_request:44028|pull_request:44030", "pull_request:44029|pull_request:44030" ], - "prepared_review_unit_hash": "7b32d32ec2eff306543243f3fc5d11cf5d59456d51cf456020d03833ed61b47d", + "prepared_review_unit_hash": "c901facdfacf5880e8847a3f3b085e8c1b769e6a08f937b283f0c89f959567fb", "component_budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 40, - "serialized_chars": 40159, - "estimated_input_tokens": 10040, - "estimated_eval_tokens": 20336 + "serialized_chars": 40168, + "estimated_input_tokens": 10042, + "estimated_eval_tokens": 20340 }, "budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 40, - "serialized_chars": 40159, - "estimated_input_tokens": 10040, - "estimated_eval_tokens": 20336 + "serialized_chars": 40168, + "estimated_input_tokens": 10042, + "estimated_eval_tokens": 20340 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is a set of similar output-tracing refactor PRs, but they target different model families and code paths, so they are not duplicates of one another. I rejected all soft edges because the common theme is too broad for PR deduping.", - "confidence": 0.91, + "summary": "These PRs form a topical cluster around output-tracing refactors, but they are model-specific changes in different code paths, so they are not duplicates of one another.", + "confidence": 0.9, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44003 is the most substantial representative of the cluster: it spans two related Mamba implementations and introduces the output-capture helpers, making it the clearest anchor for the shared refactor theme.", + "canonical_pr_reason": "PR 44003 is the best representative of the cluster: it is the broadest refactor here, spans two related model files, and introduces the shared output-capturing machinery that the other PRs only apply in narrower model-specific ways.", "best_issue_reason": null, - "best_pr_reason": "PR 44003 is the strongest single representative of this group, with the broadest and most explicit output-tracing refactor among the listed PRs.", + "best_pr_reason": "PR 44003 is the strongest single example of the output-tracing refactor theme, with the largest and most structural change set among the PRs shown.", "soft_edge_verdicts": [ { "left": "pull_request:43998", "right": "pull_request:44002", "accept": false, - "reason": "Different model families and forward paths; same refactor theme only." + "reason": "Both are output-tracing refactors, but they affect different models and different forward paths; not the same concrete fix." }, { "left": "pull_request:43998", "right": "pull_request:44000", "accept": false, - "reason": "Different architectures and code paths; not the same underlying change." + "reason": "Different model families and files; same pattern of refactor, but not one mergeable duplicate change." }, { "left": "pull_request:43998", "right": "pull_request:44001", "accept": false, - "reason": "Unrelated model implementations; shared output-tracing wording is too broad." + "reason": "Unrelated model code paths; only the refactor style matches." }, { "left": "pull_request:43998", "right": "pull_request:44003", "accept": false, - "reason": "Timm backbone vs Mamba are different code paths and refactor targets." + "reason": "Different architectures and files; not the same underlying bug/change." }, { "left": "pull_request:43998", "right": "pull_request:44029", "accept": false, - "reason": "Different model families; no evidence of the same concrete bug or fix." + "reason": "Same tracing theme, but timm_backbone and rwkv are separate implementations with distinct fixes." }, { "left": "pull_request:43999", "right": "pull_request:44001", "accept": false, - "reason": "MobileNetV1 and UnivNet are unrelated implementations despite similar refactor intent." + "reason": "Different models and forward signatures; not a duplicate change." }, { "left": "pull_request:43999", "right": "pull_request:44002", "accept": false, - "reason": "Different subsystems and model behavior; not mergeable as one duplicate fix." + "reason": "Both refactor outputs, but for unrelated models and code paths." }, { "left": "pull_request:43999", "right": "pull_request:44025", "accept": false, - "reason": "MobileNetV1 classification backbone vs DepthAnything depth models are different code paths." + "reason": "MobileNetV1 and DepthAnything are unrelated model implementations; same general theme only." }, { "left": "pull_request:43999", "right": "pull_request:44026", "accept": false, - "reason": "Different model stacks; same tracing refactor theme only." + "reason": "No shared bug or code path; only a common decorator/refactor pattern." }, { "left": "pull_request:43999", "right": "pull_request:44027", "accept": false, - "reason": "MobileNetV1 and speech encoder-decoder are unrelated changes." + "reason": "Different encoder-decoder models; not the same concrete change." }, { "left": "pull_request:44000", "right": "pull_request:44001", "accept": false, - "reason": "Vision-text dual encoder and UnivNet are different model families and fixes." + "reason": "Same refactor wording, but vision_text_dual_encoder and univnet are separate code paths." }, { "left": "pull_request:44000", "right": "pull_request:44002", "accept": false, - "reason": "Different concrete code paths; only the refactor pattern matches." + "reason": "Different model families; not the same fix." }, { "left": "pull_request:44000", "right": "pull_request:44003", "accept": false, - "reason": "Vision-text dual encoder vs Mamba are unrelated implementations." + "reason": "These touch unrelated model implementations, so they are not mergeable duplicates." }, { "left": "pull_request:44000", "right": "pull_request:44025", "accept": false, - "reason": "Different tasks and model internals; not the same underlying issue." + "reason": "Shared output-tracing theme only; different models and different forward logic." }, { "left": "pull_request:44001", "right": "pull_request:44002", "accept": false, - "reason": "UnivNet and UperNet are unrelated code paths, despite similar output handling changes." + "reason": "Different model code paths; no indication of the same underlying bug." }, { "left": "pull_request:44001", "right": "pull_request:44003", "accept": false, - "reason": "Different models and forward signatures; no shared concrete bug." + "reason": "Unrelated model implementations; same refactor class, not the same change." }, { "left": "pull_request:44001", "right": "pull_request:44025", "accept": false, - "reason": "UnivNet vs DepthAnything are different architectures and fixes." + "reason": "Different models and outputs; not a duplicate fix." }, { "left": "pull_request:44002", "right": "pull_request:44029", "accept": false, - "reason": "UperNet segmentation and RWKV are different implementations." + "reason": "Different model families and forward paths; only the tracing refactor pattern is shared." }, { "left": "pull_request:44002", "right": "pull_request:44003", "accept": false, - "reason": "Different model families; shared tracing refactor theme is too broad." + "reason": "No shared concrete code-path problem; the similarity is only thematic." }, { "left": "pull_request:44003", "right": "pull_request:44028", "accept": false, - "reason": "Mamba/FalconMamba and SuperPoint do not fix the same code-path problem." + "reason": "Falcon/Mamba refactor versus SuperPoint refactor; separate implementations and fixes." }, { "left": "pull_request:44003", "right": "pull_request:44004", "accept": false, - "reason": "Mamba-style recurrent models vs CodeGen are distinct code paths." + "reason": "Different model internals and outputs; not the same underlying change." }, { "left": "pull_request:43998", "right": "pull_request:44004", "accept": false, - "reason": "Timm backbone and CodeGen are unrelated model implementations." + "reason": "Timm backbone and CodeGen are unrelated code paths; same refactor family only." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44004", + "accept": false, + "reason": "Unrelated model implementations; not a duplicate PR." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44004", + "accept": false, + "reason": "Different models and forward behaviors; not the same fix." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44004", + "accept": false, + "reason": "Only the output-tracing theme matches; the code paths do not." }, { "left": "pull_request:44025", "right": "pull_request:44026", "accept": false, - "reason": "DepthAnything models vs VisionEncoderDecoder are different subsystems." + "reason": "Different model families and files; same broad refactor pattern, but not the same concrete bug/change." }, { "left": "pull_request:44025", "right": "pull_request:44027", "accept": false, - "reason": "Depth-estimation models and speech encoder-decoder are unrelated changes." + "reason": "DepthAnything/PromptDepthAnything versus VisionEncoderDecoder are unrelated implementations." }, { "left": "pull_request:44025", "right": "pull_request:44028", "accept": false, - "reason": "DepthAnything and SuperPoint are different vision models with different code paths." + "reason": "Different model code paths; no evidence they fix the same problem." }, { "left": "pull_request:44025", "right": "pull_request:44029", "accept": false, - "reason": "DepthAnything and RWKV are unrelated implementations." + "reason": "Separate model families with distinct output mechanics; not mergeable as one PR." }, { "left": "pull_request:44025", "right": "pull_request:44030", "accept": false, - "reason": "Depth estimation and DPR retrieval models are not the same underlying bug or change." + "reason": "DepthAnything refactor and DPR refactor are unrelated changes." }, { "left": "pull_request:44026", "right": "pull_request:44029", "accept": false, - "reason": "VisionEncoderDecoder and RWKV are unrelated model code paths." + "reason": "VisionEncoderDecoder and RWKV are different systems; not the same code-path issue." }, { "left": "pull_request:44026", "right": "pull_request:44027", "accept": false, - "reason": "Different encoder-decoder variants and different concrete implementations." + "reason": "Different model families and forward paths; no duplicate evidence." }, { "left": "pull_request:44026", "right": "pull_request:44028", "accept": false, - "reason": "VisionEncoderDecoder and SuperPoint do not share a single fixable code-path issue." + "reason": "Same refactor style only; unrelated model implementations." }, { "left": "pull_request:44026", "right": "pull_request:44030", "accept": false, - "reason": "Different model families; shared output-tracing refactor wording is insufficient." + "reason": "VisionEncoderDecoder and DPR are distinct model code paths." }, { "left": "pull_request:44027", "right": "pull_request:44028", "accept": false, - "reason": "Speech encoder-decoder and SuperPoint are unrelated changes." + "reason": "SpeechEncoderDecoder and SuperPoint are unrelated model implementations." }, { "left": "pull_request:44027", "right": "pull_request:44029", "accept": false, - "reason": "Speech encoder-decoder and RWKV fix different code paths." + "reason": "Different model families and output shapes; not the same underlying change." }, { "left": "pull_request:44027", "right": "pull_request:44030", "accept": false, - "reason": "Speech encoder-decoder and DPR are different model implementations." + "reason": "Different code paths and behaviors; only the refactor pattern overlaps." }, { "left": "pull_request:44028", "right": "pull_request:44029", "accept": false, - "reason": "SuperPoint and RWKV are unrelated model families." + "reason": "SuperPoint and RWKV are unrelated implementations; not a duplicate." }, { "left": "pull_request:44028", "right": "pull_request:44030", "accept": false, - "reason": "SuperPoint and DPR do not appear to fix the same concrete problem." + "reason": "Different model families; no shared concrete bug or fix." }, { "left": "pull_request:44029", "right": "pull_request:44030", "accept": false, - "reason": "RWKV and DPR are different code paths; same refactor theme only." + "reason": "RWKV and DPR are separate model code paths, so these are not duplicates." } ] }, @@ -18128,70 +18128,7 @@ { "label": "pull_request", "component_index": 16, - "component_count": 27, - "review_unit_index": 1, - "review_unit_count": 1, - "status": "reviewed", - "reason": null, - "source": "llm", - "cache_hit": false, - "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-44646-2", - "nodes": [ - "pull_request:44646", - "pull_request:45824" - ], - "soft_pairs": [ - "pull_request:44646|pull_request:45824" - ], - "prepared_review_unit_hash": "c414498bf625f1ff849c8df521123aa6bb17caaebddc5d82b05acea7480de923", - "component_budget": { - "node_count": 2, - "item_count": 2, - "soft_pair_count": 1, - "serialized_chars": 4988, - "estimated_input_tokens": 1247, - "estimated_eval_tokens": 2750 - }, - "budget": { - "node_count": 2, - "item_count": 2, - "soft_pair_count": 1, - "serialized_chars": 4988, - "estimated_input_tokens": 1247, - "estimated_eval_tokens": 2750 - }, - "overflow_policy": "truncate_then_skip", - "trimmed": false, - "aggressively_trimmed": false, - "split": false, - "analyst_result": { - "summary": "Both PRs are near-duplicate typo cleanups for \"seperate\" -> \"separate\", but PR 45824 is a broader multi-file comment-only sweep and PR 44646 is a smaller overlapping subset. For strict PR deduping, I would not merge them as the same concrete change.", - "confidence": 0.89, - "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45824 is the better canonical representative because it covers the typo fix across more affected files and subsumes the overlapping edits seen in PR 44646.", - "best_issue_reason": null, - "best_pr_reason": "PR 45824 is the strongest standalone PR in the cluster: it is the more complete version of the same typo cleanup and spans all overlapping targets plus additional affected models.", - "soft_edge_verdicts": [ - { - "left": "pull_request:44646", - "right": "pull_request:45824", - "accept": false, - "reason": "Same typo theme, but these are comment-only cleanup PRs with different scopes; 45824 is a broader batch rather than the same single change, so they should stay separate under strict PR triage." - } - ] - }, - "evaluator_result": null, - "evaluator_used": false, - "retried": false, - "accepted_nontrivial_soft_edge": false, - "error_kind": null, - "error_message": null - }, - { - "label": "pull_request", - "component_index": 17, - "component_count": 27, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18210,52 +18147,52 @@ "pull_request:44662|pull_request:45075", "pull_request:45075|pull_request:45401" ], - "prepared_review_unit_hash": "42d489244868a0b9bbdb7f1f852593f04438d6c6e9aa56df552577ba93a454a1", + "prepared_review_unit_hash": "e23d3d3f2fa42a80e59ede1e3f4b13b5f28d1d8133b765f0aa21757d508f46c5", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 10913, - "estimated_input_tokens": 2729, - "estimated_eval_tokens": 5714 + "serialized_chars": 10912, + "estimated_input_tokens": 2728, + "estimated_eval_tokens": 5712 }, "budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 10913, - "estimated_input_tokens": 2729, - "estimated_eval_tokens": 5714 + "serialized_chars": 10912, + "estimated_input_tokens": 2728, + "estimated_eval_tokens": 5712 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are three separate model-addition PRs for different architectures (PenguinVL, DeepSeek-OCR-2, Voxtral TTS). They share generic scaffolding files from adding new model integrations, but they do not target the same concrete code change or bug.", - "confidence": 0.96, + "summary": "All three items are separate model-addition pull requests for different models (PenguinVL, DeepSeek-OCR-2, Voxtral TTS). They share framework-wide registry/docs files, but not the same underlying code change or bug.", + "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": null, + "canonical_pr_reason": "No single canonical PR: each PR implements a different model integration, so they are not duplicates of one another.", "best_issue_reason": null, - "best_pr_reason": null, + "best_pr_reason": "Voxtral TTS is the most self-contained/traceable of the three because it has an explicit issue target, but it still represents a distinct model addition rather than a duplicate of the others.", "soft_edge_verdicts": [ { "left": "pull_request:44662", "right": "pull_request:45401", "accept": false, - "reason": "Different model implementations and different code paths: PenguinVL vs Voxtral TTS. Shared auto/docs files are just standard model-registration boilerplate, not the same fix." + "reason": "Different model implementations (PenguinVL vs Voxtral TTS). Shared auto-registry/docs files are generic integration boilerplate, not the same concrete change." }, { "left": "pull_request:44662", "right": "pull_request:45075", "accept": false, - "reason": "Different model additions for unrelated models (PenguinVL vs DeepSeek-OCR-2). Overlap in docs/auto registry files reflects template integration work, not one underlying change." + "reason": "PenguinVL and DeepSeek-OCR-2 are unrelated model additions. Overlap is limited to common model-registration files and does not indicate the same fix/change." }, { "left": "pull_request:45075", "right": "pull_request:45401", "accept": false, - "reason": "DeepSeek-OCR-2 and Voxtral TTS are distinct model-support PRs with different implementations and tests. They cannot plausibly be merged as one duplicate change." + "reason": "DeepSeek-OCR-2 and Voxtral TTS target different models and codepaths. Similar filenames reflect standard model onboarding, not duplicate work." } ] }, @@ -18268,8 +18205,8 @@ }, { "label": "pull_request", - "component_index": 18, - "component_count": 27, + "component_index": 17, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18285,7 +18222,7 @@ "soft_pairs": [ "pull_request:44979|pull_request:45363" ], - "prepared_review_unit_hash": "38521e52697b214ea9fe218bb59740c934893f7298a67450a2e0ec42d7c85773", + "prepared_review_unit_hash": "31a0e84d7dbdcc13dcd35f9ea6bc3bb8d5f6d5dfdd051cd271be32d7d7fb76c6", "component_budget": { "node_count": 2, "item_count": 2, @@ -18307,18 +18244,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are both about fusion, but they address different layers of the stack: #44979 introduces a generic module-fusion API, while #45363 wires a specific KernelConfig-based n-to-1 kernel fusion flow into model loading/integration. They are related infrastructure, not duplicates.", + "summary": "Two related PRs around fusion, but they address different levels of the stack: one introduces a generic Module Fusion API, the other adds n-to-1 kernel fusion integration via KernelConfig. They are connected, but not the same concrete change and would not be merged as a single PR.", "confidence": 0.87, "canonical_issue_reason": null, - "canonical_pr_reason": "#45363 is the more concrete, end-to-end feature PR with explicit integration points and a usage example; #44979 is a broader API scaffold that could support many future fusion mechanisms.", + "canonical_pr_reason": "PR #44979 is the more foundational change: it introduces the generic Module Fusion API and test coverage. It is the broader reusable base that the later KernelConfig work builds on.", "best_issue_reason": null, - "best_pr_reason": "#45363 is the best representative of the cluster because it delivers a specific, testable fusion path rather than only defining a reusable API surface.", + "best_pr_reason": "PR #45363 is the more user-facing and complete feature proposal for kernel fusion via KernelConfig, with integration across multiple files and an example demonstrating the workflow.", "soft_edge_verdicts": [ { "left": "pull_request:44979", "right": "pull_request:45363", "accept": false, - "reason": "Different change sets and code paths: #44979 adds a new generic module_fusion API module, while #45363 implements KernelConfig-driven n-to-1 fusion across modeling/integration files. They are related by theme but not the same concrete fix/change, and would not plausibly merge into one duplicate PR." + "reason": "Related fusion work, but not the same concrete bug/change. #44979 adds a generic module-fusion API, while #45363 wires n-to-1 kernel fusion through KernelConfig and integration code. They could coexist as separate PRs and are not strict duplicates." } ] }, @@ -18331,8 +18268,8 @@ }, { "label": "pull_request", - "component_index": 19, - "component_count": 27, + "component_index": 18, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18348,7 +18285,7 @@ "soft_pairs": [ "pull_request:45086|pull_request:45317" ], - "prepared_review_unit_hash": "816fce9d7b10c37555cfcb7cc453ebb23c1ed9f8083964fbfe1221f82897c0e7", + "prepared_review_unit_hash": "62ae4d570e382e1d5e49f120c105839d792dce9b3714430ee876f98f96a53da4", "component_budget": { "node_count": 2, "item_count": 2, @@ -18370,18 +18307,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs address the same concrete AttributeError in `_patch_mistral_regex` by switching from `tokenizer.backend_tokenizer.pre_tokenizer` to `tokenizer.pre_tokenizer` in the same file. PR 45317 is the stronger canonical choice because it is the more complete follow-up, with a clearer title and added test coverage.", + "summary": "Both pull requests target the same Mistral regex patch in the same file, with the same fix for the AttributeError and the same issue link. PR 45317 is the more complete duplicate because it adds test coverage while implementing the same code-path fix.", "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45317 is the best canonical PR: it fixes the same code path as 45086 but is more complete and specific, and it adds tests in addition to the source change.", + "canonical_pr_reason": "PR 45317 is the best canonical PR: it fixes the same AttributeError in `_patch_mistral_regex` as PR 45086, but adds accompanying tests and has the more complete implementation.", "best_issue_reason": null, - "best_pr_reason": "PR 45317 is the best overall PR candidate because it contains the same fix plus test coverage and a more explicit description of the failure mode.", + "best_pr_reason": "PR 45317 is the best overall representative because it addresses the same concrete bug as 45086 and includes tests, making it the stronger final patch.", "soft_edge_verdicts": [ { "left": "pull_request:45086", "right": "pull_request:45317", "accept": true, - "reason": "Same underlying bug and same file/function; the diff is effectively the same fix, with 45317 just adding tests and polish. These could plausibly be merged as one PR." + "reason": "Same explicit issue target, same file, same AttributeError fix in `_patch_mistral_regex`; 45317 is a superset with tests, so these are duplicate PRs for the same change." } ] }, @@ -18394,8 +18331,8 @@ }, { "label": "pull_request", - "component_index": 20, - "component_count": 27, + "component_index": 19, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18411,7 +18348,7 @@ "soft_pairs": [ "pull_request:45115|pull_request:45569" ], - "prepared_review_unit_hash": "f8e9303440715e92d9b6727cefd5b03cd0e1c59228c54d78a90e8381b53a0b38", + "prepared_review_unit_hash": "bc8918f70e8285c7a2befd9b0990a9e7e480479b73ed352967ddca94396eeba9", "component_budget": { "node_count": 2, "item_count": 2, @@ -18433,18 +18370,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open PRs both touch NemotronH internals, but they are not duplicates: #45115 is a narrow inheritance/conversion-mapping refactor, while #45569 is a broader model-splitting and documentation update for NemotronH dense/sparse variants. They overlap in files because #45569 builds on the same model family, not because they fix the same concrete change.", - "confidence": 0.91, + "summary": "Two NemotronH pull requests that overlap in model files but target different changes: one refactors NemotronH to inherit GraniteMoeHybrid behavior, the other splits NemotronH into dense/sparse variants with docs and tests. They are related but not duplicates.", + "confidence": 0.89, "canonical_issue_reason": null, - "canonical_pr_reason": "#45569 is the better canonical PR because it is the more complete, user-facing change: it introduces the dense/sparse model split, updates auto-mapping, docs, and tests, whereas #45115 is a narrower internal refactor.", + "canonical_pr_reason": "45569 is the more complete, user-facing model change: it adds the dense/sparse architecture split plus docs/tests, whereas 45115 is a narrower inheritance/conversion refactor.", "best_issue_reason": null, - "best_pr_reason": "#45569 best represents the cluster\u2019s main direction and scope; #45115 is a smaller precursor refactor and not a substitute for the larger implementation change.", + "best_pr_reason": "45569 is the strongest representative PR for this cluster because it covers the main architectural and documentation update rather than just an internal refactor.", "soft_edge_verdicts": [ { "left": "pull_request:45115", "right": "pull_request:45569", "accept": false, - "reason": "Related NemotronH work, but not the same underlying change: #45115 only adds conversion/mapping and inheritance refactors, while #45569 creates separate NemotronH dense/sparse model packages, docs, and test updates. They could not plausibly be merged as one single PR without conflating distinct tasks." + "reason": "They share NemotronH implementation files, but 45115 focuses on GraniteMoeHybrid-style refactoring/conversion mapping while 45569 introduces a broader NemotronH dense/sparse model split with docs and tests. Different concrete changes, so not the same PR." } ] }, @@ -18457,8 +18394,8 @@ }, { "label": "pull_request", - "component_index": 21, - "component_count": 27, + "component_index": 20, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18474,7 +18411,7 @@ "soft_pairs": [ "pull_request:45332|pull_request:45333" ], - "prepared_review_unit_hash": "881c28c5a8bfd935ee44e153f427bc9fbc780b3d3433f653b74f335c9f64aee3", + "prepared_review_unit_hash": "34146f9b604c6318807b619275f90816a46f2bf466f1e66c10177b3eef9e3d85", "component_budget": { "node_count": 2, "item_count": 2, @@ -18496,18 +18433,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two PRs are related heterogeneous-modeling work, but they are not the same change: PR 45333 adds per-layer config support, while PR 45332 adds broader model/cache integration that builds on it.", - "confidence": 0.89, + "summary": "These PRs are related feature work, not duplicates: one adds heterogeneous per-layer config plumbing, the other adds heterogeneous model/runtime support that consumes it. They share some foundational files, but they address different layers of the implementation and would not be merged as one duplicate change.", + "confidence": 0.84, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45333 is the more foundational and self-contained change: it introduces the heterogeneous per-layer configuration API, whereas PR 45332 depends on that idea and extends into modeling/cache behavior.", + "canonical_pr_reason": "PR #45332 is the broader umbrella change: it includes the runtime/modeling integration and also references the heterogeneous config plumbing needed to make the feature usable end-to-end.", "best_issue_reason": null, - "best_pr_reason": "PR 45333 is the best representative of the cluster because it is narrower and establishes the core config mechanism; PR 45332 is a larger follow-on integration rather than a duplicate.", + "best_pr_reason": "PR #45332 is the best representative because it covers the user-facing heterogeneous model support and the concrete code-path changes beyond the config scaffolding.", "soft_edge_verdicts": [ { "left": "pull_request:45332", "right": "pull_request:45333", "accept": false, - "reason": "Related but distinct PRs: one adds heterogeneous config support, the other adds heterogeneous model/cache support. They share infrastructure but do not fix the same concrete code-path problem and would not be merged as one PR." + "reason": "Related but distinct scopes: #45333 is config-only per-layer support, while #45332 adds modeling/cache/masking integration that uses that config. They share groundwork, but they are not the same underlying change and should not be merged as duplicates." } ] }, @@ -18520,8 +18457,8 @@ }, { "label": "pull_request", - "component_index": 22, - "component_count": 27, + "component_index": 21, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18537,7 +18474,7 @@ "soft_pairs": [ "pull_request:45415|pull_request:45425" ], - "prepared_review_unit_hash": "5e414bf499d7c8976be5178eb04d2e0ed361c956eaf8fc1b0a32eef8cf24c5b7", + "prepared_review_unit_hash": "6a484169d52d658c4d988a673c2c1aa39fc03f2299eb860797ef8d14ff0fa954", "component_budget": { "node_count": 2, "item_count": 2, @@ -18559,18 +18496,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both items are typing-focused PRs, but they address different scopes: #45415 is a broad type-checking sweep across many `src/transformers/*.py` files, while #45425 adds specific typing protocols/helpers around `_typing.py` and modeling utilities. They are related in theme, not the same change.", - "confidence": 0.91, + "summary": "These are two separate typing-related PRs, but they address different changes: one is a broad repo-wide type-checking cleanup, the other adds specific typing protocols and targeted integration updates. They are not duplicates.", + "confidence": 0.89, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45425 is the more focused, concrete typing change; #45415 is a broad repo-wide type-checking cleanup rather than the same fix.", + "canonical_pr_reason": "PR 45425 is the more focused, self-contained typing change; it introduces concrete protocol/type aliases and targeted code updates rather than a broad sweep.", "best_issue_reason": null, - "best_pr_reason": "PR #45425 is the best representative because it has a narrow, specific code change and a clearer mergeable scope.", + "best_pr_reason": "PR 45425 is the better representative of the cluster because it has a narrower, more coherent purpose and clearer code-path intent.", "soft_edge_verdicts": [ { "left": "pull_request:45415", "right": "pull_request:45425", "accept": false, - "reason": "Shared typing theme and some overlapping files are too broad; one is a type-checking sweep, the other adds typing protocols/helpers. They do not fix the same concrete problem and should not be merged as duplicates." + "reason": "Overlap is only at the level of general typing cleanup and a few shared files. 45415 is a broad type-checking pass with ignore-rule adjustments, while 45425 adds specific typing protocols and targeted fixes; they are not the same underlying change and would not plausibly be merged as one PR." } ] }, @@ -18583,8 +18520,8 @@ }, { "label": "pull_request", - "component_index": 23, - "component_count": 27, + "component_index": 22, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18592,48 +18529,115 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-45487-2", + "cluster_id": "cluster-45487-6", "nodes": [ "pull_request:45487", - "pull_request:45836" + "pull_request:45817", + "pull_request:45836", + "pull_request:45842", + "pull_request:45843", + "pull_request:45844" ], "soft_pairs": [ - "pull_request:45487|pull_request:45836" + "pull_request:45487|pull_request:45843", + "pull_request:45487|pull_request:45842", + "pull_request:45487|pull_request:45836", + "pull_request:45817|pull_request:45843", + "pull_request:45817|pull_request:45842", + "pull_request:45836|pull_request:45842", + "pull_request:45836|pull_request:45843", + "pull_request:45836|pull_request:45844", + "pull_request:45842|pull_request:45843", + "pull_request:45843|pull_request:45844" ], - "prepared_review_unit_hash": "c5288973bf12fa988e7b1975a6f5e46f1f356126171e26e9b8c8b991f72b8f67", + "prepared_review_unit_hash": "5163687df060a9a391d9261d3f0216f5aed010755e73254c12de968be9629f6d", "component_budget": { - "node_count": 2, - "item_count": 2, - "soft_pair_count": 1, - "serialized_chars": 4722, - "estimated_input_tokens": 1181, - "estimated_eval_tokens": 2618 + "node_count": 6, + "item_count": 6, + "soft_pair_count": 10, + "serialized_chars": 15296, + "estimated_input_tokens": 3824, + "estimated_eval_tokens": 7904 }, "budget": { - "node_count": 2, - "item_count": 2, - "soft_pair_count": 1, - "serialized_chars": 4722, - "estimated_input_tokens": 1181, - "estimated_eval_tokens": 2618 + "node_count": 6, + "item_count": 6, + "soft_pair_count": 10, + "serialized_chars": 15296, + "estimated_input_tokens": 3824, + "estimated_eval_tokens": 7904 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two pull requests are unrelated: one fixes a real model-parallel/device placement bug in AltCLIP/ChineseCLIP code, while the other only skips an invalid MiniCPM-V test. The soft similarity is superficial and should not be merged.", - "confidence": 0.97, + "summary": "This is a loose topical cluster, not a duplicate set: most PRs are unrelated model-parallel fixes for different architectures, and a couple are test-only adjustments. They share a broad theme of \u201cfixing failures,\u201d but not the same underlying bug or change.", + "confidence": 0.91, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45487 is the substantive code fix: it patches device placement in model-parallel forward paths across AltCLIP/ChineseCLIP-related model files, addressing an actual runtime bug.", + "canonical_pr_reason": "45487 is the best representative because it makes a concrete code-path device-placement fix in model forward logic and includes targeted tests; the other substantive PRs fix different models, while the remaining ones are test-only changes.", "best_issue_reason": null, - "best_pr_reason": "PR 45487 is the best representative of the cluster because it changes production code to fix a concrete model-parallel issue; PR 45836 is only a test skip with no shared bug/change scope.", + "best_pr_reason": "45487 is the strongest PR candidate in this cluster for the same reason: it is the clearest real bug fix rather than a test tweak, but it is not duplicate with the others.", "soft_edge_verdicts": [ + { + "left": "pull_request:45487", + "right": "pull_request:45843", + "accept": false, + "reason": "Same broad model-parallel theme, but different models and different code paths; not the same underlying bug or change." + }, + { + "left": "pull_request:45487", + "right": "pull_request:45842", + "accept": false, + "reason": "45487 fixes a model-parallel device-placement bug; 45842 only adjusts Laguna test setup. Different problems." + }, { "left": "pull_request:45487", "right": "pull_request:45836", "accept": false, - "reason": "Different underlying problems and change types: 45487 fixes device handling in model code, while 45836 just disables a failing test for MiniCPM-V quantized cache compatibility. They could not plausibly be merged into one PR." + "reason": "45487 is a code fix; 45836 skips an invalid test. These are unrelated changes." + }, + { + "left": "pull_request:45817", + "right": "pull_request:45843", + "accept": false, + "reason": "Both are model-parallel fixes, but for different models and different failing paths; too broad to be a duplicate." + }, + { + "left": "pull_request:45817", + "right": "pull_request:45842", + "accept": false, + "reason": "Gemma4 model-parallel code fix versus Laguna test parameter change; not the same bug." + }, + { + "left": "pull_request:45836", + "right": "pull_request:45842", + "accept": false, + "reason": "Both are test-only changes, but they address different models and different failures." + }, + { + "left": "pull_request:45836", + "right": "pull_request:45843", + "accept": false, + "reason": "Test skip for MiniCPM-V versus Deimv2 model-parallel code fix; unrelated." + }, + { + "left": "pull_request:45836", + "right": "pull_request:45844", + "accept": false, + "reason": "MiniCPM-V test skip and Granite4-Vision test/model-parallel change are not the same underlying issue." + }, + { + "left": "pull_request:45842", + "right": "pull_request:45843", + "accept": false, + "reason": "Laguna test fix and Deimv2 model-parallel code fix target different failures." + }, + { + "left": "pull_request:45843", + "right": "pull_request:45844", + "accept": false, + "reason": "Deimv2 model-parallel fix versus Granite4-Vision test/model-splitting tweak; same general area, not the same change." } ] }, @@ -18646,8 +18650,8 @@ }, { "label": "pull_request", - "component_index": 24, - "component_count": 27, + "component_index": 23, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18663,7 +18667,7 @@ "soft_pairs": [ "pull_request:45548|pull_request:45662" ], - "prepared_review_unit_hash": "475f21378b0a178cda8a5ead73b5c8a3abf3306b6d3bda77e6973e1c8dc1f698", + "prepared_review_unit_hash": "80f456fff708dc0e9843c9bf21f6b0fd7a5509206865cea698629eb7ba32792a", "component_budget": { "node_count": 2, "item_count": 2, @@ -18685,18 +18689,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two PRs are related to expert-parallel/distributed loading, but they fix different bugs and should not be merged as duplicates. 45548 is about preserving EP config during Accelerate + ZeRO-3 loading, while 45662 prevents expert parameters from being overwritten during FSDP2 shard wrapping.", - "confidence": 0.94, + "summary": "These PRs are thematically related around expert-parallel loading, but they fix different concrete bugs and should not be merged as duplicates. PR 45548 is about EP + DeepSpeed ZeRO-3 loading via accelerate launch and config serialization; PR 45662 is about experts being overwritten by rank-0 broadcast in EP + FSDP2 loading.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "No true canonical duplicate here; the PRs target different failure modes and different load paths, so neither should be treated as the same change.", + "canonical_pr_reason": "45662 is the stronger canonical PR for the cluster because it addresses a specific data-corruption bug in expert-parallel loading with a clearer multi-file fix; 45548 is a separate, narrower accelerate/DeepSpeed serialization/loading issue.", "best_issue_reason": null, - "best_pr_reason": "If a representative is needed, 45662 is the stronger one because it fixes a concrete parameter-loading overwrite in the core code path and has the broader, more explicit runtime impact.", + "best_pr_reason": "45662 is the best overall PR candidate here because it targets a concrete code-path corruption problem and includes the more substantial fix across loading/integration paths.", "soft_edge_verdicts": [ { "left": "pull_request:45548", "right": "pull_request:45662", "accept": false, - "reason": "Both concern EP/distributed loading, but 45548 fixes config serialization and EP detection for Accelerate+ZeRO-3, while 45662 fixes a separate FSDP2 rank-0 broadcast overwrite in parameter assignment. Different bugs, not one PR." + "reason": "Both involve expert-parallel model loading, but the bugs differ: 45548 fixes EP + DeepSpeed ZeRO-3/accelerate serialization and initialization, while 45662 fixes expert parameters being overwritten by rank-0 broadcast under EP + FSDP2. Shared subsystem is not enough to treat them as the same change." } ] }, @@ -18709,8 +18713,8 @@ }, { "label": "pull_request", - "component_index": 25, - "component_count": 27, + "component_index": 24, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18726,7 +18730,7 @@ "soft_pairs": [ "pull_request:45639|pull_request:45645" ], - "prepared_review_unit_hash": "9c56c8a14903d1e3eed4711f029d764178371753e5f5d552677ff8fd03a2aca5", + "prepared_review_unit_hash": "39276d985a6250d297d5f633c665fe4ea5dcf697962aa5ac782ffba0dece6f09", "component_budget": { "node_count": 2, "item_count": 2, @@ -18748,18 +18752,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs target the same xdist collision problem for captured_info debug artifacts; one is a narrow fix, the other adds the CI-side log aggregation needed to handle multiple per-worker files.", - "confidence": 0.92, + "summary": "Both PRs target the same xdist collision in patched testing debug log capture; one is a narrower implementation, the other includes the broader CI/log handling around the same artifact path.", + "confidence": 0.84, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45645 is the better canonical PR because it includes the core xdist-safe file split in `testing_utils.py` and also updates CI/reporting to consume `captured_info*.txt`, making it the more complete implementation of the fix.", + "canonical_pr_reason": "PR 45645 is the more complete fix: it addresses the xdist-safe capture file naming and also updates CI to collect multiple captured_info files, matching the broader artifact-handling problem.", "best_issue_reason": null, - "best_pr_reason": "PR 45645 is the strongest standalone PR: it addresses the underlying collision bug and the downstream log-preservation path, so it is the most complete and mergeable change set.", + "best_pr_reason": "PR 45645 is the best standalone candidate because it covers the core bug plus the downstream log collection change needed to preserve debug output in CI.", "soft_edge_verdicts": [ { "left": "pull_request:45639", "right": "pull_request:45645", "accept": true, - "reason": "Same underlying bug: unsafe shared `captured_info.txt` output under xdist. PR 45645 appears to extend the same fix with workflow changes to read multiple per-worker files, so they are closely related enough to cluster as one change." + "reason": "Both PRs fix the same underlying captured_info/xdist collision path in testing_utils; 45645 extends the same fix with CI log aggregation, and they could plausibly be merged into one PR." } ] }, @@ -18772,8 +18776,8 @@ }, { "label": "pull_request", - "component_index": 26, - "component_count": 27, + "component_index": 25, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18835,8 +18839,8 @@ }, { "label": "pull_request", - "component_index": 27, - "component_count": 27, + "component_index": 26, + "component_count": 26, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", diff --git a/analysis/current/manifest.json b/analysis/current/manifest.json index 3b6dd9833e4ae590904d5f208d43de0ba903be67..75f1c2b75f06ccf2ce6e34c3bdaf430362dcf1f5 100644 --- a/analysis/current/manifest.json +++ b/analysis/current/manifest.json @@ -1,8 +1,8 @@ { - "analysis_id": "hybrid-model-20260508t060024z", + "analysis_id": "hybrid-model-20260508t120022z", "archived_artifacts": { - "hybrid": "snapshots/20260508T060024Z/analysis-runs/hybrid-model-20260508t060024z/analysis-report-hybrid.json", - "hybrid_reviews": "snapshots/20260508T060024Z/analysis-runs/hybrid-model-20260508t060024z/analysis-report-hybrid.llm-reviews.json" + "hybrid": "snapshots/20260508T120022Z/analysis-runs/hybrid-model-20260508t120022z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260508T120022Z/analysis-runs/hybrid-model-20260508t120022z/analysis-report-hybrid.llm-reviews.json" }, "artifacts": { "hybrid": "analysis/current/analysis-report-hybrid.json", @@ -10,9 +10,9 @@ }, "channel": "canonical", "model": null, - "published_at": "2026-05-08T06:10:57Z", + "published_at": "2026-05-08T12:10:15Z", "repo": "huggingface/transformers", "schema_version": 1, - "snapshot_id": "20260508T060024Z", + "snapshot_id": "20260508T120022Z", "variant": "hybrid" } diff --git a/snapshots/20260508T120022Z/analysis-runs/hybrid-model-20260508t120022z/analysis-report-hybrid.json b/snapshots/20260508T120022Z/analysis-runs/hybrid-model-20260508t120022z/analysis-report-hybrid.json new file mode 100644 index 0000000000000000000000000000000000000000..3be775bcf4551a3bd6eef8b783269cddb622cf7e --- /dev/null +++ b/snapshots/20260508T120022Z/analysis-runs/hybrid-model-20260508t120022z/analysis-report-hybrid.json @@ -0,0 +1,2076 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260508T120022Z", + "generated_at": "2026-05-08T12:10:13Z", + "evidence_quality": "full", + "llm_enrichment": true, + "meta_bugs": [ + { + "cluster_id": "cluster-43979-11", + "summary": "Cluster of 1 issues and 10 PRs centered on issue #43979.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 43979, + "canonical_pr_number": 44007, + "issue_numbers": [ + 43979 + ], + "pr_numbers": [ + 43996, + 44007, + 44013, + 44044, + 44066, + 44072, + 44085, + 44129, + 44154, + 44722 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 43996, + "right_pr_number": 44007, + "code_similarity": 0.179, + "size_similarity": 0.576, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.429, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44013, + "code_similarity": 0.122, + "size_similarity": 0.318, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.392, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44044, + "code_similarity": 0.245, + "size_similarity": 0.864, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.479, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44066, + "code_similarity": 0.225, + "size_similarity": 0.818, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.408, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44072, + "code_similarity": 0.14, + "size_similarity": 0.303, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.528, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44085, + "code_similarity": 0.216, + "size_similarity": 0.783, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.398, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44129, + "code_similarity": 0.163, + "size_similarity": 0.643, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.229, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44154, + "code_similarity": 0.153, + "size_similarity": 0.535, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.31, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44722, + "code_similarity": 0.225, + "size_similarity": 0.848, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.368, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44013, + "code_similarity": 0.19, + "size_similarity": 0.553, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.531, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44044, + "code_similarity": 0.186, + "size_similarity": 0.667, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.354, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44066, + "code_similarity": 0.188, + "size_similarity": 0.704, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.315, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44072, + "code_similarity": 0.212, + "size_similarity": 0.526, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.708, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44085, + "code_similarity": 0.195, + "size_similarity": 0.735, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.318, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44129, + "code_similarity": 0.103, + "size_similarity": 0.37, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.191, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44154, + "code_similarity": 0.238, + "size_similarity": 0.93, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.344, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44722, + "code_similarity": 0.178, + "size_similarity": 0.679, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.28, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44044, + "code_similarity": 0.126, + "size_similarity": 0.368, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.351, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44066, + "code_similarity": 0.127, + "size_similarity": 0.389, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.325, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44072, + "code_similarity": 0.29, + "size_similarity": 0.952, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.667, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44085, + "code_similarity": 0.131, + "size_similarity": 0.406, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.329, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44129, + "code_similarity": 0.07, + "size_similarity": 0.205, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.192, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44154, + "code_similarity": 0.177, + "size_similarity": 0.594, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.389, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44722, + "code_similarity": 0.118, + "size_similarity": 0.375, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.287, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44066, + "code_similarity": 0.25, + "size_similarity": 0.947, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.404, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44072, + "code_similarity": 0.136, + "size_similarity": 0.351, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.442, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44085, + "code_similarity": 0.24, + "size_similarity": 0.906, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.394, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44129, + "code_similarity": 0.147, + "size_similarity": 0.555, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.243, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44154, + "code_similarity": 0.17, + "size_similarity": 0.62, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.306, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44722, + "code_similarity": 0.257, + "size_similarity": 0.982, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.402, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44072, + "code_similarity": 0.133, + "size_similarity": 0.37, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.393, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44085, + "code_similarity": 0.763, + "size_similarity": 0.957, + "file_overlap": 0.5, + "area_overlap": 0.825, + "patch_similarity": 0.887, + "shared_filenames": [ + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 41 + ], + [ + 174, + 181 + ], + [ + 250, + 257 + ], + [ + 398, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 466 + ], + [ + 471, + 488 + ], + [ + 518, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 606 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ], + "right_ranges": [ + [ + 33, + 40 + ], + [ + 173, + 180 + ], + [ + 249, + 256 + ], + [ + 397, + 405 + ], + [ + 408, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 465 + ], + [ + 470, + 489 + ], + [ + 517, + 539 + ], + [ + 553, + 559 + ], + [ + 565, + 574 + ], + [ + 579, + 597 + ], + [ + 600, + 611 + ], + [ + 633, + 639 + ], + [ + 645, + 652 + ], + [ + 657, + 673 + ], + [ + 716, + 728 + ], + [ + 737, + 743 + ], + [ + 748, + 771 + ], + [ + 789, + 794 + ] + ] + } + ] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44129, + "code_similarity": 0.145, + "size_similarity": 0.526, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.263, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44154, + "code_similarity": 0.174, + "size_similarity": 0.654, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.286, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44722, + "code_similarity": 0.907, + "size_similarity": 0.964, + "file_overlap": 1.0, + "area_overlap": 0.808, + "patch_similarity": 0.874, + "shared_filenames": [ + "src/transformers/models/codegen/modeling_codegen.py", + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/codegen/modeling_codegen.py", + "left_ranges": [ + [ + 245, + 266 + ] + ], + "right_ranges": [ + [ + 228, + 234 + ] + ] + }, + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 41 + ], + [ + 174, + 181 + ], + [ + 250, + 257 + ], + [ + 398, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 466 + ], + [ + 471, + 488 + ], + [ + 518, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 606 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ], + "right_ranges": [ + [ + 33, + 42 + ], + [ + 175, + 182 + ], + [ + 251, + 258 + ], + [ + 399, + 420 + ], + [ + 426, + 435 + ], + [ + 460, + 467 + ], + [ + 472, + 489 + ], + [ + 519, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 612 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 663 + ], + [ + 666, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ] + } + ] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44085, + "code_similarity": 0.137, + "size_similarity": 0.387, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.398, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44129, + "code_similarity": 0.074, + "size_similarity": 0.195, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.231, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44154, + "code_similarity": 0.175, + "size_similarity": 0.566, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.414, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44722, + "code_similarity": 0.124, + "size_similarity": 0.357, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.347, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44129, + "code_similarity": 0.141, + "size_similarity": 0.503, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.272, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44154, + "code_similarity": 0.18, + "size_similarity": 0.684, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.289, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44722, + "code_similarity": 0.728, + "size_similarity": 0.923, + "file_overlap": 0.5, + "area_overlap": 0.791, + "patch_similarity": 0.78, + "shared_filenames": [ + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 40 + ], + [ + 173, + 180 + ], + [ + 249, + 256 + ], + [ + 397, + 405 + ], + [ + 408, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 465 + ], + [ + 470, + 489 + ], + [ + 517, + 539 + ], + [ + 553, + 559 + ], + [ + 565, + 574 + ], + [ + 579, + 597 + ], + [ + 600, + 611 + ], + [ + 633, + 639 + ], + [ + 645, + 652 + ], + [ + 657, + 673 + ], + [ + 716, + 728 + ], + [ + 737, + 743 + ], + [ + 748, + 771 + ], + [ + 789, + 794 + ] + ], + "right_ranges": [ + [ + 33, + 42 + ], + [ + 175, + 182 + ], + [ + 251, + 258 + ], + [ + 399, + 420 + ], + [ + 426, + 435 + ], + [ + 460, + 467 + ], + [ + 472, + 489 + ], + [ + 519, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 612 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 663 + ], + [ + 666, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ] + } + ] + }, + { + "left_pr_number": 44129, + "right_pr_number": 44154, + "code_similarity": 0.099, + "size_similarity": 0.344, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.199, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44129, + "right_pr_number": 44722, + "code_similarity": 0.146, + "size_similarity": 0.545, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.247, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44154, + "right_pr_number": 44722, + "code_similarity": 0.164, + "size_similarity": 0.631, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.255, + "shared_filenames": [], + "shared_file_areas": [] + } + ] + }, + { + "cluster_id": "cluster-41211-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #41211.", + "status": "open", + "confidence": 0.55, + "canonical_issue_number": 41211, + "canonical_pr_number": 44339, + "issue_numbers": [ + 41211 + ], + "pr_numbers": [ + 41356, + 44339 + ], + "evidence_types": [ + "closing_reference" + ], + "pr_comparisons": [ + { + "left_pr_number": 41356, + "right_pr_number": 44339, + "code_similarity": 0.155, + "size_similarity": 0.094, + "file_overlap": 0.273, + "area_overlap": 0.078, + "patch_similarity": 0.183, + "shared_filenames": [ + "docs/source/en/model_doc/deimv2.md", + "src/transformers/models/deimv2/__init__.py", + "src/transformers/models/deimv2/configuration_deimv2.py", + "src/transformers/models/deimv2/modeling_deimv2.py", + "tests/models/deimv2/__init__.py", + "tests/models/deimv2/test_modeling_deimv2.py" + ], + "shared_file_areas": [ + { + "filename": "docs/source/en/model_doc/deimv2.md", + "left_ranges": [ + [ + 1, + 132 + ] + ], + "right_ranges": [ + [ + 1, + 65 + ] + ] + }, + { + "filename": "src/transformers/models/deimv2/__init__.py", + "left_ranges": [ + [ + 1, + 15 + ] + ], + "right_ranges": [ + [ + 1, + 29 + ] + ] + }, + { + "filename": "src/transformers/models/deimv2/configuration_deimv2.py", + "left_ranges": [ + [ + 1, + 74 + ] + ], + "right_ranges": [ + [ + 1, + 266 + ] + ] + }, + { + "filename": "tests/models/deimv2/test_modeling_deimv2.py", + "left_ranges": [ + [ + 1, + 15 + ] + ], + "right_ranges": [ + [ + 1, + 1734 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43240-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #43240.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 43240, + "canonical_pr_number": 43251, + "issue_numbers": [ + 43240 + ], + "pr_numbers": [ + 43251, + 43254 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 43251, + "right_pr_number": 43254, + "code_similarity": 0.794, + "size_similarity": 0.64, + "file_overlap": 1.0, + "area_overlap": 0.667, + "patch_similarity": 0.882, + "shared_filenames": [ + "src/transformers/loss/loss_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/loss/loss_utils.py", + "left_ranges": [ + [ + 30, + 50 + ] + ], + "right_ranges": [ + [ + 30, + 43 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-41115-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #41115.", + "status": "open", + "confidence": 0.55, + "canonical_issue_number": 41115, + "canonical_pr_number": 45613, + "issue_numbers": [ + 41115 + ], + "pr_numbers": [ + 41116, + 45613 + ], + "evidence_types": [ + "closing_reference" + ], + "pr_comparisons": [ + { + "left_pr_number": 41116, + "right_pr_number": 45613, + "code_similarity": 0.805, + "size_similarity": 0.885, + "file_overlap": 0.75, + "area_overlap": 0.854, + "patch_similarity": 0.693, + "shared_filenames": [ + "docs/source/en/_toctree.yml", + "docs/source/en/model_doc/minicpm3.md", + "src/transformers/models/auto/modeling_auto.py", + "src/transformers/models/minicpm3/__init__.py", + "src/transformers/models/minicpm3/configuration_minicpm3.py", + "src/transformers/models/minicpm3/modeling_minicpm3.py", + "src/transformers/models/minicpm3/modular_minicpm3.py", + "tests/models/minicpm3/__init__.py", + "tests/models/minicpm3/test_modeling_minicpm3.py" + ], + "shared_file_areas": [ + { + "filename": "docs/source/en/_toctree.yml", + "left_ranges": [ + [ + 713, + 720 + ] + ], + "right_ranges": [ + [ + 713, + 720 + ] + ] + }, + { + "filename": "docs/source/en/model_doc/minicpm3.md", + "left_ranges": [ + [ + 1, + 67 + ] + ], + "right_ranges": [ + [ + 1, + 45 + ] + ] + }, + { + "filename": "src/transformers/models/auto/modeling_auto.py", + "left_ranges": [ + [ + 285, + 291 + ], + [ + 700, + 706 + ], + [ + 1298, + 1304 + ] + ], + "right_ranges": [ + [ + 699, + 705 + ], + [ + 1301, + 1307 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/__init__.py", + "left_ranges": [ + [ + 1, + 29 + ] + ], + "right_ranges": [ + [ + 1, + 29 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/configuration_minicpm3.py", + "left_ranges": [ + [ + 1, + 141 + ] + ], + "right_ranges": [ + [ + 1, + 126 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/modeling_minicpm3.py", + "left_ranges": [ + [ + 1, + 544 + ] + ], + "right_ranges": [ + [ + 1, + 522 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/modular_minicpm3.py", + "left_ranges": [ + [ + 1, + 444 + ] + ], + "right_ranges": [ + [ + 1, + 342 + ] + ] + }, + { + "filename": "tests/models/minicpm3/test_modeling_minicpm3.py", + "left_ranges": [ + [ + 1, + 109 + ] + ], + "right_ranges": [ + [ + 1, + 136 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45647-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45647.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 45647, + "canonical_pr_number": 45738, + "issue_numbers": [ + 45647 + ], + "pr_numbers": [ + 45737, + 45738 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 45737, + "right_pr_number": 45738, + "code_similarity": 0.526, + "size_similarity": 0.11, + "file_overlap": 0.5, + "area_overlap": 1.0, + "patch_similarity": 0.024, + "shared_filenames": [ + "src/transformers/models/musicgen_melody/modeling_musicgen_melody.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/musicgen_melody/modeling_musicgen_melody.py", + "left_ranges": [ + [ + 491, + 497 + ] + ], + "right_ranges": [ + [ + 491, + 497 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43824-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #43824.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 43824, + "canonical_pr_number": 43836, + "issue_numbers": [ + 43824 + ], + "pr_numbers": [ + 43836, + 43842 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 43836, + "right_pr_number": 43842, + "code_similarity": 0.332, + "size_similarity": 0.088, + "file_overlap": 1.0, + "area_overlap": 0.033, + "patch_similarity": 0.017, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 359, + 429 + ], + [ + 584, + 590 + ], + [ + 1892, + 1910 + ], + [ + 1917, + 1923 + ] + ], + "right_ranges": [ + [ + 54, + 61 + ], + [ + 587, + 593 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45081-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45081.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 45081, + "canonical_pr_number": 45317, + "issue_numbers": [ + 45081 + ], + "pr_numbers": [ + 45086, + 45317 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 45086, + "right_pr_number": 45317, + "code_similarity": 0.589, + "size_similarity": 0.34, + "file_overlap": 0.5, + "area_overlap": 1.0, + "patch_similarity": 0.136, + "shared_filenames": [ + "src/transformers/tokenization_utils_tokenizers.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/tokenization_utils_tokenizers.py", + "left_ranges": [ + [ + 1360, + 1370 + ], + [ + 1374, + 1380 + ] + ], + "right_ranges": [ + [ + 1360, + 1370 + ], + [ + 1374, + 1380 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45561-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45561.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 45561, + "canonical_pr_number": 45645, + "issue_numbers": [ + 45561 + ], + "pr_numbers": [ + 45639, + 45645 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 45639, + "right_pr_number": 45645, + "code_similarity": 0.532, + "size_similarity": 0.619, + "file_overlap": 0.5, + "area_overlap": 0.543, + "patch_similarity": 0.451, + "shared_filenames": [ + "src/transformers/testing_utils.py", + "tests/utils/test_testing_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/testing_utils.py", + "left_ranges": [ + [ + 3529, + 3536 + ], + [ + 3753, + 3787 + ] + ], + "right_ranges": [ + [ + 3525, + 3558 + ], + [ + 3782, + 3788 + ] + ] + }, + { + "filename": "tests/utils/test_testing_utils.py", + "left_ranges": [ + [ + 1, + 86 + ] + ], + "right_ranges": [ + [ + 1, + 114 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43698-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #43698.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 43698, + "canonical_pr_number": 43779, + "issue_numbers": [ + 43698 + ], + "pr_numbers": [ + 43779, + 43816 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 43779, + "right_pr_number": 43816, + "code_similarity": 0.418, + "size_similarity": 0.538, + "file_overlap": 1.0, + "area_overlap": 0.02, + "patch_similarity": 0.02, + "shared_filenames": [ + "src/transformers/integrations/integration_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/integrations/integration_utils.py", + "left_ranges": [ + [ + 2227, + 2241 + ], + [ + 2303, + 2309 + ] + ], + "right_ranges": [ + [ + 2278, + 2291 + ], + [ + 2309, + 2322 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-44018-2", + "summary": "Cluster of 2 related pull requests linked by soft_similarity.", + "status": "open", + "confidence": 0.5, + "canonical_issue_number": null, + "canonical_pr_number": 44068, + "issue_numbers": [], + "pr_numbers": [ + 44018, + 44068 + ], + "evidence_types": [ + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 44018, + "right_pr_number": 44068, + "code_similarity": 0.766, + "size_similarity": 0.939, + "file_overlap": 1.0, + "area_overlap": 0.425, + "patch_similarity": 0.866, + "shared_filenames": [ + "src/transformers/models/gpt_neo/modeling_gpt_neo.py", + "tests/models/gpt_neo/test_modeling_gpt_neo.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/gpt_neo/modeling_gpt_neo.py", + "left_ranges": [ + [ + 26, + 46 + ], + [ + 138, + 143 + ], + [ + 182, + 187 + ], + [ + 283, + 295 + ], + [ + 327, + 341 + ], + [ + 348, + 354 + ], + [ + 360, + 369 + ], + [ + 399, + 406 + ], + [ + 411, + 419 + ], + [ + 428, + 433 + ], + [ + 472, + 492 + ], + [ + 507, + 513 + ], + [ + 519, + 528 + ], + [ + 541, + 559 + ], + [ + 562, + 567 + ], + [ + 595, + 601 + ], + [ + 607, + 614 + ], + [ + 627, + 643 + ], + [ + 685, + 690 + ], + [ + 708, + 714 + ], + [ + 720, + 727 + ], + [ + 740, + 757 + ], + [ + 761, + 766 + ], + [ + 780, + 786 + ], + [ + 791, + 798 + ], + [ + 807, + 822 + ], + [ + 840, + 845 + ] + ], + "right_ranges": [ + [ + 26, + 31 + ], + [ + 34, + 44 + ], + [ + 136, + 141 + ], + [ + 180, + 185 + ], + [ + 281, + 293 + ], + [ + 325, + 339 + ], + [ + 346, + 352 + ], + [ + 358, + 367 + ], + [ + 397, + 404 + ], + [ + 409, + 417 + ], + [ + 426, + 434 + ], + [ + 463, + 483 + ], + [ + 498, + 504 + ], + [ + 510, + 519 + ], + [ + 532, + 550 + ], + [ + 553, + 564 + ], + [ + 586, + 592 + ], + [ + 598, + 605 + ], + [ + 618, + 634 + ], + [ + 676, + 688 + ], + [ + 699, + 705 + ], + [ + 711, + 718 + ], + [ + 731, + 748 + ], + [ + 752, + 762 + ], + [ + 771, + 777 + ], + [ + 782, + 789 + ], + [ + 798, + 813 + ], + [ + 831, + 836 + ] + ] + }, + { + "filename": "tests/models/gpt_neo/test_modeling_gpt_neo.py", + "left_ranges": [ + [ + 458, + 464 + ] + ], + "right_ranges": [ + [ + 458, + 464 + ] + ] + } + ] + } + ] + } + ], + "duplicate_issues": [], + "duplicate_prs": [ + { + "cluster_id": "cluster-41115-3", + "canonical_pr_number": 45613, + "duplicate_pr_numbers": [ + 41116 + ], + "target_issue_number": 41115, + "reason": "PRs in cluster-41115-3 are treated as duplicates because they converge on issue #41115 with closing_reference evidence." + }, + { + "cluster_id": "cluster-41211-3", + "canonical_pr_number": 44339, + "duplicate_pr_numbers": [ + 41356 + ], + "target_issue_number": 41211, + "reason": "PRs in cluster-41211-3 are treated as duplicates because they converge on issue #41211 with closing_reference evidence." + }, + { + "cluster_id": "cluster-43240-3", + "canonical_pr_number": 43251, + "duplicate_pr_numbers": [ + 43254 + ], + "target_issue_number": 43240, + "reason": "PRs in cluster-43240-3 are treated as duplicates because they converge on issue #43240 with closing_reference, shared_issue_target evidence." + }, + { + "cluster_id": "cluster-43698-3", + "canonical_pr_number": 43779, + "duplicate_pr_numbers": [ + 43816 + ], + "target_issue_number": 43698, + "reason": "PRs in cluster-43698-3 are treated as duplicates because they converge on issue #43698 with closing_reference, shared_issue_target evidence." + }, + { + "cluster_id": "cluster-43824-3", + "canonical_pr_number": 43836, + "duplicate_pr_numbers": [ + 43842 + ], + "target_issue_number": 43824, + "reason": "PRs in cluster-43824-3 are treated as duplicates because they converge on issue #43824 with closing_reference, shared_issue_target evidence." + }, + { + "cluster_id": "cluster-43979-11", + "canonical_pr_number": 44007, + "duplicate_pr_numbers": [ + 43996, + 44013, + 44044, + 44066, + 44072, + 44085, + 44129, + 44154, + 44722 + ], + "target_issue_number": 43979, + "reason": "PRs in cluster-43979-11 are treated as duplicates because they converge on issue #43979 with closing_reference, shared_issue_target, soft_similarity evidence." + }, + { + "cluster_id": "cluster-44018-2", + "canonical_pr_number": 44068, + "duplicate_pr_numbers": [ + 44018 + ], + "target_issue_number": null, + "reason": "PRs in cluster-44018-2 are treated as duplicates because they share soft_similarity evidence." + }, + { + "cluster_id": "cluster-45081-3", + "canonical_pr_number": 45317, + "duplicate_pr_numbers": [ + 45086 + ], + "target_issue_number": 45081, + "reason": "PRs in cluster-45081-3 are treated as duplicates because they converge on issue #45081 with closing_reference, shared_issue_target, soft_similarity evidence." + }, + { + "cluster_id": "cluster-45561-3", + "canonical_pr_number": 45645, + "duplicate_pr_numbers": [ + 45639 + ], + "target_issue_number": 45561, + "reason": "PRs in cluster-45561-3 are treated as duplicates because they converge on issue #45561 with closing_reference, shared_issue_target, soft_similarity evidence." + }, + { + "cluster_id": "cluster-45647-3", + "canonical_pr_number": 45738, + "duplicate_pr_numbers": [ + 45737 + ], + "target_issue_number": 45647, + "reason": "PRs in cluster-45647-3 are treated as duplicates because they converge on issue #45647 with closing_reference, shared_issue_target evidence." + } + ], + "best_issue": { + "cluster_id": "cluster-45647-3", + "issue_number": 45647, + "reason": "Issue #45647 is the strongest global issue candidate because it is open, belongs to a cluster with 3 artifacts, and carries 12 discussion comments plus 8 inbound references.", + "score": 162.0 + }, + "best_pr": { + "cluster_id": "cluster-43979-11", + "pr_number": 44007, + "reason": "PR #44007 is the strongest global PR candidate because it is open, belongs to a cluster with 11 artifacts, links to 1 issues, and carries 2 review/discussion events.", + "score": 238.886 + } +} diff --git a/snapshots/20260508T120022Z/analysis-runs/hybrid-model-20260508t120022z/analysis-report-hybrid.llm-reviews.json b/snapshots/20260508T120022Z/analysis-runs/hybrid-model-20260508t120022z/analysis-report-hybrid.llm-reviews.json new file mode 100644 index 0000000000000000000000000000000000000000..ef036a53ad8c7e26d0253eaca8b422a79d9b3d56 --- /dev/null +++ b/snapshots/20260508T120022Z/analysis-runs/hybrid-model-20260508t120022z/analysis-report-hybrid.llm-reviews.json @@ -0,0 +1,18907 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260508T120022Z", + "generated_at": "2026-05-08T12:10:13Z", + "model": "gpt-5.4-mini?service_tier=flex", + "reviews": [ + { + "label": "issue", + "component_index": 1, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-13244-3", + "nodes": [ + "issue:13244", + "issue:15980", + "issue:16618" + ], + "soft_pairs": [ + "issue:13244|issue:16618", + "issue:15980|issue:16618" + ], + "prepared_review_unit_hash": "163347cf52a23d6c0061f8f90f2a785aee2a1a121517e2921c467a377909dc58", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 2478, + "estimated_input_tokens": 620, + "estimated_eval_tokens": 1496 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 2478, + "estimated_input_tokens": 620, + "estimated_eval_tokens": 1496 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These three issues do not appear to describe the same underlying bug: one is about Tapas tokenization parity, one about private-model download/login error handling, and one about failing to load bert-base-uncased. The soft links are too broad to merge as duplicates.", + "confidence": 0.87, + "canonical_issue_reason": "Issue #16618 is the most concrete and user-facing of the set, with a clear runtime failure scenario and a specific model name, so it is the best representative issue if one must be chosen.", + "canonical_pr_reason": null, + "best_issue_reason": "#16618 has the clearest actionable symptom and is the most likely to be useful as the cluster representative; the other two are unrelated enough that they should not be treated as duplicates.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:13244", + "right": "issue:16618", + "accept": false, + "reason": "Different problem domains: Tapas tokenization parity vs. model loading failure for bert-base-uncased. No evidence they share the same code path or fix." + }, + { + "left": "issue:15980", + "right": "issue:16618", + "accept": false, + "reason": "One is specifically about bad messaging when downloading a private model without login; the other is a load failure for a public model. Related at a very broad level, but not the same bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:24643", + "issue:30277", + "issue:34634", + "issue:34928", + "issue:35545", + "issue:36010", + "issue:36331", + "issue:39290", + "issue:41093", + "issue:41720", + "issue:41762", + "issue:42915", + "issue:43039", + "issue:43404", + "issue:43425", + "issue:43531", + "issue:43541", + "issue:43596", + "issue:43638", + "issue:43716", + "issue:43792", + "issue:43827", + "issue:43828", + "issue:43854", + "issue:43866", + "issue:43901", + "issue:43975", + "issue:44292", + "issue:44322", + "issue:44457", + "issue:44509", + "issue:44512", + "issue:44560", + "issue:44805", + "issue:44841", + "issue:44863", + "issue:44918", + "issue:45070", + "issue:45081", + "issue:45084", + "issue:45161", + "issue:45237", + "issue:45362", + "issue:45464", + "issue:45507", + "issue:45685", + "issue:45800", + "issue:45823" + ], + "soft_pairs": [ + "issue:44322|issue:45464", + "issue:45237|issue:45685", + "issue:43716|issue:45237", + "issue:43828|issue:45237", + "issue:45237|issue:45507", + "issue:44292|issue:45237", + "issue:30277|issue:35545", + "issue:35545|issue:42915", + "issue:35545|issue:41720", + "issue:44509|issue:44512", + "issue:35545|issue:36010", + "issue:44805|issue:45823", + "issue:43638|issue:44805", + "issue:43596|issue:44805", + "issue:44805|issue:45161", + "issue:44805|issue:44918", + "issue:34634|issue:35545", + "issue:30277|issue:43638", + "issue:43596|issue:43638", + "issue:43975|issue:44457", + "issue:43039|issue:45161", + "issue:44292|issue:44457", + "issue:34928|issue:44805", + "issue:24643|issue:30277", + "issue:43638|issue:45161", + "issue:34928|issue:36331", + "issue:43596|issue:45161", + "issue:43716|issue:45507", + "issue:39290|issue:45081", + "issue:43828|issue:45161", + "issue:43425|issue:44292", + "issue:44918|issue:45161", + "issue:34928|issue:41720", + "issue:43716|issue:45685", + "issue:43541|issue:43716", + "issue:43828|issue:44292", + "issue:45507|issue:45685", + "issue:43716|issue:44292", + "issue:44292|issue:44918", + "issue:43039|issue:44918", + "issue:41762|issue:43638", + "issue:43827|issue:44512", + "issue:43716|issue:44560", + "issue:43828|issue:45685", + "issue:44560|issue:45685", + "issue:43039|issue:43828", + "issue:30277|issue:36331", + "issue:34928|issue:36010", + "issue:43039|issue:44805", + "issue:41762|issue:43596", + "issue:43901|issue:44512", + "issue:39290|issue:41720", + "issue:44841|issue:45823", + "issue:43039|issue:44560", + "issue:43866|issue:44863", + "issue:43854|issue:43866", + "issue:39290|issue:43531", + "issue:41093|issue:43638", + "issue:43425|issue:45070", + "issue:43596|issue:45800", + "issue:45362|issue:45464", + "issue:43792|issue:45070", + "issue:43404|issue:43866", + "issue:39290|issue:45823", + "issue:45464|issue:45685", + "issue:43541|issue:45685", + "issue:43541|issue:43828", + "issue:36010|issue:39290", + "issue:44841|issue:45084", + "issue:41093|issue:41762", + "issue:45800|issue:45823" + ], + "prepared_review_unit_hash": "2734970753240655d80ec58cc7a5a101573ded43fad79c17f2d0241bb1a34924", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 71, + "serialized_chars": 48874, + "estimated_input_tokens": 12219, + "estimated_eval_tokens": 24694 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly a grab bag of unrelated issues. The only clear duplicate pair is the Deepspeed ZeRO-3/Bert index-out-of-bounds reports (43596 and 43638); the rest are different model, docs, or runtime failures.", + "confidence": 0.61, + "canonical_issue_reason": "Issue 43596 is the best anchor for the ZeRO-3/Bert \"index 0 is out of bounds\" duplicate pair; it is the broader, earlier phrasing of that bug, which also covers 43638.", + "canonical_pr_reason": null, + "best_issue_reason": "43596 is the strongest single representative because it matches the same concrete ZeRO-3/Bert failure mode as 43638 and is the cleanest canonical target in this set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44322", + "right": "issue:45464", + "accept": false, + "reason": "Different model and failure mode; not the same bug." + }, + { + "left": "issue:45237", + "right": "issue:45685", + "accept": false, + "reason": "Different hardware/backend error paths; not the same issue." + }, + { + "left": "issue:43716", + "right": "issue:45237", + "accept": false, + "reason": "Different model family and runtime problem." + }, + { + "left": "issue:43828", + "right": "issue:45237", + "accept": false, + "reason": "Both mention inference errors, but they are different concrete bugs." + }, + { + "left": "issue:45237", + "right": "issue:45507", + "accept": false, + "reason": "Different model and error type; not mergeable as one fix." + }, + { + "left": "issue:44292", + "right": "issue:45237", + "accept": false, + "reason": "Different model/runtime context; no clear shared code path." + }, + { + "left": "issue:30277", + "right": "issue:35545", + "accept": false, + "reason": "Different subsystems: distributed training vs ONNX export." + }, + { + "left": "issue:35545", + "right": "issue:42915", + "accept": false, + "reason": "Different model/export bug vs FP8 config failure." + }, + { + "left": "issue:35545", + "right": "issue:41720", + "accept": false, + "reason": "Different failure modes and model paths." + }, + { + "left": "issue:44509", + "right": "issue:44512", + "accept": false, + "reason": "Both are docs regressions, but they concern different removed topics." + }, + { + "left": "issue:35545", + "right": "issue:36010", + "accept": false, + "reason": "Different bugs: export to ONNX vs import error." + }, + { + "left": "issue:44805", + "right": "issue:45823", + "accept": false, + "reason": "Different model/runtime errors; no shared concrete bug." + }, + { + "left": "issue:43638", + "right": "issue:44805", + "accept": false, + "reason": "Both are IndexError-shaped, but the triggering conditions and stack paths differ." + }, + { + "left": "issue:43596", + "right": "issue:44805", + "accept": false, + "reason": "Different error signatures and likely different code paths." + }, + { + "left": "issue:44805", + "right": "issue:45161", + "accept": false, + "reason": "Different failure modes; only a broad index-error similarity." + }, + { + "left": "issue:44805", + "right": "issue:44918", + "accept": false, + "reason": "Different model and runtime context." + }, + { + "left": "issue:34634", + "right": "issue:35545", + "accept": false, + "reason": "Unrelated features: BarkProcessor preset handling vs ONNX export." + }, + { + "left": "issue:30277", + "right": "issue:43638", + "accept": false, + "reason": "Different distributed-training bugs and different models." + }, + { + "left": "issue:43596", + "right": "issue:43638", + "accept": true, + "reason": "Same ZeRO-3/Bert \"index 0 is out of bounds\" failure; only the pretrained/non-pretrained wording differs." + }, + { + "left": "issue:43975", + "right": "issue:44457", + "accept": false, + "reason": "Different models and different tokenization/LoRA behaviors." + }, + { + "left": "issue:43039", + "right": "issue:45161", + "accept": false, + "reason": "Different MoE/kernel issue vs TP-only failure." + }, + { + "left": "issue:44292", + "right": "issue:44457", + "accept": false, + "reason": "Different model/runtime bug; no shared underlying change." + }, + { + "left": "issue:34928", + "right": "issue:44805", + "accept": false, + "reason": "Checkpointing/FSDP mismatch is unrelated to the mask-shape IndexError." + }, + { + "left": "issue:24643", + "right": "issue:30277", + "accept": false, + "reason": "Different DeepSpeed-related errors with different symptoms." + }, + { + "left": "issue:43638", + "right": "issue:45161", + "accept": false, + "reason": "Different model and distributed setup; not the same bug." + }, + { + "left": "issue:34928", + "right": "issue:36331", + "accept": false, + "reason": "Activation-checkpointing/FSDP issue is unrelated to CustomTrainer signature mismatch." + }, + { + "left": "issue:43596", + "right": "issue:45161", + "accept": false, + "reason": "Different failure mode and model family." + }, + { + "left": "issue:43716", + "right": "issue:45507", + "accept": false, + "reason": "Different model and different error category." + }, + { + "left": "issue:39290", + "right": "issue:45081", + "accept": false, + "reason": "Different models and distinct attribute/tokenizer errors." + }, + { + "left": "issue:43828", + "right": "issue:45161", + "accept": false, + "reason": "Dtype mismatch under autocast is unrelated to TP-only MoE failure." + }, + { + "left": "issue:44918", + "right": "issue:45161", + "accept": false, + "reason": "Different model and training stack; not the same bug." + }, + { + "left": "issue:34928", + "right": "issue:41720", + "accept": false, + "reason": "Different distributed-training issues with no common concrete code path." + }, + { + "left": "issue:43827", + "right": "issue:44512", + "accept": false, + "reason": "Both are documentation regressions, but they target different removed APIs/commands." + }, + { + "left": "issue:43716", + "right": "issue:44560", + "accept": false, + "reason": "Different model/runtime bugs." + }, + { + "left": "issue:43828", + "right": "issue:45685", + "accept": false, + "reason": "Different backend and symptom; only superficial dtype/runtime overlap." + }, + { + "left": "issue:44560", + "right": "issue:45685", + "accept": false, + "reason": "Different model areas and distinct backend errors." + }, + { + "left": "issue:43039", + "right": "issue:43828", + "accept": false, + "reason": "Different MoE/kernel failure vs autocast dtype mismatch." + }, + { + "left": "issue:30277", + "right": "issue:36331", + "accept": false, + "reason": "Different stack layers: distributed collectives vs trainer API signature." + }, + { + "left": "issue:34928", + "right": "issue:36010", + "accept": false, + "reason": "Different bugs in unrelated subsystems." + }, + { + "left": "issue:43039", + "right": "issue:44805", + "accept": false, + "reason": "Different model/runtime failures." + }, + { + "left": "issue:41762", + "right": "issue:43596", + "accept": false, + "reason": "Both are zero-3 related, but they involve different models and distinct error signatures." + }, + { + "left": "issue:41762", + "right": "issue:43638", + "accept": false, + "reason": "Same broad ZeRO-3 area, but not the same concrete bug." + }, + { + "left": "issue:43901", + "right": "issue:44512", + "accept": false, + "reason": "Different docs topics and different removals." + }, + { + "left": "issue:39290", + "right": "issue:41720", + "accept": false, + "reason": "Different model families and different runtime failures." + }, + { + "left": "issue:44841", + "right": "issue:45084", + "accept": false, + "reason": "Different processor/parsing bug vs template compilation error." + }, + { + "left": "issue:43039", + "right": "issue:44560", + "accept": false, + "reason": "Different model/runtime issues; too broad to merge." + }, + { + "left": "issue:43866", + "right": "issue:44863", + "accept": false, + "reason": "Different model loading problems with no clear shared code path." + }, + { + "left": "issue:43854", + "right": "issue:43866", + "accept": false, + "reason": "Unit-test loading failure vs checkpoint corruption are different bugs." + }, + { + "left": "issue:39290", + "right": "issue:43531", + "accept": false, + "reason": "Related Qwen3/Gemma area, but different attribute/shape issues." + }, + { + "left": "issue:41093", + "right": "issue:43638", + "accept": false, + "reason": "Both are IndexErrors, but the mismatched mask/tensor shape bug is different from the ZeRO-3/Bert zero-size index bug." + }, + { + "left": "issue:43425", + "right": "issue:45070", + "accept": false, + "reason": "Different compatibility problems: torch version vs pydantic model field." + }, + { + "left": "issue:43596", + "right": "issue:45800", + "accept": false, + "reason": "Both mention runtime compatibility-ish failures, but they are unrelated." + }, + { + "left": "issue:45362", + "right": "issue:45464", + "accept": false, + "reason": "Different Qwen3.5 surfaces and different symptoms." + }, + { + "left": "issue:43792", + "right": "issue:45070", + "accept": false, + "reason": "Whisper runtime failure is unrelated to pydantic-model breakage." + }, + { + "left": "issue:43404", + "right": "issue:43866", + "accept": false, + "reason": "Different model families and different loading/tie-weight problems." + }, + { + "left": "issue:39290", + "right": "issue:45823", + "accept": false, + "reason": "Different model/config mismatch and device-map forward issue." + }, + { + "left": "issue:45464", + "right": "issue:45685", + "accept": false, + "reason": "Different models and completely different failure modes." + }, + { + "left": "issue:43541", + "right": "issue:45685", + "accept": false, + "reason": "Different model/runtime problems; not the same underlying bug." + }, + { + "left": "issue:43541", + "right": "issue:43828", + "accept": false, + "reason": "Different code paths and distinct error types." + }, + { + "left": "issue:36010", + "right": "issue:39290", + "accept": false, + "reason": "Import error vs config attribute error; unrelated bugs." + }, + { + "left": "issue:41762", + "right": "issue:43638", + "accept": false, + "reason": "Same broad zero-3 category, but not the same concrete failure." + }, + { + "left": "issue:43828", + "right": "issue:44292", + "accept": false, + "reason": "Different model-specific runtime errors." + }, + { + "left": "issue:43425", + "right": "issue:44292", + "accept": false, + "reason": "Torch compatibility issue vs Qwen3 NVFP4 runtime error; unrelated." + }, + { + "left": "issue:45800", + "right": "issue:45823", + "accept": false, + "reason": "Different incompatibility and device-mapping bugs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary stays within the packet: it treats most pairs conservatively as unrelated and only accepts the very close ZeRO-3/Bert IndexError pair (43596, 43638), which is well supported by the titles. No overstatement stands out." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 2, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:39186", + "issue:39692", + "issue:40990", + "issue:41093", + "issue:42915", + "issue:43054", + "issue:43296", + "issue:43366", + "issue:43404", + "issue:43531", + "issue:43541", + "issue:43572", + "issue:43596", + "issue:43644", + "issue:43645", + "issue:43716", + "issue:43828", + "issue:43866", + "issue:43873", + "issue:43950", + "issue:43975", + "issue:43994", + "issue:44291", + "issue:44292", + "issue:44360", + "issue:44387", + "issue:44403", + "issue:44492", + "issue:44512", + "issue:44530", + "issue:44534", + "issue:44589", + "issue:44863", + "issue:44918", + "issue:44928", + "issue:44960", + "issue:45005", + "issue:45020", + "issue:45070", + "issue:45161", + "issue:45399", + "issue:45464", + "issue:45507", + "issue:45542", + "issue:45632", + "issue:45685", + "issue:45698", + "issue:45800" + ], + "soft_pairs": [ + "issue:43296|issue:43366", + "issue:43572|issue:45070", + "issue:44387|issue:45005", + "issue:43541|issue:45161", + "issue:43828|issue:45464", + "issue:44291|issue:45070", + "issue:45020|issue:45800", + "issue:43366|issue:45464", + "issue:43531|issue:45070", + "issue:43541|issue:44589", + "issue:41093|issue:43596", + "issue:43054|issue:43994", + "issue:45542|issue:45800", + "issue:43716|issue:44918", + "issue:44918|issue:45685", + "issue:45632|issue:45698", + "issue:43404|issue:45005", + "issue:43645|issue:45399", + "issue:40990|issue:44960", + "issue:44530|issue:45005", + "issue:42915|issue:45399", + "issue:44360|issue:44512", + "issue:44863|issue:45005", + "issue:43873|issue:45005", + "issue:39186|issue:44918", + "issue:44492|issue:44512", + "issue:44918|issue:45507", + "issue:43975|issue:44292", + "issue:43950|issue:44534", + "issue:43644|issue:43950", + "issue:44292|issue:45507", + "issue:39692|issue:43054", + "issue:43828|issue:44928", + "issue:43866|issue:44403" + ], + "prepared_review_unit_hash": "3e1d880e260b5cc772cb18716942d26819e8185ab75ead1eedf62611dda4f08e", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37464, + "estimated_input_tokens": 9366, + "estimated_eval_tokens": 18988 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is mostly unrelated issues. The only clear duplicate family is the Transformers v5 non-persistent-buffer corruption regression (43644/43950/44534), and there is one plausible SigLIP2 duplicate pair (43054/43994).", + "confidence": 0.81, + "canonical_issue_reason": "Issue 43950 is the best canonical issue for the non-persistent-buffer regression: it states the underlying v5 corruption directly and subsumes the older, less specific report.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43950 is the strongest representative issue overall because it names the regression clearly, has the most actionable root-cause framing, and cleanly covers the duplicate buffer-corruption reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43296", + "right": "issue:43366", + "accept": false, + "reason": "Different products and failure modes: PaddleOCR-VL loading vs GGUF/gpt-oss support." + }, + { + "left": "issue:43572", + "right": "issue:45070", + "accept": false, + "reason": "Both involve config changes in v5, but the concrete bugs differ: missing pad_token_idx vs pydantic PretrainedConfig field handling." + }, + { + "left": "issue:44387", + "right": "issue:45005", + "accept": false, + "reason": "Different symptoms and code paths: int4 OOM/reserved memory vs tied-weights behavior in translation models." + }, + { + "left": "issue:43541", + "right": "issue:45161", + "accept": false, + "reason": "Both mention MoE, but one is torch-dynamo grouped_mm tracing and the other is tensor-parallel behavior; not the same bug." + }, + { + "left": "issue:43828", + "right": "issue:45464", + "accept": false, + "reason": "Different models and triggers: autocast dtype mismatch in Phi-tiny-MoE vs streaming chat/completions failure in Qwen3.5." + }, + { + "left": "issue:44291", + "right": "issue:45070", + "accept": false, + "reason": "Unexpected _is_hf_initialized argument during init_empty_weights is unrelated to the pydantic PretrainedConfig regression." + }, + { + "left": "issue:45020", + "right": "issue:45800", + "accept": false, + "reason": "Broad remote_code breakage is not the same concrete issue as a torch/transformers version incompatibility." + }, + { + "left": "issue:43366", + "right": "issue:45464", + "accept": false, + "reason": "Different subsystems: GGUF architecture support vs chat/completions streaming inference." + }, + { + "left": "issue:43531", + "right": "issue:45070", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior is unrelated to the PretrainedConfig v5.4.0 field regression." + }, + { + "left": "issue:43541", + "right": "issue:44589", + "accept": false, + "reason": "Distinct runtime failures: grouped_mm tracing error vs missing Float8 storage type." + }, + { + "left": "issue:41093", + "right": "issue:43596", + "accept": false, + "reason": "Both are tensor-shape/index errors, but they occur in different contexts and do not indicate the same underlying bug." + }, + { + "left": "issue:43054", + "right": "issue:43994", + "accept": true, + "reason": "Both report SigLIP2 producing bad or nonsensical outputs for the same model family, likely the same model/processor implementation issue." + }, + { + "left": "issue:45542", + "right": "issue:45800", + "accept": false, + "reason": "TensorBoard/TensorFlow backend handling is unrelated to torch-version incompatibility." + }, + { + "left": "issue:43716", + "right": "issue:44918", + "accept": false, + "reason": "Different multimodal failures: image preprocessor dtype mismatch vs Qwen3.5 embedding unpacking in TRL SFT." + }, + { + "left": "issue:44918", + "right": "issue:45685", + "accept": false, + "reason": "Different errors in different backends: TRL input embedding unpacking vs MPS histogram not implemented for Int." + }, + { + "left": "issue:45632", + "right": "issue:45698", + "accept": false, + "reason": "Related area, but not clearly the same concrete bug: local-model leaf-dir cache collision vs wrong custom module after save_pretrained." + }, + { + "left": "issue:43404", + "right": "issue:45005", + "accept": false, + "reason": "Both mention tied weights, but they target different model families and trigger paths; not enough evidence of one shared bug." + }, + { + "left": "issue:43645", + "right": "issue:45399", + "accept": false, + "reason": "Jupyter custom-model initialization regression is unrelated to flash-attn2 fallback gating." + }, + { + "left": "issue:40990", + "right": "issue:44960", + "accept": false, + "reason": "High perplexity on gpt-oss-20b is unrelated to the GLM5 issue." + }, + { + "left": "issue:44530", + "right": "issue:45005", + "accept": false, + "reason": "PagedAttentionCache linear_attention crash is a different issue than tied-weights regression." + }, + { + "left": "issue:42915", + "right": "issue:45399", + "accept": false, + "reason": "Qwen3-MoE FineGrainedFP8Config failure is unrelated to flash-attn2 fallback logic." + }, + { + "left": "issue:44360", + "right": "issue:44512", + "accept": false, + "reason": "DSA indexer implementation discussion is unrelated to the removed run-command documentation." + }, + { + "left": "issue:44863", + "right": "issue:45005", + "accept": false, + "reason": "NemotronH checkpoint loading failure is unrelated to tied-weights behavior." + }, + { + "left": "issue:43873", + "right": "issue:45005", + "accept": false, + "reason": "Quantization offloading behavior is a different bug from tied weights in v5 translation models." + }, + { + "left": "issue:39186", + "right": "issue:44918", + "accept": false, + "reason": "FSDP 2-D weight runtime error is unrelated to Qwen3.5 input embedding unpacking." + }, + { + "left": "issue:44492", + "right": "issue:44512", + "accept": false, + "reason": "A cache-strategies typo and removed-command docs are unrelated." + }, + { + "left": "issue:44918", + "right": "issue:45507", + "accept": false, + "reason": "Different model families and failures: TRL embedding unpacking vs GraniteMoEHybrid invalid method call." + }, + { + "left": "issue:43975", + "right": "issue:44292", + "accept": false, + "reason": "Incorrect detokenization in DeepSeek coder is unrelated to the NVFP4 runtime error." + }, + { + "left": "issue:43950", + "right": "issue:44534", + "accept": true, + "reason": "Same underlying v5 regression: non-persistent buffers are being corrupted/filled with junk on load." + }, + { + "left": "issue:43644", + "right": "issue:43950", + "accept": true, + "reason": "Same non-persistent-buffer corruption bug; 43950 is the clearer, more explicit report." + }, + { + "left": "issue:44292", + "right": "issue:45507", + "accept": false, + "reason": "Different runtime failures and model families; no shared code-path evidence." + }, + { + "left": "issue:43866", + "right": "issue:44403", + "accept": false, + "reason": "Checkpoint corruption for Ovis2 is unrelated to the transformer-loading noise issue." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet, and the duplicate calls are conservative. The non-persistent-buffer regression cluster is well supported by the issue titles, and the SigLIP2 pair is only presented as plausible rather than certain. No obvious overstatement or mergeability problem for 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": 16, + "review_unit_index": 3, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:36331", + "issue:38175", + "issue:41553", + "issue:41628", + "issue:41762", + "issue:42491", + "issue:42915", + "issue:42947", + "issue:43054", + "issue:43257", + "issue:43404", + "issue:43493", + "issue:43638", + "issue:43643", + "issue:43742", + "issue:43782", + "issue:43792", + "issue:43824", + "issue:43827", + "issue:43828", + "issue:43856", + "issue:43866", + "issue:43872", + "issue:43881", + "issue:43883", + "issue:43950", + "issue:43975", + "issue:44220", + "issue:44368", + "issue:44387", + "issue:44403", + "issue:44451", + "issue:44488", + "issue:44509", + "issue:44589", + "issue:44661", + "issue:44960", + "issue:44991", + "issue:45020", + "issue:45081", + "issue:45237", + "issue:45356", + "issue:45399", + "issue:45520", + "issue:45685", + "issue:45701", + "issue:45800", + "issue:45823" + ], + "soft_pairs": [ + "issue:36331|issue:41762", + "issue:41628|issue:45800", + "issue:43872|issue:44589", + "issue:41553|issue:43883", + "issue:38175|issue:43054", + "issue:43054|issue:45701", + "issue:41553|issue:43881", + "issue:42947|issue:44387", + "issue:44403|issue:44451", + "issue:43643|issue:45020", + "issue:43975|issue:45520", + "issue:43054|issue:43493", + "issue:43975|issue:45237", + "issue:44403|issue:44488", + "issue:42947|issue:43856", + "issue:43881|issue:43883", + "issue:41762|issue:42915", + "issue:42491|issue:44368", + "issue:45685|issue:45823", + "issue:43975|issue:44451", + "issue:45020|issue:45823", + "issue:43824|issue:43872", + "issue:44991|issue:45399", + "issue:44661|issue:45020", + "issue:43828|issue:45823", + "issue:45020|issue:45356", + "issue:43782|issue:44960", + "issue:45081|issue:45399", + "issue:43827|issue:44509", + "issue:43404|issue:43950", + "issue:43792|issue:44220", + "issue:43742|issue:45399", + "issue:42915|issue:45020", + "issue:43638|issue:45823", + "issue:43257|issue:43866" + ], + "prepared_review_unit_hash": "859c30f6e9e12dfec3002bf0ddcd994ac5d065ff99ffcb06fd1294682aaca841", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 35, + "serialized_chars": 38124, + "estimated_input_tokens": 9531, + "estimated_eval_tokens": 19318 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This is a loose, mostly heterogeneous cluster of issue reports around loading/regression problems. I only see two clear duplicate-like pairs: the SigLIP2 implementation discrepancy reports and the v5 docs pipeline-removal docs reports. Most other pairs are related only at a subsystem level, not the same underlying bug.", + "confidence": 0.76, + "canonical_issue_reason": "issue:45020 is the best broad umbrella for the cluster\u2019s recurring recent-version loading/compatibility regressions, especially remote_code-related breakages, though it does not cleanly cover the whole heterogeneous set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45020 is the strongest representative because it is the broadest open issue and aligns with the dominant theme of recent transformers version regressions; still, it is only a partial fit for this cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36331", + "right": "issue:41762", + "accept": false, + "reason": "Different failure modes: custom trainer signature mismatch vs ZeRO-3 index error during Gemma3 loading." + }, + { + "left": "issue:41628", + "right": "issue:45800", + "accept": false, + "reason": "Import error for a missing symbol is not the same bug as a torch/transformers version incompatibility." + }, + { + "left": "issue:43872", + "right": "issue:44589", + "accept": false, + "reason": "Both are compatibility problems, but one is bitsandbytes int8 init and the other is float8 storage resolution; different code paths." + }, + { + "left": "issue:41553", + "right": "issue:43883", + "accept": false, + "reason": "Bad AutoTokenizer error messaging for Voxtral is unrelated to Molmo missing all_tied_weights_keys." + }, + { + "left": "issue:38175", + "right": "issue:43054", + "accept": false, + "reason": "Both involve SigLIP2 quality, but the reports describe different symptoms and no shared concrete bug is evident." + }, + { + "left": "issue:43054", + "right": "issue:45701", + "accept": false, + "reason": "SigLIP2 embedding quality is unrelated to a general tokenization change across transformers versions." + }, + { + "left": "issue:41553", + "right": "issue:43881", + "accept": false, + "reason": "Different models and different load failures; no same underlying bug." + }, + { + "left": "issue:42947", + "right": "issue:44387", + "accept": false, + "reason": "Both mention memory/performance, but one is LoRA checkpointing behavior and the other is int4 CUDA reserved memory OOM." + }, + { + "left": "issue:44403", + "right": "issue:44451", + "accept": false, + "reason": "One is noisy loading output, the other is a concrete model-loading failure for ScandiBERT." + }, + { + "left": "issue:43643", + "right": "issue:45020", + "accept": false, + "reason": "Both touch remote_code, but one is missing fields in AutoConfig and the other is a broader breakage report; not the same concrete bug." + }, + { + "left": "issue:43975", + "right": "issue:45520", + "accept": false, + "reason": "DeepSeek detokenization and a flash_attn import_utils KeyError are unrelated issues." + }, + { + "left": "issue:43054", + "right": "issue:43493", + "accept": true, + "reason": "Both point to the same SigLIP2 implementation discrepancy theme; the JAX-vs-HF mismatch plausibly explains the degraded text embeddings." + }, + { + "left": "issue:43975", + "right": "issue:45237", + "accept": false, + "reason": "Tokenizer/detokenization behavior is unrelated to AMD GPU execution support." + }, + { + "left": "issue:44403", + "right": "issue:44488", + "accept": false, + "reason": "General loading noise and a specific model load failure are not the same bug." + }, + { + "left": "issue:42947", + "right": "issue:43856", + "accept": false, + "reason": "Both are efficiency-related, but one is gradient checkpointing with PEFT LoRA and the other is Qwen3 MoE training memory usage." + }, + { + "left": "issue:43881", + "right": "issue:43883", + "accept": false, + "reason": "Different model families and different errors: glm-4v loading vs Molmo weight-tying attribute missing." + }, + { + "left": "issue:41762", + "right": "issue:42915", + "accept": false, + "reason": "ZeRO-3 index error during Gemma3 loading is not the same as Qwen3 MoE fine-grained FP8 failure." + }, + { + "left": "issue:42491", + "right": "issue:44368", + "accept": false, + "reason": "LoRA compatibility across hf versions and a tie_word_embeddings warning are different issues." + }, + { + "left": "issue:45685", + "right": "issue:45823", + "accept": false, + "reason": "MPS histogram support for Int and Gemma4 PLE device placement mismatch are different device bugs." + }, + { + "left": "issue:43975", + "right": "issue:44451", + "accept": false, + "reason": "Detokenization regression and a ScandiBERT load failure are unrelated." + }, + { + "left": "issue:45020", + "right": "issue:45823", + "accept": false, + "reason": "Remote_code loading regressions do not match a Gemma4 PLE device_map forward mismatch." + }, + { + "left": "issue:43824", + "right": "issue:43872", + "accept": false, + "reason": "Importing a Qwen2.5-VL class and a bitsandbytes int8 constructor error are unrelated." + }, + { + "left": "issue:44991", + "right": "issue:45399", + "accept": false, + "reason": "Tokenizer loading for EMBEDDIA/est-roberta and flash-attn fallback gating are unrelated." + }, + { + "left": "issue:44661", + "right": "issue:45020", + "accept": false, + "reason": "add-new-model-like failing inside TOKENIZER_MAPPING_NAMES is a registry issue, not the same remote_code regression." + }, + { + "left": "issue:43828", + "right": "issue:45823", + "accept": false, + "reason": "Autocast dtype mismatch for Phi-tiny-MoE and Gemma4 device mismatch are different runtime errors." + }, + { + "left": "issue:45020", + "right": "issue:45356", + "accept": false, + "reason": "Both concern recent tokenizer regressions, but the concrete failures differ: remote_code loading vs Kimi-K2.5 codec/fix_mistral_regex behavior." + }, + { + "left": "issue:43782", + "right": "issue:44960", + "accept": false, + "reason": "Qwen3VL weight_only loading error and GLM5 are separate model-specific issues." + }, + { + "left": "issue:45081", + "right": "issue:45399", + "accept": false, + "reason": "Mistral tokenizer patch crash and flash-attn fallback gating are unrelated code paths." + }, + { + "left": "issue:43827", + "right": "issue:44509", + "accept": true, + "reason": "These are clear duplicates: both report stale docs still referencing removed v5 pipeline tasks." + }, + { + "left": "issue:43404", + "right": "issue:43950", + "accept": false, + "reason": "Mistral3 weight tying and non-persistent buffer corruption are different regression types." + }, + { + "left": "issue:43792", + "right": "issue:44220", + "accept": false, + "reason": "Whisper failing to run may involve feature extraction, but the titles do not show the same concrete bug with enough confidence." + }, + { + "left": "issue:43742", + "right": "issue:45399", + "accept": false, + "reason": "MobileLLM key errors and flash-attn fallback gating are unrelated failures." + }, + { + "left": "issue:42915", + "right": "issue:43866", + "accept": false, + "reason": "Qwen3 MoE FP8/deepspeed issues and an Ovis2 checkpoint corruption report are separate problems." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays appropriately conservative. The two accepted duplicate-like pairs are supported by the titles, and the other soft-edge rejections avoid overclaiming same-bug identity. Minor caution: the umbrella framing around issue:45020 is broad and should remain presented as partial/approximate rather than definitive." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 4, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:24643", + "issue:30064", + "issue:36010", + "issue:36331", + "issue:38175", + "issue:41093", + "issue:41553", + "issue:42617", + "issue:42915", + "issue:43257", + "issue:43366", + "issue:43531", + "issue:43550", + "issue:43632", + "issue:43645", + "issue:43646", + "issue:43824", + "issue:43828", + "issue:43854", + "issue:43872", + "issue:43940", + "issue:43950", + "issue:43957", + "issue:43994", + "issue:44155", + "issue:44291", + "issue:44479", + "issue:44488", + "issue:44530", + "issue:44560", + "issue:44589", + "issue:44661", + "issue:44805", + "issue:44863", + "issue:44910", + "issue:44918", + "issue:44928", + "issue:44991", + "issue:45161", + "issue:45305", + "issue:45313", + "issue:45325", + "issue:45538", + "issue:45584", + "issue:45588", + "issue:45663", + "issue:45823", + "issue:45834" + ], + "soft_pairs": [ + "issue:43940|issue:45313", + "issue:43872|issue:44291", + "issue:45161|issue:45823", + "issue:43854|issue:44863", + "issue:41553|issue:44991", + "issue:42915|issue:43872", + "issue:44928|issue:45588", + "issue:43257|issue:45305", + "issue:36331|issue:41093", + "issue:41553|issue:44488", + "issue:43872|issue:45538", + "issue:44530|issue:44863", + "issue:41093|issue:44805", + "issue:44479|issue:44560", + "issue:24643|issue:30064", + "issue:43366|issue:43828", + "issue:45663|issue:45823", + "issue:43366|issue:43531", + "issue:43950|issue:45834", + "issue:43550|issue:44910", + "issue:43645|issue:43646", + "issue:43366|issue:44589", + "issue:43950|issue:45325", + "issue:44560|issue:44918", + "issue:42617|issue:43366", + "issue:43824|issue:43957", + "issue:42915|issue:43957", + "issue:36010|issue:42915", + "issue:44661|issue:45823", + "issue:38175|issue:43994", + "issue:43632|issue:45834", + "issue:44155|issue:45584" + ], + "prepared_review_unit_hash": "ba3dbced55ccc82e9a153bace62548ac658c25b713e5ce02a6f7232a0b48011d", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37421, + "estimated_input_tokens": 9356, + "estimated_eval_tokens": 18968 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a heterogeneous set of Transformers bug reports with a few close duplicate pairs around initialization/loading regressions. I did not find any PRs, and the safest umbrella issue is the Transformers 5 `_is_hf_initialized` regression. Accepted duplicates: the custom model init notebook/general pair, the identical mask-shape IndexError pair, and the `_is_hf_initialized`/init_empty_weights pair.", + "confidence": 0.68, + "canonical_issue_reason": "Issue 43632 is the broadest root-cause report in the cluster: it describes the Transformers 5 `_is_hf_initialized` regression that appears to underlie several later loading/initialization failures.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43632 is the best representative issue because it captures the common upstream initialization bug rather than a single model-specific symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43940", + "right": "issue:45313", + "accept": false, + "reason": "Both are DeepSpeed ZeRO-3 loading failures, but they target different Qwen variants and different symptoms, so they do not look like the same bug." + }, + { + "left": "issue:43872", + "right": "issue:44291", + "accept": true, + "reason": "Both report the same `_is_hf_initialized` kwarg regression during model loading; one surfaces through bitsandbytes and the other through init_empty_weights, but the underlying bug is the same." + }, + { + "left": "issue:45161", + "right": "issue:45823", + "accept": false, + "reason": "These are unrelated model-specific failures: GPT-OSS MoE tensor-parallel loading vs Gemma4 PLE device placement." + }, + { + "left": "issue:43854", + "right": "issue:44863", + "accept": false, + "reason": "Different models and different loading failures; no sign of a shared code-path bug." + }, + { + "left": "issue:41553", + "right": "issue:44991", + "accept": false, + "reason": "Both mention tokenizer loading, but the reported failures and models are different, so this is too broad to merge." + }, + { + "left": "issue:42915", + "right": "issue:43872", + "accept": false, + "reason": "Qwen3MoE FP8 config failure is unrelated to the `_is_hf_initialized` bitsandbytes regression." + }, + { + "left": "issue:44928", + "right": "issue:45588", + "accept": false, + "reason": "RLHF NaNs from Qwen3.5 position-ids and Whisper empty-transcription handling are different bugs." + }, + { + "left": "issue:43257", + "right": "issue:45305", + "accept": false, + "reason": "Both involve DeepSpeed training, but one is missing Qwen3 MoE weights and the other is gradient averaging with GAS." + }, + { + "left": "issue:36331", + "right": "issue:41093", + "accept": false, + "reason": "Unexpected compute_loss kwarg and mask/tensor shape mismatch are different failure modes." + }, + { + "left": "issue:41553", + "right": "issue:44488", + "accept": false, + "reason": "Different tokenizer/model loading problems with no shared concrete bug." + }, + { + "left": "issue:43872", + "right": "issue:45538", + "accept": false, + "reason": "Bitsandbytes `_is_hf_initialized` incompatibility is unrelated to CLIPTokenizer's model_max_length value." + }, + { + "left": "issue:44530", + "right": "issue:44863", + "accept": false, + "reason": "PagedAttentionCache invalid group type on Qwen3.5 is not the same as NemotronH checkpoint loading." + }, + { + "left": "issue:41093", + "right": "issue:44805", + "accept": true, + "reason": "These are effectively the same IndexError symptom with the same shape-mismatch wording, so they look like duplicate reports of one underlying bug." + }, + { + "left": "issue:44479", + "right": "issue:44560", + "accept": false, + "reason": "Both are Qwen video/position-id issues, but the specific models and failures differ enough that they should stay separate." + }, + { + "left": "issue:24643", + "right": "issue:30064", + "accept": false, + "reason": "DeepSpeed training weight-dimension error and void segmentation-map processing are unrelated." + }, + { + "left": "issue:43366", + "right": "issue:43828", + "accept": false, + "reason": "GGUF gpt-oss support and Phi-tiny-MoE autocast dtype mismatch are unrelated." + }, + { + "left": "issue:45663", + "right": "issue:45823", + "accept": false, + "reason": "Gemma4 FSDP2 shared_kv_states corruption is a different issue from Gemma4 PLE device mismatch under device_map=auto." + }, + { + "left": "issue:43366", + "right": "issue:43531", + "accept": false, + "reason": "Both mention GPT-OSS/Qwen-style MoE models, but one is GGUF support and the other is a sliding_window bug on Qwen3-MoE." + }, + { + "left": "issue:43950", + "right": "issue:45834", + "accept": false, + "reason": "Non-persistent buffer corruption in from_pretrained and Kosmos2.5 OCR index errors are unrelated." + }, + { + "left": "issue:43550", + "right": "issue:44910", + "accept": false, + "reason": "Bamba SDPA compile failure and Qwen3.5 flash-attn illegal memory access stem from different code paths." + }, + { + "left": "issue:43645", + "right": "issue:43646", + "accept": true, + "reason": "These are the same custom model initialization regression; one is the notebook repro, the other the general issue." + }, + { + "left": "issue:43366", + "right": "issue:44589", + "accept": false, + "reason": "GGUF gpt-oss support and missing Float8 storage are unrelated." + }, + { + "left": "issue:43950", + "right": "issue:45325", + "accept": false, + "reason": "Non-persistent buffer handling and Qwen2.5-VL rope-index scaling are different bugs." + }, + { + "left": "issue:44560", + "right": "issue:44918", + "accept": false, + "reason": "Both involve Qwen3.5-ish inputs, but one is a video StopIteration and the other is TRL SFT embedding unpacking." + }, + { + "left": "issue:42617", + "right": "issue:43366", + "accept": false, + "reason": "3d_parallel.py execution failure is unrelated to GPT-OSS GGUF support." + }, + { + "left": "issue:43824", + "right": "issue:43957", + "accept": false, + "reason": "Missing import for Qwen2_5_VLForConditionalGeneration and meta-device loading regressions are not the same bug." + }, + { + "left": "issue:42915", + "right": "issue:43957", + "accept": false, + "reason": "Qwen3MoE FP8 config failure and meta-device loading regressions differ in both trigger and code path." + }, + { + "left": "issue:36010", + "right": "issue:42915", + "accept": false, + "reason": "GenerationMixin import failure and Qwen3MoE FP8 failure are unrelated." + }, + { + "left": "issue:44661", + "right": "issue:45823", + "accept": false, + "reason": "Tokenizer mapping-name handling and Gemma4 device mismatch are unrelated issues." + }, + { + "left": "issue:38175", + "right": "issue:43994", + "accept": false, + "reason": "Both are about SigLIP2 behavior, but one is zero probabilities and the other is nonsensical AutoModel/pipeline output; not enough to call them duplicates." + }, + { + "left": "issue:43632", + "right": "issue:45834", + "accept": false, + "reason": "The `_is_hf_initialized` regression is unrelated to Kosmos2.5 OCR long-input indexing." + }, + { + "left": "issue:44155", + "right": "issue:45584", + "accept": false, + "reason": "AudioFlamingo3 track embedding leakage and Whisper empty-transcription handling are different failures." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary stays grounded in the packet and the duplicate calls are conservative: the accepted pairs have clear title-level overlap, and the rejected pairs are appropriately cautious. The umbrella issue choice is plausible given the `_is_hf_initialized` cluster, and there is no overstatement beyond the evidence provided." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 5, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:36010", + "issue:38175", + "issue:39404", + "issue:39692", + "issue:41720", + "issue:42491", + "issue:42915", + "issue:43257", + "issue:43317", + "issue:43404", + "issue:43454", + "issue:43596", + "issue:43638", + "issue:43644", + "issue:43645", + "issue:43708", + "issue:43720", + "issue:43854", + "issue:43856", + "issue:43873", + "issue:43931", + "issue:43994", + "issue:44075", + "issue:44387", + "issue:44451", + "issue:44488", + "issue:44534", + "issue:44560", + "issue:44661", + "issue:44756", + "issue:44805", + "issue:44877", + "issue:44910", + "issue:44960", + "issue:44977", + "issue:44991", + "issue:45030", + "issue:45276", + "issue:45292", + "issue:45313", + "issue:45335", + "issue:45357", + "issue:45362", + "issue:45406", + "issue:45488", + "issue:45588", + "issue:45812" + ], + "soft_pairs": [ + "issue:44877|issue:45030", + "issue:44560|issue:44805", + "issue:43638|issue:44661", + "issue:43317|issue:44756", + "issue:43596|issue:44661", + "issue:44661|issue:44805", + "issue:38175|issue:39692", + "issue:43644|issue:44534", + "issue:45313|issue:45357", + "issue:45488|issue:45812", + "issue:44960|issue:44977", + "issue:44451|issue:44488", + "issue:42491|issue:43720", + "issue:43854|issue:43931", + "issue:41720|issue:42915", + "issue:42491|issue:45276", + "issue:43708|issue:44075", + "issue:43257|issue:43854", + "issue:43856|issue:43873", + "issue:42915|issue:44756", + "issue:39692|issue:43994", + "issue:42491|issue:43931", + "issue:43856|issue:44387", + "issue:43644|issue:43645", + "issue:44910|issue:45588", + "issue:45362|issue:45406", + "issue:42491|issue:45292", + "issue:44488|issue:44991", + "issue:36010|issue:39404", + "issue:45276|issue:45335", + "issue:43404|issue:43454" + ], + "prepared_review_unit_hash": "f700a6c738a5f94fef5c8355d5a6e4bd06996cb6017a6fd73b6c31721cba25e5", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "serialized_chars": 36412, + "estimated_input_tokens": 9103, + "estimated_eval_tokens": 18462 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a loose mix of Transformers v5 regression reports across loading, tokenizers, quantization, and model-specific generation bugs. Only one soft pair is a clear duplicate; the rest are too model- or symptom-specific to merge confidently.", + "confidence": 0.62, + "canonical_issue_reason": "Issue 43644 is the clearest, most detailed report of the confirmed duplicate buffer-regression bug, and it is directly echoed by 44534.", + "canonical_pr_reason": null, + "best_issue_reason": "43644 is the best overall anchor because it captures the bug concretely and has the strongest duplicate evidence in the set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44877", + "right": "issue:45030", + "accept": false, + "reason": "Both are config-validation load failures, but they affect different models and describe different breakages." + }, + { + "left": "issue:44560", + "right": "issue:44805", + "accept": false, + "reason": "Different failures: Whisper video StopIteration vs a mask/tensor shape mismatch." + }, + { + "left": "issue:43638", + "right": "issue:44661", + "accept": false, + "reason": "BERT ZeRO-3 initialization crash and tokenizer-mapping-name issue are unrelated bugs." + }, + { + "left": "issue:43317", + "right": "issue:44756", + "accept": false, + "reason": "Both mention offload/memory, but one is a dequantized-model loading failure and the other is mmap OOM on Strix Halo." + }, + { + "left": "issue:43596", + "right": "issue:44661", + "accept": false, + "reason": "Different code paths: ZeRO-3/BertModel index error vs add-new-model-like tokenizer mapping failure." + }, + { + "left": "issue:44661", + "right": "issue:44805", + "accept": false, + "reason": "Tokenizer-mapping logic and tensor mask shape mismatch are unrelated." + }, + { + "left": "issue:38175", + "right": "issue:39692", + "accept": false, + "reason": "Same model family, but one reports zero probabilities and the other reports docs-example/model-processor and quantization errors." + }, + { + "left": "issue:43644", + "right": "issue:44534", + "accept": true, + "reason": "Same underlying bug: Transformers 5.0.0 fills non-persistent buffers with junk; the titles are effectively the same report." + }, + { + "left": "issue:45313", + "right": "issue:45357", + "accept": false, + "reason": "Both are Qwen3.5-related, but one is ZeRO-3 weight loading and the other is save_pretrained key serialization." + }, + { + "left": "issue:45488", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but one is LlamaTokenizer pre-tokenizer override and the other is Granite token-id corruption." + }, + { + "left": "issue:44960", + "right": "issue:44977", + "accept": false, + "reason": "Different models and different flash-attention/generation failures." + }, + { + "left": "issue:44451", + "right": "issue:44488", + "accept": false, + "reason": "Both are model-load regressions, but the reports are for different models and no shared concrete bug is evident." + }, + { + "left": "issue:42491", + "right": "issue:43720", + "accept": false, + "reason": "Different problems: Qwen3 MoE LoRA compatibility vs BitNet packed-weight loading." + }, + { + "left": "issue:43854", + "right": "issue:43931", + "accept": false, + "reason": "Different model load failures with different symptoms and model families." + }, + { + "left": "issue:41720", + "right": "issue:42915", + "accept": false, + "reason": "Both are Qwen3-family issues, but one is auto device mapping cuda assert and the other is FineGrainedFP8Config failure." + }, + { + "left": "issue:42491", + "right": "issue:45276", + "accept": false, + "reason": "Qwen3 MoE LoRA compatibility and Gemma4 embedding resize behavior are unrelated." + }, + { + "left": "issue:43708", + "right": "issue:44075", + "accept": false, + "reason": "Trainer resume/max_steps bug and SGD-args-not-used bug are different trainer/optimizer issues." + }, + { + "left": "issue:43257", + "right": "issue:43854", + "accept": false, + "reason": "Different loading paths and failures: accelerate/deepspeed MoE conversion vs GLM-4.7-Flash unit-test loading." + }, + { + "left": "issue:43856", + "right": "issue:43873", + "accept": false, + "reason": "Both touch memory/offloading, but one is Qwen3 MoE training memory use and the other is quantization offloading behavior." + }, + { + "left": "issue:42915", + "right": "issue:44756", + "accept": false, + "reason": "Qwen3Moe FP8 failure and Strix Halo mmap OOM are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:43994", + "accept": false, + "reason": "Same SigLIP2 model family, but one is a docs-example/model-processor issue and the other is a runtime nonsensical-output report." + }, + { + "left": "issue:42491", + "right": "issue:43931", + "accept": false, + "reason": "Qwen3 MoE LoRA compatibility and Qwen3-VL weight-shape mismatch are different bugs." + }, + { + "left": "issue:43856", + "right": "issue:44387", + "accept": false, + "reason": "Memory inefficiency during Qwen3 MoE training is not the same as increased CUDA reserved memory under int4 quantization." + }, + { + "left": "issue:43644", + "right": "issue:43645", + "accept": false, + "reason": "Both are Transformers 5 regressions, but one is buffer junk and the other is Jupyter custom-model initialization." + }, + { + "left": "issue:44910", + "right": "issue:45588", + "accept": false, + "reason": "Both are flash-attention crashes, but the causes differ: packed-sequence misinterpretation vs s_aux=None AttributeError." + }, + { + "left": "issue:45362", + "right": "issue:45406", + "accept": false, + "reason": "Different crash sites and model families: Qwen3.5 chat vs Gemma4Processor _tokenizer missing." + }, + { + "left": "issue:44488", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer-loading regressions, but they target different external models and appear to be different root causes." + }, + { + "left": "issue:36010", + "right": "issue:39404", + "accept": false, + "reason": "Importing GenerationMixin and Whisper pipeline return_language are unrelated issues." + }, + { + "left": "issue:45276", + "right": "issue:45335", + "accept": false, + "reason": "Both concern resize_token_embeddings, but they affect different model families and different embedding targets; not enough evidence for one bug." + }, + { + "left": "issue:43404", + "right": "issue:43454", + "accept": false, + "reason": "Both mention untied lm_head weights, but they are different model implementations and not clearly the same code-path fix." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Grounded overall. The 43644/44534 pairing is the only clearly mergeable duplicate in this packet, and the other soft-edge rejections are appropriately conservative given the model/symptom differences. The summary stays within the evidence, though wording like \"confirmed duplicate\" is a bit stronger than the packet explicitly proves." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 6, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:39404", + "issue:39692", + "issue:41720", + "issue:42947", + "issue:43257", + "issue:43335", + "issue:43381", + "issue:43425", + "issue:43611", + "issue:43645", + "issue:43646", + "issue:43708", + "issue:43828", + "issue:43854", + "issue:43873", + "issue:43906", + "issue:43931", + "issue:43957", + "issue:44155", + "issue:44164", + "issue:44291", + "issue:44292", + "issue:44387", + "issue:44402", + "issue:44451", + "issue:44479", + "issue:44488", + "issue:44530", + "issue:44589", + "issue:44683", + "issue:44756", + "issue:44863", + "issue:44877", + "issue:44912", + "issue:44928", + "issue:44960", + "issue:45216", + "issue:45276", + "issue:45292", + "issue:45335", + "issue:45588", + "issue:45663", + "issue:45684", + "issue:45698", + "issue:45701", + "issue:45704", + "issue:45759", + "issue:45823" + ], + "soft_pairs": [ + "issue:44164|issue:44291", + "issue:44402|issue:44488", + "issue:43425|issue:43957", + "issue:39692|issue:44960", + "issue:42947|issue:45704", + "issue:43335|issue:45663", + "issue:43873|issue:44387", + "issue:45663|issue:45759", + "issue:44155|issue:45823", + "issue:43854|issue:45216", + "issue:44387|issue:44756", + "issue:44291|issue:44756", + "issue:44292|issue:44912", + "issue:42947|issue:43381", + "issue:45684|issue:45698", + "issue:45276|issue:45292", + "issue:43381|issue:44928", + "issue:44164|issue:44756", + "issue:41720|issue:44155", + "issue:44479|issue:44877", + "issue:45588|issue:45663", + "issue:43646|issue:43708", + "issue:43854|issue:44960", + "issue:43957|issue:44756", + "issue:45292|issue:45335", + "issue:44402|issue:44451", + "issue:43828|issue:43957", + "issue:43645|issue:44164", + "issue:43257|issue:44863", + "issue:43425|issue:43828", + "issue:44589|issue:44756", + "issue:44683|issue:45823", + "issue:44479|issue:45663", + "issue:43906|issue:44530", + "issue:39404|issue:45701", + "issue:43611|issue:43645", + "issue:43425|issue:45823", + "issue:43931|issue:44863" + ], + "prepared_review_unit_hash": "aaa30b88e7224198aca175dcdbfa3ebe465897767d44cdce860708095a08d9c9", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 38, + "serialized_chars": 39073, + "estimated_input_tokens": 9769, + "estimated_eval_tokens": 19794 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab-bag of unrelated Transformers issues. The only strong duplicate candidate is the resize_token_embeddings/output_embeddings regression pair around Gemma4, with one issue being the broader/general form and the other a model-specific manifestation.", + "confidence": 0.67, + "canonical_issue_reason": "issue:45292 is the most general statement of the duplicate pair and cleanly represents the shared bug: `resize_token_embeddings` not updating output embeddings.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45292 is the best representative issue because it states the core regression in the broadest way and is the most plausible canonical target for the related Gemma4-specific report.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44164", + "right": "issue:44291", + "accept": false, + "reason": "Both involve loading/saving mechanics, but one is about `extra_state` handling and the other about `init_empty_weights` / `_is_hf_initialized`; different failure paths." + }, + { + "left": "issue:44402", + "right": "issue:44488", + "accept": false, + "reason": "Both mention model loading problems, but the titles point to different concrete issues and different model names; not enough evidence of the same bug." + }, + { + "left": "issue:43425", + "right": "issue:43957", + "accept": false, + "reason": "One is a Torch 2.10 compatibility claim, the other is a `meta`-device loading regression; same broad area, different code-paths." + }, + { + "left": "issue:39692", + "right": "issue:44960", + "accept": false, + "reason": "Completely unrelated topics: SigLIP2 documentation errors versus a GLM5 issue." + }, + { + "left": "issue:42947", + "right": "issue:45704", + "accept": false, + "reason": "Gradient checkpointing/LoRA behavior and a T5 RMSNorm memory leak are unrelated bugs." + }, + { + "left": "issue:43335", + "right": "issue:45663", + "accept": false, + "reason": "Sparse-layer config creation and Gemma4 FSDP2 shared-kv-state handling are different model/config regressions." + }, + { + "left": "issue:43873", + "right": "issue:44387", + "accept": false, + "reason": "Both touch quantization/memory, but one is offloading behavior and the other is int4 reserved-memory/OOM; not the same underlying defect." + }, + { + "left": "issue:45663", + "right": "issue:45759", + "accept": false, + "reason": "FSDP2 shared_kv_states bug versus custom-module selection after save/load; different code paths." + }, + { + "left": "issue:44155", + "right": "issue:45823", + "accept": false, + "reason": "AudioFlamingo3 batched inference corruption and Gemma4 device-map mismatch are unrelated." + }, + { + "left": "issue:43854", + "right": "issue:45216", + "accept": false, + "reason": "Different model-loading regressions with no concrete overlap in the reported failure mode." + }, + { + "left": "issue:44387", + "right": "issue:44756", + "accept": false, + "reason": "Int4 quantization OOM versus disabling mmap on Strix Halo; different symptoms and fixes." + }, + { + "left": "issue:44291", + "right": "issue:44756", + "accept": false, + "reason": "`init_empty_weights` argument handling and Strix Halo mmap/OOM are unrelated." + }, + { + "left": "issue:44292", + "right": "issue:44912", + "accept": false, + "reason": "`resize_token_embeddings` output embedding propagation and MXFP4 quantization fallback are different bugs." + }, + { + "left": "issue:42947", + "right": "issue:43381", + "accept": false, + "reason": "Both mention gradient checkpointing, but one is LoRA ineffectiveness and the other is eval-mode prohibition; not the same issue." + }, + { + "left": "issue:45684", + "right": "issue:45698", + "accept": false, + "reason": "One is about read-only file permissions during save, the other about loading the wrong custom module after save; related workflow, different bug." + }, + { + "left": "issue:45276", + "right": "issue:45292", + "accept": true, + "reason": "Both report the same underlying regression: `resize_token_embeddings` not propagating to output embeddings, with 45276 appearing to be a Gemma4-specific manifestation." + }, + { + "left": "issue:43381", + "right": "issue:44928", + "accept": false, + "reason": "Gradient checkpointing in eval mode versus RLHF NaNs from 3D position_ids / SDPA fallback are unrelated." + }, + { + "left": "issue:44164", + "right": "issue:44756", + "accept": false, + "reason": "`extra_state` save/load handling and Strix Halo mmap/OOM are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:44155", + "accept": false, + "reason": "Qwen3 auto device-mapping CUDA assert and AudioFlamingo3 batched inference leakage are different failures." + }, + { + "left": "issue:44479", + "right": "issue:44877", + "accept": false, + "reason": "Qwen video-input regression and strict config rejection for granite_speech are not the same bug." + }, + { + "left": "issue:45588", + "right": "issue:45663", + "accept": false, + "reason": "Flash-attention `s_aux=None` crash and Gemma4 FSDP2 shared-state rebuild are unrelated." + }, + { + "left": "issue:43646", + "right": "issue:43708", + "accept": false, + "reason": "Custom model initialization regression and Trainer resume/max_steps miscalculation are different areas." + }, + { + "left": "issue:43854", + "right": "issue:44960", + "accept": false, + "reason": "Different model-loading problems with no clear shared root cause." + }, + { + "left": "issue:43957", + "right": "issue:44756", + "accept": false, + "reason": "`meta`-device loading regressions versus Strix Halo mmap/OOM; different code paths." + }, + { + "left": "issue:45292", + "right": "issue:45335", + "accept": false, + "reason": "Both concern `resize_token_embeddings`, but one is general output embeddings and the other is decoder.embed_tokens in t5gemma; likely related but not clearly the same concrete bug." + }, + { + "left": "issue:44402", + "right": "issue:44451", + "accept": false, + "reason": "Two distinct model-loading failures for different models; insufficient evidence of identity." + }, + { + "left": "issue:43828", + "right": "issue:43957", + "accept": false, + "reason": "Autocast dtype mismatch in Phi-tiny-MoE and `meta`-device loading failures are different issues." + }, + { + "left": "issue:43645", + "right": "issue:44164", + "accept": false, + "reason": "Notebook custom-model init regression and save/from_pretrained `extra_state` handling are different bugs." + }, + { + "left": "issue:43257", + "right": "issue:44863", + "accept": false, + "reason": "Qwen3 MOE conversion with accelerate+deepspeed and NemotronH checkpoint loading are unrelated." + }, + { + "left": "issue:43425", + "right": "issue:43828", + "accept": false, + "reason": "Torch version incompatibility and autocast dtype mismatch are different failures." + }, + { + "left": "issue:44589", + "right": "issue:44756", + "accept": false, + "reason": "Float8 storage lookup error and mmap-related OOM are unrelated." + }, + { + "left": "issue:44683", + "right": "issue:45823", + "accept": false, + "reason": "Compiled flex_attention on torch>=2.9 and Gemma4 PLE device mismatch are different code paths." + }, + { + "left": "issue:44479", + "right": "issue:45663", + "accept": false, + "reason": "Video-input regression and Gemma4 FSDP2 attention-state bug are unrelated." + }, + { + "left": "issue:43906", + "right": "issue:44530", + "accept": false, + "reason": "Isolated reproduction of another issue and a PagedAttentionCache crash on Qwen3.5 are not the same bug." + }, + { + "left": "issue:39404", + "right": "issue:45701", + "accept": false, + "reason": "Whisper pipeline `return_language` regression and tokenization changes across versions are different issues." + }, + { + "left": "issue:43611", + "right": "issue:43645", + "accept": false, + "reason": "Both involve Transformers 5.0.0 custom-model behavior, but one is `base_model_prefix` loading and the other is notebook initialization; not enough to merge." + }, + { + "left": "issue:43425", + "right": "issue:45823", + "accept": false, + "reason": "Torch incompatibility and Gemma4 forward device mismatch are unrelated." + }, + { + "left": "issue:43931", + "right": "issue:44863", + "accept": false, + "reason": "Different model families and different load failures." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative overall. The single accepted duplicate pair, 45276/45292, is well supported by the titles and the very high similarity score. The other soft-edge rejections are phrased cautiously and do not overclaim identity from the evidence provided." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 7, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:32090", + "issue:34567", + "issue:36032", + "issue:39404", + "issue:40444", + "issue:40990", + "issue:42947", + "issue:43299", + "issue:43421", + "issue:43425", + "issue:43452", + "issue:43582", + "issue:43596", + "issue:43611", + "issue:43632", + "issue:43643", + "issue:43644", + "issue:43716", + "issue:43856", + "issue:43883", + "issue:43901", + "issue:43931", + "issue:43994", + "issue:44079", + "issue:44164", + "issue:44206", + "issue:44220", + "issue:44265", + "issue:44479", + "issue:44488", + "issue:44509", + "issue:44530", + "issue:44589", + "issue:44661", + "issue:44671", + "issue:44683", + "issue:44756", + "issue:44805", + "issue:44811", + "issue:44898", + "issue:44912", + "issue:44918", + "issue:44987", + "issue:44991", + "issue:45081", + "issue:45084", + "issue:45584", + "issue:45759" + ], + "soft_pairs": [ + "issue:44530|issue:45084", + "issue:43425|issue:43716", + "issue:43901|issue:44509", + "issue:39404|issue:44912", + "issue:44265|issue:44898", + "issue:43299|issue:43931", + "issue:44479|issue:44805", + "issue:43425|issue:44918", + "issue:44589|issue:45084", + "issue:43856|issue:44756", + "issue:40990|issue:42947", + "issue:39404|issue:44671", + "issue:43994|issue:44079", + "issue:44164|issue:45759", + "issue:36032|issue:43452", + "issue:43596|issue:44683", + "issue:44671|issue:44991", + "issue:44991|issue:45081", + "issue:32090|issue:39404", + "issue:44164|issue:44479", + "issue:44488|issue:45081", + "issue:44661|issue:44683", + "issue:40990|issue:43421", + "issue:43582|issue:43632", + "issue:43611|issue:43644", + "issue:44206|issue:44220", + "issue:43716|issue:45084", + "issue:43883|issue:44488", + "issue:44488|issue:44987", + "issue:43643|issue:44530", + "issue:34567|issue:40444", + "issue:44811|issue:45584" + ], + "prepared_review_unit_hash": "2cccaab6747c76850d78bc13c764d77ff1ab854ae157f9c8989b30d2ed753cd2", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37332, + "estimated_input_tokens": 9333, + "estimated_eval_tokens": 18922 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This looks like a loose similarity cluster rather than a true duplicate set. The issues span unrelated subsystems (Whisper, Qwen/VL, tokenizers, docs, loaders, training, torch/export). I did not find any soft-edge pair that clearly describes the same underlying bug or change.", + "confidence": 0.22, + "canonical_issue_reason": "Issue 44479 is the most representative standalone bug in the set: it describes a concrete regression, names the affected model families, and has a clear runtime failure mode.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44479 is the strongest issue to keep as the representative example because it is specific, user-visible, and broadly scoped enough to indicate the underlying regression pattern.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44530", + "right": "issue:45084", + "accept": false, + "reason": "Different failures: one is a Qwen3.5 PagedAttentionCache runtime crash, the other is a template-compilation TypeError. No shared code-path evidence." + }, + { + "left": "issue:43425", + "right": "issue:43716", + "accept": false, + "reason": "Unrelated problems: Torch 2.10 compatibility vs. a multimodal dtype mismatch in Mistral-3." + }, + { + "left": "issue:43901", + "right": "issue:44509", + "accept": false, + "reason": "Both are docs-related, but they cover different pipeline API changes and are not the same documentation bug." + }, + { + "left": "issue:39404", + "right": "issue:44912", + "accept": false, + "reason": "Whisper pipeline language output regression vs. MXFP4 quantization fallback; different subsystems and symptoms." + }, + { + "left": "issue:44265", + "right": "issue:44898", + "accept": false, + "reason": "Different model/export failures: torch.export with torch_compilable_check vs. Perceiver image classification at non-default resolution." + }, + { + "left": "issue:43299", + "right": "issue:43931", + "accept": false, + "reason": "Both concern Qwen3-VL loading, but one is a dev-version model-loading regression and the other is a specific weight-shape mismatch. Not the same bug." + }, + { + "left": "issue:44479", + "right": "issue:44805", + "accept": false, + "reason": "Both mention multimodal input failures, but one is a broad video-input regression across Qwen models and the other is a generic mask/index shape error with no concrete match." + }, + { + "left": "issue:43425", + "right": "issue:44918", + "accept": false, + "reason": "Torch version incompatibility vs. TRL SFT embedding unpacking failure; no shared defect." + }, + { + "left": "issue:44589", + "right": "issue:45084", + "accept": false, + "reason": "Float8 storage lookup error and non-template-node compilation error are unrelated." + }, + { + "left": "issue:43856", + "right": "issue:44756", + "accept": false, + "reason": "Different memory issues: Qwen3 MoE training inefficiency vs. Apple Silicon mmap OOM mitigation." + }, + { + "left": "issue:40990", + "right": "issue:42947", + "accept": false, + "reason": "High perplexity on GPT-OSS evaluation is not the same as ineffective gradient checkpointing with LoRA." + }, + { + "left": "issue:39404", + "right": "issue:44671", + "accept": false, + "reason": "Whisper pipeline regression and CamemBERT masked LM prediction regression are unrelated models and code paths." + }, + { + "left": "issue:43994", + "right": "issue:44079", + "accept": false, + "reason": "SigLIP2 inference issue is not the same as ModelOutput key assignment when a previous value was None." + }, + { + "left": "issue:44164", + "right": "issue:45759", + "accept": false, + "reason": "Different loading/saving problems: extra_state handling vs. from_config text_config unwrapping for composite Qwen multimodal configs." + }, + { + "left": "issue:36032", + "right": "issue:43452", + "accept": false, + "reason": "Tokenizer special-token method conflict and gguf_file loading breakage are separate loading bugs." + }, + { + "left": "issue:43596", + "right": "issue:44683", + "accept": false, + "reason": "DeepSpeed ZeRO-3/BertModel index error is unrelated to compiled flex_attention on newer torch versions." + }, + { + "left": "issue:44671", + "right": "issue:44991", + "accept": false, + "reason": "CamemBERT MLM predictions in v5 and tokenizer loading failure for EMBEDDIA/est-roberta are different defects." + }, + { + "left": "issue:44991", + "right": "issue:45081", + "accept": false, + "reason": "Different tokenizer-loading failures affecting different models and different failure points." + }, + { + "left": "issue:32090", + "right": "issue:39404", + "accept": false, + "reason": "Trainer GPU broadcast TypeError and Whisper return_language regression are unrelated." + }, + { + "left": "issue:44164", + "right": "issue:44479", + "accept": false, + "reason": "Extra_state save/load handling is not the same issue as Qwen video-input regression." + }, + { + "left": "issue:44488", + "right": "issue:45081", + "accept": false, + "reason": "Both are tokenizer-loading related, but the affected models and failing mechanisms differ." + }, + { + "left": "issue:44661", + "right": "issue:44683", + "accept": false, + "reason": "Model-registration logic and compiled flex_attention are unrelated areas." + }, + { + "left": "issue:40990", + "right": "issue:43421", + "accept": false, + "reason": "Perplexity evaluation regression and runtime special-token post-processor update bug are distinct." + }, + { + "left": "issue:43582", + "right": "issue:43632", + "accept": false, + "reason": "Apple Silicon caching allocator TypeError does not match the _is_hf_initialized flag regression." + }, + { + "left": "issue:43611", + "right": "issue:43644", + "accept": false, + "reason": "Both are v5 regressions, but one is base_model_prefix loading and the other is non-persistent buffer initialization; not the same code-path bug." + }, + { + "left": "issue:44206", + "right": "issue:44220", + "accept": false, + "reason": "Audio feature-extraction failures, but one is an unsupported argument in LasrFeatureExtractor and the other is a lower-level fbank helper issue; not clearly the same defect." + }, + { + "left": "issue:43716", + "right": "issue:45084", + "accept": false, + "reason": "Mistral-3 dtype mismatch and template-compilation error are unrelated." + }, + { + "left": "issue:43883", + "right": "issue:44488", + "accept": false, + "reason": "Missing tied-weights metadata in Molmo is unrelated to the sleng-bert tokenizer loading failure." + }, + { + "left": "issue:44488", + "right": "issue:45081", + "accept": false, + "reason": "Tokenizer-loading failures for different models with different symptoms; no strong evidence they share one underlying bug." + }, + { + "left": "issue:43643", + "right": "issue:44530", + "accept": false, + "reason": "trust_remote_code config-field loss and Qwen3.5 PagedAttention crash are different problems." + }, + { + "left": "issue:34567", + "right": "issue:40444", + "accept": false, + "reason": "TrainerState token counting and Qwen2.5-VL IterableDataset multi-image finetuning are unrelated." + }, + { + "left": "issue:44811", + "right": "issue:45584", + "accept": false, + "reason": "Both are Whisper-related, but batch_decode skip_special_tokens handling and empty-transcription generation after align_special_tokens 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": 16, + "review_unit_index": 8, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:36032", + "issue:42915", + "issue:43262", + "issue:43296", + "issue:43317", + "issue:43322", + "issue:43377", + "issue:43404", + "issue:43452", + "issue:43482", + "issue:43531", + "issue:43540", + "issue:43541", + "issue:43611", + "issue:43632", + "issue:43644", + "issue:43645", + "issue:43646", + "issue:43742", + "issue:43819", + "issue:43856", + "issue:43883", + "issue:43994", + "issue:44062", + "issue:44220", + "issue:44265", + "issue:44291", + "issue:44403", + "issue:44451", + "issue:44466", + "issue:44530", + "issue:44534", + "issue:44589", + "issue:44610", + "issue:44683", + "issue:44756", + "issue:44849", + "issue:44877", + "issue:44987", + "issue:44991", + "issue:45081", + "issue:45084", + "issue:45127", + "issue:45216", + "issue:45325", + "issue:45357", + "issue:45507" + ], + "soft_pairs": [ + "issue:43644|issue:43646", + "issue:44451|issue:44987", + "issue:36032|issue:42915", + "issue:43541|issue:45084", + "issue:43452|issue:43482", + "issue:42915|issue:44530", + "issue:43317|issue:43482", + "issue:44849|issue:45325", + "issue:43883|issue:44991", + "issue:43404|issue:44466", + "issue:36032|issue:43645", + "issue:45084|issue:45507", + "issue:43262|issue:43377", + "issue:43646|issue:44534", + "issue:44987|issue:44991", + "issue:43994|issue:44610", + "issue:43322|issue:43540", + "issue:44403|issue:45081", + "issue:43377|issue:43819", + "issue:42915|issue:45084", + "issue:43645|issue:44534", + "issue:45216|issue:45357", + "issue:44451|issue:45081", + "issue:44987|issue:45081", + "issue:44265|issue:44610", + "issue:44220|issue:44683", + "issue:43404|issue:45127", + "issue:43632|issue:44756", + "issue:43296|issue:43531", + "issue:42915|issue:44291", + "issue:44062|issue:44987", + "issue:36032|issue:43742", + "issue:43531|issue:44877", + "issue:42915|issue:44589", + "issue:43611|issue:44534", + "issue:43317|issue:43856" + ], + "prepared_review_unit_hash": "7a1d5033249f07a064d1d2193d9ab4148bbf02578cbc0f9627103ba61cd7b945", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 36, + "serialized_chars": 37909, + "estimated_input_tokens": 9478, + "estimated_eval_tokens": 19212 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab-bag of separate Transformers v5/model-loading regressions. I see one exact duplicate pair around non-persistent buffer junk, and one likely duplicate pair around Qwen3.5 save_pretrained serialization; the rest are too different to merge.", + "confidence": 0.78, + "canonical_issue_reason": "issue:43644 is the clearest representative because it states the precise v5 regression and is an exact duplicate of 44534; it is narrower and better-scoped than the other broadly related loading bugs in the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43644 is the best issue to keep as the representative duplicate target: concrete, reproducible, and directly matched by an exact duplicate title, while the remaining items are mostly distinct regressions.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43644", + "right": "issue:43646", + "accept": false, + "reason": "Related v5 init regressions, but one is buffer corruption and the other is custom model initialization; different concrete bugs." + }, + { + "left": "issue:44451", + "right": "issue:44987", + "accept": false, + "reason": "Different models and different loading failures; no clear shared underlying bug." + }, + { + "left": "issue:36032", + "right": "issue:42915", + "accept": false, + "reason": "Tokenizer special-token conflict vs Qwen3MoE FP8 config failure; unrelated code paths." + }, + { + "left": "issue:43541", + "right": "issue:45084", + "accept": false, + "reason": "Torch dynamo grouped_mm error vs template compilation error; distinct failures." + }, + { + "left": "issue:43452", + "right": "issue:43482", + "accept": false, + "reason": "Both involve GGUF loading, but one is a generic from_pretrained/gguf_file regression and the other is a model-specific Qwen2.5-GGUF failure; not enough evidence of the same bug." + }, + { + "left": "issue:42915", + "right": "issue:44530", + "accept": false, + "reason": "Both Qwen-related, but FP8 config failure and PagedAttentionCache linear_attention crash are different problems." + }, + { + "left": "issue:43317", + "right": "issue:43482", + "accept": false, + "reason": "Different load paths: dequantized device_map offload vs GGUF/Qwen2.5 loading." + }, + { + "left": "issue:44849", + "right": "issue:45325", + "accept": false, + "reason": "Different Qwen model bugs with unrelated symptoms and code paths." + }, + { + "left": "issue:43883", + "right": "issue:44991", + "accept": false, + "reason": "Missing tied-weights attribute vs tokenizer load failure; unrelated." + }, + { + "left": "issue:43404", + "right": "issue:44466", + "accept": false, + "reason": "Both touch tied weights, but one is a missing tie in a model class and the other is device-dependent serialization inconsistency; not the same bug." + }, + { + "left": "issue:36032", + "right": "issue:43645", + "accept": false, + "reason": "Tokenizer method conflict vs custom model initialization in notebooks; different regressions." + }, + { + "left": "issue:45084", + "right": "issue:45507", + "accept": false, + "reason": "Template compilation failure vs GraniteMoEHybrid invalid method call; distinct issues." + }, + { + "left": "issue:43262", + "right": "issue:43377", + "accept": false, + "reason": "Sampling-rate default bug vs missing padding mask support; unrelated audio/model bugs." + }, + { + "left": "issue:43646", + "right": "issue:44534", + "accept": false, + "reason": "Custom model initialization breakage vs non-persistent buffer junk; different concrete failures." + }, + { + "left": "issue:44987", + "right": "issue:44991", + "accept": false, + "reason": "Different model-specific loading regressions, only loosely related by Transformers v5." + }, + { + "left": "issue:43994", + "right": "issue:44610", + "accept": false, + "reason": "Nonsensical model outputs vs processor resolution mismatch; not the same bug." + }, + { + "left": "issue:43322", + "right": "issue:43540", + "accept": false, + "reason": "Segfault loading Llava Next vs ValueError processing Qwen3OmniMoe video inputs; different paths." + }, + { + "left": "issue:44403", + "right": "issue:45081", + "accept": false, + "reason": "Loading noise issue vs Mistral tokenizer regex patch crash; unrelated." + }, + { + "left": "issue:43377", + "right": "issue:43819", + "accept": false, + "reason": "Both are correctness bugs, but one is padding-mask related and the other is missing STE in DAC; different underlying problems." + }, + { + "left": "issue:42915", + "right": "issue:45084", + "accept": false, + "reason": "Qwen3MoE FP8 config issue vs template compilation failure; unrelated." + }, + { + "left": "issue:43645", + "right": "issue:44534", + "accept": false, + "reason": "Custom model init in notebooks vs buffer junk regression; different bugs." + }, + { + "left": "issue:45216", + "right": "issue:45357", + "accept": true, + "reason": "Both report the same Qwen3.5 save_pretrained serialization regression, with the later issue narrowing it to incorrect visual encoder keys." + }, + { + "left": "issue:44451", + "right": "issue:45081", + "accept": false, + "reason": "Different model/tokenizer failures with no shared code-path evidence." + }, + { + "left": "issue:44987", + "right": "issue:45081", + "accept": false, + "reason": "Model loading failure vs Mistral tokenizer regex crash; distinct issues." + }, + { + "left": "issue:44265", + "right": "issue:44610", + "accept": false, + "reason": "torch.export/exportability issue vs processor image-size mismatch; not the same bug." + }, + { + "left": "issue:44220", + "right": "issue:44683", + "accept": false, + "reason": "fbank feature extraction bug vs compiled flex_attention failure on torch>=2.9; unrelated." + }, + { + "left": "issue:43404", + "right": "issue:45127", + "accept": false, + "reason": "Tied-weights bug in model loading vs LoRA merge collapse after vocab extension; different failure modes." + }, + { + "left": "issue:43632", + "right": "issue:44756", + "accept": false, + "reason": "_is_hf_initialized regression vs mmap/OOM workaround request; unrelated." + }, + { + "left": "issue:43296", + "right": "issue:43531", + "accept": false, + "reason": "PaddleOCR-VL load failure in vLLM vs Qwen3-MoE sliding_window issue; different model/code paths." + }, + { + "left": "issue:42915", + "right": "issue:44291", + "accept": false, + "reason": "FP8 config failure vs unexpected _is_hf_initialized argument in init_empty_weights; distinct regressions." + }, + { + "left": "issue:44062", + "right": "issue:44987", + "accept": false, + "reason": "AddedToken keyword collision vs model loading failure; unrelated." + }, + { + "left": "issue:36032", + "right": "issue:43742", + "accept": false, + "reason": "Tokenizer special-token conflict vs MobileLLM key error; different bugs." + }, + { + "left": "issue:43531", + "right": "issue:44877", + "accept": false, + "reason": "Qwen3-MoE sliding_window bug vs granite_speech strict-config load failure; unrelated." + }, + { + "left": "issue:42915", + "right": "issue:44589", + "accept": false, + "reason": "Qwen3MoE FP8 config issue vs missing Float8 storage object; different problems." + }, + { + "left": "issue:43611", + "right": "issue:44534", + "accept": false, + "reason": "base_model_prefix loading regression vs non-persistent buffer junk; distinct failures." + }, + { + "left": "issue:43644", + "right": "issue:44534", + "accept": true, + "reason": "Exact same v5 regression about non-persistent buffers being filled with junk; this is a clear duplicate." + }, + { + "left": "issue:43317", + "right": "issue:43856", + "accept": false, + "reason": "Device-map/offload load failure vs training memory inefficiency; not duplicates." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative overall. The one clear duplicate pair around non-persistent buffers is well supported by the titles, and the Qwen3.5 save_pretrained pair is presented only as a likely duplicate. The rejected soft-edge pairs are also reasonably cautious and do not overclaim shared root causes based on the available evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 9, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:33666", + "issue:36032", + "issue:40444", + "issue:40990", + "issue:41553", + "issue:41720", + "issue:42175", + "issue:43296", + "issue:43377", + "issue:43421", + "issue:43425", + "issue:43454", + "issue:43482", + "issue:43525", + "issue:43531", + "issue:43582", + "issue:43611", + "issue:43632", + "issue:43646", + "issue:43792", + "issue:43818", + "issue:43994", + "issue:44079", + "issue:44265", + "issue:44291", + "issue:44403", + "issue:44462", + "issue:44466", + "issue:44479", + "issue:44534", + "issue:44568", + "issue:44589", + "issue:44683", + "issue:44811", + "issue:44829", + "issue:44898", + "issue:44991", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45325", + "issue:45357", + "issue:45479", + "issue:45491", + "issue:45538", + "issue:45542", + "issue:45663", + "issue:45812" + ], + "soft_pairs": [ + "issue:41553|issue:43582", + "issue:44479|issue:45325", + "issue:40990|issue:44811", + "issue:42175|issue:45542", + "issue:43425|issue:44403", + "issue:44462|issue:45812", + "issue:43818|issue:45357", + "issue:44079|issue:45663", + "issue:43421|issue:44568", + "issue:36032|issue:41720", + "issue:43792|issue:44589", + "issue:43632|issue:44534", + "issue:44403|issue:44991", + "issue:44829|issue:45479", + "issue:44683|issue:45020", + "issue:43482|issue:45538", + "issue:33666|issue:40444", + "issue:43482|issue:43525", + "issue:44291|issue:44589", + "issue:40444|issue:45325", + "issue:43377|issue:45491", + "issue:41720|issue:45081", + "issue:42175|issue:43296", + "issue:43531|issue:44291", + "issue:43611|issue:43646", + "issue:44265|issue:45072", + "issue:43632|issue:45072", + "issue:43454|issue:44466", + "issue:44079|issue:44534", + "issue:43994|issue:44898" + ], + "prepared_review_unit_hash": "c0882aae5ad7140050d4831a80f7b5e506dd26e70e49e2c10ad47eafc57c7b26", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 37015, + "estimated_input_tokens": 9254, + "estimated_eval_tokens": 18764 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly distinct regression reports with issue 45020 as the best umbrella anchor. The only soft links that look plausibly duplicate-like are 44462\u219445812 and 43421\u219444568, but those are better described as strong title/subsystem similarities than confirmed same-bug matches. The v5 init/_is_hf_initialized-related links do not look like duplicates here and should stay rejected.", + "confidence": 0.66, + "canonical_issue_reason": "Issue 45020 is the broadest and most representative umbrella for the cluster: it captures the general recent-transformers-v5 breakage theme without overcommitting to any single narrow failure mode.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45020 is the best global anchor because it is open, broad, and matches the cluster\u2019s shared regression theme across multiple version-specific reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41553", + "right": "issue:43582", + "accept": false, + "reason": "Different failure modes and subsystems: AutoTokenizer/Voxtral loading vs Apple Silicon allocator TypeError." + }, + { + "left": "issue:44479", + "right": "issue:45325", + "accept": false, + "reason": "Same broad model family, but different concrete bugs: video-input regression vs still-image rope-index scaling." + }, + { + "left": "issue:40990", + "right": "issue:44811", + "accept": false, + "reason": "Unrelated behavior: perplexity/eval complaint vs Whisper batch_decode skip_special_tokens handling." + }, + { + "left": "issue:42175", + "right": "issue:45542", + "accept": false, + "reason": "Both involve TF packaging, but the missing-dependency paths and fixes appear different." + }, + { + "left": "issue:43425", + "right": "issue:44403", + "accept": false, + "reason": "Torch compatibility issue vs loading-noise/reporting issue; no shared bug." + }, + { + "left": "issue:44462", + "right": "issue:45812", + "accept": true, + "reason": "Plausibly the same tokenizer-loading path: ignoring tokenizer.json could reasonably surface as wrong token IDs, though this is still mostly title-level evidence." + }, + { + "left": "issue:43818", + "right": "issue:45357", + "accept": false, + "reason": "Different model families and different problems: Video-LLaVA architecture issue vs Qwen3.5 save_pretrained key regression." + }, + { + "left": "issue:44079", + "right": "issue:45663", + "accept": false, + "reason": "ModelOutput key assignment bug and Gemma-4 FSDP2 KeyError are unrelated code paths." + }, + { + "left": "issue:43421", + "right": "issue:44568", + "accept": true, + "reason": "Plausible same tokenizer/post-processor area: both point to special-token handling changing behavior at runtime, but evidence is still mostly similarity-based." + }, + { + "left": "issue:36032", + "right": "issue:41720", + "accept": false, + "reason": "T5 tokenizer attribute conflict vs Qwen3 auto device-mapping crash; unrelated." + }, + { + "left": "issue:43792", + "right": "issue:44589", + "accept": false, + "reason": "Whisper runtime failure and float8 storage lookup TypeError are unrelated." + }, + { + "left": "issue:43632", + "right": "issue:44534", + "accept": false, + "reason": "Both are v5 regressions, but the concrete bugs differ: _is_hf_initialized vs non-persistent buffer corruption." + }, + { + "left": "issue:44403", + "right": "issue:44991", + "accept": false, + "reason": "General loading-noise report vs a specific tokenizer-loading failure; not the same bug." + }, + { + "left": "issue:44829", + "right": "issue:45479", + "accept": false, + "reason": "Similar symptom class, but different causes: flash_attention_3 training collapse vs num_labels=1 zero-loss logic." + }, + { + "left": "issue:44683", + "right": "issue:45020", + "accept": false, + "reason": "A separate torch/compiler flex_attention issue, not the remote_code loading regression." + }, + { + "left": "issue:43482", + "right": "issue:45538", + "accept": false, + "reason": "GGUF loading failure vs CLIPTokenizer model_max_length sentinel issue; unrelated." + }, + { + "left": "issue:33666", + "right": "issue:40444", + "accept": false, + "reason": "Both are Qwen VL training issues, but they concern different models and failure modes." + }, + { + "left": "issue:43482", + "right": "issue:43525", + "accept": false, + "reason": "GGUF/v5 loading failure vs missing pad_token_id on Llama4Config; unrelated." + }, + { + "left": "issue:44291", + "right": "issue:44589", + "accept": false, + "reason": "init_empty_weights/_is_hf_initialized bug vs float8 storage lookup error; unrelated." + }, + { + "left": "issue:40444", + "right": "issue:45325", + "accept": false, + "reason": "Different Qwen2.5-VL bugs: multi-image iterable-dataset failure vs still-image temporal position scaling." + }, + { + "left": "issue:43377", + "right": "issue:45491", + "accept": false, + "reason": "Different batching bugs in different models: padding-mask issue vs mixed-length NaNs from all-padding windows." + }, + { + "left": "issue:41720", + "right": "issue:45081", + "accept": false, + "reason": "Qwen3 device-mapping crash vs Mistral regex/backend_tokenizer AttributeError; unrelated." + }, + { + "left": "issue:42175", + "right": "issue:43296", + "accept": false, + "reason": "Packaging/extras issue vs vLLM PaddleOCR-VL load failure; unrelated." + }, + { + "left": "issue:43531", + "right": "issue:44291", + "accept": false, + "reason": "Qwen3-MoE sliding_window issue vs init_empty_weights unexpected _is_hf_initialized argument; unrelated." + }, + { + "left": "issue:43611", + "right": "issue:43646", + "accept": false, + "reason": "Both are v5-related, but one is base_model_prefix handling and the other is custom model initialization; not the same concrete bug." + }, + { + "left": "issue:44265", + "right": "issue:45072", + "accept": false, + "reason": "torch.export/torch_compilable_check failure vs bf16 dtype mismatch; unrelated." + }, + { + "left": "issue:43632", + "right": "issue:45072", + "accept": false, + "reason": "_is_hf_initialized regression vs bf16 dtype mismatch; unrelated." + }, + { + "left": "issue:43454", + "right": "issue:44466", + "accept": false, + "reason": "Related tied-weight theme, but the concrete failures differ: tying bug vs serialization inconsistency." + }, + { + "left": "issue:44079", + "right": "issue:44534", + "accept": false, + "reason": "ModelOutput key assignment issue vs non-persistent buffer junk; unrelated." + }, + { + "left": "issue:43994", + "right": "issue:44898", + "accept": false, + "reason": "Different models and different bugs: SigLIP2 nonsensical outputs vs Perceiver interpolation failure." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "Reject: the broad anchor on issue 45020 is reasonable, and most soft-edge rejections are conservative, but the summary overstates the evidence by implying the v5 init/_is_hf_initialized cases are convincing duplicates when the packet only supports rejecting those links. The accepted pairs (44462\u219445812 and 43421\u219444568) are plausible, but should be framed more cautiously as title-level similarities rather than confirmed same-bug matches." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 10, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:35707", + "issue:39692", + "issue:40444", + "issue:40990", + "issue:41720", + "issue:42915", + "issue:43262", + "issue:43296", + "issue:43317", + "issue:43377", + "issue:43454", + "issue:43482", + "issue:43526", + "issue:43550", + "issue:43572", + "issue:43606", + "issue:43644", + "issue:43701", + "issue:43746", + "issue:43792", + "issue:43819", + "issue:43873", + "issue:43881", + "issue:43883", + "issue:43957", + "issue:44079", + "issue:44186", + "issue:44265", + "issue:44291", + "issue:44387", + "issue:44466", + "issue:44479", + "issue:44488", + "issue:44610", + "issue:44617", + "issue:44683", + "issue:44877", + "issue:44898", + "issue:44991", + "issue:45072", + "issue:45325", + "issue:45357", + "issue:45381", + "issue:45584", + "issue:45759", + "issue:45800", + "issue:45823", + "issue:45834" + ], + "soft_pairs": [ + "issue:45325|issue:45834", + "issue:42915|issue:43482", + "issue:43792|issue:43957", + "issue:44079|issue:45072", + "issue:40444|issue:45381", + "issue:45325|issue:45381", + "issue:43644|issue:44079", + "issue:44387|issue:44617", + "issue:43296|issue:45800", + "issue:43881|issue:44488", + "issue:44479|issue:45823", + "issue:35707|issue:40444", + "issue:44291|issue:44877", + "issue:43317|issue:43873", + "issue:43606|issue:44265", + "issue:43701|issue:45325", + "issue:44186|issue:44265", + "issue:43606|issue:43819", + "issue:43262|issue:43746", + "issue:41720|issue:45823", + "issue:43454|issue:43550", + "issue:43377|issue:44610", + "issue:43526|issue:43883", + "issue:43454|issue:45072", + "issue:43377|issue:44898", + "issue:40990|issue:45584", + "issue:43572|issue:45759", + "issue:39692|issue:40444", + "issue:43881|issue:44991", + "issue:44466|issue:45357", + "issue:43296|issue:44991", + "issue:43792|issue:44683" + ], + "prepared_review_unit_hash": "4952346d1732e0a6c6fd649fc1c278d8061b9428ae5300ca5156dd29f8fdd22f", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37300, + "estimated_input_tokens": 9325, + "estimated_eval_tokens": 18906 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These issues are mostly separate model-loading, quantization, multimodal, and serialization bugs. I don\u2019t see any soft pair that clearly describes the exact same underlying defect, so no duplicates should be merged here.", + "confidence": 0.84, + "canonical_issue_reason": "issue:43873 is the broadest representative of the cluster\u2019s dominant theme: offloading/quantization/device-mapping regressions. It is also open and central to several nearby load/offload reports.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43873 is the best single issue to keep as the representative because it is the most general and most likely to subsume the offload/quantization subset of this cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45325", + "right": "issue:45834", + "accept": false, + "reason": "Different bugs: still-image temporal position IDs vs long OCR input indexing on a different model." + }, + { + "left": "issue:42915", + "right": "issue:43482", + "accept": false, + "reason": "Same model family, but different failure modes: FP8 config failure vs GGUF loading regression." + }, + { + "left": "issue:43792", + "right": "issue:43957", + "accept": false, + "reason": "Whisper runtime failure and meta-device loading breakage are different code paths." + }, + { + "left": "issue:44079", + "right": "issue:45072", + "accept": false, + "reason": "ModelOutput key assignment bug is unrelated to the bfloat16 dtype mismatch issue." + }, + { + "left": "issue:40444", + "right": "issue:45381", + "accept": false, + "reason": "Multi-image finetuning failure is not the same as the video vision_position_ids regression." + }, + { + "left": "issue:45325", + "right": "issue:45381", + "accept": false, + "reason": "Both involve Qwen VL positions, but one is still-image scaling and the other is a video-input bug." + }, + { + "left": "issue:43644", + "right": "issue:44079", + "accept": false, + "reason": "Non-persistent buffer junk values and ModelOutput key assignment are unrelated defects." + }, + { + "left": "issue:44387", + "right": "issue:44617", + "accept": false, + "reason": "Memory growth under int4 quantization is not the same bug as SAM3Video OOM." + }, + { + "left": "issue:43296", + "right": "issue:45800", + "accept": false, + "reason": "vLLM/PaddleOCR-VL load failure is unrelated to the torch 2.4.1 / transformers 5.8.0 incompatibility report." + }, + { + "left": "issue:43881", + "right": "issue:44488", + "accept": false, + "reason": "Different models and different loading failures; no shared underlying bug." + }, + { + "left": "issue:44479", + "right": "issue:45823", + "accept": false, + "reason": "Both are device-map related, but one is a Qwen video regression and the other is a Gemma4 device mismatch." + }, + { + "left": "issue:35707", + "right": "issue:40444", + "accept": false, + "reason": "Progressive generation with inputs_embeds/past_key_values is unrelated to multi-image iterable finetuning." + }, + { + "left": "issue:44291", + "right": "issue:44877", + "accept": false, + "reason": "init_empty_weights argument mismatch and strict config loading are different issues." + }, + { + "left": "issue:43317", + "right": "issue:43873", + "accept": false, + "reason": "Related offload area, but one is dequantized model loading with gpu/cpu offload and the other is a broader quantization/offload complaint." + }, + { + "left": "issue:43606", + "right": "issue:44265", + "accept": false, + "reason": "CPU offload device mismatch is unrelated to torch.export failures around torch_compilable_check." + }, + { + "left": "issue:43701", + "right": "issue:45325", + "accept": false, + "reason": "Checkpoint resume key mismatch is unrelated to the Qwen2.5-VL positional bug." + }, + { + "left": "issue:44186", + "right": "issue:44265", + "accept": false, + "reason": "Tokenizer padding/truncation crash and export checker failure are not the same underlying problem." + }, + { + "left": "issue:43606", + "right": "issue:43819", + "accept": false, + "reason": "CPU offload device mismatch is unrelated to DAC.from_latents vs forward mismatch." + }, + { + "left": "issue:43262", + "right": "issue:43746", + "accept": false, + "reason": "Audio chat-template sampling-rate default and PEFT checkpoint loading are different bugs." + }, + { + "left": "issue:41720", + "right": "issue:45823", + "accept": false, + "reason": "Both mention device mapping, but they affect different models and fail differently." + }, + { + "left": "issue:43454", + "right": "issue:43550", + "accept": false, + "reason": "Weight tying/garbage text is unrelated to the torch.compile SDPA failure." + }, + { + "left": "issue:43377", + "right": "issue:44610", + "accept": false, + "reason": "MIMI batching/padding-mask bug and OmDet processor resolution mismatch are unrelated." + }, + { + "left": "issue:43526", + "right": "issue:43883", + "accept": false, + "reason": "reduce_labels returning one label is unrelated to missing all_tied_weights_keys." + }, + { + "left": "issue:43454", + "right": "issue:45072", + "accept": false, + "reason": "Serialization/weight-tying bug and bfloat16 dtype mismatch are different issues." + }, + { + "left": "issue:43377", + "right": "issue:44898", + "accept": false, + "reason": "Different models and different failure modes: batching mask bug vs positional interpolation bug." + }, + { + "left": "issue:40990", + "right": "issue:45584", + "accept": false, + "reason": "Perplexity regression on GPT-OSS is unrelated to Whisper empty-transcription generation failure." + }, + { + "left": "issue:43572", + "right": "issue:45759", + "accept": false, + "reason": "Missing pad_token_idx in StableLmConfig is not the same as unwrapping text_config for composite Qwen configs." + }, + { + "left": "issue:39692", + "right": "issue:40444", + "accept": false, + "reason": "Doc-example errors for SigLIP2 are unrelated to Qwen2.5-VL multi-image finetuning failures." + }, + { + "left": "issue:43881", + "right": "issue:44991", + "accept": false, + "reason": "Different models and different tokenizer/loading paths; not a duplicate." + }, + { + "left": "issue:44466", + "right": "issue:45357", + "accept": false, + "reason": "Both touch save_pretrained/serialization, but one is tied lm_head serialization and the other is visual-encoder key saving." + }, + { + "left": "issue:43819", + "right": "issue:44617", + "accept": false, + "reason": "DAC latent mismatch is unrelated to SAM3Video out-of-memory." + }, + { + "left": "issue:43296", + "right": "issue:44991", + "accept": false, + "reason": "Different model families and different loading failures." + }, + { + "left": "issue:43792", + "right": "issue:44683", + "accept": false, + "reason": "Whisper runtime failure and compiled flex_attention failure are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 11, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:34634", + "issue:35707", + "issue:36331", + "issue:40990", + "issue:41720", + "issue:42617", + "issue:42915", + "issue:43295", + "issue:43316", + "issue:43317", + "issue:43322", + "issue:43404", + "issue:43450", + "issue:43454", + "issue:43526", + "issue:43550", + "issue:43577", + "issue:43606", + "issue:43708", + "issue:43720", + "issue:43749", + "issue:43873", + "issue:43881", + "issue:44008", + "issue:44186", + "issue:44387", + "issue:44423", + "issue:44479", + "issue:44534", + "issue:44610", + "issue:44756", + "issue:44877", + "issue:44898", + "issue:44913", + "issue:44918", + "issue:44977", + "issue:44991", + "issue:45072", + "issue:45081", + "issue:45161", + "issue:45357", + "issue:45406", + "issue:45632", + "issue:45684", + "issue:45701", + "issue:45704", + "issue:45812", + "issue:45823" + ], + "soft_pairs": [ + "issue:43454|issue:43720", + "issue:43873|issue:45701", + "issue:41720|issue:44977", + "issue:44008|issue:45823", + "issue:45632|issue:45684", + "issue:43404|issue:45357", + "issue:44423|issue:45406", + "issue:34634|issue:35707", + "issue:44186|issue:45072", + "issue:43577|issue:43708", + "issue:35707|issue:41720", + "issue:43873|issue:44756", + "issue:43749|issue:44534", + "issue:44877|issue:44991", + "issue:42617|issue:42915", + "issue:43450|issue:45701", + "issue:43550|issue:43720", + "issue:36331|issue:42915", + "issue:44610|issue:44898", + "issue:44186|issue:44610", + "issue:44387|issue:45704", + "issue:36331|issue:42617", + "issue:44479|issue:44918", + "issue:43526|issue:43881", + "issue:43316|issue:44913", + "issue:42915|issue:43317", + "issue:45081|issue:45812", + "issue:43550|issue:43606", + "issue:41720|issue:43322", + "issue:40990|issue:45701", + "issue:43295|issue:45701", + "issue:41720|issue:45161" + ], + "prepared_review_unit_hash": "ba3da608036e3681501c0a53f39edb6c439e8fbde2e214f411e00e6f2b6fb379", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37387, + "estimated_input_tokens": 9347, + "estimated_eval_tokens": 18950 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "No duplicate cluster here: the soft-similarity pairs are mostly false positives spanning unrelated models, trainers, tokenizers, configs, and runtime/offloading failures. I would not merge any of the suggested pairs.", + "confidence": 0.97, + "canonical_issue_reason": "No single canonical issue: the items cover unrelated bugs across many models and subsystems, so there is no safe duplicate anchor.", + "canonical_pr_reason": null, + "best_issue_reason": "No single best issue for deduping this set; if forced to pick a broad representative, 43873 is the closest on offloading/quantization, but it does not represent the rest of the items.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43454", + "right": "issue:43720", + "accept": false, + "reason": "Different model families and root causes: lm_head tying vs packed-weight unpacking during accelerate loading." + }, + { + "left": "issue:43873", + "right": "issue:45701", + "accept": false, + "reason": "One is an offloading/quantization runtime bug; the other is a tokenizer/version regression. Not the same code path." + }, + { + "left": "issue:41720", + "right": "issue:44977", + "accept": false, + "reason": "CUDA assert under auto device mapping is unrelated to flash-attention generation behavior." + }, + { + "left": "issue:44008", + "right": "issue:45823", + "accept": false, + "reason": "Both are Gemma-related, but they are different models and bugs: variable-name collision vs PLE device mismatch." + }, + { + "left": "issue:45632", + "right": "issue:45684", + "accept": false, + "reason": "Cache-path collision for trust_remote_code is unrelated to save_pretrained permission propagation." + }, + { + "left": "issue:43404", + "right": "issue:45357", + "accept": false, + "reason": "Mistral3 weight tying and Qwen3.5 visual-key saving are unrelated bugs." + }, + { + "left": "issue:44423", + "right": "issue:45406", + "accept": false, + "reason": "Both crash in serve, but one is a multimodal batching bug and the other is a missing processor attribute. Different causes." + }, + { + "left": "issue:34634", + "right": "issue:35707", + "accept": false, + "reason": "Bark voice_preset failure and inputs_embeds/past_key_values generation regression are unrelated." + }, + { + "left": "issue:44186", + "right": "issue:45072", + "accept": false, + "reason": "Tokenizer crash on NER padding/truncation is unrelated to dtype mismatches in inference." + }, + { + "left": "issue:43577", + "right": "issue:43708", + "accept": false, + "reason": "BLIP2 dtype loading bug and Trainer checkpoint-resume max_steps bug are different subsystems." + }, + { + "left": "issue:35707", + "right": "issue:41720", + "accept": false, + "reason": "Different failures: progressive generation with embeddings vs device-map CUDA assert." + }, + { + "left": "issue:43873", + "right": "issue:44756", + "accept": false, + "reason": "Both mention memory/offload, but one is quantization offload behavior and the other is mmap OOM on Strix Halo." + }, + { + "left": "issue:43749", + "right": "issue:44534", + "accept": false, + "reason": "FSDP CPU RAM efficient loading and non-persistent buffer junk are separate loading/state bugs." + }, + { + "left": "issue:44877", + "right": "issue:44991", + "accept": false, + "reason": "Strict config loading and tokenizer loading regression are different failures with different root causes." + }, + { + "left": "issue:42617", + "right": "issue:42915", + "accept": false, + "reason": "3d_parallel.py startup failure and FineGrainedFP8Config failure are unrelated." + }, + { + "left": "issue:43450", + "right": "issue:45701", + "accept": false, + "reason": "Video batch shape handling is unrelated to tokenizer/version changes." + }, + { + "left": "issue:43550", + "right": "issue:43720", + "accept": false, + "reason": "torch.compile SDPA failure in Bamba and BitNet packed-weight loading are unrelated." + }, + { + "left": "issue:36331", + "right": "issue:42915", + "accept": false, + "reason": "CustomTrainer signature regression is unrelated to Qwen3Moe FP8 loading." + }, + { + "left": "issue:44610", + "right": "issue:44898", + "accept": false, + "reason": "Both are image-size/preprocessing issues, but they affect different models and different code paths; not a single concrete bug." + }, + { + "left": "issue:44186", + "right": "issue:44610", + "accept": false, + "reason": "Tokenizer padding crash and processor resolution mismatch are unrelated." + }, + { + "left": "issue:44387", + "right": "issue:45704", + "accept": false, + "reason": "Both involve memory, but int4 quantization OOM and apex RMSNorm leak are distinct issues." + }, + { + "left": "issue:43526", + "right": "issue:43881", + "accept": false, + "reason": "Beit reduce_labels bug is unrelated to glm-4v-9b loading failure." + }, + { + "left": "issue:43316", + "right": "issue:44913", + "accept": false, + "reason": "Config API discrepancy and GPTNeoX rotary_pct reload regression are different model/config bugs." + }, + { + "left": "issue:42915", + "right": "issue:43317", + "accept": false, + "reason": "FP8 model failure and dequantized model offload loading failure are unrelated." + }, + { + "left": "issue:45081", + "right": "issue:45812", + "accept": false, + "reason": "Tokenizer backend patch crash and Granite token-ID regression are different tokenizer problems." + }, + { + "left": "issue:43550", + "right": "issue:43606", + "accept": false, + "reason": "Bamba torch.compile failure and Bark CPU offload device mismatch are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:43322", + "accept": false, + "reason": "Auto device-map CUDA assert and Llava Next segmentation fault are different model-loading failures." + }, + { + "left": "issue:40990", + "right": "issue:45701", + "accept": false, + "reason": "High perplexity on one model is not the same as a general tokenization version-change report." + }, + { + "left": "issue:43295", + "right": "issue:45701", + "accept": false, + "reason": "Processor/tokenizer API regression and tokenization changes are related only loosely by version, not by the same bug." + }, + { + "left": "issue:41720", + "right": "issue:45161", + "accept": false, + "reason": "Qwen3 auto device-map assert and GPT-OSS MoE tensor-parallel failure 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": 16, + "review_unit_index": 12, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:30064", + "issue:33666", + "issue:34567", + "issue:34634", + "issue:35707", + "issue:36010", + "issue:41720", + "issue:42617", + "issue:42915", + "issue:43322", + "issue:43388", + "issue:43421", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43572", + "issue:43606", + "issue:43653", + "issue:43720", + "issue:43746", + "issue:43782", + "issue:43873", + "issue:43927", + "issue:44062", + "issue:44186", + "issue:44361", + "issue:44368", + "issue:44451", + "issue:44492", + "issue:44509", + "issue:44514", + "issue:44545", + "issue:44671", + "issue:44743", + "issue:44779", + "issue:44898", + "issue:44987", + "issue:44991", + "issue:45042", + "issue:45059", + "issue:45072", + "issue:45357", + "issue:45406", + "issue:45464", + "issue:45701", + "issue:45704", + "issue:45759", + "issue:45812" + ], + "soft_pairs": [ + "issue:43531|issue:43572", + "issue:44671|issue:44743", + "issue:43421|issue:45812", + "issue:41720|issue:42617", + "issue:36010|issue:42617", + "issue:43540|issue:43782", + "issue:44186|issue:44361", + "issue:45406|issue:45464", + "issue:43421|issue:45701", + "issue:30064|issue:34634", + "issue:44492|issue:44509", + "issue:44779|issue:45812", + "issue:42915|issue:43322", + "issue:43606|issue:43720", + "issue:43388|issue:45059", + "issue:43550|issue:43653", + "issue:44514|issue:44545", + "issue:43531|issue:45759", + "issue:43606|issue:43653", + "issue:43421|issue:43927", + "issue:34567|issue:35707", + "issue:44368|issue:45357", + "issue:43873|issue:45704", + "issue:44451|issue:44991", + "issue:41720|issue:43746", + "issue:44898|issue:45072", + "issue:44062|issue:44451", + "issue:44987|issue:45042", + "issue:33666|issue:35707" + ], + "prepared_review_unit_hash": "dcd9c990c8f5714d17b731e95e748d01724b3be4f6d414356a18404810264113", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36342, + "estimated_input_tokens": 9086, + "estimated_eval_tokens": 18428 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly unrelated issue reports; only one soft pair is a clear duplicate (`Qwen2_5_VLProcessor.apply_chat_template` crashing on batched input with `padding=False`). The remaining pairs share broad subsystems or model families, but not the same concrete bug or change.", + "confidence": 0.97, + "canonical_issue_reason": "Issue 44514 is the best canonical issue because it is the earlier report of the exact same `Qwen2_5_VLProcessor.apply_chat_template` batched-`padding=False` crash as 44545.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44514 is the strongest representative in this set since it anchors the only clear duplicate pair and has the clearest, most specific bug description.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43531", + "right": "issue:43572", + "accept": false, + "reason": "Different bugs in different models/configs: Qwen3-MoE sliding-window behavior vs StableLm missing `pad_token_idx` after v5 update." + }, + { + "left": "issue:44671", + "right": "issue:44743", + "accept": false, + "reason": "Both are model-specific regression reports, but one is CamemBERT MLM output and the other is Qwen modular cache state handling; not the same code path." + }, + { + "left": "issue:43421", + "right": "issue:45812", + "accept": false, + "reason": "Both concern tokenizer behavior, but one is runtime post-processor updates and the other is wrong token IDs for Granite models; too different to merge." + }, + { + "left": "issue:41720", + "right": "issue:42617", + "accept": false, + "reason": "Unrelated failures: Qwen3 auto device mapping CUDA assert vs inability to run `3d_parallel.py`." + }, + { + "left": "issue:36010", + "right": "issue:42617", + "accept": false, + "reason": "Importing `GenerationMixin` and running `3d_parallel.py` are unrelated problems." + }, + { + "left": "issue:43540", + "right": "issue:43782", + "accept": false, + "reason": "Different Qwen multimodal loading/processing failures with different triggers and code paths." + }, + { + "left": "issue:44186", + "right": "issue:44361", + "accept": false, + "reason": "Both are tokenizer/task issues, but they affect different tokenizers and different failure modes." + }, + { + "left": "issue:45406", + "right": "issue:45464", + "accept": false, + "reason": "Serve crashes on missing `_tokenizer` versus streaming chat/completions failure on Qwen3.5-0.8B; not the same bug." + }, + { + "left": "issue:43421", + "right": "issue:45701", + "accept": false, + "reason": "`TokenizersBackend` post-processor refresh bug is not the same as a general version-dependent tokenization change report." + }, + { + "left": "issue:30064", + "right": "issue:34634", + "accept": false, + "reason": "Image processor void segmentation maps and Bark voice_preset are unrelated." + }, + { + "left": "issue:44492", + "right": "issue:44509", + "accept": false, + "reason": "A cache-strategy typo and docs referencing removed pipeline tasks are separate documentation issues." + }, + { + "left": "issue:44779", + "right": "issue:45812", + "accept": false, + "reason": "Both involve tokenizer regressions, but on different model families and different symptoms." + }, + { + "left": "issue:42915", + "right": "issue:43322", + "accept": false, + "reason": "Qwen3Moe FP8 config failure and Llava Next segmentation fault are unrelated." + }, + { + "left": "issue:43606", + "right": "issue:43720", + "accept": false, + "reason": "CPU offload device mismatch for Bark-small is unrelated to BitNet packed-weight loading." + }, + { + "left": "issue:43388", + "right": "issue:45059", + "accept": false, + "reason": "gather-for-metrics label truncation and SAM3 text/bbox behavior are different bugs." + }, + { + "left": "issue:43550", + "right": "issue:43653", + "accept": false, + "reason": "torch.compile SDPA failure in Bamba and BigBird tokenizer special-token decode issue are unrelated." + }, + { + "left": "issue:44514", + "right": "issue:44545", + "accept": true, + "reason": "Same bug and same title: `Qwen2_5_VLProcessor.apply_chat_template` crashes on batched input when `padding=False`." + }, + { + "left": "issue:43531", + "right": "issue:45759", + "accept": false, + "reason": "Both mention Qwen3-related configs, but one is a sliding-window MoE issue and the other is `from_config` unwrapping of `text_config`." + }, + { + "left": "issue:43606", + "right": "issue:43653", + "accept": false, + "reason": "CPU offload device mismatch for Bark-small is not the same as BigBird tokenizer mask-token decoding." + }, + { + "left": "issue:43421", + "right": "issue:43927", + "accept": false, + "reason": "Both are token-related, but one is runtime special-token post-processing and the other is config token IDs lost after save/load." + }, + { + "left": "issue:34567", + "right": "issue:35707", + "accept": false, + "reason": "Trainer token-count tracking and progressive generation with `inputs_embeds`/`past_key_values` are unrelated." + }, + { + "left": "issue:44368", + "right": "issue:45357", + "accept": false, + "reason": "A LoRA warning about `tie_word_embeddings` and incorrect visual encoder keys in `save_pretrained` are different issues." + }, + { + "left": "issue:43873", + "right": "issue:45704", + "accept": false, + "reason": "Quantization/offloading behavior and a T5 apex RMSNorm memory leak are unrelated." + }, + { + "left": "issue:44451", + "right": "issue:44991", + "accept": false, + "reason": "Different model-loading regressions for different models; not the same underlying tokenizer/load bug." + }, + { + "left": "issue:41720", + "right": "issue:43746", + "accept": false, + "reason": "Qwen3 auto device mapping CUDA assert and GraniteSpeech PEFT local checkpoint loading are different failure modes." + }, + { + "left": "issue:44898", + "right": "issue:45072", + "accept": false, + "reason": "Perceiver resolution handling and dtype mismatches in bfloat16 inference are unrelated." + }, + { + "left": "issue:44062", + "right": "issue:44451", + "accept": false, + "reason": "`AddedToken` keyword collision and ScandiBERT loading failure are separate tokenizer/model issues." + }, + { + "left": "issue:44987", + "right": "issue:45042", + "accept": false, + "reason": "A model load regression and a PIL-backend torchvision dependency regression are unrelated." + }, + { + "left": "issue:33666", + "right": "issue:35707", + "accept": false, + "reason": "Qwen2-VL multi-GPU training and progressive generation with `inputs_embeds`/`past_key_values` are not the same problem." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet. The duplicate call on issue:44514/44545 is supported by near-identical titles and dates, and the remaining soft-edge rejections stay conservative by citing distinct bug descriptions rather than broad subsystem overlap. No overstatement noticed." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 13, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:30064", + "issue:34634", + "issue:36010", + "issue:39692", + "issue:41720", + "issue:42886", + "issue:42915", + "issue:43335", + "issue:43381", + "issue:43421", + "issue:43525", + "issue:43531", + "issue:43540", + "issue:43575", + "issue:43596", + "issue:43618", + "issue:43653", + "issue:43697", + "issue:43716", + "issue:43720", + "issue:43746", + "issue:43756", + "issue:43782", + "issue:43819", + "issue:43844", + "issue:43873", + "issue:43994", + "issue:44008", + "issue:44077", + "issue:44186", + "issue:44220", + "issue:44589", + "issue:44610", + "issue:44625", + "issue:44661", + "issue:44671", + "issue:44756", + "issue:44843", + "issue:44918", + "issue:44936", + "issue:45081", + "issue:45183", + "issue:45356", + "issue:45381", + "issue:45479", + "issue:45588", + "issue:45704", + "issue:45759" + ], + "soft_pairs": [ + "issue:43531|issue:44589", + "issue:43421|issue:43653", + "issue:45588|issue:45759", + "issue:42886|issue:44843", + "issue:43381|issue:43844", + "issue:39692|issue:44610", + "issue:43421|issue:44186", + "issue:44918|issue:44936", + "issue:43525|issue:43531", + "issue:44625|issue:45479", + "issue:43782|issue:45381", + "issue:45081|issue:45356", + "issue:34634|issue:41720", + "issue:43994|issue:44671", + "issue:43381|issue:45704", + "issue:39692|issue:43873", + "issue:42915|issue:45759", + "issue:43596|issue:44220", + "issue:43540|issue:44008", + "issue:43618|issue:43697", + "issue:45183|issue:45479", + "issue:44220|issue:44661", + "issue:44077|issue:44625", + "issue:43575|issue:45704", + "issue:30064|issue:36010", + "issue:43720|issue:43819", + "issue:43335|issue:43756", + "issue:44756|issue:45759", + "issue:43653|issue:43720", + "issue:43716|issue:44008", + "issue:42915|issue:43746" + ], + "prepared_review_unit_hash": "c6f6118d23c05bb697c0a6a1e6cf98ab0898e18c40d9a3d9a8b64a1da1d27a44", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37192, + "estimated_input_tokens": 9298, + "estimated_eval_tokens": 18852 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous issue reports. Only one soft edge looks like a true duplicate: two reports of the same Mistral-regex/offline tokenizer loading regression. The rest share broad themes but not the same concrete bug.", + "confidence": 0.71, + "canonical_issue_reason": "issue:44843 is the clearest representative of the only tightly related subthread in the cluster: it names the _patch_mistral_regex offline regression directly and has inbound reference signal, while most other issues are unrelated one-off model or trainer bugs.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44843 is the best global issue candidate because it is concrete, well-scoped, and central to the only real duplicate pair in this set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43531", + "right": "issue:44589", + "accept": false, + "reason": "Different models and failures: sliding_window config bug vs float8 storage/type error." + }, + { + "left": "issue:43421", + "right": "issue:43653", + "accept": false, + "reason": "Both involve tokenizers/special tokens, but one is a runtime post-processor update request and the other is a mask-token decode bug; not the same defect." + }, + { + "left": "issue:45588", + "right": "issue:45759", + "accept": false, + "reason": "Different areas: flash-attention sinkless crash vs composite Qwen config unwrapping." + }, + { + "left": "issue:42886", + "right": "issue:44843", + "accept": true, + "reason": "Same underlying tokenizer-loading regression in _patch_mistral_regex; one report emphasizes HF_HUB_OFFLINE/cache failure, the other the direct offline breakage from unconditional model_info()." + }, + { + "left": "issue:43381", + "right": "issue:43844", + "accept": false, + "reason": "Both mention gradients/checkpointing, but they describe different training behaviors and code paths." + }, + { + "left": "issue:39692", + "right": "issue:44610", + "accept": false, + "reason": "Both are vision processor/model mismatches, but for different models and different concrete size/quantization failures." + }, + { + "left": "issue:43421", + "right": "issue:44186", + "accept": false, + "reason": "Tokenizer-related, but one is special-token post-processing at runtime and the other is LayoutLMv2 NER/padding crashes." + }, + { + "left": "issue:44918", + "right": "issue:44936", + "accept": false, + "reason": "Trainer-related, but one is embedding unpacking with TRL SFT and the other is evaluate-after-train failure." + }, + { + "left": "issue:43525", + "right": "issue:43531", + "accept": false, + "reason": "Different Qwen/Llama config problems; not the same underlying bug." + }, + { + "left": "issue:44625", + "right": "issue:45479", + "accept": false, + "reason": "Both touch classification config, but one is Qwen3.5 text-config propagation and the other is loss behavior for num_labels=1." + }, + { + "left": "issue:43782", + "right": "issue:45381", + "accept": false, + "reason": "Both are Qwen VL issues, but one is from_pretrained weight-only loading and the other is incorrect video vision_position_ids." + }, + { + "left": "issue:45081", + "right": "issue:45356", + "accept": false, + "reason": "Related to fix_mistral_regex, but the titles point to different failures: an AttributeError crash versus codec-handling/regression warning issues." + }, + { + "left": "issue:34634", + "right": "issue:41720", + "accept": false, + "reason": "Unrelated model families and errors." + }, + { + "left": "issue:43994", + "right": "issue:44671", + "accept": false, + "reason": "Both are bad outputs, but they are different model-specific regressions with different likely causes." + }, + { + "left": "issue:43381", + "right": "issue:45704", + "accept": false, + "reason": "Different bugs: eval-mode checkpointing limitation vs apex RMSNorm memory leak." + }, + { + "left": "issue:39692", + "right": "issue:43873", + "accept": false, + "reason": "Different problems: docs/example mismatch vs quantization offloading behavior." + }, + { + "left": "issue:42915", + "right": "issue:45759", + "accept": false, + "reason": "Both involve Qwen models, but the concrete failures are unrelated." + }, + { + "left": "issue:43596", + "right": "issue:44220", + "accept": false, + "reason": "Different subsystems: DeepSpeed/BertModel zero3 init vs audio fbank feature extraction." + }, + { + "left": "issue:43540", + "right": "issue:44008", + "accept": false, + "reason": "Different modalities and code paths: Qwen3OmniMoe video processing vs Gemma3n variable collision." + }, + { + "left": "issue:43618", + "right": "issue:43697", + "accept": false, + "reason": "Different regressions in different models; no shared concrete fix is evident." + }, + { + "left": "issue:45183", + "right": "issue:45479", + "accept": false, + "reason": "Different class of bug: input validation messaging vs classification loss degeneracy." + }, + { + "left": "issue:44220", + "right": "issue:44661", + "accept": false, + "reason": "Audio feature extraction vs tokenizer/model registration logic; unrelated." + }, + { + "left": "issue:44077", + "right": "issue:44625", + "accept": false, + "reason": "Different model/config issues with no shared failure mode." + }, + { + "left": "issue:43575", + "right": "issue:45704", + "accept": false, + "reason": "TP OOM versus RMSNorm memory leak; unrelated." + }, + { + "left": "issue:30064", + "right": "issue:36010", + "accept": false, + "reason": "Different domains: image processor segmentation handling vs GenerationMixin import error." + }, + { + "left": "issue:43720", + "right": "issue:43819", + "accept": false, + "reason": "Different low-level numerical/loading bugs in unrelated models." + }, + { + "left": "issue:43335", + "right": "issue:43756", + "accept": false, + "reason": "Both are model-architecture quirks, but they concern different components and symptoms." + }, + { + "left": "issue:44756", + "right": "issue:45759", + "accept": false, + "reason": "Memory/offloading concern versus composite config unwrapping; not the same issue." + }, + { + "left": "issue:43653", + "right": "issue:43720", + "accept": false, + "reason": "Tokenizer special-token decode bug versus BitNet packed-weight loading bug." + }, + { + "left": "issue:43716", + "right": "issue:44008", + "accept": false, + "reason": "Different multimodal model bugs with no shared code path." + }, + { + "left": "issue:42915", + "right": "issue:43746", + "accept": false, + "reason": "Different Qwen/Moe FP8 loading versus GraniteSpeech PEFT local checkpoint loading." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet, and the accepted soft edge (42886 \u2194 44843) is well-supported by the shared _patch_mistral_regex / HF_HUB_OFFLINE failure mode. The remaining soft-edge rejections are conservative and match the issue titles; no evidence is overstated." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 14, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:30064", + "issue:34634", + "issue:36010", + "issue:36331", + "issue:39692", + "issue:43295", + "issue:43322", + "issue:43421", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43577", + "issue:43582", + "issue:43606", + "issue:43643", + "issue:43653", + "issue:43746", + "issue:43782", + "issue:43818", + "issue:43819", + "issue:43825", + "issue:43827", + "issue:43873", + "issue:43994", + "issue:44062", + "issue:44186", + "issue:44442", + "issue:44448", + "issue:44479", + "issue:44485", + "issue:44488", + "issue:44509", + "issue:44561", + "issue:44671", + "issue:44811", + "issue:44821", + "issue:44843", + "issue:44877", + "issue:44898", + "issue:44977", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45084", + "issue:45381", + "issue:45584", + "issue:45685", + "issue:45834" + ], + "soft_pairs": [ + "issue:43295|issue:45834", + "issue:43746|issue:45381", + "issue:43746|issue:43873", + "issue:43550|issue:45072", + "issue:43550|issue:43819", + "issue:44186|issue:44898", + "issue:44843|issue:45081", + "issue:43531|issue:43643", + "issue:43643|issue:44877", + "issue:43421|issue:44811", + "issue:44062|issue:44488", + "issue:43577|issue:43818", + "issue:43540|issue:45381", + "issue:43653|issue:43819", + "issue:44448|issue:44671", + "issue:43782|issue:44977", + "issue:45584|issue:45834", + "issue:44561|issue:45020", + "issue:43825|issue:43994", + "issue:43322|issue:45685", + "issue:44821|issue:45084", + "issue:39692|issue:45834", + "issue:30064|issue:36331", + "issue:44479|issue:45834", + "issue:43825|issue:43827", + "issue:44485|issue:44509", + "issue:44186|issue:44442", + "issue:43606|issue:45072", + "issue:43577|issue:43582", + "issue:34634|issue:36010" + ], + "prepared_review_unit_hash": "dbea9a34ea5c20b8a6c482a53340fe16b8d2968392b72171f613d0ee605413f6", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36805, + "estimated_input_tokens": 9202, + "estimated_eval_tokens": 18660 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a loose collection of unrelated Transformers bug reports, many about v5 regressions, model loading, tokenizers, or modality-specific processing. None of the soft pairs look like the same underlying bug/change, so I would not merge any of them.", + "confidence": 0.93, + "canonical_issue_reason": "issue:45020 is the broadest umbrella item: it captures the recurring theme of recent-version regressions breaking remote-code/custom-model usage. That said, the cluster is still too heterogeneous for a strong single canonical issue.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45020 is the best representative issue by scope and wording, even though it does not truly subsume all items in the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43295", + "right": "issue:45834", + "accept": false, + "reason": "Different models and failures: processor/tokenizer regression vs Kosmos2.5 long-OCR index error." + }, + { + "left": "issue:43746", + "right": "issue:45381", + "accept": false, + "reason": "Local checkpoint/PEFT load failure is unrelated to Qwen video position-id handling." + }, + { + "left": "issue:43746", + "right": "issue:43873", + "accept": false, + "reason": "Loading local PEFT adapters is a different code path from quantization/offloading behavior." + }, + { + "left": "issue:43550", + "right": "issue:45072", + "accept": false, + "reason": "Torch.compile + SDPA bug in Bamba is unrelated to dtype mismatch inference issues in SwitchTransformers/TimmWrapperModel." + }, + { + "left": "issue:43550", + "right": "issue:43819", + "accept": false, + "reason": "Different subsystems and symptoms: SDPA/compile vs DAC latent reconstruction mismatch." + }, + { + "left": "issue:44186", + "right": "issue:44898", + "accept": false, + "reason": "LayoutLMv2 tokenizer crash is unrelated to Perceiver image classification resizing/interpolation failure." + }, + { + "left": "issue:44843", + "right": "issue:45081", + "accept": false, + "reason": "Both involve _patch_mistral_regex, but one is HF offline/model_info behavior and the other is a backend_tokenizer attribute crash; not the same bug." + }, + { + "left": "issue:43531", + "right": "issue:43643", + "accept": false, + "reason": "Sliding-window handling for Qwen3-MoE is unrelated to trust_remote_code config field loss." + }, + { + "left": "issue:43643", + "right": "issue:44877", + "accept": false, + "reason": "Both concern config loading, but one is missing fields from trust_remote_code and the other is strict config rejection for granite_speech." + }, + { + "left": "issue:43421", + "right": "issue:44811", + "accept": false, + "reason": "Runtime special-token/post-processor update bug is different from Whisper batch_decode ignoring skip_special_tokens." + }, + { + "left": "issue:44062", + "right": "issue:44488", + "accept": false, + "reason": "AddedToken constructor error is not the same as a model load failure for cjvt/sleng-bert." + }, + { + "left": "issue:43577", + "right": "issue:43818", + "accept": false, + "reason": "Blip2 dtype propagation bug is unrelated to Video-LLaVA missing temporal attention/shared weights." + }, + { + "left": "issue:43540", + "right": "issue:45381", + "accept": false, + "reason": "Both are video-related, but they affect different models and different processing failures." + }, + { + "left": "issue:43653", + "right": "issue:43819", + "accept": false, + "reason": "BigBirdTokenizer special-token registration issue is unrelated to DAC forward/from_latents mismatch." + }, + { + "left": "issue:44448", + "right": "issue:44671", + "accept": false, + "reason": "Different model regressions: Pegasus output drift vs CamemBERT masked-LM prediction errors." + }, + { + "left": "issue:43782", + "right": "issue:44977", + "accept": false, + "reason": "Weight-only load error in Qwen3VL is different from flash-attention generation problems in Qwen3.5." + }, + { + "left": "issue:45584", + "right": "issue:45834", + "accept": false, + "reason": "Whisper empty-transcription generation failure is unrelated to Kosmos2.5 OCR long-input index errors." + }, + { + "left": "issue:44561", + "right": "issue:45020", + "accept": false, + "reason": "44561 is a specific is_torch_fx_available regression; 45020 is a broad umbrella issue, not the same concrete bug." + }, + { + "left": "issue:43825", + "right": "issue:43994", + "accept": false, + "reason": "Pipeline error-message wording is unrelated to SigLIP2 nonsensical output from AutoModel/pipeline." + }, + { + "left": "issue:43322", + "right": "issue:45685", + "accept": false, + "reason": "Llava Next segfault and MPS histogram/int error are unrelated failures." + }, + { + "left": "issue:44821", + "right": "issue:45084", + "accept": false, + "reason": "AutoImageProcessor URL loading is a different problem from the template-node compilation error." + }, + { + "left": "issue:39692", + "right": "issue:45834", + "accept": false, + "reason": "SigLIP2 docs/example issues are unrelated to Kosmos2.5 OCR indexing." + }, + { + "left": "issue:30064", + "right": "issue:36331", + "accept": false, + "reason": "Image processor segmentation-map failure is unrelated to CustomTrainer.compute_loss signature mismatch." + }, + { + "left": "issue:44479", + "right": "issue:45834", + "accept": false, + "reason": "Qwen video-input regression is unrelated to Kosmos2.5 long OCR input handling." + }, + { + "left": "issue:43825", + "right": "issue:43827", + "accept": false, + "reason": "One is an error-message bug; the other is stale docs. Related topic, but not the same change or code-path." + }, + { + "left": "issue:44485", + "right": "issue:44509", + "accept": false, + "reason": "GLM-5 RoPE implementation discussion is unrelated to documentation references to removed pipeline tasks." + }, + { + "left": "issue:44186", + "right": "issue:44442", + "accept": false, + "reason": "LayoutLMv2 tokenizer crash is unrelated to AutoTokenizer loading FastSpeech2ConformerTokenizer." + }, + { + "left": "issue:43606", + "right": "issue:45072", + "accept": false, + "reason": "CPU offload device mismatch in Bark-small is unrelated to bfloat16 dtype mismatches in other models." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 15, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:36010", + "issue:38175", + "issue:39692", + "issue:42175", + "issue:43262", + "issue:43329", + "issue:43404", + "issue:43452", + "issue:43526", + "issue:43582", + "issue:43638", + "issue:43644", + "issue:43645", + "issue:43650", + "issue:43653", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43746", + "issue:43749", + "issue:43782", + "issue:43819", + "issue:43854", + "issue:43906", + "issue:44060", + "issue:44368", + "issue:44554", + "issue:44589", + "issue:44610", + "issue:44671", + "issue:44805", + "issue:44811", + "issue:44857", + "issue:44912", + "issue:44936", + "issue:44977", + "issue:44991", + "issue:45020", + "issue:45042", + "issue:45072", + "issue:45081", + "issue:45084", + "issue:45406", + "issue:45459", + "issue:45538", + "issue:45600", + "issue:45701", + "issue:45803" + ], + "soft_pairs": [ + "issue:43452|issue:44991", + "issue:44805|issue:44936", + "issue:42175|issue:45081", + "issue:44610|issue:45072", + "issue:45081|issue:45406", + "issue:43720|issue:45072", + "issue:44060|issue:44368", + "issue:44671|issue:45701", + "issue:43650|issue:43906", + "issue:43404|issue:43782", + "issue:43582|issue:44857", + "issue:45459|issue:45803", + "issue:43262|issue:43819", + "issue:43526|issue:43697", + "issue:45084|issue:45538", + "issue:43329|issue:45600", + "issue:43644|issue:43749", + "issue:43742|issue:45020", + "issue:43653|issue:44912", + "issue:43638|issue:44936", + "issue:43746|issue:44811", + "issue:44589|issue:45042", + "issue:43854|issue:44977", + "issue:38175|issue:44610", + "issue:39692|issue:44912", + "issue:43526|issue:44554", + "issue:36010|issue:43645" + ], + "prepared_review_unit_hash": "17a05f14a1fd45fbd00e236451709943e373bfae302d149ddbb8f1a80f3bf4a5", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "serialized_chars": 36095, + "estimated_input_tokens": 9024, + "estimated_eval_tokens": 18304 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items are a loose collection of closed/open Transformers issues with only topical similarity; the soft pairs mostly share broad themes (tokenizers, loading, warnings, multimodal processors) but not the same concrete bug. I found no safe duplicate merge candidates and no PRs in the set.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43452", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer-loading failures, but one is gguf_file-related and the other is a model-specific regression; different code paths and symptoms." + }, + { + "left": "issue:44805", + "right": "issue:44936", + "accept": false, + "reason": "Different failure modes: mask/index shape error vs trainer.evaluate() breaking after train(); not the same underlying bug." + }, + { + "left": "issue:42175", + "right": "issue:45081", + "accept": false, + "reason": "One is an install/backend packaging issue, the other is a tokenizer regex patch crash; unrelated defects." + }, + { + "left": "issue:44610", + "right": "issue:45072", + "accept": false, + "reason": "Image size mismatch in OmDet-Turbo vs dtype mismatch in bfloat16 inference; separate model paths." + }, + { + "left": "issue:45081", + "right": "issue:45406", + "accept": false, + "reason": "Both involve tokenizer/processor loading, but the failing objects and root causes differ (Mistral regex patch vs Gemma4Processor missing _tokenizer)." + }, + { + "left": "issue:43720", + "right": "issue:45072", + "accept": false, + "reason": "BitNet packed-weight unpacking bug is unrelated to the SwitchTransformers/TimmWrapperModel dtype mismatch." + }, + { + "left": "issue:44060", + "right": "issue:44368", + "accept": false, + "reason": "Both mention tied-weights warnings, but the model versions and concrete defect are different; too weak to merge." + }, + { + "left": "issue:44671", + "right": "issue:45701", + "accept": false, + "reason": "CamemBERT masked-LM regression is not the same as a broad tokenization change report." + }, + { + "left": "issue:43650", + "right": "issue:43906", + "accept": false, + "reason": "No shared bug: one is a nonspecific request, the other is a reproduction of a separate issue." + }, + { + "left": "issue:43404", + "right": "issue:43782", + "accept": false, + "reason": "Untied lm_head weights in Mistral3 is different from Qwen3VL from_pretrained weight_only loading failure." + }, + { + "left": "issue:43582", + "right": "issue:44857", + "accept": false, + "reason": "Apple Silicon warmup TypeError and CUDA AMP crash are different platform-specific problems." + }, + { + "left": "issue:45459", + "right": "issue:45803", + "accept": false, + "reason": "Both are exception-handling bugs, but they affect different functions and hide different errors." + }, + { + "left": "issue:43262", + "right": "issue:43819", + "accept": false, + "reason": "Audio apply_chat_template sample-rate defaulting is unrelated to DAC.from_latents vs forward mismatch." + }, + { + "left": "issue:43526", + "right": "issue:43697", + "accept": false, + "reason": "BEiT label reduction bug and RTDetrV2 output drift are separate vision-model regressions." + }, + { + "left": "issue:45084", + "right": "issue:45538", + "accept": false, + "reason": "Template compilation failure and CLIPTokenizer max_length misconfiguration are unrelated." + }, + { + "left": "issue:43329", + "right": "issue:45600", + "accept": false, + "reason": "Multimodal token counting bug and stale auto_mappings config references are different code areas." + }, + { + "left": "issue:43644", + "right": "issue:43749", + "accept": false, + "reason": "Non-persistent buffer junk initialization and FSDP CPU RAM efficient loading are not the same defect." + }, + { + "left": "issue:43742", + "right": "issue:45020", + "accept": false, + "reason": "A MobileLLM loading key error is not the same as a broad remote_code regression across recent versions." + }, + { + "left": "issue:43653", + "right": "issue:44912", + "accept": false, + "reason": "BigBird special-token decode bug and MXFP4 quantization fallback are unrelated." + }, + { + "left": "issue:43638", + "right": "issue:44936", + "accept": false, + "reason": "Zero3/Bert indexing failure and trainer.evaluate() after train() failure do not share a concrete root cause." + }, + { + "left": "issue:43746", + "right": "issue:44811", + "accept": false, + "reason": "PEFT checkpoint loading and Whisper batch_decode skip_special_tokens behavior are separate processor/model issues." + }, + { + "left": "issue:44589", + "right": "issue:45042", + "accept": false, + "reason": "Float8 storage lookup error and PIL backend torchvision dependency regression are unrelated." + }, + { + "left": "issue:43854", + "right": "issue:44977", + "accept": false, + "reason": "GLM-4.7-Flash loading in tests and Qwen3.5 flash-attention generation are different model-specific bugs." + }, + { + "left": "issue:38175", + "right": "issue:44610", + "accept": false, + "reason": "SigLIP2 zero probabilities and OmDet input-size mismatch are distinct vision-model issues." + }, + { + "left": "issue:39692", + "right": "issue:44912", + "accept": false, + "reason": "Documentation example errors for SigLIP2 are not the same as a quantization loading/fallback bug." + }, + { + "left": "issue:43526", + "right": "issue:44554", + "accept": false, + "reason": "BEiT label reduction bug is unrelated to the MPS attention correctness issue." + }, + { + "left": "issue:36010", + "right": "issue:43645", + "accept": false, + "reason": "GenerationMixin import failure and custom model initialization in notebooks are different v5 regressions." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 16, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:33357", + "issue:34567", + "issue:34634", + "issue:36010", + "issue:36331", + "issue:40990", + "issue:41720", + "issue:42915", + "issue:43257", + "issue:43262", + "issue:43317", + "issue:43329", + "issue:43450", + "issue:43452", + "issue:43454", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43577", + "issue:43582", + "issue:43643", + "issue:43696", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43749", + "issue:43756", + "issue:43819", + "issue:43927", + "issue:43931", + "issue:44291", + "issue:44479", + "issue:44560", + "issue:44568", + "issue:44610", + "issue:44811", + "issue:44821", + "issue:44849", + "issue:44912", + "issue:44987", + "issue:45042", + "issue:45356", + "issue:45357", + "issue:45381", + "issue:45488", + "issue:45538", + "issue:45701", + "issue:45759" + ], + "soft_pairs": [ + "issue:34634|issue:36331", + "issue:43454|issue:43577", + "issue:43257|issue:43329", + "issue:43819|issue:43927", + "issue:43720|issue:44610", + "issue:43550|issue:44912", + "issue:44568|issue:45488", + "issue:43749|issue:44291", + "issue:43531|issue:45042", + "issue:43262|issue:44811", + "issue:43643|issue:45759", + "issue:44568|issue:45356", + "issue:36010|issue:36331", + "issue:44849|issue:45701", + "issue:43329|issue:43450", + "issue:34567|issue:40990", + "issue:43329|issue:44479", + "issue:43257|issue:43931", + "issue:43697|issue:45357", + "issue:44291|issue:45042", + "issue:41720|issue:43540", + "issue:43452|issue:43582", + "issue:42915|issue:43742", + "issue:33357|issue:34567", + "issue:43317|issue:45538", + "issue:43927|issue:44912", + "issue:44987|issue:45538", + "issue:44479|issue:45381", + "issue:42915|issue:44821", + "issue:42915|issue:45538", + "issue:43257|issue:43756", + "issue:43540|issue:44560", + "issue:43540|issue:44479", + "issue:43257|issue:43696" + ], + "prepared_review_unit_hash": "8d1e70b0a2888148e75ae9031fd2898dd88089c4d701d28af489862e74a94995", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 38028, + "estimated_input_tokens": 9507, + "estimated_eval_tokens": 19270 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly heterogeneous issue set. issue:44479 is still the best umbrella for the Qwen video-input regression family, but issue:43329 looks like a narrower undefined-variable bug in `_get_num_multimodal_tokens`, not a confident duplicate of the broader 5.3.0 regression.", + "confidence": 0.72, + "canonical_issue_reason": "issue:44479 best captures the broad v5.3.0 video-input regression across multiple Qwen VL/MoE variants, so it is the strongest umbrella issue.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44479 is the most representative global issue because it spans the widest user-facing Qwen video regression while matching the shared subsystem.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:34634", + "right": "issue:36331", + "accept": false, + "reason": "Different areas: BarkProcessor voice preset handling vs Trainer compute_loss signature change." + }, + { + "left": "issue:43454", + "right": "issue:43577", + "accept": false, + "reason": "Unrelated model bugs: AyaVision weight tying vs BLIP-2 dtype loading." + }, + { + "left": "issue:43257", + "right": "issue:43329", + "accept": false, + "reason": "Both are Qwen-related, but one is MOE weight conversion on load and the other is a video token-counting bug; different code paths." + }, + { + "left": "issue:43819", + "right": "issue:43927", + "accept": false, + "reason": "DAC latent conversion mismatch vs DiaConfig custom token ID persistence; unrelated model behaviors." + }, + { + "left": "issue:43720", + "right": "issue:44610", + "accept": false, + "reason": "Accelerate packed-weight loading bug vs OmDet-Turbo image size mismatch; not the same underlying defect." + }, + { + "left": "issue:43550", + "right": "issue:44912", + "accept": false, + "reason": "Different failure modes: torch.compile with SDPA vs MXFP4 quantization fallback." + }, + { + "left": "issue:44568", + "right": "issue:45488", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different tokenizer implementations and code paths." + }, + { + "left": "issue:43749", + "right": "issue:44291", + "accept": false, + "reason": "Both touch loading, but one is FSDP CPU RAM efficient loading and the other is init_empty_weights/_is_hf_initialized handling; not the same bug." + }, + { + "left": "issue:43531", + "right": "issue:45042", + "accept": false, + "reason": "Qwen3-MoE sliding-window issue vs PIL backend torchvision dependency regression; unrelated." + }, + { + "left": "issue:43262", + "right": "issue:44811", + "accept": false, + "reason": "Audio processor chat-template sampling-rate default vs Whisper batch_decode skip_special_tokens; different processor bugs." + }, + { + "left": "issue:43643", + "right": "issue:45759", + "accept": false, + "reason": "AutoConfig trust_remote_code field loss vs AutoModelForCausalLM from_config text_config unwrapping; separate config-loading issues." + }, + { + "left": "issue:44568", + "right": "issue:45356", + "accept": false, + "reason": "Different tokenizer regressions on different models; not the same code-path problem." + }, + { + "left": "issue:36010", + "right": "issue:36331", + "accept": false, + "reason": "Import path regression for GenerationMixin vs trainer loss signature mismatch." + }, + { + "left": "issue:44849", + "right": "issue:45701", + "accept": false, + "reason": "Qwen3.5 hidden-state output bug vs generic tokenization version-change report; unrelated." + }, + { + "left": "issue:43329", + "right": "issue:43450", + "accept": false, + "reason": "Both involve video features, but one is undefined variables in multimodal token counting and the other is batched video tensor shape handling." + }, + { + "left": "issue:34567", + "right": "issue:40990", + "accept": false, + "reason": "TrainerState token counter bug vs high perplexity on gpt-oss-20b; no shared root cause." + }, + { + "left": "issue:43329", + "right": "issue:44479", + "accept": false, + "reason": "The packet supports thematic similarity only: 43329 is an undefined-variable bug in video token counting, while 44479 is a broader v5.3.0 video-input/vision_position_ids regression." + }, + { + "left": "issue:43257", + "right": "issue:43931", + "accept": false, + "reason": "MOE weight conversion on load vs Qwen3-VL weight-shape mismatch; distinct loading issues." + }, + { + "left": "issue:43697", + "right": "issue:45357", + "accept": false, + "reason": "RTDetrV2 output drift in v5 vs Qwen3.5 visual-encoder save_pretrained key regression; unrelated." + }, + { + "left": "issue:44291", + "right": "issue:45042", + "accept": false, + "reason": "Model init_empty_weights TypeError vs PIL image processor torchvision dependency regression." + }, + { + "left": "issue:41720", + "right": "issue:43540", + "accept": false, + "reason": "Different Qwen video failures: CUDA assert on auto device mapping vs ValueError in Qwen3OmniMoe video processing." + }, + { + "left": "issue:43452", + "right": "issue:43582", + "accept": false, + "reason": "gguf_file tokenizer/model loading bug vs Apple Silicon caching_allocator_warmup TypeError." + }, + { + "left": "issue:42915", + "right": "issue:43742", + "accept": false, + "reason": "Qwen3Moe FineGrainedFP8Config failure vs MobileLLM key error; unrelated model-loading problems." + }, + { + "left": "issue:33357", + "right": "issue:34567", + "accept": false, + "reason": "MacOS CLIP bus error vs TrainerState token counter not updating; no common bug." + }, + { + "left": "issue:43317", + "right": "issue:45538", + "accept": false, + "reason": "Dequantized model offload failure vs CLIPTokenizer model_max_length constant; unrelated." + }, + { + "left": "issue:43927", + "right": "issue:44912", + "accept": false, + "reason": "DiaConfig token IDs lost on save/load vs MXFP4 quantization fallback; different failures." + }, + { + "left": "issue:44987", + "right": "issue:45538", + "accept": false, + "reason": "Model loading failure in 5.1.0 vs CLIPTokenizer max-length issue; unrelated." + }, + { + "left": "issue:44479", + "right": "issue:45381", + "accept": true, + "reason": "Same Qwen video regression: 45381 is a narrower qwen2.5-vl manifestation of the broader v5.3.0 video-input bug described in 44479." + }, + { + "left": "issue:42915", + "right": "issue:44821", + "accept": false, + "reason": "FineGrainedFP8Config loading issue vs AutoImageProcessor-from-URL problem; unrelated." + }, + { + "left": "issue:42915", + "right": "issue:45538", + "accept": false, + "reason": "Qwen3Moe FP8 loading failure vs CLIPTokenizer max-length constant; unrelated." + }, + { + "left": "issue:43257", + "right": "issue:43756", + "accept": false, + "reason": "Qwen MOE weight conversion/load issue vs Smollm3 RoPE-layer mismatch; different subsystems." + }, + { + "left": "issue:43540", + "right": "issue:44560", + "accept": false, + "reason": "Both are video-related, but one is Qwen3OmniMoe ValueError and the other is Qwen3-VL-embedding StopIteration; not the same concrete bug." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The clustering is mostly grounded, but one soft-edge acceptance is too strong for the evidence in the packet. In particular, issue:43329 and issue:44479 are both Qwen/video-related, but their titles point to different concrete failures (_get_num_multimodal_tokens undefined variables vs a broader v5.3.0 video input/vision_position_ids regression). The packet supports thematic similarity, not a confident duplicate/merge decision. The other rejections look conservative, and 44479 is a reasonable representative, but the accepted 43329\u219444479 link overstates the evidence." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 17, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:28282", + "issue:34567", + "issue:34689", + "issue:36010", + "issue:36331", + "issue:38175", + "issue:42175", + "issue:43452", + "issue:43493", + "issue:43526", + "issue:43531", + "issue:43540", + "issue:43577", + "issue:43643", + "issue:43646", + "issue:43697", + "issue:43742", + "issue:43749", + "issue:43756", + "issue:43824", + "issue:43906", + "issue:43994", + "issue:44062", + "issue:44291", + "issue:44484", + "issue:44488", + "issue:44589", + "issue:44704", + "issue:44737", + "issue:44756", + "issue:44792", + "issue:44821", + "issue:44898", + "issue:44964", + "issue:44991", + "issue:45042", + "issue:45072", + "issue:45081", + "issue:45137", + "issue:45216", + "issue:45325", + "issue:45375", + "issue:45381", + "issue:45405", + "issue:45479", + "issue:45588", + "issue:45600", + "issue:45823" + ], + "soft_pairs": [ + "issue:43577|issue:45072", + "issue:45137|issue:45405", + "issue:38175|issue:44898", + "issue:44737|issue:45588", + "issue:44062|issue:44991", + "issue:43742|issue:44291", + "issue:43540|issue:45823", + "issue:43906|issue:45381", + "issue:43646|issue:43749", + "issue:44062|issue:45081", + "issue:43749|issue:44756", + "issue:43643|issue:45375", + "issue:34567|issue:36331", + "issue:43493|issue:43994", + "issue:36010|issue:42175", + "issue:42175|issue:43824", + "issue:43452|issue:44488", + "issue:44291|issue:44821", + "issue:44792|issue:44964", + "issue:43526|issue:45479", + "issue:28282|issue:34689", + "issue:45042|issue:45081", + "issue:43756|issue:45325", + "issue:43742|issue:44589", + "issue:45405|issue:45600", + "issue:44484|issue:44704", + "issue:43697|issue:45216", + "issue:43531|issue:44821" + ], + "prepared_review_unit_hash": "bce97931270d83d25c1debe66f0c5794c63b844ecb28c43a7de10e3e4b99dc8e", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36324, + "estimated_input_tokens": 9081, + "estimated_eval_tokens": 18418 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a mixed bag of unrelated Transformers issues. The only clear duplicate-like pair is the SigLIP2 bug reports; everything else looks like distinct failures in different models or subsystems. No PRs are present.", + "confidence": 0.83, + "canonical_issue_reason": "issue:43493 is the best canonical issue because it describes the underlying SigLIP2 implementation discrepancy at the root of the duplicate pair; issue:43994 is a downstream user-facing symptom of the same bug.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43493 is the most representative and actionable issue: it states the core HF-vs-JAX mismatch, which is broader than the end-user symptom in issue:43994.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43577", + "right": "issue:45072", + "accept": false, + "reason": "Both are dtype-related, but they affect different models and different code paths; not the same bug." + }, + { + "left": "issue:45137", + "right": "issue:45405", + "accept": false, + "reason": "DeepSpeed ZeRO3 deque failure and a PEFT version bump are unrelated." + }, + { + "left": "issue:38175", + "right": "issue:44898", + "accept": false, + "reason": "Different models, different symptoms, and different processing paths." + }, + { + "left": "issue:44737", + "right": "issue:45588", + "accept": false, + "reason": "XLNet CPU device placement and flash-attention crash with s_aux=None are unrelated." + }, + { + "left": "issue:44062", + "right": "issue:44991", + "accept": false, + "reason": "Both involve tokenizers, but one is an AddedToken argument error and the other is a tokenizer loading regression." + }, + { + "left": "issue:43742", + "right": "issue:44291", + "accept": false, + "reason": "Both fail during loading, but one is a model config key error and the other is an init-empty-weights API mismatch." + }, + { + "left": "issue:43540", + "right": "issue:45823", + "accept": false, + "reason": "Different models and different failure mechanisms; not mergeable as one fix." + }, + { + "left": "issue:43906", + "right": "issue:45381", + "accept": false, + "reason": "One is an isolated reproduction reference, the other is a Qwen2.5-VL position-id bug; insufficient evidence they are the same issue." + }, + { + "left": "issue:43646", + "right": "issue:43749", + "accept": false, + "reason": "Transformers 5.0 custom model init breakage and FSDP CPU-efficient loading are separate regressions." + }, + { + "left": "issue:44062", + "right": "issue:45081", + "accept": false, + "reason": "Distinct tokenizer bugs: AddedToken keyword collision vs Mistral regex patch crashing on backend_tokenizer." + }, + { + "left": "issue:43749", + "right": "issue:44756", + "accept": false, + "reason": "FSDP CPU RAM efficient loading and Strix Halo mmap OOM are different memory/loading problems." + }, + { + "left": "issue:43643", + "right": "issue:45375", + "accept": false, + "reason": "Both mention missing config fields, but the reported contexts and root causes differ." + }, + { + "left": "issue:34567", + "right": "issue:36331", + "accept": false, + "reason": "Trainer state token counting and custom compute_loss signature are unrelated Trainer issues." + }, + { + "left": "issue:43493", + "right": "issue:43994", + "accept": true, + "reason": "Both reports point to the same SigLIP2 model-implementation discrepancy causing bad outputs." + }, + { + "left": "issue:36010", + "right": "issue:42175", + "accept": false, + "reason": "Importing GenerationMixin and backend selection for torch installs are unrelated." + }, + { + "left": "issue:42175", + "right": "issue:43824", + "accept": false, + "reason": "TensorFlow backend packaging and missing Qwen2.5-VL export are different issues." + }, + { + "left": "issue:43452", + "right": "issue:44488", + "accept": false, + "reason": "gguf_file handling and a specific model load failure are not the same bug." + }, + { + "left": "issue:44291", + "right": "issue:44821", + "accept": false, + "reason": "init_empty_weights argument handling and loading AutoImageProcessor from URL are unrelated." + }, + { + "left": "issue:44792", + "right": "issue:44964", + "accept": false, + "reason": "Different multimodal models and different failure points; no shared underlying code-path is evident." + }, + { + "left": "issue:43526", + "right": "issue:45479", + "accept": false, + "reason": "Processor label reduction and single-label classification zero-loss behavior are different bugs." + }, + { + "left": "issue:28282", + "right": "issue:34689", + "accept": false, + "reason": "AutoModel missing PyTorch and Llama 3.2 Vision load failure are unrelated import/load issues." + }, + { + "left": "issue:45042", + "right": "issue:45081", + "accept": false, + "reason": "Torchvision requirement in PIL image processors and a Mistral tokenizer patch crash are distinct problems." + }, + { + "left": "issue:43756", + "right": "issue:45325", + "accept": false, + "reason": "Both involve positional encoding, but they are different models and different calculations." + }, + { + "left": "issue:43742", + "right": "issue:44589", + "accept": false, + "reason": "A MobileLLM key error and a Float8 storage lookup failure are not the same failure mode." + }, + { + "left": "issue:45405", + "right": "issue:45600", + "accept": false, + "reason": "A dependency version bump and broken auto_mappings references are unrelated changes." + }, + { + "left": "issue:44484", + "right": "issue:44704", + "accept": false, + "reason": "Shard-size behavior and AutoProcessor kwarg forwarding are separate API issues." + }, + { + "left": "issue:43697", + "right": "issue:45216", + "accept": false, + "reason": "Different models, different regressions, and no shared code-path is indicated." + }, + { + "left": "issue:43531", + "right": "issue:44821", + "accept": false, + "reason": "Qwen3-MoE sliding window behavior and AutoImageProcessor URL loading are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: the items are mostly unrelated issue reports, and the only plausible duplicate-like pair is the SigLIP2 pair (43493/43994). The soft-edge verdicts are conservative, with rejections justified by different models, subsystems, or failure modes. No PR pairs are present." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 18, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:24643", + "issue:28282", + "issue:29127", + "issue:30064", + "issue:33666", + "issue:38175", + "issue:41720", + "issue:41762", + "issue:42175", + "issue:43295", + "issue:43452", + "issue:43531", + "issue:43550", + "issue:43577", + "issue:43582", + "issue:43643", + "issue:43653", + "issue:43688", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43819", + "issue:43906", + "issue:43927", + "issue:44361", + "issue:44442", + "issue:44464", + "issue:44466", + "issue:44514", + "issue:44561", + "issue:44568", + "issue:44625", + "issue:44743", + "issue:44811", + "issue:44843", + "issue:44877", + "issue:44898", + "issue:44936", + "issue:44938", + "issue:44977", + "issue:44991", + "issue:45005", + "issue:45290", + "issue:45356", + "issue:45381", + "issue:45440", + "issue:45588", + "issue:45823" + ], + "soft_pairs": [ + "issue:28282|issue:29127", + "issue:44514|issue:45381", + "issue:43582|issue:44977", + "issue:44625|issue:44877", + "issue:43643|issue:44561", + "issue:42175|issue:44938", + "issue:43720|issue:44898", + "issue:43452|issue:43577", + "issue:44514|issue:45290", + "issue:44466|issue:45005", + "issue:43452|issue:44843", + "issue:41762|issue:44936", + "issue:43295|issue:45356", + "issue:43819|issue:44811", + "issue:43653|issue:44568", + "issue:24643|issue:29127", + "issue:44936|issue:45823", + "issue:30064|issue:33666", + "issue:38175|issue:43295", + "issue:44361|issue:44442", + "issue:43653|issue:44361", + "issue:44464|issue:44743", + "issue:43577|issue:43697", + "issue:44843|issue:44991", + "issue:41720|issue:43906", + "issue:44977|issue:45356", + "issue:43688|issue:45440", + "issue:43531|issue:43742", + "issue:43653|issue:43927", + "issue:44464|issue:44977", + "issue:43577|issue:45588", + "issue:43550|issue:43927", + "issue:43550|issue:44361" + ], + "prepared_review_unit_hash": "6ba49062fb3c928af44b91b3051d4ef06dbefeefa2166e5a659335cf4d896b38", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37761, + "estimated_input_tokens": 9441, + "estimated_eval_tokens": 19138 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items are mostly a heterogeneous mix of unrelated bugs with only superficial title similarity. I would not merge any of the proposed soft pairs; they do not look like the same underlying issue or change.", + "confidence": 0.89, + "canonical_issue_reason": "issue:43653 is the most self-contained and concrete bug in the set, with clear tokenizer special-token behavior and nearby tokenizer-related similarities, making it the best anchor among otherwise unrelated reports.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43653 is the best representative issue because it is narrowly scoped, reproducible, and more canonical than the broader config/training regressions in the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:28282", + "right": "issue:29127", + "accept": false, + "reason": "Different problems: missing PyTorch import vs unclear LayoutLMv3 box-validation error." + }, + { + "left": "issue:44514", + "right": "issue:45381", + "accept": false, + "reason": "Both involve Qwen2.5-VL, but one is chat-template batching and the other is video position IDs; different code paths." + }, + { + "left": "issue:43582", + "right": "issue:44977", + "accept": false, + "reason": "Apple Silicon allocator TypeError vs Qwen3.5 flash-attention generation failure; unrelated bugs." + }, + { + "left": "issue:44625", + "right": "issue:44877", + "accept": false, + "reason": "Different config issues for different models; num_labels propagation is not the same as strict config loading." + }, + { + "left": "issue:43643", + "right": "issue:44561", + "accept": false, + "reason": "Both touch trust_remote_code, but one is missing config fields and the other is removal of is_torch_fx_available; not the same bug." + }, + { + "left": "issue:42175", + "right": "issue:44938", + "accept": false, + "reason": "Dependency packaging issue vs Python 3.14 import failure; no shared underlying defect." + }, + { + "left": "issue:43720", + "right": "issue:44898", + "accept": false, + "reason": "BitNet accelerate-loading/unpacking problem vs Perceiver interpolation failure; unrelated model paths." + }, + { + "left": "issue:43452", + "right": "issue:43577", + "accept": false, + "reason": "gguf_file loading regression vs Blip2 dtype retention; different subsystems and symptoms." + }, + { + "left": "issue:44514", + "right": "issue:45290", + "accept": false, + "reason": "Same processor family, but batching/padding crash is distinct from tool-call messages with empty content." + }, + { + "left": "issue:44466", + "right": "issue:45005", + "accept": false, + "reason": "Both mention tied weights, but one is serialization behavior and the other is translation-model loading issues; not the same change." + }, + { + "left": "issue:43452", + "right": "issue:44843", + "accept": false, + "reason": "gguf_file tokenizer/model loading issue vs offline model_info call in Mistral regex patch; unrelated." + }, + { + "left": "issue:41762", + "right": "issue:44936", + "accept": false, + "reason": "Gemma3 ZeRO-3 load failure vs trainer.evaluate after train; different failure modes." + }, + { + "left": "issue:43295", + "right": "issue:45356", + "accept": false, + "reason": "Processor/tokenizer regression vs Kimi codec-handling regression; same broad area but different bugs." + }, + { + "left": "issue:43819", + "right": "issue:44811", + "accept": false, + "reason": "DAC latent/forward mismatch vs Whisper batch_decode special-token handling; unrelated." + }, + { + "left": "issue:43653", + "right": "issue:44568", + "accept": false, + "reason": "Both tokenizer-special-token bugs, but different tokenizers and different missing-token behavior." + }, + { + "left": "issue:24643", + "right": "issue:29127", + "accept": false, + "reason": "DeepSpeed weight-dimension runtime error vs LayoutLMv3 box-content clarity issue; unrelated." + }, + { + "left": "issue:44936", + "right": "issue:45823", + "accept": false, + "reason": "trainer.evaluate lifecycle issue vs Gemma4 device-map mismatch; different code paths." + }, + { + "left": "issue:30064", + "right": "issue:33666", + "accept": false, + "reason": "Void segmentation map processing vs Qwen2-VL multi-GPU training; not the same bug." + }, + { + "left": "issue:38175", + "right": "issue:43295", + "accept": false, + "reason": "siglip2 zero-probabilities issue vs processor/tokenizer regression; no concrete overlap." + }, + { + "left": "issue:44361", + "right": "issue:44442", + "accept": false, + "reason": "MLuke task AttributeError vs FastSpeech2ConformerTokenizer loading failure; unrelated tokenizer bugs." + }, + { + "left": "issue:43653", + "right": "issue:44361", + "accept": false, + "reason": "BigBird special-token decode bug vs MLuke task AttributeError; different models and code paths." + }, + { + "left": "issue:44464", + "right": "issue:44743", + "accept": false, + "reason": "Compiled-forward chunked generation inconsistency vs Qwen3-MoE recurrent-state reset; different generation issues." + }, + { + "left": "issue:43577", + "right": "issue:43697", + "accept": false, + "reason": "Blip2 dtype mismatch vs RTDetrV2 output divergence; unrelated model behaviors." + }, + { + "left": "issue:44843", + "right": "issue:44991", + "accept": false, + "reason": "Offline hub/model_info regression vs tokenizer load failure for a specific model; not the same defect." + }, + { + "left": "issue:41720", + "right": "issue:43906", + "accept": false, + "reason": "Qwen3 auto device-map cuda assert vs isolated reproduction of another issue; no evidence of a shared root cause." + }, + { + "left": "issue:44977", + "right": "issue:45356", + "accept": false, + "reason": "Flash-attention generation failure vs tokenizer codec regression; unrelated." + }, + { + "left": "issue:43688", + "right": "issue:45440", + "accept": false, + "reason": "Both are MoE-related correctness issues, but auxiliary-loss normalization and DeepSeekV3 divergence are distinct concrete bugs." + }, + { + "left": "issue:43531", + "right": "issue:43742", + "accept": false, + "reason": "Qwen3-MoE sliding_window issue vs MobileLLM loading key error; unrelated." + }, + { + "left": "issue:43653", + "right": "issue:43927", + "accept": false, + "reason": "Tokenizer special-token bug vs config token-ID persistence bug; similar theme but different underlying problem." + }, + { + "left": "issue:44464", + "right": "issue:44977", + "accept": false, + "reason": "Compiled-forward output inconsistency vs flash-attention generation failure; different code paths." + }, + { + "left": "issue:43577", + "right": "issue:45588", + "accept": false, + "reason": "Blip2 dtype issue vs flash_attention s_aux=None crash; unrelated." + }, + { + "left": "issue:43550", + "right": "issue:43927", + "accept": false, + "reason": "torch.compile/SDPA failure vs DiaConfig save/load token-ID loss; different subsystems." + }, + { + "left": "issue:43550", + "right": "issue:44361", + "accept": false, + "reason": "Bamba compile failure vs MLuke tokenizer AttributeError; unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 19, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:28282", + "issue:32090", + "issue:33357", + "issue:33666", + "issue:34567", + "issue:35141", + "issue:36010", + "issue:36331", + "issue:39692", + "issue:41720", + "issue:43122", + "issue:43262", + "issue:43295", + "issue:43329", + "issue:43334", + "issue:43452", + "issue:43493", + "issue:43504", + "issue:43525", + "issue:43540", + "issue:43550", + "issue:43572", + "issue:43577", + "issue:43606", + "issue:43688", + "issue:43720", + "issue:43742", + "issue:43749", + "issue:43756", + "issue:43825", + "issue:43906", + "issue:43927", + "issue:44361", + "issue:44451", + "issue:44464", + "issue:44554", + "issue:44568", + "issue:44610", + "issue:44821", + "issue:44849", + "issue:44913", + "issue:44964", + "issue:44977", + "issue:45325", + "issue:45357", + "issue:45405", + "issue:45704", + "issue:45812" + ], + "soft_pairs": [ + "issue:32090|issue:34567", + "issue:43504|issue:43550", + "issue:43504|issue:43720", + "issue:43122|issue:43906", + "issue:32090|issue:33666", + "issue:28282|issue:35141", + "issue:43504|issue:44610", + "issue:43452|issue:44451", + "issue:44849|issue:45357", + "issue:44568|issue:45812", + "issue:43742|issue:44821", + "issue:41720|issue:44464", + "issue:33666|issue:36010", + "issue:43525|issue:43572", + "issue:43329|issue:45325", + "issue:43688|issue:43749", + "issue:43493|issue:43825", + "issue:43756|issue:44913", + "issue:43262|issue:43295", + "issue:43606|issue:43927", + "issue:43720|issue:43927", + "issue:28282|issue:32090", + "issue:28282|issue:33357", + "issue:43577|issue:44554", + "issue:33666|issue:36331", + "issue:43334|issue:43572", + "issue:39692|issue:43493", + "issue:43688|issue:45704", + "issue:43720|issue:44361", + "issue:44964|issue:45405", + "issue:43540|issue:44977" + ], + "prepared_review_unit_hash": "3aa6e0ba9d981cc2ef0075952ceb76cb3e016615e1d8c638bca72d8260453fbe", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37228, + "estimated_input_tokens": 9307, + "estimated_eval_tokens": 18870 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous: the soft edges are topical similarities, but none look like the same underlying bug or change. There are no PRs to compare. The strongest representative issue is the Granite tokenizer regression (#45812), because it is concrete, recent, and clearly actionable.", + "confidence": 0.47, + "canonical_issue_reason": "#45812 is the clearest, most actionable report here: it describes a concrete tokenizer regression with a specific model family, silent incorrect outputs, and real downstream impact. It is a better representative than the more speculative or niche issues in the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "#45812 is the best standalone issue candidate because it has a well-scoped failure mode, clear reproduction context, and a broad user-facing regression signal. The rest of the cluster does not form a single duplicate family.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:32090", + "right": "issue:34567", + "accept": false, + "reason": "Different failures: GPU broadcast NoneType vs TrainerState token counter not updating. Same training area, not the same bug." + }, + { + "left": "issue:43504", + "right": "issue:43550", + "accept": false, + "reason": "Legacy-field preset loading bug vs torch.compile/SDPA failure in a specific model. Unrelated code paths." + }, + { + "left": "issue:43504", + "right": "issue:43720", + "accept": false, + "reason": "Both involve loading, but one is a legacy config field issue and the other is packed-weight unpacking during accelerate loading. Not the same defect." + }, + { + "left": "issue:43122", + "right": "issue:43906", + "accept": false, + "reason": "One is a tokenization regression across versions; the other is only a reproduction of a different issue. No evidence they share the same root cause." + }, + { + "left": "issue:32090", + "right": "issue:33666", + "accept": false, + "reason": "Trainer broadcast error and multi-GPU training request are not the same problem." + }, + { + "left": "issue:28282", + "right": "issue:35141", + "accept": false, + "reason": "ImportError about missing PyTorch is unrelated to embedding reinitialization after resize." + }, + { + "left": "issue:43504", + "right": "issue:44610", + "accept": false, + "reason": "Model preset loading vs processor image-size mismatch. Different bugs in different subsystems." + }, + { + "left": "issue:43452", + "right": "issue:44451", + "accept": false, + "reason": "Both are model/tokenizer loading failures, but the affected APIs and likely causes differ; not enough to merge as one bug." + }, + { + "left": "issue:44849", + "right": "issue:45357", + "accept": false, + "reason": "One is an output_hidden_states behavior bug; the other is incorrect save_pretrained visual encoder keys. Different regression surfaces." + }, + { + "left": "issue:44568", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different model families and different behaviors. Too broad to treat as the same bug." + }, + { + "left": "issue:43742", + "right": "issue:44821", + "accept": false, + "reason": "Key error loading a model is unrelated to loading an AutoImageProcessor from a URL." + }, + { + "left": "issue:41720", + "right": "issue:44464", + "accept": false, + "reason": "CUDA assert during auto device mapping and inconsistent chunked generation under compile are distinct failures." + }, + { + "left": "issue:33666", + "right": "issue:36010", + "accept": false, + "reason": "Multi-GPU training issue and GenerationMixin import failure do not share a concrete root cause." + }, + { + "left": "issue:43525", + "right": "issue:43572", + "accept": false, + "reason": "Both are missing-config-field reports, but they concern different models and different fields. Similar pattern, not the same issue." + }, + { + "left": "issue:43329", + "right": "issue:45325", + "accept": false, + "reason": "Video multimodal token counting bug vs still-image rope index scaling bug. Different branches and symptoms." + }, + { + "left": "issue:43688", + "right": "issue:43749", + "accept": false, + "reason": "Aux-loss normalization and FSDP CPU RAM-efficient loading are unrelated." + }, + { + "left": "issue:43493", + "right": "issue:43825", + "accept": false, + "reason": "SigLIP2 implementation discrepancy and pipeline translation-task error message are different topics entirely." + }, + { + "left": "issue:43756", + "right": "issue:44913", + "accept": false, + "reason": "Both mention rotary-related settings, but one is a model architecture discrepancy and the other is a config reload defaulting issue. Not the same bug." + }, + { + "left": "issue:43262", + "right": "issue:43295", + "accept": false, + "reason": "Audio sampling-rate defaulting and processor.tokenizer regression are separate processor-layer problems." + }, + { + "left": "issue:43606", + "right": "issue:43927", + "accept": false, + "reason": "CPU offload device mismatch and DiaConfig token-id loss are unrelated failures." + }, + { + "left": "issue:43720", + "right": "issue:44361", + "accept": false, + "reason": "Packed-weight loading bug and MLukeTokenizer AttributeError are different components and code paths." + }, + { + "left": "issue:44964", + "right": "issue:45405", + "accept": false, + "reason": "Model loading failure and dependency version bump are not the same underlying bug." + }, + { + "left": "issue:43540", + "right": "issue:44977", + "accept": false, + "reason": "Video-input processing error in Qwen3OmniMoe and flash-attention generation bug in Qwen3.5 are distinct issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 20, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:29942", + "issue:30333", + "issue:33357", + "issue:33666", + "issue:39692", + "issue:43257", + "issue:43278", + "issue:43295", + "issue:43299", + "issue:43334", + "issue:43493", + "issue:43504", + "issue:43572", + "issue:43575", + "issue:43606", + "issue:43646", + "issue:43653", + "issue:43688", + "issue:43756", + "issue:43824", + "issue:43844", + "issue:43927", + "issue:43994", + "issue:44112", + "issue:44291", + "issue:44361", + "issue:44423", + "issue:44464", + "issue:44466", + "issue:44479", + "issue:44488", + "issue:44493", + "issue:44521", + "issue:44589", + "issue:44625", + "issue:44734", + "issue:44792", + "issue:44843", + "issue:45083", + "issue:45200", + "issue:45229", + "issue:45290", + "issue:45405", + "issue:45520", + "issue:45584", + "issue:45701", + "issue:45759", + "issue:45823" + ], + "soft_pairs": [ + "issue:44479|issue:44625", + "issue:43334|issue:45759", + "issue:43493|issue:43844", + "issue:45200|issue:45229", + "issue:43756|issue:45083", + "issue:44488|issue:44843", + "issue:43257|issue:43299", + "issue:43278|issue:43844", + "issue:43646|issue:44466", + "issue:43824|issue:44589", + "issue:45229|issue:45823", + "issue:44589|issue:45520", + "issue:43688|issue:45701", + "issue:39692|issue:43295", + "issue:33357|issue:33666", + "issue:43572|issue:44291", + "issue:43504|issue:43606", + "issue:44423|issue:44734", + "issue:43927|issue:44361", + "issue:43504|issue:43653", + "issue:43575|issue:45405", + "issue:44625|issue:45759", + "issue:43606|issue:44112", + "issue:44792|issue:45405", + "issue:43994|issue:44493", + "issue:44521|issue:45290", + "issue:44464|issue:45584", + "issue:29942|issue:30333" + ], + "prepared_review_unit_hash": "ed6aeb5db6aa5ca2ec6f148266c6f28228d6da7f73f66a0fab8b4707334252ea", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36266, + "estimated_input_tokens": 9067, + "estimated_eval_tokens": 18390 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items are mostly unrelated single-issue reports. Several are in similar model families (Qwen, Gemma, SigLIP2), but the paired bugs are different concrete failure modes, so none of the soft duplicate candidates should be merged.", + "confidence": 0.95, + "canonical_issue_reason": "issue:44479 is a concrete regression report with a clear, specific failure mode and broad impact across multiple Qwen multimodal variants, making it the strongest representative issue in this set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44479 is the most self-contained and representative bug report here; the others are either narrowly scoped loading/config edge cases, CI flakes, or unrelated feature/regression reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44479", + "right": "issue:44625", + "accept": false, + "reason": "Both involve Qwen models, but one is a video-input regression and the other is config propagation for num_labels; different bug classes and code paths." + }, + { + "left": "issue:43334", + "right": "issue:45759", + "accept": false, + "reason": "Both are Qwen multimodal loading issues, but one is a missing pad_token_id on text config and the other is from_config not unwrapping composite configs; not the same defect." + }, + { + "left": "issue:43493", + "right": "issue:43844", + "accept": false, + "reason": "SigLIP2 implementation discrepancy and ZeRO-3 gradient growth are unrelated problems." + }, + { + "left": "issue:45200", + "right": "issue:45229", + "accept": false, + "reason": "Gemma4 token-type defaults and Gemma4 multi-GPU OOM are different issues with different symptoms and fixes." + }, + { + "left": "issue:43756", + "right": "issue:45083", + "accept": false, + "reason": "Smollm3 RoPE-layer loss and qwen3_omni_moe feature-length helper behavior are unrelated model bugs." + }, + { + "left": "issue:44488", + "right": "issue:44843", + "accept": false, + "reason": "A model load failure for cjvt/sleng-bert is not the same as an offline-mode tokenizer patch issue." + }, + { + "left": "issue:43257", + "right": "issue:43299", + "accept": false, + "reason": "Both mention Qwen3 MoE loading, but one is about accelerate+deepspeed weight conversion and the other about a dev-version config/loading regression; different concrete failures." + }, + { + "left": "issue:43278", + "right": "issue:43844", + "accept": false, + "reason": "Embedding dtype drift during evaluate is unrelated to the ZeRO-3 gradient anomaly." + }, + { + "left": "issue:43646", + "right": "issue:44466", + "accept": false, + "reason": "Custom model init regression and lm_head serialization inconsistency are separate bugs." + }, + { + "left": "issue:43824", + "right": "issue:44589", + "accept": false, + "reason": "An import error for Qwen2.5-VL is unrelated to the missing Float8 storage type error." + }, + { + "left": "issue:45229", + "right": "issue:45823", + "accept": false, + "reason": "Both are Gemma4 inference issues, but one is OOM and the other is a device mismatch during forward; not the same bug." + }, + { + "left": "issue:44589", + "right": "issue:45520", + "accept": false, + "reason": "Different failures: missing Float8 storage support versus a flash_attn import_utils KeyError on Python 3.13." + }, + { + "left": "issue:43688", + "right": "issue:45701", + "accept": false, + "reason": "Aux-loss normalization and tokenization-version changes are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:43295", + "accept": false, + "reason": "SigLIP2 doc example errors are not the same as a regression in processor.tokenizer/image handling." + }, + { + "left": "issue:33357", + "right": "issue:33666", + "accept": false, + "reason": "A MacOS bus error for CLIP is unrelated to Qwen2-VL multi-GPU training." + }, + { + "left": "issue:43572", + "right": "issue:44291", + "accept": false, + "reason": "Both are 5.0 compatibility regressions, but they affect different APIs and model-loading paths." + }, + { + "left": "issue:43504", + "right": "issue:43606", + "accept": false, + "reason": "Legacy-field loading for Beit and CPU-offload device mismatch for bark-small are unrelated." + }, + { + "left": "issue:44423", + "right": "issue:44734", + "accept": false, + "reason": "Both are serve regressions, but one is multimodal input handling and the other is KV-cache continuation indexing; different code paths." + }, + { + "left": "issue:43927", + "right": "issue:44361", + "accept": false, + "reason": "DiaConfig save/load token-id loss and MLukeTokenizer task failures are not the same underlying bug." + }, + { + "left": "issue:43504", + "right": "issue:43653", + "accept": false, + "reason": "Beit legacy-field loading and BigBirdTokenizer special-token registration are unrelated." + }, + { + "left": "issue:43575", + "right": "issue:45405", + "accept": false, + "reason": "A tensor-parallel OOM and a dependency-version bump are entirely different issues." + }, + { + "left": "issue:44625", + "right": "issue:45759", + "accept": false, + "reason": "These are related in theme, but one is num_labels propagation and the other is composite-config unwrapping in from_config; too different to treat as one duplicate." + }, + { + "left": "issue:43606", + "right": "issue:44112", + "accept": false, + "reason": "A real device-mismatch bug is not the same as a stale CI test." + }, + { + "left": "issue:44792", + "right": "issue:45405", + "accept": false, + "reason": "A failing janus image-generation test is unrelated to the PEFT minimum-version bump." + }, + { + "left": "issue:43994", + "right": "issue:44493", + "accept": false, + "reason": "SigLIP2 nonsensical outputs and unexpected position-id keys are different bugs with different failure modes." + }, + { + "left": "issue:44521", + "right": "issue:45290", + "accept": false, + "reason": "All-zero assistant masks and a crash on tool-call messages are distinct chat-template issues." + }, + { + "left": "issue:44464", + "right": "issue:45584", + "accept": false, + "reason": "Compiled-forward inconsistency and empty-transcription Whisper failure are unrelated." + }, + { + "left": "issue:29942", + "right": "issue:30333", + "accept": false, + "reason": "Flash Attention 2 test failures and MLflow job-reporting problems are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 21, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:15354", + "issue:28218", + "issue:33357", + "issue:34567", + "issue:37428", + "issue:38175", + "issue:42915", + "issue:43232", + "issue:43278", + "issue:43295", + "issue:43334", + "issue:43450", + "issue:43493", + "issue:43525", + "issue:43540", + "issue:43572", + "issue:43688", + "issue:43701", + "issue:43824", + "issue:43844", + "issue:43856", + "issue:43873", + "issue:43957", + "issue:43975", + "issue:44315", + "issue:44464", + "issue:44466", + "issue:44554", + "issue:44568", + "issue:44610", + "issue:44849", + "issue:44898", + "issue:44936", + "issue:44964", + "issue:44987", + "issue:45072", + "issue:45084", + "issue:45127", + "issue:45198", + "issue:45200", + "issue:45325", + "issue:45356", + "issue:45412", + "issue:45446", + "issue:45520", + "issue:45701", + "issue:45823" + ], + "soft_pairs": [ + "issue:28218|issue:34567", + "issue:43844|issue:44964", + "issue:45084|issue:45520", + "issue:44554|issue:45446", + "issue:44568|issue:45701", + "issue:43688|issue:43873", + "issue:15354|issue:38175", + "issue:43540|issue:45200", + "issue:43232|issue:44849", + "issue:45200|issue:45823", + "issue:45072|issue:45198", + "issue:44315|issue:44849", + "issue:43278|issue:43701", + "issue:28218|issue:33357", + "issue:44554|issue:45356", + "issue:45200|issue:45325", + "issue:44466|issue:45127", + "issue:43295|issue:44610", + "issue:44898|issue:45412", + "issue:43334|issue:43525", + "issue:43493|issue:43701", + "issue:37428|issue:43957", + "issue:43572|issue:44987", + "issue:43572|issue:43957", + "issue:43873|issue:44464", + "issue:43295|issue:43450", + "issue:43844|issue:44936", + "issue:43824|issue:43975", + "issue:43295|issue:43873", + "issue:38175|issue:45412", + "issue:37428|issue:43824", + "issue:43278|issue:43856", + "issue:42915|issue:43824" + ], + "prepared_review_unit_hash": "edb404142f0c82fe857af4f35e30a4eafb756567749ba15b5c30541a80b60800", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 33, + "serialized_chars": 37104, + "estimated_input_tokens": 9276, + "estimated_eval_tokens": 18808 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is highly heterogeneous: the soft-similarity pairs mostly connect unrelated tokenizer, training, loading, multimodal, import, and runtime bugs. I would not merge any of the candidate soft edges.", + "confidence": 0.87, + "canonical_issue_reason": "Issue 43873 is the broadest active bug with inbound references, but there is no true duplicate hub here because the cluster spans many unrelated failure modes.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43873 is the most suitable representative thread only in a loose triage sense; it is open and has the strongest external interest, but it does not unify the rest of the items as duplicates.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:28218", + "right": "issue:34567", + "accept": false, + "reason": "Tokenizer spacing vs TrainerState token-count tracking; unrelated bugs." + }, + { + "left": "issue:43844", + "right": "issue:44964", + "accept": false, + "reason": "ZeRO-3 gradient growth vs Phi-4 model loading failure; different code paths." + }, + { + "left": "issue:45084", + "right": "issue:45520", + "accept": false, + "reason": "Compile/template-node error vs flash_attn import guard; unrelated." + }, + { + "left": "issue:44554", + "right": "issue:45446", + "accept": false, + "reason": "MPS attention correctness bug vs PyTorch version-check/import bug; not the same issue." + }, + { + "left": "issue:44568", + "right": "issue:45701", + "accept": false, + "reason": "Specific add_special_tokens regression vs broad tokenizer-version change report; too different." + }, + { + "left": "issue:43688", + "right": "issue:43873", + "accept": false, + "reason": "Aux-loss normalization and quantized offloading are unrelated." + }, + { + "left": "issue:15354", + "right": "issue:38175", + "accept": false, + "reason": "TorchScript export limitation vs SigLIP2 zero-probability bug; unrelated." + }, + { + "left": "issue:43540", + "right": "issue:45200", + "accept": false, + "reason": "Video processing ValueError vs Gemma4 fine-tuning token-ID requirement; different failures." + }, + { + "left": "issue:43232", + "right": "issue:44849", + "accept": false, + "reason": "Generation kwarg update after sync_gpus vs hidden-states output bug; different paths." + }, + { + "left": "issue:45200", + "right": "issue:45823", + "accept": false, + "reason": "Same model family, but mm_token_type_ids defaulting and device mismatch are distinct bugs." + }, + { + "left": "issue:45072", + "right": "issue:45198", + "accept": false, + "reason": "bfloat16 dtype mismatch in inference vs Wav2Vec2 save/tokenization failure; unrelated." + }, + { + "left": "issue:44315", + "right": "issue:44849", + "accept": false, + "reason": "model_init/Liger application issue vs Qwen3.5 hidden-states bug; unrelated." + }, + { + "left": "issue:43278", + "right": "issue:43701", + "accept": false, + "reason": "BF16-to-FP32 eval dtype drift vs checkpoint key mismatch; unrelated." + }, + { + "left": "issue:28218", + "right": "issue:33357", + "accept": false, + "reason": "Tokenizer added-space bug vs CLIP bus error on macOS; unrelated." + }, + { + "left": "issue:44554", + "right": "issue:45356", + "accept": false, + "reason": "MPS attention bug vs Kimi tokenizer regression; unrelated." + }, + { + "left": "issue:45200", + "right": "issue:45325", + "accept": false, + "reason": "Gemma4 token-ID fine-tuning issue vs Qwen2.5-VL rope indexing bug; unrelated." + }, + { + "left": "issue:44466", + "right": "issue:45127", + "accept": false, + "reason": "Serialization/tied-weights inconsistency vs LoRA merge collapse; similar area but not the same bug." + }, + { + "left": "issue:43295", + "right": "issue:44610", + "accept": false, + "reason": "Processor.tokenizer regression vs video-input size mismatch; different code paths." + }, + { + "left": "issue:44898", + "right": "issue:45412", + "accept": false, + "reason": "Perceiver resolution failure vs RT-DETR memory leak; unrelated." + }, + { + "left": "issue:43334", + "right": "issue:43525", + "accept": false, + "reason": "Both mention pad_token_id, but they affect different model configs and load paths." + }, + { + "left": "issue:37428", + "right": "issue:43957", + "accept": false, + "reason": "Flash-attn import error vs meta-device loading breakage; unrelated." + }, + { + "left": "issue:43572", + "right": "issue:44987", + "accept": false, + "reason": "StableLmConfig pad_token_idx regression vs unrelated model-loading failure." + }, + { + "left": "issue:43572", + "right": "issue:43957", + "accept": false, + "reason": "Missing pad_token_idx in StableLmConfig vs meta-device loading breakage; unrelated." + }, + { + "left": "issue:43873", + "right": "issue:44464", + "accept": false, + "reason": "Quantized offloading vs compiled-forward chunked generation; unrelated." + }, + { + "left": "issue:43295", + "right": "issue:43450", + "accept": false, + "reason": "Processor.tokenizer/images regression vs batched video-shape bug; different issues." + }, + { + "left": "issue:43844", + "right": "issue:44936", + "accept": false, + "reason": "ZeRO-3 gradient anomaly vs trainer.evaluate() after train() failure; unrelated." + }, + { + "left": "issue:43824", + "right": "issue:43975", + "accept": false, + "reason": "ImportError for a VL class vs DeepSeek detokenization regression; unrelated." + }, + { + "left": "issue:43295", + "right": "issue:43873", + "accept": false, + "reason": "Processor/tokenizer regression vs quantization offloading bug; unrelated." + }, + { + "left": "issue:38175", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 probability issue vs RT-DETR memory-release bug; unrelated." + }, + { + "left": "issue:37428", + "right": "issue:43824", + "accept": false, + "reason": "Different missing-import failures in different modules; not the same bug." + }, + { + "left": "issue:42915", + "right": "issue:43824", + "accept": false, + "reason": "FP8 config failure vs Qwen2.5-VL import failure; unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 22, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:37428", + "issue:38175", + "issue:39692", + "issue:43262", + "issue:43278", + "issue:43335", + "issue:43388", + "issue:43425", + "issue:43450", + "issue:43493", + "issue:43526", + "issue:43550", + "issue:43575", + "issue:43606", + "issue:43611", + "issue:43653", + "issue:43819", + "issue:43825", + "issue:43827", + "issue:43901", + "issue:43931", + "issue:44112", + "issue:44206", + "issue:44351", + "issue:44360", + "issue:44442", + "issue:44448", + "issue:44462", + "issue:44514", + "issue:44521", + "issue:44561", + "issue:44610", + "issue:44743", + "issue:44779", + "issue:44792", + "issue:44857", + "issue:45083", + "issue:45127", + "issue:45198", + "issue:45200", + "issue:45245", + "issue:45290", + "issue:45381", + "issue:45563", + "issue:45584", + "issue:45588", + "issue:45593", + "issue:45823" + ], + "soft_pairs": [ + "issue:44514|issue:44521", + "issue:44442|issue:45198", + "issue:38175|issue:43493", + "issue:43827|issue:43901", + "issue:43653|issue:44112", + "issue:43450|issue:43493", + "issue:43450|issue:43575", + "issue:44792|issue:45563", + "issue:44360|issue:44561", + "issue:45127|issue:45245", + "issue:43819|issue:45083", + "issue:44206|issue:45584", + "issue:43819|issue:44112", + "issue:43262|issue:43450", + "issue:44610|issue:44857", + "issue:37428|issue:43425", + "issue:44857|issue:45593", + "issue:43278|issue:43825", + "issue:45290|issue:45381", + "issue:43606|issue:45083", + "issue:45200|issue:45588", + "issue:43335|issue:43550", + "issue:44448|issue:44743", + "issue:37428|issue:44351", + "issue:43611|issue:43931", + "issue:39692|issue:43526", + "issue:44561|issue:44779", + "issue:44462|issue:44561", + "issue:44206|issue:45823", + "issue:43388|issue:43526", + "issue:43335|issue:43653" + ], + "prepared_review_unit_hash": "6776169d6a956f50038302a2f9db6a982a8d75c552581e622f21565e6bf50cd2", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37070, + "estimated_input_tokens": 9268, + "estimated_eval_tokens": 18792 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This is not a true duplicate cluster: the soft pairs span unrelated bugs, regressions, docs issues, tokenizer/model problems, and CI failures. I would reject all soft edges; issue 44521 is only the closest representative because it is the most active open item, not because it duplicates the others.", + "confidence": 0.79, + "canonical_issue_reason": "Issue 44521 is the closest representative of the set only because it is open, high-activity, and user-facing; however, the surrounding items are too heterogeneous to form a real duplicate group.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44521 is the best standalone anchor among these items due to the highest discussion/inbound activity and a broadly relevant apply_chat_template bug, but it does not subsume the rest.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44514", + "right": "issue:44521", + "accept": false, + "reason": "Both involve chat-template paths, but one is a batched crash and the other is an all-zero mask bug; different symptoms and likely different fixes." + }, + { + "left": "issue:44442", + "right": "issue:45198", + "accept": false, + "reason": "Different models and different failure modes: AutoTokenizer loading vs save_pretrained/tokenization failure." + }, + { + "left": "issue:38175", + "right": "issue:43493", + "accept": false, + "reason": "Both mention SigLIP2, but one is zero probabilities and the other is an HF-vs-JAX discrepancy; not enough to treat as the same bug." + }, + { + "left": "issue:43827", + "right": "issue:43901", + "accept": false, + "reason": "Both are docs-related, but they cover different pipeline deprecations and different API details." + }, + { + "left": "issue:43653", + "right": "issue:44112", + "accept": false, + "reason": "Unrelated: tokenizer special-token registration vs a GraniteSpeech CI device-override test failure." + }, + { + "left": "issue:43450", + "right": "issue:43493", + "accept": false, + "reason": "Video batching shape bug vs SigLIP2 implementation discrepancy; different subsystems and symptoms." + }, + { + "left": "issue:43450", + "right": "issue:43575", + "accept": false, + "reason": "Unrelated: video processor shape issue vs Qwen2 TP load OOM." + }, + { + "left": "issue:44792", + "right": "issue:45563", + "accept": false, + "reason": "Janus image generation test failure and a paged-generate warning are different code paths and failures." + }, + { + "left": "issue:44360", + "right": "issue:44561", + "accept": false, + "reason": "Different areas entirely: DSA indexer discussion vs removal of is_torch_fx_available breaking trust_remote_code." + }, + { + "left": "issue:45127", + "right": "issue:45245", + "accept": false, + "reason": "LoRA/extended-vocab collapse and category-cardinality overflow are unrelated bugs." + }, + { + "left": "issue:43819", + "right": "issue:45083", + "accept": false, + "reason": "DAC from_latents mismatch is unrelated to the qwen3_omni_moe feature-length helper behavior." + }, + { + "left": "issue:44206", + "right": "issue:45584", + "accept": false, + "reason": "Laser feature-extractor center-arg crash vs Whisper empty-transcription failure are different issues." + }, + { + "left": "issue:43819", + "right": "issue:44112", + "accept": false, + "reason": "No shared code path: DAC latent conversion vs GraniteSpeech CI device override." + }, + { + "left": "issue:43262", + "right": "issue:43450", + "accept": false, + "reason": "Audio chat-template sampling-rate default and video batching shape are unrelated." + }, + { + "left": "issue:44610", + "right": "issue:44857", + "accept": false, + "reason": "Processor input-size mismatch vs float16 AMP CUDA crash; different layers of the stack." + }, + { + "left": "issue:37428", + "right": "issue:43425", + "accept": false, + "reason": "ImportError for a missing flash-attention helper is not the same concrete bug as general Torch 2.10 incompatibility." + }, + { + "left": "issue:44857", + "right": "issue:45593", + "accept": false, + "reason": "AMP/CUDA crash and missing auxiliary losses are unrelated model-training bugs." + }, + { + "left": "issue:43278", + "right": "issue:43825", + "accept": false, + "reason": "Embedding dtype drift is unrelated to a pipeline docs/error-message regression." + }, + { + "left": "issue:45290", + "right": "issue:45381", + "accept": false, + "reason": "One is a chat-template tool-call crash; the other is a video vision_position_ids bug." + }, + { + "left": "issue:43606", + "right": "issue:45083", + "accept": false, + "reason": "CPU offload device mismatch and qwen3_omni_moe feature-length behavior are unrelated." + }, + { + "left": "issue:45200", + "right": "issue:45588", + "accept": false, + "reason": "Gemma4 mm_token_type_ids defaulting and flash_attention s_aux handling are different bugs in different components." + }, + { + "left": "issue:43335", + "right": "issue:43550", + "accept": false, + "reason": "SwitchTransformers sparse-layer construction and Bamba torch.compile/SDPA failure are unrelated." + }, + { + "left": "issue:44448", + "right": "issue:44743", + "accept": false, + "reason": "Pegasus v4/v5 output drift and qwen3_5 recurrent-state reset are different model-specific issues." + }, + { + "left": "issue:37428", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but they miss different symbols in different places and do not point to one shared fix." + }, + { + "left": "issue:43611", + "right": "issue:43931", + "accept": false, + "reason": "Base-model-prefix loading breakage and Qwen3-VL weight-shape mismatch are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:43526", + "accept": false, + "reason": "SigLIP2 doc/example problems and BeitImageProcessorFast reduce_labels behavior are different issues." + }, + { + "left": "issue:44561", + "right": "issue:44779", + "accept": false, + "reason": "trust_remote_code breakage from a removed helper is unrelated to DeepSeek tokenizer correctness." + }, + { + "left": "issue:44462", + "right": "issue:44561", + "accept": false, + "reason": "Tokenizer.json loading behavior and is_torch_fx_available removal are different failures." + }, + { + "left": "issue:44206", + "right": "issue:45823", + "accept": false, + "reason": "Different Gemma/feature-extractor device issues with different code paths and symptoms." + }, + { + "left": "issue:43388", + "right": "issue:43526", + "accept": false, + "reason": "Distributed metric gathering label truncation is not the same as BeitImageProcessorFast reduce_labels returning only one label." + }, + { + "left": "issue:43335", + "right": "issue:43653", + "accept": false, + "reason": "SwitchTransformers sparse-layer config bug and BigBirdTokenizer special-token registration are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 23, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:28218", + "issue:29127", + "issue:29942", + "issue:32090", + "issue:34689", + "issue:35141", + "issue:36010", + "issue:37428", + "issue:38175", + "issue:39692", + "issue:40444", + "issue:43335", + "issue:43412", + "issue:43504", + "issue:43526", + "issue:43550", + "issue:43606", + "issue:43701", + "issue:43720", + "issue:43819", + "issue:43873", + "issue:43927", + "issue:44112", + "issue:44292", + "issue:44448", + "issue:44493", + "issue:44568", + "issue:44779", + "issue:44855", + "issue:44857", + "issue:44977", + "issue:45072", + "issue:45083", + "issue:45198", + "issue:45229", + "issue:45245", + "issue:45310", + "issue:45372", + "issue:45459", + "issue:45478", + "issue:45491", + "issue:45520", + "issue:45563", + "issue:45588", + "issue:45593", + "issue:45698", + "issue:45712", + "issue:45803" + ], + "soft_pairs": [ + "issue:45310|issue:45478", + "issue:43819|issue:44493", + "issue:29942|issue:32090", + "issue:43550|issue:44112", + "issue:44855|issue:45083", + "issue:43335|issue:43504", + "issue:43335|issue:45083", + "issue:39692|issue:44493", + "issue:44292|issue:45520", + "issue:44448|issue:44779", + "issue:38175|issue:44493", + "issue:28218|issue:35141", + "issue:43335|issue:45072", + "issue:43720|issue:44112", + "issue:43335|issue:45593", + "issue:44977|issue:45229", + "issue:44448|issue:44977", + "issue:44568|issue:45491", + "issue:43606|issue:44857", + "issue:45459|issue:45712", + "issue:44857|issue:45072", + "issue:29127|issue:32090", + "issue:45198|issue:45803", + "issue:43927|issue:45698", + "issue:44977|issue:45563", + "issue:34689|issue:35141", + "issue:45372|issue:45588", + "issue:40444|issue:43526", + "issue:43701|issue:45083", + "issue:43550|issue:45083", + "issue:43412|issue:45588", + "issue:45245|issue:45563", + "issue:29942|issue:35141", + "issue:43873|issue:44493", + "issue:36010|issue:37428", + "issue:45372|issue:45459" + ], + "prepared_review_unit_hash": "970963853e7ef349ca114f33ae30a73e4db994a43e4971447a2ba06eef13b5b9", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 36, + "serialized_chars": 38716, + "estimated_input_tokens": 9679, + "estimated_eval_tokens": 19614 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a set of loosely related transformer/model bug reports with one clear exact duplicate pair. Most soft matches are false positives based on broad keyword similarity rather than the same underlying defect.", + "confidence": 0.74, + "canonical_issue_reason": "issue:45310 is the clearest representative of the one real duplicate pair: it\u2019s the earlier, concrete report and matches issue:45478 by title and failure mode exactly.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45310 is the best issue anchor because it is a precise, concrete bug report with an exact duplicate counterpart and the strongest evidence of true duplication in the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45310", + "right": "issue:45478", + "accept": true, + "reason": "Exact duplicate: same Qwen3.5 MoE from_pretrained error, same title and underlying failure." + }, + { + "left": "issue:43819", + "right": "issue:44493", + "accept": false, + "reason": "Different bug classes: DAC forward/latents mismatch vs position-id unexpected key handling." + }, + { + "left": "issue:29942", + "right": "issue:32090", + "accept": false, + "reason": "Unrelated failures: Flash Attention 2 tests vs Trainer GPU broadcast NoneType error." + }, + { + "left": "issue:43550", + "right": "issue:44112", + "accept": false, + "reason": "Different models and failure paths: torch.compile/SDPA vs CI stale device override test." + }, + { + "left": "issue:44855", + "right": "issue:45083", + "accept": false, + "reason": "Different code paths: Python 3.13 import/parsing error vs feature-extract output length helper behavior." + }, + { + "left": "issue:43335", + "right": "issue:43504", + "accept": false, + "reason": "Different models and bugs: SwitchTransformers sparse layer creation vs BEiT pretrained preset loading." + }, + { + "left": "issue:43335", + "right": "issue:45083", + "accept": false, + "reason": "No shared underlying defect; config construction bug vs helper output-length behavior." + }, + { + "left": "issue:39692", + "right": "issue:44493", + "accept": false, + "reason": "Docs/example errors and model/processor mismatch are not the same as unexpected position-id keys." + }, + { + "left": "issue:44292", + "right": "issue:45520", + "accept": false, + "reason": "Different failures: Qwen-3-8B-NVFP4 runtime issue vs flash_attn import KeyError on Python 3.13." + }, + { + "left": "issue:44448", + "right": "issue:44779", + "accept": false, + "reason": "Both concern model behavior changes across versions, but they are different models and distinct regressions." + }, + { + "left": "issue:38175", + "right": "issue:44493", + "accept": false, + "reason": "Different symptoms and likely causes: zero probabilities vs unexpected position-id keys." + }, + { + "left": "issue:28218", + "right": "issue:35141", + "accept": false, + "reason": "Tokenizer spacing after added tokens is unrelated to output embedding reinitialization on resize." + }, + { + "left": "issue:43335", + "right": "issue:45072", + "accept": false, + "reason": "Different bugs: sparse-layer construction vs dtype mismatches in bfloat16 inference." + }, + { + "left": "issue:43720", + "right": "issue:44112", + "accept": false, + "reason": "Packed-weight loading failure is unrelated to a stale CI device override test." + }, + { + "left": "issue:43335", + "right": "issue:45593", + "accept": false, + "reason": "Different models and behavior: SwitchTransformers config bug vs D-FINE auxiliary-loss handling." + }, + { + "left": "issue:44977", + "right": "issue:45229", + "accept": false, + "reason": "Flash-attention generation issue is unrelated to a multi-GPU CUDA OOM." + }, + { + "left": "issue:44448", + "right": "issue:44977", + "accept": false, + "reason": "Both are generation regressions, but on different models and different attention paths." + }, + { + "left": "issue:44568", + "right": "issue:45491", + "accept": false, + "reason": "Tokenizer add_special_tokens behavior is unrelated to Gemma3 NaN embeddings with mixed-length batching." + }, + { + "left": "issue:43606", + "right": "issue:44857", + "accept": false, + "reason": "CPU offload device mismatch is unrelated to float16 AMP CUDA crashes." + }, + { + "left": "issue:45459", + "right": "issue:45712", + "accept": false, + "reason": "Tokenizer error masking is unrelated to leftover dummy classes and repo-check failures." + }, + { + "left": "issue:44857", + "right": "issue:45072", + "accept": false, + "reason": "Different symptoms and subsystems: AMP/CUDA loss crash vs bfloat16 dtype mismatch in inference." + }, + { + "left": "issue:29127", + "right": "issue:32090", + "accept": false, + "reason": "Clarifying an error message for LayoutLMv3 boxes is not the same bug as GPU broadcast NoneType handling." + }, + { + "left": "issue:45198", + "right": "issue:45803", + "accept": false, + "reason": "Wav2Vec2 save/tokenization failure is unrelated to a bare-except swallowing errors in FuyuBatchFeature." + }, + { + "left": "issue:43927", + "right": "issue:45698", + "accept": false, + "reason": "Both involve save/load behavior, but custom token IDs being lost is not the same as loading the wrong custom module." + }, + { + "left": "issue:44977", + "right": "issue:45563", + "accept": false, + "reason": "One is a flash-attention generation bug, the other is a stale warning about num_return_sequences." + }, + { + "left": "issue:34689", + "right": "issue:35141", + "accept": false, + "reason": "Model loading breakage for Llama vision is unrelated to embedding resize/post_init reinitialization." + }, + { + "left": "issue:45372", + "right": "issue:45588", + "accept": false, + "reason": "Gemma 4 processor import failure is unrelated to flash_attention integration crashing on s_aux=None." + }, + { + "left": "issue:40444", + "right": "issue:43526", + "accept": false, + "reason": "Different BEiT/Qwen2.5-VL data handling bugs with no shared concrete code path." + }, + { + "left": "issue:43701", + "right": "issue:45083", + "accept": false, + "reason": "Checkpoint key mismatch is unrelated to a helper function returning unexpected lengths." + }, + { + "left": "issue:43550", + "right": "issue:45072", + "accept": false, + "reason": "Different model/runtime issues: torch.compile SDPA failure vs bfloat16 dtype mismatch." + }, + { + "left": "issue:43412", + "right": "issue:45588", + "accept": false, + "reason": "Executorch export guard/support issues are unrelated to flash_attention sink-less model crashes." + }, + { + "left": "issue:45245", + "right": "issue:45563", + "accept": false, + "reason": "Category-count limit runtime error is unrelated to a paged-generate warning." + }, + { + "left": "issue:29942", + "right": "issue:35141", + "accept": false, + "reason": "Flash Attention 2 test failures are unrelated to embedding reinitialization after resizing." + }, + { + "left": "issue:43873", + "right": "issue:44493", + "accept": false, + "reason": "Quantization/offloading behavior is not the same as unexpected position-id key reports." + }, + { + "left": "issue:36010", + "right": "issue:37428", + "accept": false, + "reason": "Two different import errors in different modules; same broad theme, not the same bug." + }, + { + "left": "issue:45372", + "right": "issue:45459", + "accept": false, + "reason": "Gemma 4 processor import error is unrelated to protobuf tokenizer error masking." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet: the only accepted soft edge is an identical-title pair (issue:45310 / issue:45478), and the rest of the verdicts are conservatively rejected based on clearly different titles/subsystems. No overstatement is apparent." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 24, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:25251", + "issue:29127", + "issue:29942", + "issue:30064", + "issue:32090", + "issue:33357", + "issue:34567", + "issue:39692", + "issue:42915", + "issue:42994", + "issue:43065", + "issue:43066", + "issue:43278", + "issue:43381", + "issue:43421", + "issue:43653", + "issue:43723", + "issue:43756", + "issue:43873", + "issue:43976", + "issue:43994", + "issue:44186", + "issue:44206", + "issue:44265", + "issue:44361", + "issue:44448", + "issue:44451", + "issue:44462", + "issue:44466", + "issue:44479", + "issue:44554", + "issue:44610", + "issue:44734", + "issue:44743", + "issue:44857", + "issue:44871", + "issue:44977", + "issue:45103", + "issue:45198", + "issue:45229", + "issue:45372", + "issue:45406", + "issue:45412", + "issue:45440", + "issue:45491", + "issue:45520", + "issue:45588", + "issue:45823" + ], + "soft_pairs": [ + "issue:43066|issue:44462", + "issue:45588|issue:45823", + "issue:44857|issue:45588", + "issue:44448|issue:44466", + "issue:43278|issue:43381", + "issue:25251|issue:32090", + "issue:43065|issue:45412", + "issue:43653|issue:44743", + "issue:44451|issue:45520", + "issue:43976|issue:45440", + "issue:44186|issue:45198", + "issue:42915|issue:42994", + "issue:43994|issue:45412", + "issue:43421|issue:45491", + "issue:44361|issue:45198", + "issue:44871|issue:44977", + "issue:44265|issue:45198", + "issue:44206|issue:44479", + "issue:29942|issue:30064", + "issue:43065|issue:43994", + "issue:44734|issue:45406", + "issue:33357|issue:39692", + "issue:29127|issue:34567", + "issue:44610|issue:45412", + "issue:45103|issue:45372", + "issue:43873|issue:45229", + "issue:43756|issue:45440", + "issue:43723|issue:44554", + "issue:45372|issue:45406" + ], + "prepared_review_unit_hash": "f147da53eb0df96a8806bb958cd0d589d5944266765abf8cc5e3aad6491c9e9e", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36446, + "estimated_input_tokens": 9112, + "estimated_eval_tokens": 18480 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The items are mostly unrelated tokenizer/model regressions that only look superficially similar by subsystem. No soft pair looks like the same underlying bug or change closely enough to merge.", + "confidence": 0.82, + "canonical_issue_reason": "issue:44462 is the clearest standalone bug report: it describes a concrete AutoTokenizer loading regression with a specific repository-level failure mode.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44462 is the most actionable and user-facing report in the set, with a focused code path and a broad impact on tokenizer loading.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43066", + "right": "issue:44462", + "accept": false, + "reason": "Both involve tokenizer loading in v5, but one is a decoder-type mismatch and the other is AutoTokenizer ignoring tokenizer.json; different failure modes and likely different fixes." + }, + { + "left": "issue:45588", + "right": "issue:45823", + "accept": false, + "reason": "One is a flash-attention sink-less crash, the other is a Gemma4 PLE device-map mismatch; different code paths and symptoms." + }, + { + "left": "issue:44857", + "right": "issue:45588", + "accept": false, + "reason": "LwDetrImageLoss AMP/CUDA crash is unrelated to flash_attention.py s_aux handling." + }, + { + "left": "issue:44448", + "right": "issue:44466", + "accept": false, + "reason": "Pegasus output differences and lm_head.weight serialization inconsistencies are distinct regressions with different surfaces." + }, + { + "left": "issue:43278", + "right": "issue:43381", + "accept": false, + "reason": "Eval-mode dtype drift and gradient-checkpointing-in-eval are separate training/eval issues, not the same bug." + }, + { + "left": "issue:25251", + "right": "issue:32090", + "accept": false, + "reason": "Pipeline top_k nesting and Trainer NoneType broadcast are unrelated." + }, + { + "left": "issue:43065", + "right": "issue:45412", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder and RT-DETR memory leaks are different problems." + }, + { + "left": "issue:43653", + "right": "issue:44743", + "accept": false, + "reason": "Tokenizer special-token registration and Qwen3.5 recurrent state reset are unrelated." + }, + { + "left": "issue:44451", + "right": "issue:45520", + "accept": false, + "reason": "Tokenizer loading failure for a model repo and a flash_attn import KeyError on Python 3.13 are different issues." + }, + { + "left": "issue:43976", + "right": "issue:45440", + "accept": false, + "reason": "Python-version compatibility and DeepseekV3MoE behavioral divergence are not the same bug." + }, + { + "left": "issue:44186", + "right": "issue:45198", + "accept": false, + "reason": "LayoutLMv2Tokenizer NER/padding crash and Wav2Vec2 save/tokenization failure are different tokenizer/model paths." + }, + { + "left": "issue:42915", + "right": "issue:42994", + "accept": false, + "reason": "FineGrainedFP8Config failure for Qwen3Moe and quantized model saving failure are distinct quantization bugs." + }, + { + "left": "issue:43994", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 inference mismatch and RT-DETR memory release are unrelated." + }, + { + "left": "issue:43421", + "right": "issue:45491", + "accept": false, + "reason": "Runtime post-processor updates for special tokens and Gemma3 NaN embeddings are different tokenizer/model behaviors." + }, + { + "left": "issue:44361", + "right": "issue:45198", + "accept": false, + "reason": "MLukeTokenizer AttributeError and Wav2Vec2 save/tokenization failure do not share a concrete code-path problem." + }, + { + "left": "issue:44871", + "right": "issue:44977", + "accept": false, + "reason": "Gemma eos_token_id config mismatch and Qwen3.5 flash-attention generation regression are unrelated." + }, + { + "left": "issue:44265", + "right": "issue:45198", + "accept": false, + "reason": "torch.export failures with torch_compilable_check and Wav2Vec2 save/tokenization problems are different areas." + }, + { + "left": "issue:44206", + "right": "issue:44479", + "accept": false, + "reason": "Feature-extractor center-arg crash and Qwen VL video regression are unrelated." + }, + { + "left": "issue:29942", + "right": "issue:30064", + "accept": false, + "reason": "Flash Attention 2 test failures and void segmentation map processing are different bugs." + }, + { + "left": "issue:43065", + "right": "issue:43994", + "accept": false, + "reason": "Sam3PixelDecoder dummy Conv2d and SigLIP2 incorrect outputs are not the same change." + }, + { + "left": "issue:44734", + "right": "issue:45406", + "accept": false, + "reason": "KV-cache continuation tensor indexing in transformers serve and Gemma4Processor missing _tokenizer are different failures." + }, + { + "left": "issue:33357", + "right": "issue:39692", + "accept": false, + "reason": "MacOS bus error for community CLIP and SigLIP2 doc example errors are separate issues." + }, + { + "left": "issue:29127", + "right": "issue:34567", + "accept": false, + "reason": "LayoutLMv3 box-clarity error and TrainerState token-count tracking are unrelated." + }, + { + "left": "issue:44610", + "right": "issue:45412", + "accept": false, + "reason": "OmDet-Turbo processor size mismatch and RT-DETR memory leak are different bugs." + }, + { + "left": "issue:45103", + "right": "issue:45372", + "accept": false, + "reason": "auto_docstring crash under future annotations and Gemma4 processor import failure are unrelated." + }, + { + "left": "issue:43873", + "right": "issue:45229", + "accept": false, + "reason": "Quantization/offloading behavior and Gemma4 multi-GPU OOM are different problems." + }, + { + "left": "issue:43756", + "right": "issue:45440", + "accept": false, + "reason": "Smollm3 RoPE-layer discrepancy and DeepseekV3MoE divergence are unrelated model-architecture issues." + }, + { + "left": "issue:43723", + "right": "issue:44554", + "accept": false, + "reason": "AutoTokenizer loading regression and an MPS attention correctness issue are different code paths." + }, + { + "left": "issue:45372", + "right": "issue:45406", + "accept": false, + "reason": "Both mention Gemma4, but one is an import-time dependency failure and the other is a serve-time missing attribute; 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": 16, + "review_unit_index": 25, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:29127", + "issue:29942", + "issue:32090", + "issue:33357", + "issue:35141", + "issue:36010", + "issue:38175", + "issue:41720", + "issue:42915", + "issue:43262", + "issue:43278", + "issue:43316", + "issue:43329", + "issue:43334", + "issue:43381", + "issue:43441", + "issue:43452", + "issue:43525", + "issue:43526", + "issue:43531", + "issue:43575", + "issue:43646", + "issue:43653", + "issue:43701", + "issue:43824", + "issue:43931", + "issue:44077", + "issue:44186", + "issue:44206", + "issue:44279", + "issue:44387", + "issue:44442", + "issue:44464", + "issue:44743", + "issue:44811", + "issue:44857", + "issue:44964", + "issue:44977", + "issue:45072", + "issue:45229", + "issue:45245", + "issue:45440", + "issue:45491", + "issue:45584", + "issue:45588", + "issue:45593", + "issue:45803", + "issue:45834" + ], + "soft_pairs": [ + "issue:43278|issue:43575", + "issue:43381|issue:43701", + "issue:43526|issue:45834", + "issue:43653|issue:44442", + "issue:43278|issue:43329", + "issue:41720|issue:45229", + "issue:45440|issue:45593", + "issue:29942|issue:36010", + "issue:43334|issue:43531", + "issue:32090|issue:33357", + "issue:44977|issue:45245", + "issue:43824|issue:44279", + "issue:43526|issue:44186", + "issue:43526|issue:44857", + "issue:42915|issue:43931", + "issue:43441|issue:45588", + "issue:44464|issue:45491", + "issue:43262|issue:44206", + "issue:44442|issue:45072", + "issue:44743|issue:44811", + "issue:43575|issue:43701", + "issue:43646|issue:44077", + "issue:43452|issue:45588", + "issue:29127|issue:35141", + "issue:44442|issue:45803", + "issue:43575|issue:44387", + "issue:44977|issue:45584", + "issue:33357|issue:38175", + "issue:43316|issue:43525", + "issue:44964|issue:45440" + ], + "prepared_review_unit_hash": "ec8e76295e4957adb3b6026f01330a623c48aee97e6d3627f374b079e463f00b", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36641, + "estimated_input_tokens": 9161, + "estimated_eval_tokens": 18578 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The candidate pairs are mostly unrelated issues across different models, components, and failure modes. I would reject all soft edges; none look like the same underlying bug or change.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43278", + "right": "issue:43575", + "accept": false, + "reason": "Different problems: dtype drift in eval vs a tensor-parallel OOM while loading a large Qwen model." + }, + { + "left": "issue:43381", + "right": "issue:43701", + "accept": false, + "reason": "One is gradient checkpointing in eval mode; the other is a resume_from_checkpoint key mismatch. No shared code-path bug." + }, + { + "left": "issue:43526", + "right": "issue:45834", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug vs Kosmos2.5 OCR long-input index error; distinct processors and failures." + }, + { + "left": "issue:43653", + "right": "issue:44442", + "accept": false, + "reason": "BigBirdTokenizer special-token registration issue vs FastSpeech2ConformerTokenizer loading failure; unrelated tokenization bugs." + }, + { + "left": "issue:43278", + "right": "issue:43329", + "accept": false, + "reason": "Embedding dtype mismatch is unrelated to the multimodal token-count video-branch undefined variable bug." + }, + { + "left": "issue:41720", + "right": "issue:45229", + "accept": false, + "reason": "Different models and symptoms: Qwen3 auto device mapping assert vs Gemma4 multi-GPU CUDA OOM." + }, + { + "left": "issue:45440", + "right": "issue:45593", + "accept": false, + "reason": "DeepSeekV3MoE implementation divergence vs D-FINE auxiliary-loss handling; no common underlying change." + }, + { + "left": "issue:29942", + "right": "issue:36010", + "accept": false, + "reason": "Flash Attention 2 test failures are not the same as a GenerationMixin import error." + }, + { + "left": "issue:43334", + "right": "issue:43531", + "accept": false, + "reason": "Missing pad_token_id on Qwen3-VL config is unrelated to sliding_window behavior in Qwen3-MoE." + }, + { + "left": "issue:32090", + "right": "issue:33357", + "accept": false, + "reason": "Trainer broadcast TypeError and MacOS CLIP bus error are different runtime failures in different paths." + }, + { + "left": "issue:44977", + "right": "issue:45245", + "accept": false, + "reason": "Flash-attention generation issue vs category-cardinality limit error; no shared bug." + }, + { + "left": "issue:43824", + "right": "issue:44279", + "accept": false, + "reason": "Specific missing Qwen2.5-VL symbol import vs a broad dependency issue; not the same failure." + }, + { + "left": "issue:43526", + "right": "issue:44186", + "accept": false, + "reason": "Different tokenizer/processor crashes with different inputs and root causes." + }, + { + "left": "issue:43526", + "right": "issue:44857", + "accept": false, + "reason": "BEiT label reduction bug is unrelated to LwDetrImageLoss AMP/CUDA crash." + }, + { + "left": "issue:42915", + "right": "issue:43931", + "accept": false, + "reason": "FineGrainedFP8Config failure for Qwen3Moe vs weight-shape mismatch loading Qwen3-VL; distinct issues." + }, + { + "left": "issue:43441", + "right": "issue:45588", + "accept": false, + "reason": "Ministral FlashAttention regression and sink-less-models s_aux None crash are separate FlashAttention-related bugs." + }, + { + "left": "issue:44464", + "right": "issue:45491", + "accept": false, + "reason": "Compiled chunked generation inconsistency is not the same as Gemma3 NaN embeddings from sliding-window/all-padding windows." + }, + { + "left": "issue:43262", + "right": "issue:44206", + "accept": false, + "reason": "Audio chat-template sampling-rate default bug vs LasrFeatureExtractor unsupported argument crash; different components." + }, + { + "left": "issue:44442", + "right": "issue:45072", + "accept": false, + "reason": "FastSpeech2ConformerTokenizer load failure vs dtype mismatch in SwitchTransformers/TimmWrapperModel; unrelated." + }, + { + "left": "issue:44743", + "right": "issue:44811", + "accept": false, + "reason": "Qwen3.5 recurrent-state reset bug is not the same as Whisper batch_decode skip_special_tokens handling." + }, + { + "left": "issue:43575", + "right": "issue:43701", + "accept": false, + "reason": "Loading OOM for a large Qwen model is unrelated to resume checkpoint key mismatches." + }, + { + "left": "issue:43646", + "right": "issue:44077", + "accept": false, + "reason": "Transformers 5 custom model init break is broader than the patchtsmixer post_init policy issue; not the same concrete bug." + }, + { + "left": "issue:43452", + "right": "issue:45588", + "accept": false, + "reason": "Tokenizer/model loading with gguf_file is unrelated to an s_aux=None flash_attention crash." + }, + { + "left": "issue:29127", + "right": "issue:35141", + "accept": false, + "reason": "LayoutLMv3 error-message clarity issue vs embedding reinitialization in post_init; different behavior and code paths." + }, + { + "left": "issue:44442", + "right": "issue:45803", + "accept": false, + "reason": "Tokenizer loading failure vs bare-except swallowing errors in FuyuBatchFeature; no common underlying bug." + }, + { + "left": "issue:43575", + "right": "issue:44387", + "accept": false, + "reason": "OOM while loading a model with tensor parallelism is distinct from increased CUDA reserved memory under int4 quantization." + }, + { + "left": "issue:44977", + "right": "issue:45584", + "accept": false, + "reason": "Qwen3.5 flash-attention generation bug is unrelated to Whisper empty-transcription generation after align_special_tokens." + }, + { + "left": "issue:33357", + "right": "issue:38175", + "accept": false, + "reason": "MacOS bus error on CLIP is not the same as zero probabilities on siglip2-base-patch16-224." + }, + { + "left": "issue:43316", + "right": "issue:43525", + "accept": false, + "reason": "Both mention config API issues, but they are different models and missing fields; not the same bug." + }, + { + "left": "issue:44964", + "right": "issue:45440", + "accept": false, + "reason": "Phi-4 multimodal loading regression is unrelated to DeepSeekV3MoE implementation divergence." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 26, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:28218", + "issue:29127", + "issue:32090", + "issue:33290", + "issue:33357", + "issue:34567", + "issue:34689", + "issue:36010", + "issue:39692", + "issue:41628", + "issue:42907", + "issue:43316", + "issue:43381", + "issue:43493", + "issue:43540", + "issue:43550", + "issue:43611", + "issue:43643", + "issue:43720", + "issue:43761", + "issue:43827", + "issue:43856", + "issue:43873", + "issue:43931", + "issue:44077", + "issue:44079", + "issue:44188", + "issue:44190", + "issue:44442", + "issue:44479", + "issue:44496", + "issue:44514", + "issue:44568", + "issue:44743", + "issue:44855", + "issue:44871", + "issue:44877", + "issue:44898", + "issue:44913", + "issue:45137", + "issue:45216", + "issue:45290", + "issue:45372", + "issue:45479", + "issue:45491", + "issue:45656", + "issue:45698", + "issue:45759" + ], + "soft_pairs": [ + "issue:43761|issue:44079", + "issue:44479|issue:45290", + "issue:28218|issue:29127", + "issue:42907|issue:45698", + "issue:43931|issue:45216", + "issue:28218|issue:32090", + "issue:33290|issue:34567", + "issue:34689|issue:43611", + "issue:39692|issue:45491", + "issue:44442|issue:44898", + "issue:43761|issue:44188", + "issue:43381|issue:43873", + "issue:43493|issue:43827", + "issue:43550|issue:44743", + "issue:44568|issue:45479", + "issue:43316|issue:45759", + "issue:41628|issue:45372", + "issue:43643|issue:44913", + "issue:43720|issue:44442", + "issue:32090|issue:33290", + "issue:44190|issue:44496", + "issue:43873|issue:44871", + "issue:34689|issue:36010", + "issue:43381|issue:43856", + "issue:44077|issue:44479", + "issue:44855|issue:45137", + "issue:33290|issue:45656", + "issue:43316|issue:44877", + "issue:29127|issue:33357", + "issue:43540|issue:44514" + ], + "prepared_review_unit_hash": "70db5139c0ea59200a2f037a331eebd06a05e5d0aed6a497c43b5629835ca808", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 37030, + "estimated_input_tokens": 9258, + "estimated_eval_tokens": 18772 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items are mostly unrelated Transformers bugs spanning tokenization, config/loading, training, and docs. None of the soft pairs look like the same concrete bug, so I would not merge any of them.", + "confidence": 0.83, + "canonical_issue_reason": "No single canonical issue stands out; the cluster is heterogeneous and the soft links are weak.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45698 is the most broadly representative load/save-pretrained regression among the set, so it is the best anchor if one issue must be chosen.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43761", + "right": "issue:44079", + "accept": false, + "reason": "Different failures: CLIPVisionModel hidden_states regression vs ModelOutput key assignment when a value was previously None." + }, + { + "left": "issue:44479", + "right": "issue:45290", + "accept": false, + "reason": "Video-input regression and chat-template tool-call crash are separate code paths and different bugs." + }, + { + "left": "issue:28218", + "right": "issue:29127", + "accept": false, + "reason": "Tokenizer spacing after added tokens is unrelated to LayoutLMv3 error-message clarity." + }, + { + "left": "issue:42907", + "right": "issue:45698", + "accept": false, + "reason": "Different save/load problems: dequantized model saving vs wrong custom module loaded after save_pretrained." + }, + { + "left": "issue:43931", + "right": "issue:45216", + "accept": false, + "reason": "Qwen3-VL weight-shape mismatch and Qwen3.5 checkpoint save corruption are different model-loading issues." + }, + { + "left": "issue:28218", + "right": "issue:32090", + "accept": false, + "reason": "Tokenizer behavior bug vs Trainer/_gpu_broadcast_one NoneType error." + }, + { + "left": "issue:33290", + "right": "issue:34567", + "accept": false, + "reason": "DeepSpeed+AdaFactor OOM and TrainerState token counter not updating are unrelated." + }, + { + "left": "issue:34689", + "right": "issue:43611", + "accept": false, + "reason": "Model loading break for Llama 3.2 Vision is not the same as the base_model_prefix loading regression." + }, + { + "left": "issue:39692", + "right": "issue:45491", + "accept": false, + "reason": "Documentation/example errors for SigLIP2 are unrelated to Gemma3 NaN embeddings in attention." + }, + { + "left": "issue:44442", + "right": "issue:44898", + "accept": false, + "reason": "AutoTokenizer loading failure and Perceiver non-default-resolution failure are separate bugs." + }, + { + "left": "issue:43761", + "right": "issue:44188", + "accept": false, + "reason": "Hidden-states return bug is unrelated to attention kernel divergence under torch.compile." + }, + { + "left": "issue:43381", + "right": "issue:43873", + "accept": false, + "reason": "Gradient-checkpointing eval-mode restriction and quantization offloading issues are different problems." + }, + { + "left": "issue:43493", + "right": "issue:43827", + "accept": false, + "reason": "SigLIP2 implementation discrepancy and docs still referencing pipeline() are unrelated." + }, + { + "left": "issue:43550", + "right": "issue:44743", + "accept": false, + "reason": "torch.compile SDPA failure in Bamba-9B-v2 is not the same as recurrent states resetting in modular_qwen3_5.py." + }, + { + "left": "issue:44568", + "right": "issue:45479", + "accept": false, + "reason": "Tokenizer add_special_tokens regression and zero-loss sequence-classification bug do not share the same code path." + }, + { + "left": "issue:43316", + "right": "issue:45759", + "accept": false, + "reason": "Both involve config/model APIs, but one is a Gemma3TextConfig discrepancy and the other is Qwen composite-config unwrapping." + }, + { + "left": "issue:41628", + "right": "issue:45372", + "accept": false, + "reason": "AutoImageProcessor import failure and mistral_common ReasoningEffort import failure are different import regressions." + }, + { + "left": "issue:43643", + "right": "issue:44913", + "accept": false, + "reason": "trust_remote_code missing fields and GPTNeoX rotary_pct resetting on reload are distinct config bugs." + }, + { + "left": "issue:43720", + "right": "issue:44442", + "accept": false, + "reason": "BitNet packed-weight loading and FastSpeech2ConformerTokenizer loading failure are unrelated loader issues." + }, + { + "left": "issue:32090", + "right": "issue:33290", + "accept": false, + "reason": "Trainer NoneType broadcast error and DeepSpeed AdaFactor OOM are different training/runtime failures." + }, + { + "left": "issue:44190", + "right": "issue:44496", + "accept": false, + "reason": "Local dataset loading in an example script is unrelated to an unrecognized-model/config model_type error." + }, + { + "left": "issue:43873", + "right": "issue:44871", + "accept": false, + "reason": "Quantization/offloading behavior and Gemma-3 eos_token_id mismatch are different issues." + }, + { + "left": "issue:34689", + "right": "issue:36010", + "accept": false, + "reason": "Llama 3.2 Vision loading break is not the same as the GenerationMixin import error." + }, + { + "left": "issue:43381", + "right": "issue:43856", + "accept": false, + "reason": "Gradient checkpointing eval-mode bug and Qwen3 MoE memory inefficiency are separate concerns." + }, + { + "left": "issue:44077", + "right": "issue:44479", + "accept": false, + "reason": "patchtsmixer post_init API rule and video-input regression affect different components." + }, + { + "left": "issue:44855", + "right": "issue:45137", + "accept": false, + "reason": "Python 3.13 import/torch.jit parsing error is unrelated to DeepSpeed ZeRO3 deque underflow." + }, + { + "left": "issue:33290", + "right": "issue:45656", + "accept": false, + "reason": "Both mention DeepSpeed, but one is OOM with AdaFactor and the other is duplicate optimizer stepping." + }, + { + "left": "issue:43316", + "right": "issue:44877", + "accept": false, + "reason": "Gemma3TextConfig API mismatch and strict config preventing granite_speech loading are different config-loading problems." + }, + { + "left": "issue:29127", + "right": "issue:33357", + "accept": false, + "reason": "LayoutLMv3 error-message clarity and CLIP bus error on macOS are unrelated." + }, + { + "left": "issue:43540", + "right": "issue:44514", + "accept": false, + "reason": "Video-input processing failure in Qwen3OmniMoe is different from batched chat-template padding crash in Qwen2_5_VLProcessor." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 27, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:25251", + "issue:28282", + "issue:33290", + "issue:34689", + "issue:35141", + "issue:36331", + "issue:41720", + "issue:41950", + "issue:42175", + "issue:42617", + "issue:43065", + "issue:43232", + "issue:43295", + "issue:43316", + "issue:43381", + "issue:43388", + "issue:43404", + "issue:43441", + "issue:43452", + "issue:43475", + "issue:43550", + "issue:43575", + "issue:43606", + "issue:43646", + "issue:43673", + "issue:43701", + "issue:43742", + "issue:43761", + "issue:43825", + "issue:43931", + "issue:44060", + "issue:44077", + "issue:44162", + "issue:44242", + "issue:44464", + "issue:44479", + "issue:44496", + "issue:44534", + "issue:44617", + "issue:44743", + "issue:44792", + "issue:44871", + "issue:44913", + "issue:44936", + "issue:45127", + "issue:45200", + "issue:45584", + "issue:45698" + ], + "soft_pairs": [ + "issue:43381|issue:43742", + "issue:42175|issue:43316", + "issue:33290|issue:34689", + "issue:43404|issue:43441", + "issue:44162|issue:44792", + "issue:25251|issue:28282", + "issue:43232|issue:43388", + "issue:43295|issue:43825", + "issue:41950|issue:43475", + "issue:44871|issue:45584", + "issue:45127|issue:45200", + "issue:43550|issue:43701", + "issue:43606|issue:43701", + "issue:43295|issue:44871", + "issue:43065|issue:44617", + "issue:33290|issue:35141", + "issue:43761|issue:44479", + "issue:33290|issue:36331", + "issue:43673|issue:44743", + "issue:44936|issue:45698", + "issue:43452|issue:44496", + "issue:43575|issue:43742", + "issue:43646|issue:44913", + "issue:42617|issue:43575", + "issue:43761|issue:44242", + "issue:41720|issue:43575", + "issue:44077|issue:44534", + "issue:43931|issue:44060", + "issue:44464|issue:44871" + ], + "prepared_review_unit_hash": "a7bbec2d8ef31a89541061c3cbd84fe5e4ea2b5e5034c6e4e7ae6c7a62bb0f85", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36313, + "estimated_input_tokens": 9079, + "estimated_eval_tokens": 18414 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These issues are broadly heterogeneous and do not collapse into one duplicate cluster. Most pairs share only a subsystem or release theme, not the same concrete bug or change, so all soft edges should be rejected.", + "confidence": 0.96, + "canonical_issue_reason": "issue:43295 is the clearest high-signal regression report in the set, but the overall cluster is too diverse for a true canonical duplicate anchor.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43295 is the best representative issue: it is concrete, reproducible, and has a well-scoped regression description. It is not a duplicate of the others.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43381", + "right": "issue:43742", + "accept": false, + "reason": "Different failures: eval-mode gradient checkpointing vs model load key error." + }, + { + "left": "issue:42175", + "right": "issue:43316", + "accept": false, + "reason": "Unrelated topics: optional backend packaging vs Gemma3 config API mismatch." + }, + { + "left": "issue:33290", + "right": "issue:34689", + "accept": false, + "reason": "Different code paths and symptoms: deepspeed/Adafactor OOM vs model loading regression." + }, + { + "left": "issue:43404", + "right": "issue:43441", + "accept": false, + "reason": "Both touch Mistral-family models, but one is tied-weights initialization and the other is FlashAttention runtime failure." + }, + { + "left": "issue:44162", + "right": "issue:44792", + "accept": false, + "reason": "Completely different models and failures: ESM2 breakage vs Janus test regression." + }, + { + "left": "issue:25251", + "right": "issue:28282", + "accept": false, + "reason": "Pipeline output shape bug vs missing PyTorch ImportError; not the same issue." + }, + { + "left": "issue:43232", + "right": "issue:43388", + "accept": false, + "reason": "Generation kwargs update after sync_gpus is unrelated to gather_for_metrics label handling." + }, + { + "left": "issue:43295", + "right": "issue:43825", + "accept": false, + "reason": "Both are v5-related pipeline regressions, but one is tokenizer/processor API breakage and the other is an error-message wording issue." + }, + { + "left": "issue:41950", + "right": "issue:43475", + "accept": false, + "reason": "Different video/SAM bugs: wrong processor lookup vs missing encoder attribute." + }, + { + "left": "issue:44871", + "right": "issue:45584", + "accept": false, + "reason": "Different generation edge cases: Gemma eos-token config mismatch vs Whisper empty-transcription failure." + }, + { + "left": "issue:45127", + "right": "issue:45200", + "accept": false, + "reason": "Unrelated model-finetuning issues: LoRA merge collapse vs Gemma4 mm token defaults." + }, + { + "left": "issue:43550", + "right": "issue:43701", + "accept": false, + "reason": "torch.compile/SDPA OOM is unrelated to resume_from_checkpoint key mismatch." + }, + { + "left": "issue:43606", + "right": "issue:43701", + "accept": false, + "reason": "CPU offload device mismatch and checkpoint key mismatch are different bugs." + }, + { + "left": "issue:43295", + "right": "issue:44871", + "accept": false, + "reason": "Both are config/regression reports, but they affect different APIs and symptoms." + }, + { + "left": "issue:43065", + "right": "issue:44617", + "accept": false, + "reason": "Dummy Conv2d placeholder issue vs SAM3 video OOM; not the same underlying bug." + }, + { + "left": "issue:33290", + "right": "issue:35141", + "accept": false, + "reason": "Optimizer OOM and embedding reinitialization are unrelated." + }, + { + "left": "issue:43761", + "right": "issue:44479", + "accept": false, + "reason": "CLIP hidden_states regression is unrelated to Qwen VL video-input regression." + }, + { + "left": "issue:33290", + "right": "issue:36331", + "accept": false, + "reason": "OOM in deepspeed/Adafactor vs Trainer signature TypeError; different layers." + }, + { + "left": "issue:43673", + "right": "issue:44743", + "accept": false, + "reason": "Both involve cache/state, but one is GenerationMixin missing cache in v5 and the other is Qwen recurrent state reset logic." + }, + { + "left": "issue:44936", + "right": "issue:45698", + "accept": false, + "reason": "Trainer evaluate-after-train failure is unrelated to loading the wrong custom module." + }, + { + "left": "issue:43452", + "right": "issue:44496", + "accept": false, + "reason": "Tokenizer/model gguf_file breakage is different from missing model_type config errors." + }, + { + "left": "issue:43575", + "right": "issue:43742", + "accept": false, + "reason": "Large-model tensor-parallel OOM is unrelated to MobileLLM load key errors." + }, + { + "left": "issue:43646", + "right": "issue:44913", + "accept": false, + "reason": "Custom model init breakage and GPTNeoX rotary_pct reload bug are different code paths." + }, + { + "left": "issue:42617", + "right": "issue:43575", + "accept": false, + "reason": "3d_parallel.py execution problem is not the same as tensor-parallel OOM on model load." + }, + { + "left": "issue:43761", + "right": "issue:44242", + "accept": false, + "reason": "Vision-model hidden-state regression is unrelated to load-balancing loss omission." + }, + { + "left": "issue:41720", + "right": "issue:43575", + "accept": false, + "reason": "cudaErrorAssert on Qwen3 auto device mapping is different from OOM during tensor-parallel loading." + }, + { + "left": "issue:44077", + "right": "issue:44534", + "accept": false, + "reason": "PatchTSMixer post_init policy and non-persistent buffer junk are separate v5 issues." + }, + { + "left": "issue:43931", + "right": "issue:44060", + "accept": false, + "reason": "Model weight shape mismatch and tied-weights warning are different loading/config problems." + }, + { + "left": "issue:44464", + "right": "issue:44871", + "accept": false, + "reason": "Compiled-forward chunked generation inconsistency is unrelated to Gemma eos_token_id configuration." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 28, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:41720", + "issue:43065", + "issue:43116", + "issue:43295", + "issue:43335", + "issue:43479", + "issue:43540", + "issue:43550", + "issue:43644", + "issue:43650", + "issue:43761", + "issue:43827", + "issue:43906", + "issue:43976", + "issue:43994", + "issue:44077", + "issue:44112", + "issue:44190", + "issue:44220", + "issue:44479", + "issue:44496", + "issue:44521", + "issue:44534", + "issue:44610", + "issue:44617", + "issue:44734", + "issue:44737", + "issue:44792", + "issue:44855", + "issue:44877", + "issue:44913", + "issue:44938", + "issue:44964", + "issue:44977", + "issue:45127", + "issue:45245", + "issue:45276", + "issue:45290", + "issue:45357", + "issue:45375", + "issue:45381", + "issue:45542", + "issue:45584", + "issue:45588", + "issue:45600", + "issue:45803", + "issue:45834" + ], + "soft_pairs": [ + "issue:44479|issue:44734", + "issue:44617|issue:45584", + "issue:43827|issue:43994", + "issue:44792|issue:44977", + "issue:43906|issue:45290", + "issue:44534|issue:44913", + "issue:43065|issue:44610", + "issue:41720|issue:45245", + "issue:44190|issue:44964", + "issue:44792|issue:45600", + "issue:44737|issue:45803", + "issue:44855|issue:45588", + "issue:44521|issue:45381", + "issue:45127|issue:45357", + "issue:44938|issue:45542", + "issue:43335|issue:44855", + "issue:43976|issue:44855", + "issue:44077|issue:44877", + "issue:43761|issue:45834", + "issue:43644|issue:44913", + "issue:44496|issue:45803", + "issue:43550|issue:44190", + "issue:43540|issue:44734", + "issue:43650|issue:44220", + "issue:45276|issue:45584", + "issue:44112|issue:45600", + "issue:43335|issue:44190", + "issue:43116|issue:44190", + "issue:43295|issue:45276", + "issue:45245|issue:45584", + "issue:43479|issue:45375" + ], + "prepared_review_unit_hash": "d86657ae7a7a68960f8125b8ca1e566d5fa972cd8857fcd10989e4a385c34f6a", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "serialized_chars": 36434, + "estimated_input_tokens": 9109, + "estimated_eval_tokens": 18474 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "No soft pair appears to describe the same underlying bug or change closely enough to merge. The set is mostly unrelated issues with some superficial overlap in subsystem keywords (e.g. multimodal, pipeline, config, CI).", + "confidence": 0.97, + "canonical_issue_reason": "issue:44521 is the strongest representative issue in the set: it is active, well-scoped, has multiple inbound references, and clearly describes a reproducible multimodal chat-template bug.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44521 is the best overall issue to keep as a representative entry because it is specific, actionable, and appears to be the most central/open problem among the listed items.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44479", + "right": "issue:44734", + "accept": false, + "reason": "Both mention video/serving behavior, but one is a multimodal video-input regression and the other is a KV-cache tensor-indexing crash in serve; different code paths and failure modes." + }, + { + "left": "issue:44617", + "right": "issue:45584", + "accept": false, + "reason": "CUDA OOM in Sam3Video is unrelated to Whisper empty-transcription generation failure after token alignment." + }, + { + "left": "issue:43827", + "right": "issue:43994", + "accept": false, + "reason": "One is documentation cleanup after pipeline removals; the other is a model/pipeline behavior bug for SigLIP2. Same word \"pipeline\" only, not same issue." + }, + { + "left": "issue:44792", + "right": "issue:44977", + "accept": false, + "reason": "Janus image-generation test failure and Qwen3.5 flash-attention generation bug are different models and different failure mechanisms." + }, + { + "left": "issue:43906", + "right": "issue:45290", + "accept": false, + "reason": "A reproduction issue for an external report is not enough to equate it with a specific apply_chat_template crash on tool-call assistant messages." + }, + { + "left": "issue:44534", + "right": "issue:44913", + "accept": false, + "reason": "Non-persistent buffer initialization junk and GPTNeoXConfig rotary_pct reload behavior are separate config/runtime bugs." + }, + { + "left": "issue:43065", + "right": "issue:44610", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder and OmDet-Turbo processor size mismatch are unrelated vision-model problems." + }, + { + "left": "issue:41720", + "right": "issue:45245", + "accept": false, + "reason": "Qwen3 auto device-map cudaErrorAssert and category-count limit 2^24 are different errors with no shared code path." + }, + { + "left": "issue:44190", + "right": "issue:44964", + "accept": false, + "reason": "Local dataset loading in an example script and loading a Phi-4 multimodal model are unrelated failure reports." + }, + { + "left": "issue:44792", + "right": "issue:45600", + "accept": false, + "reason": "A Janus generation test and stale auto_mappings references for Sam3LiteText are different subsystems and different bugs." + }, + { + "left": "issue:44737", + "right": "issue:45803", + "accept": false, + "reason": "CPU device placement bug in XLNet relative positions is unrelated to a bare except swallowing errors in Fuyu tensor conversion." + }, + { + "left": "issue:44855", + "right": "issue:45588", + "accept": false, + "reason": "Python 3.13 import parsing failure in DebertaV2 and flash-attention sink-less crash are unrelated." + }, + { + "left": "issue:44521", + "right": "issue:45381", + "accept": false, + "reason": "assistant_masks being all-zero for multimodal inputs is not the same concrete bug as wrong vision_position_ids in qwen2.5-vl video input handling." + }, + { + "left": "issue:45127", + "right": "issue:45357", + "accept": false, + "reason": "LoRA merge collapse with extended vocab and incorrect visual encoder keys on save_pretrained are different Qwen-related issues, not the same bug." + }, + { + "left": "issue:44938", + "right": "issue:45542", + "accept": false, + "reason": "Python 3.14 import/load failure and tensorboard-only TensorFlow backend error are unrelated environment/package issues." + }, + { + "left": "issue:43335", + "right": "issue:44855", + "accept": false, + "reason": "SwitchTransformers sparse-layer construction and DebertaV2 import parsing are unrelated." + }, + { + "left": "issue:43976", + "right": "issue:44855", + "accept": false, + "reason": "Python-version compatibility regression and a JIT/decorator parsing issue are not the same defect." + }, + { + "left": "issue:44077", + "right": "issue:44877", + "accept": false, + "reason": "Optional post_init in patchtsmixer config and strict config blocking granite_speech loading are different config-validation problems." + }, + { + "left": "issue:43761", + "right": "issue:45834", + "accept": false, + "reason": "CLIPVisionModel hidden_states regression and Kosmos2.5 long-OCR index error are unrelated model bugs." + }, + { + "left": "issue:43644", + "right": "issue:44913", + "accept": false, + "reason": "Non-persistent buffers filled with junk and GPTNeoX rotary_pct reset on reload are different failure classes." + }, + { + "left": "issue:44496", + "right": "issue:45803", + "accept": false, + "reason": "Unrecognized model_type for a specific model repo and a bare except in Fuyu tensor conversion are unrelated." + }, + { + "left": "issue:43550", + "right": "issue:44190", + "accept": false, + "reason": "torch.compile/SDPA failure in Bamba and dataset loading in an example script are not the same underlying issue." + }, + { + "left": "issue:43540", + "right": "issue:44734", + "accept": false, + "reason": "Qwen3OmniMoe video-input ValueError and serve KV-cache continuation indexing crash affect different paths and models." + }, + { + "left": "issue:43650", + "right": "issue:44220", + "accept": false, + "reason": "Generic placeholder issue and an fbank feature extraction bug are unrelated." + }, + { + "left": "issue:45276", + "right": "issue:45584", + "accept": false, + "reason": "Gemma4 embedding resize mismatch and Whisper empty-transcription generation failure are different model-specific bugs." + }, + { + "left": "issue:44112", + "right": "issue:45600", + "accept": false, + "reason": "A stale GraniteSpeech CI test and broken auto_mappings references for removed Sam3LiteText configs are different CI failures." + }, + { + "left": "issue:43335", + "right": "issue:44190", + "accept": false, + "reason": "SwitchTransformers config bug and image-classification example local dataset loading bug are unrelated." + }, + { + "left": "issue:43116", + "right": "issue:44190", + "accept": false, + "reason": "Text classification example always empty results and image classification local dataset loading are different example-script issues." + }, + { + "left": "issue:43295", + "right": "issue:45276", + "accept": false, + "reason": "Processor/tokenizer API regression and Gemma4 embedding resize behavior do not describe the same code path." + }, + { + "left": "issue:45245", + "right": "issue:45584", + "accept": false, + "reason": "Category-count limit RuntimeError and Whisper empty transcription failure are unrelated." + }, + { + "left": "issue:43479", + "right": "issue:45375", + "accept": false, + "reason": "Incorrect default config initialization when None is passed and missing deepstack_visual_indexes in strict config are separate config bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 29, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:36246", + "issue:38175", + "issue:38617", + "issue:41628", + "issue:41950", + "issue:42175", + "issue:42907", + "issue:43065", + "issue:43295", + "issue:43299", + "issue:43388", + "issue:43404", + "issue:43441", + "issue:43526", + "issue:43531", + "issue:43643", + "issue:43673", + "issue:43688", + "issue:43854", + "issue:43901", + "issue:44016", + "issue:44112", + "issue:44186", + "issue:44220", + "issue:44246", + "issue:44279", + "issue:44336", + "issue:44464", + "issue:44466", + "issue:44496", + "issue:44561", + "issue:44683", + "issue:44734", + "issue:44913", + "issue:44933", + "issue:44964", + "issue:45003", + "issue:45042", + "issue:45216", + "issue:45335", + "issue:45362", + "issue:45406", + "issue:45446", + "issue:45563", + "issue:45584", + "issue:45600", + "issue:45632" + ], + "soft_pairs": [ + "issue:36246|issue:41628", + "issue:44933|issue:45362", + "issue:44464|issue:45563", + "issue:43404|issue:45216", + "issue:44186|issue:44734", + "issue:44734|issue:45632", + "issue:44683|issue:45446", + "issue:44561|issue:45632", + "issue:44466|issue:44913", + "issue:38175|issue:43065", + "issue:44246|issue:45003", + "issue:36246|issue:38617", + "issue:43643|issue:44496", + "issue:45406|issue:45632", + "issue:45563|issue:45584", + "issue:41950|issue:44016", + "issue:44964|issue:45600", + "issue:43388|issue:43688", + "issue:42907|issue:43441", + "issue:44112|issue:44964", + "issue:43295|issue:45335", + "issue:43854|issue:44964", + "issue:44016|issue:44220", + "issue:44496|issue:45042", + "issue:43673|issue:44336", + "issue:43299|issue:45216", + "issue:43531|issue:45600", + "issue:43526|issue:43901", + "issue:42175|issue:44279", + "issue:45335|issue:45584" + ], + "prepared_review_unit_hash": "6a20e8f7a6092f273e5bc0e4614408b970ec4f9920a9526b7badeea82762cac1", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36122, + "estimated_input_tokens": 9031, + "estimated_eval_tokens": 18318 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is heterogeneous: the soft-similar pairs mostly share broad keywords (imports, generation, model loading, save/load, vision, trust_remote_code) but not the same concrete bug or fix. I would not merge any of the suggested pairs as duplicates.", + "confidence": 0.94, + "canonical_issue_reason": "issue:41628 is the cleanest broad user-facing import regression in the set, but there is no true duplicate cluster here.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:41628 is the best overall anchor if one must pick a representative, though it still does not subsume the other reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36246", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but for different missing symbols and different code paths; not the same bug." + }, + { + "left": "issue:44933", + "right": "issue:45362", + "accept": false, + "reason": "Different failures: missing image-utils import vs Qwen3.5 chat crash." + }, + { + "left": "issue:44464", + "right": "issue:45563", + "accept": false, + "reason": "One is a generation correctness bug, the other a stale warning; not the same change." + }, + { + "left": "issue:43404", + "right": "issue:45216", + "accept": false, + "reason": "Both involve tied weights/serialization, but they are different models and different failure modes." + }, + { + "left": "issue:44186", + "right": "issue:44734", + "accept": false, + "reason": "Tokenizer padding/NER crash versus serve KV-cache indexing crash; unrelated code paths." + }, + { + "left": "issue:44734", + "right": "issue:45632", + "accept": false, + "reason": "Serve cache indexing bug and trust_remote_code cache-path collision are separate problems." + }, + { + "left": "issue:44683", + "right": "issue:45446", + "accept": false, + "reason": "Both touch flex_attention, but one is a runtime failure on torch 2.9 and the other is a version-check/import issue." + }, + { + "left": "issue:44561", + "right": "issue:45632", + "accept": false, + "reason": "Different trust_remote_code/cache behaviors; not the same defect." + }, + { + "left": "issue:44466", + "right": "issue:44913", + "accept": false, + "reason": "Serialization of tied weights and GPTNeoX config reload are unrelated bugs." + }, + { + "left": "issue:38175", + "right": "issue:43065", + "accept": false, + "reason": "Different vision-model issues with no shared concrete failure path." + }, + { + "left": "issue:44246", + "right": "issue:45003", + "accept": false, + "reason": "Import slowness is a performance issue; unsafe sys.modules access is a different implementation bug." + }, + { + "left": "issue:36246", + "right": "issue:38617", + "accept": false, + "reason": "Both are ImportErrors, but for different missing APIs and modules." + }, + { + "left": "issue:43643", + "right": "issue:44496", + "accept": false, + "reason": "One is missing fields when using trust_remote_code; the other is a missing model_type in config." + }, + { + "left": "issue:45406", + "right": "issue:45632", + "accept": false, + "reason": "Gemma4Processor _tokenizer crash is unrelated to the local-model cache-path collision." + }, + { + "left": "issue:45563", + "right": "issue:45584", + "accept": false, + "reason": "A stale warning and an empty-transcription generation failure are not the same bug." + }, + { + "left": "issue:41950", + "right": "issue:44016", + "accept": false, + "reason": "Pipeline image-processor lookup bug versus a notebook syntax error." + }, + { + "left": "issue:44964", + "right": "issue:45600", + "accept": false, + "reason": "Model-loading regression and auto_mappings CI breakage are separate issues." + }, + { + "left": "issue:43388", + "right": "issue:43688", + "accept": false, + "reason": "Different training/evaluation bugs: dropped labels versus auxiliary-loss normalization." + }, + { + "left": "issue:42907", + "right": "issue:43441", + "accept": false, + "reason": "Saving dequantized checkpoints and FlashAttention load failure are different model-specific regressions." + }, + { + "left": "issue:44112", + "right": "issue:44964", + "accept": false, + "reason": "CI stale-test failure is unrelated to Phi-4 multimodal loading." + }, + { + "left": "issue:43295", + "right": "issue:45335", + "accept": false, + "reason": "Processor/tokenizer regression and t5gemma embedding resize bug are distinct code paths." + }, + { + "left": "issue:43854", + "right": "issue:44964", + "accept": false, + "reason": "Both are model-loading problems, but for different models and different root causes." + }, + { + "left": "issue:44016", + "right": "issue:44220", + "accept": false, + "reason": "Notebook syntax error versus audio feature extraction bug." + }, + { + "left": "issue:44496", + "right": "issue:45042", + "accept": false, + "reason": "Unrecognized model config and PIL/torchvision dependency regression are unrelated." + }, + { + "left": "issue:43673", + "right": "issue:44336", + "accept": false, + "reason": "Generation cache regression and ANSI logging output issue are unrelated." + }, + { + "left": "issue:43299", + "right": "issue:45216", + "accept": false, + "reason": "Different Qwen-related regressions: model loading versus save_pretrained checkpoint correctness." + }, + { + "left": "issue:43531", + "right": "issue:45600", + "accept": false, + "reason": "Sliding-window behavior in Qwen3-MoE and removed Sam3LiteText configs are unrelated." + }, + { + "left": "issue:43526", + "right": "issue:43901", + "accept": false, + "reason": "Image processor label reduction bug versus documentation mismatch." + }, + { + "left": "issue:42175", + "right": "issue:44279", + "accept": false, + "reason": "Dependency/package-install issue and vague dependency issue are not the same concrete bug." + }, + { + "left": "issue:45335", + "right": "issue:45584", + "accept": false, + "reason": "Decoder embedding resize bug and Whisper empty-transcription failure are separate." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 30, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:32090", + "issue:35141", + "issue:38175", + "issue:39692", + "issue:41950", + "issue:43295", + "issue:43299", + "issue:43381", + "issue:43388", + "issue:43441", + "issue:43479", + "issue:43525", + "issue:43577", + "issue:43650", + "issue:43824", + "issue:43827", + "issue:43854", + "issue:43901", + "issue:43976", + "issue:44016", + "issue:44062", + "issue:44075", + "issue:44242", + "issue:44279", + "issue:44297", + "issue:44351", + "issue:44368", + "issue:44462", + "issue:44496", + "issue:44617", + "issue:44683", + "issue:44779", + "issue:44933", + "issue:44987", + "issue:45020", + "issue:45081", + "issue:45200", + "issue:45216", + "issue:45278", + "issue:45357", + "issue:45405", + "issue:45542", + "issue:45593", + "issue:45600", + "issue:45712", + "issue:45759", + "issue:45823", + "issue:45834" + ], + "soft_pairs": [ + "issue:44075|issue:44368", + "issue:43381|issue:45593", + "issue:43299|issue:45357", + "issue:44496|issue:45759", + "issue:43901|issue:44496", + "issue:44351|issue:45278", + "issue:44242|issue:45200", + "issue:44016|issue:44062", + "issue:43388|issue:43827", + "issue:43976|issue:45405", + "issue:41950|issue:45020", + "issue:43479|issue:43525", + "issue:43577|issue:45216", + "issue:43824|issue:44933", + "issue:41950|issue:45823", + "issue:44683|issue:45542", + "issue:43299|issue:43854", + "issue:44279|issue:45405", + "issue:39692|issue:43901", + "issue:38175|issue:44617", + "issue:32090|issue:35141", + "issue:44462|issue:45081", + "issue:41950|issue:43650", + "issue:43295|issue:44779", + "issue:44297|issue:44462", + "issue:43976|issue:44279", + "issue:45600|issue:45712", + "issue:43976|issue:44987", + "issue:43441|issue:45834" + ], + "prepared_review_unit_hash": "c95be6db3523bd269f3dbd828c872f44040358db89e5f490f1db6d3b8020674d", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36498, + "estimated_input_tokens": 9125, + "estimated_eval_tokens": 18506 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These issues are mostly broad Transformers regressions and docs/model-loading bugs, but the soft pairs do not describe the same underlying defect closely enough to merge as duplicates. I would treat this cluster as largely non-duplicate and keep a broad umbrella issue only as a loose organizer, not a canonical duplicate.", + "confidence": 0.91, + "canonical_issue_reason": "issue:45020 is the broadest representative report in the set, covering recent-version breakage for remote-code models. It is the best umbrella candidate, though it is not a true duplicate of the others.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45020 is the most general user-facing regression report and can serve as the cluster\u2019s loose anchor.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44075", + "right": "issue:44368", + "accept": false, + "reason": "Different bugs: unused SGD args vs a tie_word_embeddings warning during Qwen3.5 LoRA fine-tuning." + }, + { + "left": "issue:43381", + "right": "issue:45593", + "accept": false, + "reason": "Different code paths: gradient checkpointing in eval mode vs D-FINE auxiliary losses with denoising disabled." + }, + { + "left": "issue:43299", + "right": "issue:45357", + "accept": false, + "reason": "Both are Qwen-related, but one is a model-loading regression and the other is a save_pretrained serialization bug." + }, + { + "left": "issue:44496", + "right": "issue:45759", + "accept": false, + "reason": "Different problems: tokenizer file selection vs from_config unwrapping of composite multimodal configs." + }, + { + "left": "issue:43901", + "right": "issue:44496", + "accept": false, + "reason": "Docs mismatch for return_all_scores is unrelated to tokenizer loading behavior." + }, + { + "left": "issue:44351", + "right": "issue:45278", + "accept": false, + "reason": "Both mention imports, but one is a specific missing symbol and the other is a broad post-upgrade import breakage report." + }, + { + "left": "issue:44242", + "right": "issue:45200", + "accept": false, + "reason": "Unrelated training-loss bug vs Gemma 4 text-only fine-tuning token-type defaulting." + }, + { + "left": "issue:44016", + "right": "issue:44062", + "accept": false, + "reason": "Notebook syntax error and AddedToken argument handling are separate failures." + }, + { + "left": "issue:43388", + "right": "issue:43827", + "accept": false, + "reason": "Metric gathering drops tuple labels; docs still referencing pipeline() is a separate documentation issue." + }, + { + "left": "issue:43976", + "right": "issue:45405", + "accept": false, + "reason": "Python compatibility issue vs unreleased dependency bump; not the same defect." + }, + { + "left": "issue:41950", + "right": "issue:45020", + "accept": false, + "reason": "Video-classification processor lookup is a pipeline-specific bug, not the remote_code regression described in 45020." + }, + { + "left": "issue:43479", + "right": "issue:43525", + "accept": false, + "reason": "Different config initialization/attribute bugs in unrelated model classes." + }, + { + "left": "issue:43577", + "right": "issue:45216", + "accept": false, + "reason": "BLIP2 dtype loading issue vs Qwen3.5 save_pretrained regression are distinct." + }, + { + "left": "issue:43824", + "right": "issue:44933", + "accept": false, + "reason": "Different missing-import problems affecting different modules/symbols." + }, + { + "left": "issue:41950", + "right": "issue:45823", + "accept": false, + "reason": "Pipeline processor lookup and Gemma4 PLE device mismatch are unrelated issues." + }, + { + "left": "issue:44683", + "right": "issue:45542", + "accept": false, + "reason": "Compiled flex_attention on torch>=2.9 is unrelated to the tensorboard/tensorflow backend issue." + }, + { + "left": "issue:43299", + "right": "issue:43854", + "accept": false, + "reason": "Both are model-loading failures, but they involve different models and failure modes." + }, + { + "left": "issue:44279", + "right": "issue:45405", + "accept": false, + "reason": "Generic dependency issue vs PEFT version floor bump; no shared underlying bug." + }, + { + "left": "issue:39692", + "right": "issue:43901", + "accept": false, + "reason": "Doc example errors for SigLIP2 are unrelated to text-classification pipeline docs." + }, + { + "left": "issue:38175", + "right": "issue:44617", + "accept": false, + "reason": "Unexpected probabilities in SigLIP2 is unrelated to Sam3Video OOM." + }, + { + "left": "issue:32090", + "right": "issue:35141", + "accept": false, + "reason": "Trainer GPU broadcast TypeError and embedding reinitialization after resize are different bugs." + }, + { + "left": "issue:44462", + "right": "issue:45081", + "accept": false, + "reason": "AutoTokenizer ignoring tokenizer.json and Mistral regex patch failing on backend_tokenizer are separate tokenizer-loading defects." + }, + { + "left": "issue:41950", + "right": "issue:43650", + "accept": false, + "reason": "A real pipeline bug vs a non-informative issue title; no duplicate evidence." + }, + { + "left": "issue:43295", + "right": "issue:44779", + "accept": false, + "reason": "Custom model code regression around processor.tokenizer/images-to-tokenizer differs from Deepseek tokenizer incorrect results." + }, + { + "left": "issue:44297", + "right": "issue:44462", + "accept": false, + "reason": "Tokenizer class metadata written on save vs AutoTokenizer ignoring tokenizer.json are related to tokenizers but not the same bug." + }, + { + "left": "issue:45600", + "right": "issue:45712", + "accept": false, + "reason": "Stale auto_mappings entries and leftover dummy classes are separate cleanup/CI failures." + }, + { + "left": "issue:43976", + "right": "issue:44987", + "accept": false, + "reason": "Python/dependency compatibility vs loading a specific model under 5.1.0 are not the same underlying issue." + }, + { + "left": "issue:43441", + "right": "issue:45834", + "accept": false, + "reason": "FlashAttention compatibility for Ministral-3 and an OCR index error in Kosmos2.5 are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 31, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:42491", + "issue:42994", + "issue:43065", + "issue:43122", + "issue:43262", + "issue:43299", + "issue:43317", + "issue:43441", + "issue:43450", + "issue:43525", + "issue:43643", + "issue:43650", + "issue:43653", + "issue:43673", + "issue:43723", + "issue:43761", + "issue:43784", + "issue:43881", + "issue:43901", + "issue:43994", + "issue:44016", + "issue:44162", + "issue:44188", + "issue:44261", + "issue:44263", + "issue:44279", + "issue:44291", + "issue:44297", + "issue:44336", + "issue:44361", + "issue:44462", + "issue:44466", + "issue:44521", + "issue:44617", + "issue:44623", + "issue:44671", + "issue:44683", + "issue:44749", + "issue:44779", + "issue:44898", + "issue:44987", + "issue:45276", + "issue:45290", + "issue:45325", + "issue:45397", + "issue:45542", + "issue:45593", + "issue:45823" + ], + "soft_pairs": [ + "issue:44521|issue:45325", + "issue:44462|issue:44779", + "issue:43450|issue:44279", + "issue:42994|issue:43317", + "issue:44261|issue:44263", + "issue:44466|issue:45276", + "issue:43065|issue:44898", + "issue:43441|issue:44683", + "issue:43650|issue:45290", + "issue:43723|issue:44162", + "issue:44623|issue:44749", + "issue:44623|issue:45397", + "issue:43653|issue:45593", + "issue:44671|issue:44779", + "issue:43784|issue:45542", + "issue:44016|issue:45823", + "issue:44987|issue:45542", + "issue:44361|issue:45593", + "issue:43901|issue:43994", + "issue:43122|issue:43650", + "issue:44016|issue:44291", + "issue:43262|issue:44521", + "issue:43673|issue:43761", + "issue:43525|issue:43881", + "issue:44188|issue:44336", + "issue:43525|issue:43643", + "issue:44297|issue:45397", + "issue:43450|issue:44617", + "issue:42491|issue:43299" + ], + "prepared_review_unit_hash": "1d7de83c187260c67fbbce4bad31886ef6cae4041632796c8d7732532ed2c8fc", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36286, + "estimated_input_tokens": 9072, + "estimated_eval_tokens": 18400 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is heterogeneous, and none of the soft pairs look like true duplicates. The closest shared theme is a family of v5/Qwen3-MoE loading regressions, but the candidate pairs still differ in concrete code path and symptom.", + "confidence": 0.43, + "canonical_issue_reason": "issue:43299 is the clearest standalone regression report: it pins the breakage to v5.0.0.dev0 and a specific Qwen3VL MoE loading path, making it the best canonical issue target among the set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43299 is the strongest representative issue: specific version regression, clear failure mode, and a concrete model-loading path that is likely to attract related reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44521", + "right": "issue:45325", + "accept": false, + "reason": "Different bugs: multimodal assistant masks are all zero vs still-image temporal position scaling in Qwen2.5-VL." + }, + { + "left": "issue:44462", + "right": "issue:44779", + "accept": false, + "reason": "AutoTokenizer ignoring tokenizer.json is a loading bug; Deepseek tokenizer incorrect results is a tokenizer behavior bug." + }, + { + "left": "issue:43450", + "right": "issue:44279", + "accept": false, + "reason": "Video batched-shape bug and a generic dependency issue are unrelated failure modes." + }, + { + "left": "issue:42994", + "right": "issue:43317", + "accept": false, + "reason": "Quantized model saving failure is not the same as dequantized model loading with gpu+cpu offload." + }, + { + "left": "issue:44261", + "right": "issue:44263", + "accept": false, + "reason": "MLA q_a_layernorm epsilon precision issue is unrelated to torch.split return values in GlmMoeDsaIndexer." + }, + { + "left": "issue:44466", + "right": "issue:45276", + "accept": false, + "reason": "lm_head.weight serialization inconsistency and Gemma4 embedding resize propagation are different bugs." + }, + { + "left": "issue:43065", + "right": "issue:44898", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder and Perceiver non-default-resolution failure are different model-path issues." + }, + { + "left": "issue:43441", + "right": "issue:44683", + "accept": false, + "reason": "Both mention attention, but one is Ministral-3 FlashAttention compatibility and the other is compiled flex_attention on torch>=2.9." + }, + { + "left": "issue:43650", + "right": "issue:45290", + "accept": false, + "reason": "The placeholder title issue is unrelated to apply_chat_template crashing on tool-call messages without content." + }, + { + "left": "issue:43723", + "right": "issue:44162", + "accept": false, + "reason": "Tokenizer loading in v5 and ESM2 model breakage are different subsystems and symptoms." + }, + { + "left": "issue:44623", + "right": "issue:44749", + "accept": false, + "reason": "Missing files on processor.save_pretrained and slower filtering after upgrade are unrelated." + }, + { + "left": "issue:44623", + "right": "issue:45397", + "accept": false, + "reason": "processor.save_pretrained missing files is not the same as gemma-4 zero3 from_pretrained failure." + }, + { + "left": "issue:43653", + "right": "issue:45593", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and D-FINE auxiliary-loss behavior are unrelated." + }, + { + "left": "issue:44671", + "right": "issue:44779", + "accept": false, + "reason": "CamemBERT masked-LM prediction errors and Deepseek tokenizer errors are different model families and bugs." + }, + { + "left": "issue:43784", + "right": "issue:45542", + "accept": false, + "reason": "Import-time NameError in sentence-transformers and a TensorBoard/TensorFlow backend issue are different dependency failures." + }, + { + "left": "issue:44016", + "right": "issue:45823", + "accept": false, + "reason": "Notebook syntax error and Gemma4 device-mismatch forward bug do not share a concrete code path." + }, + { + "left": "issue:44987", + "right": "issue:45542", + "accept": false, + "reason": "Loading physical-intelligence/fast on transformers>=5.1 and undefined tf backend are unrelated." + }, + { + "left": "issue:44361", + "right": "issue:45593", + "accept": false, + "reason": "MLukeTokenizer task AttributeError and D-FINE loss handling are different areas." + }, + { + "left": "issue:43901", + "right": "issue:43994", + "accept": false, + "reason": "Docs mismatch for return_all_scores is unrelated to SigLIP2 producing nonsensical outputs." + }, + { + "left": "issue:43122", + "right": "issue:43650", + "accept": false, + "reason": "Tokenizer version drift and the unrelated placeholder issue are not duplicates." + }, + { + "left": "issue:44016", + "right": "issue:44291", + "accept": false, + "reason": "Notebook syntax error is unrelated to init_empty_weights receiving an unexpected argument." + }, + { + "left": "issue:43262", + "right": "issue:44521", + "accept": false, + "reason": "Both involve chat templates, but one is audio sampling-rate defaults and the other is multimodal assistant masks." + }, + { + "left": "issue:43673", + "right": "issue:43761", + "accept": false, + "reason": "Chunked-prefill cache missing and CLIPVisionModel hidden_states omission are different code paths." + }, + { + "left": "issue:43525", + "right": "issue:43881", + "accept": false, + "reason": "Missing pad_token_id on Llama4Config and glm-4v-9b loading failure are not the same bug." + }, + { + "left": "issue:43525", + "right": "issue:43643", + "accept": false, + "reason": "A missing config attribute on Llama4Config is not the same as trust_remote_code returning incomplete AutoConfig fields." + }, + { + "left": "issue:44297", + "right": "issue:45397", + "accept": false, + "reason": "Tokenizer save metadata mismatch and gemma-4 zero3 loading failure are unrelated." + }, + { + "left": "issue:43450", + "right": "issue:44617", + "accept": false, + "reason": "Incorrect batched video shapes and CUDA OOM in Sam3Video are different failure modes." + }, + { + "left": "issue:42491", + "right": "issue:43299", + "accept": false, + "reason": "They are related by Qwen3/MoE loading regression themes, but the concrete failures differ enough that they should not be merged as duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 32, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:16998", + "issue:22355", + "issue:36246", + "issue:41628", + "issue:41950", + "issue:42757", + "issue:43232", + "issue:43352", + "issue:43526", + "issue:43596", + "issue:43673", + "issue:43824", + "issue:43901", + "issue:43976", + "issue:44162", + "issue:44220", + "issue:44242", + "issue:44246", + "issue:44295", + "issue:44336", + "issue:44351", + "issue:44373", + "issue:44485", + "issue:44496", + "issue:44561", + "issue:44589", + "issue:44749", + "issue:44779", + "issue:44857", + "issue:44871", + "issue:44877", + "issue:44964", + "issue:44987", + "issue:45003", + "issue:45200", + "issue:45250", + "issue:45292", + "issue:45362", + "issue:45375", + "issue:45397", + "issue:45459", + "issue:45561", + "issue:45563", + "issue:45584", + "issue:45593", + "issue:45701", + "issue:45759" + ], + "soft_pairs": [ + "issue:44589|issue:45362", + "issue:41628|issue:43976", + "issue:43901|issue:44246", + "issue:44336|issue:44373", + "issue:44242|issue:45593", + "issue:43352|issue:45250", + "issue:16998|issue:22355", + "issue:44295|issue:45397", + "issue:44246|issue:44496", + "issue:41950|issue:44220", + "issue:36246|issue:42757", + "issue:36246|issue:44351", + "issue:44336|issue:44485", + "issue:43673|issue:44561", + "issue:43824|issue:43976", + "issue:43976|issue:44964", + "issue:44246|issue:44871", + "issue:44242|issue:44857", + "issue:45362|issue:45375", + "issue:44162|issue:45200", + "issue:44779|issue:45292", + "issue:44295|issue:44749", + "issue:44877|issue:45375", + "issue:45292|issue:45584", + "issue:45292|issue:45701", + "issue:45561|issue:45563", + "issue:44987|issue:45459", + "issue:43901|issue:45003", + "issue:45375|issue:45759", + "issue:43232|issue:44336", + "issue:36246|issue:43596", + "issue:43526|issue:45003", + "issue:44496|issue:45003" + ], + "prepared_review_unit_hash": "c4de05efbd22b3d964970fcb88b14b0001fe82faee546258bd16421f41eaad00", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 33, + "serialized_chars": 36703, + "estimated_input_tokens": 9176, + "estimated_eval_tokens": 18608 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab bag of unrelated Transformers bug reports, with a few surface-level overlaps around imports, configs, generation, and model-specific regressions. None of the soft edges look like true duplicates of the same underlying fix.", + "confidence": 0.86, + "canonical_issue_reason": "issue:43824 is the clearest representative of the recurring top-level import/export regression theme and has the strongest user impact/engagement among the import-error reports.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43824 is the best single issue to anchor the cluster because it is concrete, high-signal, and broadly representative of the import failure complaints.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44589", + "right": "issue:45362", + "accept": false, + "reason": "Different failures: Float8 storage lookup vs a Qwen chat runtime crash." + }, + { + "left": "issue:41628", + "right": "issue:43976", + "accept": false, + "reason": "ImportError for AutoImageProcessor is unrelated to the Python-version compatibility regression." + }, + { + "left": "issue:43901", + "right": "issue:44246", + "accept": false, + "reason": "Docs mismatch for return_all_scores is not the same as intermittent slow imports." + }, + { + "left": "issue:44336", + "right": "issue:44373", + "accept": false, + "reason": "ANSI output bug and docstring typo are unrelated." + }, + { + "left": "issue:44242", + "right": "issue:45593", + "accept": false, + "reason": "Both mention losses, but they are different model-specific loss bugs." + }, + { + "left": "issue:43352", + "right": "issue:45250", + "accept": false, + "reason": "General Flash Attention support complaint vs a specific model limitation." + }, + { + "left": "issue:16998", + "right": "issue:22355", + "accept": false, + "reason": "Model_max_length question is unrelated to missing transformers.onnx." + }, + { + "left": "issue:44295", + "right": "issue:45397", + "accept": false, + "reason": "position_ids buffer access bug is unrelated to ZeRO-3 from_pretrained loading." + }, + { + "left": "issue:44246", + "right": "issue:44496", + "accept": false, + "reason": "Slow import and unrecognized model config are different root causes." + }, + { + "left": "issue:41950", + "right": "issue:44220", + "accept": false, + "reason": "Video pipeline image-processor lookup is unrelated to _torch_extract_fbank_features." + }, + { + "left": "issue:36246", + "right": "issue:42757", + "accept": false, + "reason": "Different missing imports in different modules." + }, + { + "left": "issue:36246", + "right": "issue:44351", + "accept": false, + "reason": "Qwen2_5_VL export issue is distinct from HybridCache import failure." + }, + { + "left": "issue:44336", + "right": "issue:44485", + "accept": false, + "reason": "Loading-report ANSI codes and GLM-5 RoPE implementation are unrelated." + }, + { + "left": "issue:43673", + "right": "issue:44561", + "accept": false, + "reason": "Generation cache regression is not the same as the removed helper breaking trust_remote_code models." + }, + { + "left": "issue:43824", + "right": "issue:43976", + "accept": false, + "reason": "Missing exported symbol and Python support regression are different issues." + }, + { + "left": "issue:43976", + "right": "issue:44964", + "accept": false, + "reason": "Python 3.9+ incompatibility is unrelated to loading a specific multimodal model." + }, + { + "left": "issue:44246", + "right": "issue:44871", + "accept": false, + "reason": "Import slowness and eos_token_id config inconsistency are unrelated." + }, + { + "left": "issue:44242", + "right": "issue:44857", + "accept": false, + "reason": "Load-balancing loss omission is not the same as the float16 AMP crash." + }, + { + "left": "issue:45362", + "right": "issue:45375", + "accept": false, + "reason": "Qwen chat crash and missing config field are different bugs." + }, + { + "left": "issue:44162", + "right": "issue:45200", + "accept": false, + "reason": "ESM2 breakage and Gemma 4 token-type defaulting are unrelated." + }, + { + "left": "issue:44779", + "right": "issue:45292", + "accept": false, + "reason": "Tokenizer regression and resize_token_embeddings output mismatch are different code paths." + }, + { + "left": "issue:44295", + "right": "issue:44749", + "accept": false, + "reason": "IndexError on position_ids is unrelated to the post-upgrade filtering slowdown." + }, + { + "left": "issue:44877", + "right": "issue:45375", + "accept": false, + "reason": "Strict granite_speech config loading and missing Qwen deepstack fields are different models/issues." + }, + { + "left": "issue:45292", + "right": "issue:45584", + "accept": false, + "reason": "Embedding resize bug is unrelated to Whisper empty-transcription generation failure." + }, + { + "left": "issue:45292", + "right": "issue:45701", + "accept": false, + "reason": "Embedding resize bug is unrelated to tokenizer changes across versions." + }, + { + "left": "issue:45561", + "right": "issue:45563", + "accept": false, + "reason": "pytest-xdist race on captured_info.txt is unrelated to a stale generation warning." + }, + { + "left": "issue:44987", + "right": "issue:45459", + "accept": false, + "reason": "Model-loading failure and tokenizer error masking are different problems." + }, + { + "left": "issue:43901", + "right": "issue:45003", + "accept": false, + "reason": "A docs issue is not the same as unsafe sys.modules access in modeling_utils." + }, + { + "left": "issue:45375", + "right": "issue:45759", + "accept": false, + "reason": "Missing config field and text_config unwrapping are different multimodal/model-loading bugs." + }, + { + "left": "issue:43232", + "right": "issue:44336", + "accept": false, + "reason": "Generation kwargs handling and ANSI report output are unrelated." + }, + { + "left": "issue:36246", + "right": "issue:43596", + "accept": false, + "reason": "Missing Qwen export and deepspeed/BertModel IndexError are unrelated." + }, + { + "left": "issue:43526", + "right": "issue:45003", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug is unrelated to sys.modules access." + }, + { + "left": "issue:44496", + "right": "issue:45003", + "accept": false, + "reason": "Unrecognized model config is unrelated to unsafe sys.modules access." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 33, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:28282", + "issue:30990", + "issue:42886", + "issue:42994", + "issue:43065", + "issue:43232", + "issue:43257", + "issue:43262", + "issue:43408", + "issue:43452", + "issue:43475", + "issue:43482", + "issue:43540", + "issue:43643", + "issue:43646", + "issue:43653", + "issue:43673", + "issue:43827", + "issue:43931", + "issue:44060", + "issue:44077", + "issue:44162", + "issue:44246", + "issue:44297", + "issue:44361", + "issue:44368", + "issue:44466", + "issue:44623", + "issue:44734", + "issue:44749", + "issue:44869", + "issue:44933", + "issue:44977", + "issue:44995", + "issue:45003", + "issue:45137", + "issue:45200", + "issue:45229", + "issue:45310", + "issue:45335", + "issue:45356", + "issue:45397", + "issue:45459", + "issue:45561", + "issue:45563", + "issue:45588", + "issue:45600", + "issue:45656" + ], + "soft_pairs": [ + "issue:43257|issue:45137", + "issue:43065|issue:43408", + "issue:44995|issue:45200", + "issue:43262|issue:44246", + "issue:42886|issue:45229", + "issue:43475|issue:43540", + "issue:44466|issue:45335", + "issue:44995|issue:45588", + "issue:43653|issue:44162", + "issue:44368|issue:44977", + "issue:44368|issue:45563", + "issue:45397|issue:45656", + "issue:44060|issue:44077", + "issue:45003|issue:45561", + "issue:43673|issue:44734", + "issue:45137|issue:45600", + "issue:43931|issue:44368", + "issue:44869|issue:45356", + "issue:44933|issue:45459", + "issue:44297|issue:44623", + "issue:43646|issue:44162", + "issue:43232|issue:43673", + "issue:44361|issue:44749", + "issue:43673|issue:43827", + "issue:43452|issue:45003", + "issue:28282|issue:30990", + "issue:44623|issue:45656", + "issue:42994|issue:43482", + "issue:43475|issue:43643", + "issue:44749|issue:45310" + ], + "prepared_review_unit_hash": "cd2b6cc462cd565efdae892a81ea1645a257fed9036e8e0e29dba8156e43951e", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36631, + "estimated_input_tokens": 9158, + "estimated_eval_tokens": 18572 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is a loose collection of unrelated Transformers bug reports, mostly one-off regressions across different subsystems. The soft pairs are only superficially similar by broad topic and do not look like the same underlying bug/change.", + "confidence": 0.93, + "canonical_issue_reason": "issue:44466 is the best representative if one must choose: it describes a concrete, broadly impactful v5 regression around tied-weight serialization, with clearer generality than the more model-specific reports.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44466 is the strongest single issue to anchor the cluster because it is a well-scoped, reproducible v5 regression with broad downstream impact; the rest are mostly narrower or unrelated failures.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43257", + "right": "issue:45137", + "accept": false, + "reason": "Different failures: Qwen3 MOE weight conversion/loading vs DeepSpeed ZeRO3 deque underflow. No shared code path." + }, + { + "left": "issue:43065", + "right": "issue:43408", + "accept": false, + "reason": "Both SAM3-related, but one is a dummy Conv2d design complaint and the other is a model-type/config mismatch warning." + }, + { + "left": "issue:44995", + "right": "issue:45200", + "accept": false, + "reason": "Stale cache/indexer crash vs Gemma4 text-only mm_token_type_ids defaulting. Unrelated mechanisms." + }, + { + "left": "issue:43262", + "right": "issue:44246", + "accept": false, + "reason": "Audio processor sampling-rate default bug vs intermittent slow import. No common underlying defect." + }, + { + "left": "issue:42886", + "right": "issue:45229", + "accept": false, + "reason": "Offline tokenizer cache loading regression vs multi-GPU Gemma4 OOM. Different symptom and root cause." + }, + { + "left": "issue:43475", + "right": "issue:43540", + "accept": false, + "reason": "Both video/SAM3/Qwen3Omni-adjacent, but the concrete attribute error and video input ValueError are different bugs." + }, + { + "left": "issue:44466", + "right": "issue:45335", + "accept": false, + "reason": "Both involve embeddings/tied weights, but one is serialization inconsistency and the other is resize_token_embeddings not propagating to decoder.embed_tokens." + }, + { + "left": "issue:44995", + "right": "issue:45588", + "accept": false, + "reason": "Stale indexer cache crash vs flash_attention s_aux=None AttributeError. Not the same failure mode." + }, + { + "left": "issue:43653", + "right": "issue:44162", + "accept": false, + "reason": "Tokenizer special-token decode bug vs broad ESM2 breakage. Too different to merge." + }, + { + "left": "issue:44368", + "right": "issue:44977", + "accept": false, + "reason": "Warning about tie_word_embeddings in Qwen3.5 fine-tuning vs flash-attention generation bug. Different concrete issue." + }, + { + "left": "issue:44368", + "right": "issue:45563", + "accept": false, + "reason": "Tie_word_embeddings warning vs stale num_return_sequences warning in paged generate. Only both are warnings." + }, + { + "left": "issue:45397", + "right": "issue:45656", + "accept": false, + "reason": "Gemma-4 zero3 from_pretrained failure and optimizer.step called twice under deepspeed are separate training/runtime bugs." + }, + { + "left": "issue:44060", + "right": "issue:44077", + "accept": false, + "reason": "Incorrect tied-weights warning in Qwen3-Next vs patchtsmixer post_init policy change. Not the same code path." + }, + { + "left": "issue:45003", + "right": "issue:45561", + "accept": false, + "reason": "sys.modules access bug in modeling_utils vs pytest-xdist race on captured_info.txt. Different layers entirely." + }, + { + "left": "issue:43673", + "right": "issue:44734", + "accept": false, + "reason": "Generation cache missing in v5 chunked_prefill vs serve KV-cache continuation tensor indexing crash. Both generation-related but distinct bugs." + }, + { + "left": "issue:45137", + "right": "issue:45600", + "accept": false, + "reason": "DeepSpeed ZeRO3 deque error vs auto_mappings referencing removed Sam3LiteText configs. One is runtime, the other CI/config cleanup." + }, + { + "left": "issue:43931", + "right": "issue:44368", + "accept": false, + "reason": "Qwen3-VL weight-shape mismatch vs Qwen3.5 tie_word_embeddings warning. Same family only at a very broad level." + }, + { + "left": "issue:44869", + "right": "issue:45356", + "accept": false, + "reason": "Whisper timestamp decode crash vs Kimi-K2.5 tokenizer regression. Different models and failure surfaces." + }, + { + "left": "issue:44933", + "right": "issue:45459", + "accept": false, + "reason": "Missing/nonexistent image_utils import vs protobuf exception masking tokenizer errors. Both import-path related but not the same bug." + }, + { + "left": "issue:44297", + "right": "issue:44623", + "accept": false, + "reason": "Tokenizer.save_pretrained writes wrong tokenizer_class vs processor.save_pretrained missing files. Related persistence area, but different artifacts and fixes." + }, + { + "left": "issue:43646", + "right": "issue:44162", + "accept": false, + "reason": "Custom model initialization breaking in Transformers 5.0.0 vs ESM2 breakage. The latter is model-specific and not clearly the same regression." + }, + { + "left": "issue:43232", + "right": "issue:43673", + "accept": false, + "reason": "Post-sync_gpus generation kwargs update issue vs missing GenerationMixin cache in chunked_prefill. Different generation internals." + }, + { + "left": "issue:44361", + "right": "issue:44749", + "accept": false, + "reason": "MLukeTokenizer AttributeError on tasks vs Chinese report of slower filtering after upgrade. Not the same bug." + }, + { + "left": "issue:43673", + "right": "issue:43827", + "accept": false, + "reason": "Generation cache regression vs docs still referencing removed pipeline(). One is runtime code, the other documentation cleanup." + }, + { + "left": "issue:43452", + "right": "issue:45003", + "accept": false, + "reason": "gguf_file breaks tokenizer/model loading vs unsafe sys.modules access. Both loading-related, but not the same concrete defect." + }, + { + "left": "issue:28282", + "right": "issue:30990", + "accept": false, + "reason": "PyTorch missing ImportError for AutoModel vs Sentence Transformers getting stuck loading. Different environments and symptoms." + }, + { + "left": "issue:44623", + "right": "issue:45656", + "accept": false, + "reason": "Missing files on processor.save_pretrained vs deepspeed optimizer step called twice. No shared underlying bug." + }, + { + "left": "issue:42994", + "right": "issue:43482", + "accept": false, + "reason": "Quantized model saving failure vs Qwen2.5-GGUF loading failure in v5. Save vs load path; not mergeable." + }, + { + "left": "issue:43475", + "right": "issue:43643", + "accept": false, + "reason": "SAM3 video encoder output missing attribute vs AutoConfig trust_remote_code missing fields. Different model/config layers." + }, + { + "left": "issue:44749", + "right": "issue:45310", + "accept": false, + "reason": "Performance regression after upgrade vs Qwen3.5 MOE from_pretrained error in transformers>=5.4.0. Not the same failure." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 34, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:30990", + "issue:35141", + "issue:36010", + "issue:41628", + "issue:42175", + "issue:42222", + "issue:42371", + "issue:42673", + "issue:42831", + "issue:42898", + "issue:42994", + "issue:43232", + "issue:43377", + "issue:43475", + "issue:43525", + "issue:43704", + "issue:43784", + "issue:43824", + "issue:43901", + "issue:44038", + "issue:44188", + "issue:44222", + "issue:44242", + "issue:44351", + "issue:44496", + "issue:44568", + "issue:44623", + "issue:44661", + "issue:44749", + "issue:44792", + "issue:44933", + "issue:44964", + "issue:45081", + "issue:45092", + "issue:45103", + "issue:45137", + "issue:45200", + "issue:45230", + "issue:45310", + "issue:45375", + "issue:45381", + "issue:45397", + "issue:45478", + "issue:45561", + "issue:45600", + "issue:45656", + "issue:45712", + "issue:45812" + ], + "soft_pairs": [ + "issue:42371|issue:45092", + "issue:44749|issue:45656", + "issue:43475|issue:45381", + "issue:44038|issue:44623", + "issue:45230|issue:45397", + "issue:41628|issue:44933", + "issue:45081|issue:45103", + "issue:42994|issue:43525", + "issue:45375|issue:45478", + "issue:42673|issue:43704", + "issue:43475|issue:44661", + "issue:45310|issue:45375", + "issue:41628|issue:44351", + "issue:42831|issue:44222", + "issue:42222|issue:45200", + "issue:44222|issue:45310", + "issue:42994|issue:43824", + "issue:42175|issue:45712", + "issue:36010|issue:41628", + "issue:43377|issue:44242", + "issue:44038|issue:45310", + "issue:44496|issue:45561", + "issue:44964|issue:45137", + "issue:45561|issue:45600", + "issue:43901|issue:45561", + "issue:30990|issue:35141", + "issue:42898|issue:44568", + "issue:43232|issue:44792", + "issue:43232|issue:44188", + "issue:42898|issue:45812", + "issue:43784|issue:43824" + ], + "prepared_review_unit_hash": "3b6fa28564806d2a8ba76cbebd0623c2a4459456cbf8464b6da6a4e5f8691454", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36919, + "estimated_input_tokens": 9230, + "estimated_eval_tokens": 18716 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a heterogeneous bundle of unrelated Transformers issues, but not a single unique duplicate island: there are at least two duplicate-like mini-clusters, the Qwen3ForCausalLM VRAM leak pair (42673/43704) and the identical-titled Qwen3.5 Moe from_pretrained error pair (45310/45478). The remaining soft-edge candidates still look distinct, so this is largely separate bugs with a couple of clear duplicates.", + "confidence": 0.84, + "canonical_issue_reason": "Issue 42673 is a strong anchor because it has an exact duplicate counterpart (43704) and a specific, self-contained VRAM leak report. It is still one of the clearest representatives even though the cluster also contains another duplicate-like Qwen3.5 Moe pair elsewhere.", + "canonical_pr_reason": null, + "best_issue_reason": "42673 is the best single issue representative because it is concrete, well-scoped, and backed by an exact duplicate report. It is not the only duplicate-like topic in the packet, but it remains the cleanest canonical issue.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42371", + "right": "issue:45092", + "accept": false, + "reason": "Different problems: TF32 settings guidance vs an InternVL2/meta-init incompatibility." + }, + { + "left": "issue:44749", + "right": "issue:45656", + "accept": false, + "reason": "Unrelated bugs: tokenizer/filtering slowdown vs optimizer step being called twice under DeepSpeed." + }, + { + "left": "issue:43475", + "right": "issue:45381", + "accept": false, + "reason": "Both are vision-related, but they describe different model/code-path failures and different symptoms." + }, + { + "left": "issue:44038", + "right": "issue:44623", + "accept": false, + "reason": "Different issues: Qwen3-VL-Moe loading vs processor.save_pretrained missing files." + }, + { + "left": "issue:45230", + "right": "issue:45397", + "accept": false, + "reason": "No shared underlying bug is evident; generic bug report vs Gemma-4 ZeRO3 loading failure." + }, + { + "left": "issue:41628", + "right": "issue:44933", + "accept": false, + "reason": "Both are import errors, but they involve different missing symbols and likely different fixes." + }, + { + "left": "issue:45081", + "right": "issue:45103", + "accept": false, + "reason": "Tokenizer backend crash and auto-docstring future-annotations crash are unrelated." + }, + { + "left": "issue:42994", + "right": "issue:43525", + "accept": false, + "reason": "Different failures: quantized model saving vs missing pad_token_id on Llama4Config." + }, + { + "left": "issue:45375", + "right": "issue:45478", + "accept": false, + "reason": "Same model family, but one is a missing config field and the other is a generic from_pretrained error; not enough evidence they're the same bug." + }, + { + "left": "issue:42673", + "right": "issue:43704", + "accept": true, + "reason": "Same title and same VRAM leak symptom for Qwen3ForCausalLM; this looks like the same underlying issue." + }, + { + "left": "issue:42831", + "right": "issue:44222", + "accept": false, + "reason": "Both mention FP8, but one is an accuracy issue and the other is a save_pretrained failure." + }, + { + "left": "issue:42222", + "right": "issue:45200", + "accept": false, + "reason": "Different model families and different bugs: VitPose breakage vs Gemma 4 token-type defaults." + }, + { + "left": "issue:44222", + "right": "issue:45310", + "accept": false, + "reason": "Different bugs: FP8 save_pretrained failure vs Qwen3.5-Moe from_pretrained error." + }, + { + "left": "issue:42994", + "right": "issue:43824", + "accept": false, + "reason": "Unrelated: quantized saving failure vs missing Qwen2.5-VL import." + }, + { + "left": "issue:42175", + "right": "issue:45712", + "accept": false, + "reason": "Different concerns: backend dependency packaging vs leftover dummy classes in repo checks." + }, + { + "left": "issue:36010", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but they concern different missing APIs and likely different root causes." + }, + { + "left": "issue:43377", + "right": "issue:44242", + "accept": false, + "reason": "Different model behaviors: batched-vs-single mismatch vs router loss calculation." + }, + { + "left": "issue:44038", + "right": "issue:45310", + "accept": false, + "reason": "Related model family, but the titles point to different generations/version-specific load errors." + }, + { + "left": "issue:44496", + "right": "issue:45561", + "accept": false, + "reason": "Completely unrelated: model auto-detection failure vs xdist file-race in testing utils." + }, + { + "left": "issue:44964", + "right": "issue:45137", + "accept": false, + "reason": "Different subsystems and symptoms: multimodal model loading vs DeepSpeed ZeRO3 deque error." + }, + { + "left": "issue:45561", + "right": "issue:45600", + "accept": false, + "reason": "Testing race condition vs CI breakage from stale auto_mappings references; not the same bug." + }, + { + "left": "issue:43901", + "right": "issue:45561", + "accept": false, + "reason": "Docs/behavior mismatch for pipeline output vs xdist file race are unrelated." + }, + { + "left": "issue:30990", + "right": "issue:35141", + "accept": false, + "reason": "Sentence Transformers loading hang and embedding reinit are unrelated regressions." + }, + { + "left": "issue:42898", + "right": "issue:44568", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different behaviors and different code paths." + }, + { + "left": "issue:43232", + "right": "issue:44792", + "accept": false, + "reason": "Generation kwargs bug vs Janus image-generation test failure; no clear shared underlying defect." + }, + { + "left": "issue:43232", + "right": "issue:44188", + "accept": false, + "reason": "Different issues in generation/attention internals; not the same concrete bug." + }, + { + "left": "issue:42898", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenization regressions, but one is cleanup-space behavior and the other is wrong token IDs for Granite models." + }, + { + "left": "issue:43784", + "right": "issue:43824", + "accept": false, + "reason": "Both are import regressions, but they are for different missing symbols and different packages/models." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The summary overstates uniqueness: the packet contains another obvious duplicate-like pair with identical titles, issue:45310 and issue:45478 (`[BUG] transformers>=5.4.0, Qwen3.5 Moe from_pretrained error`), so it is not grounded to say 42673/43704 is the only clear duplicate-like pair. The rest of the soft-edge rejections are generally conservative, but the omission makes the canonicality claim 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": 16, + "review_unit_index": 35, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:28282", + "issue:30333", + "issue:33290", + "issue:34689", + "issue:35141", + "issue:36331", + "issue:41628", + "issue:42175", + "issue:42757", + "issue:42831", + "issue:42898", + "issue:43232", + "issue:43278", + "issue:43479", + "issue:43723", + "issue:43873", + "issue:43874", + "issue:43976", + "issue:44060", + "issue:44079", + "issue:44188", + "issue:44206", + "issue:44222", + "issue:44263", + "issue:44295", + "issue:44297", + "issue:44373", + "issue:44448", + "issue:44484", + "issue:44568", + "issue:44623", + "issue:44734", + "issue:44779", + "issue:44869", + "issue:44933", + "issue:44945", + "issue:44964", + "issue:44977", + "issue:45092", + "issue:45103", + "issue:45125", + "issue:45137", + "issue:45310", + "issue:45356", + "issue:45405", + "issue:45656", + "issue:45712", + "issue:45834" + ], + "soft_pairs": [ + "issue:44188|issue:44373", + "issue:43278|issue:45137", + "issue:44623|issue:45310", + "issue:44734|issue:45103", + "issue:30333|issue:33290", + "issue:43723|issue:44568", + "issue:44060|issue:45125", + "issue:42898|issue:45356", + "issue:43874|issue:45092", + "issue:42898|issue:44779", + "issue:45405|issue:45712", + "issue:42898|issue:44448", + "issue:43479|issue:44079", + "issue:44188|issue:44964", + "issue:44295|issue:45656", + "issue:44933|issue:45712", + "issue:42175|issue:44933", + "issue:43976|issue:44933", + "issue:44222|issue:44297", + "issue:43479|issue:44869", + "issue:44297|issue:45656", + "issue:44206|issue:45103", + "issue:42831|issue:44623", + "issue:44222|issue:44623", + "issue:30333|issue:36331", + "issue:41628|issue:42757", + "issue:43232|issue:45834", + "issue:30333|issue:34689", + "issue:43723|issue:44977", + "issue:43873|issue:44945", + "issue:44222|issue:44484", + "issue:28282|issue:30333", + "issue:44297|issue:45310", + "issue:30333|issue:35141", + "issue:44263|issue:45092" + ], + "prepared_review_unit_hash": "76abcf35ebffda7a534fa5b9c3807424c1a65dcf782c86990b5c78496d69880f", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 35, + "serialized_chars": 38117, + "estimated_input_tokens": 9530, + "estimated_eval_tokens": 19316 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a heterogeneous mix of unrelated Transformers bugs and regressions. The soft similarities are driven by shared vocabulary around v5, loading, tokenizers, and training rather than the same underlying defect. No PRs are present.", + "confidence": 0.94, + "canonical_issue_reason": "issue:30333 is the most connected node in this set and is broad enough to serve as the cluster anchor, though it is not a true duplicate of the others.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:30333 is the best representative issue for the cluster because it has the highest soft-edge connectivity and a broad training/workflow scope.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44188", + "right": "issue:44373", + "accept": false, + "reason": "Attention-kernel branching under torch.compile is unrelated to a docstring typo for position_ids." + }, + { + "left": "issue:43278", + "right": "issue:45137", + "accept": false, + "reason": "Embedding dtype drift in evaluation is not the same bug as a DeepSpeed ZeRO3 deque IndexError." + }, + { + "left": "issue:44623", + "right": "issue:45310", + "accept": false, + "reason": "Missing processor save files and a Qwen3.5 MoE from_pretrained failure are different code paths." + }, + { + "left": "issue:44734", + "right": "issue:45103", + "accept": false, + "reason": "KV-cache continuation indexing in serve is unrelated to an auto_docstring annotations crash." + }, + { + "left": "issue:30333", + "right": "issue:33290", + "accept": false, + "reason": "MLflow reporting on failed jobs and adafactor OOM in DeepSpeed are distinct training issues." + }, + { + "left": "issue:43723", + "right": "issue:44568", + "accept": false, + "reason": "Tokenizer loading in v5 and missing add_special_tokens behavior are separate tokenizer regressions." + }, + { + "left": "issue:44060", + "right": "issue:45125", + "accept": false, + "reason": "A tied-weights warning in Qwen3-Next is not the same as missing _tp_plan in Qwen3_5Moe." + }, + { + "left": "issue:42898", + "right": "issue:45356", + "accept": false, + "reason": "These are different tokenizer regressions affecting different models and failure modes." + }, + { + "left": "issue:43874", + "right": "issue:45092", + "accept": false, + "reason": "A missing image-patch method and meta-init incompatibility are unrelated multimodal loading bugs." + }, + { + "left": "issue:42898", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer-related, but they describe different regressions in different tokenizers/models." + }, + { + "left": "issue:45405", + "right": "issue:45712", + "accept": false, + "reason": "A PEFT version pin issue is unrelated to leftover dummy classes in the repo." + }, + { + "left": "issue:42898", + "right": "issue:44448", + "accept": false, + "reason": "These concern different output/behavior regressions and are not the same underlying tokenizer bug." + }, + { + "left": "issue:43479", + "right": "issue:44079", + "accept": false, + "reason": "Phi4 multimodal config initialization and ModelOutput key assignment are different None-handling bugs." + }, + { + "left": "issue:44188", + "right": "issue:44964", + "accept": false, + "reason": "Attention kernel divergence and Phi-4 multimodal loading failure do not share a concrete code path." + }, + { + "left": "issue:44295", + "right": "issue:45656", + "accept": false, + "reason": "Reading position_ids after buffer registration is unrelated to DeepSpeed calling optimizer.step twice." + }, + { + "left": "issue:44933", + "right": "issue:45712", + "accept": false, + "reason": "A missing image_utils import and dummy-class cleanup are different repository maintenance issues." + }, + { + "left": "issue:42175", + "right": "issue:44933", + "accept": false, + "reason": "Missing tensorflow backend in extras and a nonexistent image_utils import are separate import problems." + }, + { + "left": "issue:43976", + "right": "issue:44933", + "accept": false, + "reason": "Python version support regression and a missing image_utils symbol are not the same defect." + }, + { + "left": "issue:44222", + "right": "issue:44297", + "accept": false, + "reason": "FP8 save_pretrained behavior and tokenizer_class metadata mismatch affect different save paths." + }, + { + "left": "issue:43479", + "right": "issue:44869", + "accept": false, + "reason": "Phi4 config defaults and Whisper word timestamp decoding crash are unrelated." + }, + { + "left": "issue:44297", + "right": "issue:45656", + "accept": false, + "reason": "Tokenizer config mismatch is unrelated to DeepSpeed double optimizer steps." + }, + { + "left": "issue:44206", + "right": "issue:45103", + "accept": false, + "reason": "Unsupported center argument in LasrFeatureExtractor is unrelated to the auto_docstring annotations crash." + }, + { + "left": "issue:42831", + "right": "issue:44623", + "accept": false, + "reason": "FineGrainedFP8 accuracy issues are not the same as missing files in processor.save_pretrained." + }, + { + "left": "issue:44222", + "right": "issue:44623", + "accept": false, + "reason": "FP8 MoE save issues and processor file export issues touch different save code paths." + }, + { + "left": "issue:30333", + "right": "issue:36331", + "accept": false, + "reason": "Failed-job MLflow reporting and compute_loss signature changes are separate trainer issues." + }, + { + "left": "issue:41628", + "right": "issue:42757", + "accept": false, + "reason": "These are both import errors, but for different symbols and dependency breakages." + }, + { + "left": "issue:43232", + "right": "issue:45834", + "accept": false, + "reason": "Generation kwargs updates after sync_gpus are unrelated to Kosmos2.5 OCR index errors." + }, + { + "left": "issue:30333", + "right": "issue:34689", + "accept": false, + "reason": "MLflow reporting on failure is unrelated to a model-loading regression for Llama 3.2 Vision." + }, + { + "left": "issue:43723", + "right": "issue:44977", + "accept": false, + "reason": "Tokenizer load failures and flash-attention generation issues are different bugs." + }, + { + "left": "issue:43873", + "right": "issue:44945", + "accept": false, + "reason": "Quantization/offloading behavior and pipeline-parallel output mismatch are different runtime issues." + }, + { + "left": "issue:44222", + "right": "issue:44484", + "accept": false, + "reason": "FP8 save_pretrained MoE behavior is unrelated to the max_shard_size default question." + }, + { + "left": "issue:28282", + "right": "issue:30333", + "accept": false, + "reason": "PyTorch import availability and MLflow reporting on failed training jobs are unrelated." + }, + { + "left": "issue:44297", + "right": "issue:45310", + "accept": false, + "reason": "Tokenizer_class metadata mismatch and Qwen3.5 MoE from_pretrained failure are different problems." + }, + { + "left": "issue:30333", + "right": "issue:35141", + "accept": false, + "reason": "MLflow job reporting and embedding reinitialization in post_init are unrelated." + }, + { + "left": "issue:44263", + "right": "issue:45092", + "accept": false, + "reason": "GlmMoeDsaIndexer split semantics and InternVL2 meta-init compatibility 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": 16, + "review_unit_index": 36, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:22355", + "issue:28282", + "issue:30990", + "issue:33357", + "issue:38175", + "issue:39401", + "issue:41628", + "issue:42371", + "issue:42757", + "issue:42831", + "issue:42886", + "issue:42907", + "issue:42994", + "issue:43066", + "issue:43232", + "issue:43479", + "issue:43576", + "issue:43644", + "issue:43723", + "issue:43756", + "issue:43784", + "issue:43824", + "issue:44038", + "issue:44060", + "issue:44117", + "issue:44261", + "issue:44263", + "issue:44295", + "issue:44360", + "issue:44373", + "issue:44483", + "issue:44485", + "issue:44514", + "issue:44568", + "issue:44623", + "issue:44704", + "issue:44871", + "issue:44913", + "issue:44945", + "issue:45092", + "issue:45103", + "issue:45278", + "issue:45290", + "issue:45310", + "issue:45357", + "issue:45406", + "issue:45593", + "issue:45753" + ], + "soft_pairs": [ + "issue:44483|issue:45406", + "issue:44263|issue:44360", + "issue:44514|issue:45103", + "issue:44373|issue:44485", + "issue:43479|issue:43644", + "issue:44295|issue:44623", + "issue:44261|issue:45092", + "issue:45092|issue:45357", + "issue:43723|issue:44871", + "issue:30990|issue:38175", + "issue:43479|issue:44913", + "issue:42886|issue:42994", + "issue:41628|issue:43824", + "issue:22355|issue:28282", + "issue:39401|issue:44568", + "issue:42831|issue:45310", + "issue:44263|issue:44373", + "issue:44945|issue:45753", + "issue:42831|issue:44038", + "issue:42757|issue:45278", + "issue:43576|issue:43784", + "issue:42886|issue:43066", + "issue:43232|issue:45593", + "issue:42371|issue:44263", + "issue:43756|issue:44060", + "issue:44117|issue:44704", + "issue:30990|issue:33357", + "issue:42907|issue:44945", + "issue:44704|issue:45290" + ], + "prepared_review_unit_hash": "1ea5f8c2bea51c34c555464996d409cdfe66948f4e6b73b648ab69352a275f2d", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36004, + "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 highly heterogeneous; the soft pairs mostly share only subsystem-level similarity (imports, tokenizers, save/load, multimodal, generation) but not the same concrete bug. No soft pair is a safe duplicate merge candidate.", + "confidence": 0.72, + "canonical_issue_reason": "issue:45278 is the broadest umbrella-style report in the set: it describes many import errors after upgrading to v5.5.0, so it is the most representative issue for this mixed regression cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the strongest cluster anchor because it is open, broad, and directly captures a large class of upgrade-related import failures rather than a single narrow symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44483", + "right": "issue:45406", + "accept": false, + "reason": "Different failures: chat/completions request validation vs Gemma4Processor missing _tokenizer during serve startup." + }, + { + "left": "issue:44263", + "right": "issue:44360", + "accept": false, + "reason": "Unrelated bugs in the same general area; one is torch.split return handling, the other is a missing ReLU in a DSA indexer." + }, + { + "left": "issue:44514", + "right": "issue:45103", + "accept": false, + "reason": "Batched chat template crash is unrelated to the auto_docstring AttributeError from future annotations." + }, + { + "left": "issue:44373", + "right": "issue:44485", + "accept": false, + "reason": "A docstring mistake is not the same bug as the GLM-5 RoPE implementation issue." + }, + { + "left": "issue:43479", + "right": "issue:43644", + "accept": false, + "reason": "Config defaulting when None and non-persistent buffer junk are different code paths and symptoms." + }, + { + "left": "issue:44295", + "right": "issue:44623", + "accept": false, + "reason": "Registering position_ids as a buffer is unrelated to processor.save_pretrained missing files." + }, + { + "left": "issue:44261", + "right": "issue:45092", + "accept": false, + "reason": "LayerNorm epsilon precision mismatch and remote-code meta-init incompatibility are distinct problems." + }, + { + "left": "issue:45092", + "right": "issue:45357", + "accept": false, + "reason": "Meta-initialization incompatibility for old checkpoints is not the same as incorrect visual encoder keys on save_pretrained." + }, + { + "left": "issue:43723", + "right": "issue:44871", + "accept": false, + "reason": "Tokenizer loading regression and eos_token_id config inconsistency are different issues." + }, + { + "left": "issue:30990", + "right": "issue:38175", + "accept": false, + "reason": "Sentence-Transformers loading stall and zero-probabilities on SigLIP2 are unrelated behaviors." + }, + { + "left": "issue:43479", + "right": "issue:44913", + "accept": false, + "reason": "Different model config bugs: Phi4 multimodal defaults vs GPTNeoX rotary_pct reload." + }, + { + "left": "issue:42886", + "right": "issue:42994", + "accept": false, + "reason": "Offline tokenizer cache loading and quantized model saving are separate failure modes." + }, + { + "left": "issue:41628", + "right": "issue:43824", + "accept": false, + "reason": "Both are import errors, but they concern different missing exports and likely different fixes." + }, + { + "left": "issue:22355", + "right": "issue:28282", + "accept": false, + "reason": "onnx module import failure is not the same as missing PyTorch for AutoModel." + }, + { + "left": "issue:39401", + "right": "issue:44568", + "accept": false, + "reason": "Wrong offset_mapping and BOS/EOS insertion behavior are distinct tokenizer bugs." + }, + { + "left": "issue:42831", + "right": "issue:45310", + "accept": false, + "reason": "FineGrainedFP8 accuracy and Qwen3.5 MoE from_pretrained errors are unrelated." + }, + { + "left": "issue:44263", + "right": "issue:44373", + "accept": false, + "reason": "A runtime tensor split bug is not a docstring typo." + }, + { + "left": "issue:44945", + "right": "issue:45753", + "accept": false, + "reason": "Pipeline parallelism output corruption and an image-specific infinite loop are different LLM-generation problems." + }, + { + "left": "issue:42831", + "right": "issue:44038", + "accept": false, + "reason": "FineGrainedFP8 accuracy regression and Qwen3-VL-Moe loading bug are not the same issue." + }, + { + "left": "issue:42757", + "right": "issue:45278", + "accept": false, + "reason": "A single missing huggingface_hub symbol and a broad multi-import regression after upgrade are related only at subsystem level, not the same bug." + }, + { + "left": "issue:43576", + "right": "issue:43784", + "accept": false, + "reason": "The env command regression and the sentence-transformers import NameError are separate failures." + }, + { + "left": "issue:42886", + "right": "issue:43066", + "accept": false, + "reason": "Offline cache loading failure and wrong tokenizer decoder type are different tokenizer regressions." + }, + { + "left": "issue:43232", + "right": "issue:45593", + "accept": false, + "reason": "Generation kwargs handling after sync_gpus and D-FINE auxiliary loss behavior are unrelated." + }, + { + "left": "issue:42371", + "right": "issue:44263", + "accept": false, + "reason": "TF32 settings API guidance and torch.split return handling do not share the same code-path bug." + }, + { + "left": "issue:43756", + "right": "issue:44060", + "accept": false, + "reason": "RoPE layer dropping in Smollm3 is not the same as an incorrect tied-weights warning in Qwen3-Next." + }, + { + "left": "issue:44117", + "right": "issue:44704", + "accept": false, + "reason": "TOKENIZER_MAPPING_NAMES returning None and AutoProcessor kwargs forwarding are different from_pretrained plumbing bugs." + }, + { + "left": "issue:30990", + "right": "issue:33357", + "accept": false, + "reason": "Loading stall in Sentence-Transformers is unrelated to a bus error on MacOS with a community CLIP model." + }, + { + "left": "issue:42907", + "right": "issue:44945", + "accept": false, + "reason": "Quantized model saving failure and pipeline-parallelism output corruption are different behaviors." + }, + { + "left": "issue:44704", + "right": "issue:45290", + "accept": false, + "reason": "AutoProcessor cached_file kwargs forwarding is unrelated to assistant-message chat template crashes with tool calls." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 37, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:22355", + "issue:28218", + "issue:29127", + "issue:30990", + "issue:36296", + "issue:39401", + "issue:41628", + "issue:42757", + "issue:42907", + "issue:43066", + "issue:43116", + "issue:43122", + "issue:43232", + "issue:43408", + "issue:43452", + "issue:43475", + "issue:43723", + "issue:43784", + "issue:43824", + "issue:43937", + "issue:43992", + "issue:44038", + "issue:44222", + "issue:44261", + "issue:44295", + "issue:44297", + "issue:44351", + "issue:44360", + "issue:44373", + "issue:44442", + "issue:44485", + "issue:44488", + "issue:44514", + "issue:44521", + "issue:44625", + "issue:44704", + "issue:44779", + "issue:44829", + "issue:44964", + "issue:44977", + "issue:45200", + "issue:45216", + "issue:45245", + "issue:45278", + "issue:45446", + "issue:45478", + "issue:45600" + ], + "soft_pairs": [ + "issue:43122|issue:44514", + "issue:43232|issue:45245", + "issue:43784|issue:45600", + "issue:43723|issue:44779", + "issue:44295|issue:44297", + "issue:42907|issue:43937", + "issue:41628|issue:45278", + "issue:43723|issue:44442", + "issue:43408|issue:43475", + "issue:44261|issue:44373", + "issue:44360|issue:44485", + "issue:43122|issue:44521", + "issue:44625|issue:44829", + "issue:43116|issue:45200", + "issue:29127|issue:30990", + "issue:42907|issue:44964", + "issue:43122|issue:44779", + "issue:44038|issue:44297", + "issue:42907|issue:43452", + "issue:39401|issue:44488", + "issue:36296|issue:43116", + "issue:44038|issue:44295", + "issue:43824|issue:44351", + "issue:44038|issue:44222", + "issue:39401|issue:44521", + "issue:45216|issue:45478", + "issue:42757|issue:44351", + "issue:43066|issue:44779", + "issue:22355|issue:28218", + "issue:42907|issue:44222", + "issue:43992|issue:44704", + "issue:43122|issue:44977", + "issue:43784|issue:45446", + "issue:43937|issue:44485" + ], + "prepared_review_unit_hash": "03524216562f09dad81a299959fac2f3becdc71175c9603e5e19af2ef5c29c21", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 34, + "serialized_chars": 36838, + "estimated_input_tokens": 9210, + "estimated_eval_tokens": 18676 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most candidate pairs are only superficially similar (shared model family, tokenizer, import, or save/load wording) and do not look like the same underlying bug. The only reasonably strong duplicate pair is the AutoTokenizer loading regression in v5 (43723/44442).", + "confidence": 0.46, + "canonical_issue_reason": "Issue 43723 is the broadest and most representative report of the tokenizer-loading regression in v5; it cleanly captures the shared AutoTokenizer.from_pretrained failure mode.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43723 is the best umbrella issue because it describes the underlying AutoTokenizer loading problem at a higher level, while 44442 is a specific instance of that failure.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43122", + "right": "issue:44514", + "accept": false, + "reason": "Both are tokenizer-related, but one is about changed tokenization across versions and the other is a batched chat-template crash. Different failure modes and likely different fixes." + }, + { + "left": "issue:43232", + "right": "issue:45245", + "accept": false, + "reason": "Unrelated bugs: generation state handling after sync_gpus versus a category-count limit error." + }, + { + "left": "issue:43784", + "right": "issue:45600", + "accept": false, + "reason": "Different problems: sentence-transformers import NameError versus stale auto_mappings references to removed SAM3 configs." + }, + { + "left": "issue:43723", + "right": "issue:44779", + "accept": false, + "reason": "Both mention tokenizer regressions in v5, but one is a loading failure and the other is incorrect tokenizer output for Deepseek. Not clearly the same concrete defect." + }, + { + "left": "issue:44295", + "right": "issue:44297", + "accept": false, + "reason": "Position_ids buffer access error and tokenizer_class metadata mismatch are unrelated." + }, + { + "left": "issue:42907", + "right": "issue:43937", + "accept": false, + "reason": "Different model-specific issues: dequantized save_pretrained failure versus invalid GenerationConfig for GLM-5." + }, + { + "left": "issue:41628", + "right": "issue:45278", + "accept": false, + "reason": "The second is a broad report of many import errors; it is too vague to treat as the same specific AutoImageProcessor import bug." + }, + { + "left": "issue:43723", + "right": "issue:44442", + "accept": true, + "reason": "Both describe the same AutoTokenizer.from_pretrained loading regression in v5; 44442 is a concrete tokenizer example of the broader issue in 43723." + }, + { + "left": "issue:43408", + "right": "issue:43475", + "accept": false, + "reason": "Same model family, but one is a config/type warning and the other is a missing attribute in encoder output. Different code paths." + }, + { + "left": "issue:44261", + "right": "issue:44373", + "accept": false, + "reason": "MLA norm precision/config issue and a wrong docstring for position_ids are unrelated." + }, + { + "left": "issue:44360", + "right": "issue:44485", + "accept": false, + "reason": "No meaningful overlap: DSA indexer ReLU versus GLM-5 RoPE implementation." + }, + { + "left": "issue:43122", + "right": "issue:44521", + "accept": false, + "reason": "Both concern tokenization/chat-template behavior, but one is a tokenizer-version difference and the other is assistant_mask generation for multimodal inputs." + }, + { + "left": "issue:44625", + "right": "issue:44829", + "accept": false, + "reason": "Different subsystems: Qwen3.5 num_labels propagation versus flash_attention_3 training degeneration." + }, + { + "left": "issue:43116", + "right": "issue:45200", + "accept": false, + "reason": "An example script returning empty multi-label results is unrelated to Gemma 4 mm_token_type_ids defaults." + }, + { + "left": "issue:29127", + "right": "issue:30990", + "accept": false, + "reason": "LayoutLMv3 error-message clarity and Sentence Transformers loading stall are unrelated." + }, + { + "left": "issue:42907", + "right": "issue:44964", + "accept": false, + "reason": "Different bugs: quantized dequantized save failure versus loading a specific multimodal model." + }, + { + "left": "issue:43122", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer regressions in v5, but they affect different models and symptoms; not enough to \u0441\u0447\u0438\u0442\u0430\u0442\u044c them the same bug." + }, + { + "left": "issue:44038", + "right": "issue:44297", + "accept": false, + "reason": "Qwen3-VL-Moe bug and tokenizer save_pretrained metadata mismatch are unrelated." + }, + { + "left": "issue:39401", + "right": "issue:44488", + "accept": false, + "reason": "Wrong offset_mapping and failing to load cjvt/sleng-bert are distinct tokenizer issues." + }, + { + "left": "issue:36296", + "right": "issue:43116", + "accept": false, + "reason": "Tensor parallel training bug versus empty results in an example script are unrelated." + }, + { + "left": "issue:44038", + "right": "issue:44295", + "accept": false, + "reason": "No clear shared failure mode: Qwen3-VL-Moe issue versus position_ids buffer error." + }, + { + "left": "issue:43824", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but for different symbols and likely different root causes." + }, + { + "left": "issue:44038", + "right": "issue:44222", + "accept": false, + "reason": "Both mention MoE, but the issues are about different model families and different save/load paths." + }, + { + "left": "issue:39401", + "right": "issue:44521", + "accept": false, + "reason": "Wrong offset mapping and all-zero assistant masks are different tokenizer behaviors." + }, + { + "left": "issue:45216", + "right": "issue:45478", + "accept": false, + "reason": "Both involve Qwen3.5 and version 5.4+, but one is save_pretrained output correctness and the other is from_pretrained loading; too different to merge." + }, + { + "left": "issue:42757", + "right": "issue:44351", + "accept": false, + "reason": "Different import failures from different packages and symbols." + }, + { + "left": "issue:43066", + "right": "issue:44779", + "accept": false, + "reason": "Tokenizer decoder type mismatch and Deepseek incorrect results may be related at a high level, but the concrete problems are not clearly the same." + }, + { + "left": "issue:22355", + "right": "issue:28218", + "accept": false, + "reason": "Completely unrelated: missing transformers.onnx module versus added-token spacing behavior." + }, + { + "left": "issue:42907", + "right": "issue:44222", + "accept": false, + "reason": "Both concern saving quantized/MoE models, but they are model-specific and do not obviously share one concrete bug." + }, + { + "left": "issue:43992", + "right": "issue:44704", + "accept": false, + "reason": "UMT5 weight loading and AutoProcessor cached_file kwargs are unrelated." + }, + { + "left": "issue:43122", + "right": "issue:44977", + "accept": false, + "reason": "Tokenization regression versus flash-attention generation failure are unrelated." + }, + { + "left": "issue:43784", + "right": "issue:45446", + "accept": false, + "reason": "sentence-transformers import failure and flex_attention version check bug are unrelated." + }, + { + "left": "issue:43937", + "right": "issue:44485", + "accept": false, + "reason": "GLM-5 GenerationConfig validation and GLM-5 RoPE implementation are different issues." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is conservative and grounded in the packet. The only accepted duplicate pair, issue:43723 vs issue:44442, is supported by the titles as the same AutoTokenizer.from_pretrained loading failure class. The remaining soft-edge rejections are appropriately cautious and do not overstate evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 38, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:22355", + "issue:29127", + "issue:33453", + "issue:38617", + "issue:39401", + "issue:41628", + "issue:42222", + "issue:42371", + "issue:42673", + "issue:42831", + "issue:43064", + "issue:43116", + "issue:43381", + "issue:43421", + "issue:43441", + "issue:43450", + "issue:43493", + "issue:43673", + "issue:43825", + "issue:43827", + "issue:43874", + "issue:43937", + "issue:43976", + "issue:43986", + "issue:44038", + "issue:44075", + "issue:44117", + "issue:44222", + "issue:44291", + "issue:44410", + "issue:44779", + "issue:44829", + "issue:44936", + "issue:44945", + "issue:44977", + "issue:45071", + "issue:45072", + "issue:45081", + "issue:45083", + "issue:45216", + "issue:45278", + "issue:45310", + "issue:45405", + "issue:45446", + "issue:45478", + "issue:45563", + "issue:45588", + "issue:45753" + ], + "soft_pairs": [ + "issue:42222|issue:43441", + "issue:42371|issue:43874", + "issue:43976|issue:45446", + "issue:43493|issue:45753", + "issue:42831|issue:45753", + "issue:44075|issue:44936", + "issue:43116|issue:43825", + "issue:44038|issue:45478", + "issue:44222|issue:45478", + "issue:43116|issue:43493", + "issue:43937|issue:45563", + "issue:43064|issue:43673", + "issue:45083|issue:45446", + "issue:38617|issue:45278", + "issue:39401|issue:44779", + "issue:33453|issue:39401", + "issue:44117|issue:45588", + "issue:22355|issue:29127", + "issue:43381|issue:44945", + "issue:43827|issue:45446", + "issue:43937|issue:44977", + "issue:45405|issue:45446", + "issue:43450|issue:43986", + "issue:44117|issue:45081", + "issue:42673|issue:45072", + "issue:39401|issue:43421", + "issue:38617|issue:41628", + "issue:44410|issue:45310", + "issue:44829|issue:45216", + "issue:44291|issue:45071" + ], + "prepared_review_unit_hash": "fdd12d30987d8f53a20444edbb2d8f6e0e350af7de367ed94fe78897b47420aa", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36490, + "estimated_input_tokens": 9123, + "estimated_eval_tokens": 18502 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These are mostly unrelated single-issue reports across different subsystems; I do not see a real duplicate cluster. All soft edges should be rejected. The broadest issue is the open import-regression report 45278, but it still does not subsume the rest.", + "confidence": 0.93, + "canonical_issue_reason": "No single canonical issue stands out because the set is heterogeneous. If a broad umbrella is needed, 45278 is the closest, but it only covers import errors after upgrading to 5.5.0, not the other bugs here.", + "canonical_pr_reason": null, + "best_issue_reason": "453? No PRs are present. Among the issues, 45278 is the most general representative because it describes a broad import-regression class, but it is still not a true duplicate target for the other items.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42222", + "right": "issue:43441", + "accept": false, + "reason": "Different models and failures: vitpose model breakage vs Ministral FlashAttention error." + }, + { + "left": "issue:42371", + "right": "issue:43874", + "accept": false, + "reason": "TF32 API guidance vs missing image-patch method in GLM46V are unrelated." + }, + { + "left": "issue:43976", + "right": "issue:45446", + "accept": false, + "reason": "Python version support mismatch vs an AuxRequest PyTorch version check bug." + }, + { + "left": "issue:43493", + "right": "issue:45753", + "accept": false, + "reason": "SigLIP2 implementation discrepancy vs Qwen3.5 image infinite loop are different bugs." + }, + { + "left": "issue:42831", + "right": "issue:45753", + "accept": false, + "reason": "FineGrainedFP8 accuracy issue and Qwen3.5 infinite loop are unrelated." + }, + { + "left": "issue:44075", + "right": "issue:44936", + "accept": false, + "reason": "SGD args not applied vs trainer.evaluate() failing after train() are separate trainer issues." + }, + { + "left": "issue:43116", + "right": "issue:43825", + "accept": false, + "reason": "Multi-label classification example bug vs pipeline translation error message are different code paths." + }, + { + "left": "issue:44038", + "right": "issue:45478", + "accept": false, + "reason": "Qwen3-VL-Moe issue vs Qwen3.5 Moe from_pretrained error involve different model families." + }, + { + "left": "issue:44222", + "right": "issue:45478", + "accept": false, + "reason": "FP8 save_pretrained moe bug vs from_pretrained loading error are not the same symptom or path." + }, + { + "left": "issue:43116", + "right": "issue:43493", + "accept": false, + "reason": "Example-script multi-label bug and SigLIP2 discrepancy are unrelated." + }, + { + "left": "issue:43937", + "right": "issue:45563", + "accept": false, + "reason": "Invalid GenerationConfig vs stale num_return_sequences warning are different generation issues." + }, + { + "left": "issue:43064", + "right": "issue:43673", + "accept": false, + "reason": "FSDP2/PEFT optimizer-state corruption vs chunked_prefill cache absence are unrelated." + }, + { + "left": "issue:45083", + "right": "issue:45446", + "accept": false, + "reason": "Feature-extraction output-length behavior vs a PyTorch version check bug do not match." + }, + { + "left": "issue:38617", + "right": "issue:45278", + "accept": false, + "reason": "Specific missing import of layer_type_validation is not clearly the same as the broader 'many import errors' report." + }, + { + "left": "issue:39401", + "right": "issue:44779", + "accept": false, + "reason": "Qwen3 tokenizer offset_mapping bug vs Deepseek tokenizer regression are different tokenizer models and failures." + }, + { + "left": "issue:33453", + "right": "issue:39401", + "accept": false, + "reason": "Generic tokenizer-loading regression vs Qwen3 offset_mapping bug are not the same underlying defect." + }, + { + "left": "issue:44117", + "right": "issue:45588", + "accept": false, + "reason": "TOKENIZER_MAPPING_NAMES None handling and flash_attention s_aux=None crash are unrelated." + }, + { + "left": "issue:22355", + "right": "issue:29127", + "accept": false, + "reason": "onnx import failure vs LayoutLMv3 error-message clarity are completely different issues." + }, + { + "left": "issue:43381", + "right": "issue:44945", + "accept": false, + "reason": "Gradient checkpointing eval-mode restriction vs incorrect pipeline-parallel LLM output are separate bugs." + }, + { + "left": "issue:43827", + "right": "issue:45446", + "accept": false, + "reason": "Docs still referencing pipeline() vs a version-check bug are different kinds of problems." + }, + { + "left": "issue:43937", + "right": "issue:44977", + "accept": false, + "reason": "Invalid GenerationConfig vs Qwen3.5 flash-attention generation failure are not the same bug." + }, + { + "left": "issue:45405", + "right": "issue:45446", + "accept": false, + "reason": "Released PEFT version mismatch and AuxRequest version check are unrelated dependency issues." + }, + { + "left": "issue:43450", + "right": "issue:43986", + "accept": false, + "reason": "Batched video processor shape bug vs torchvision-missing crash are different video-processing failures." + }, + { + "left": "issue:44117", + "right": "issue:45081", + "accept": false, + "reason": "Tokenizer mapping fallback bug vs Mistral regex patch crash are separate tokenizer internals." + }, + { + "left": "issue:42673", + "right": "issue:45072", + "accept": false, + "reason": "VRAM leak in multi-threaded Qwen3.5 use vs bfloat16 dtype mismatch in CI are unrelated." + }, + { + "left": "issue:39401", + "right": "issue:43421", + "accept": false, + "reason": "Tokenizer offset_mapping regression vs runtime special-token post-processor update feature are different tokenizer behaviors." + }, + { + "left": "issue:38617", + "right": "issue:41628", + "accept": false, + "reason": "Missing layer_type_validation import and missing AutoImageProcessor import are different import regressions." + }, + { + "left": "issue:44410", + "right": "issue:45310", + "accept": false, + "reason": "Qwen3next projection omission vs Qwen3.5 Moe from_pretrained error are different model bugs." + }, + { + "left": "issue:44829", + "right": "issue:45216", + "accept": false, + "reason": "FlashAttention 3 training degeneration vs save_pretrained checkpoint regression are unrelated." + }, + { + "left": "issue:44291", + "right": "issue:45071", + "accept": false, + "reason": "init_empty_weights argument error vs PretrainedConfig type-checking breakage are distinct v5 compatibility issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 39, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:38617", + "issue:41628", + "issue:42175", + "issue:42222", + "issue:42371", + "issue:42673", + "issue:42831", + "issue:43012", + "issue:43066", + "issue:43097", + "issue:43122", + "issue:43335", + "issue:43408", + "issue:43441", + "issue:43452", + "issue:43577", + "issue:43742", + "issue:43874", + "issue:43906", + "issue:43931", + "issue:43937", + "issue:43976", + "issue:43986", + "issue:44038", + "issue:44075", + "issue:44117", + "issue:44220", + "issue:44261", + "issue:44263", + "issue:44410", + "issue:44483", + "issue:44484", + "issue:44485", + "issue:44493", + "issue:44496", + "issue:44829", + "issue:44945", + "issue:44964", + "issue:44977", + "issue:44987", + "issue:45071", + "issue:45278", + "issue:45310", + "issue:45459", + "issue:45464", + "issue:45478", + "issue:45542", + "issue:45656" + ], + "soft_pairs": [ + "issue:42222|issue:45542", + "issue:44484|issue:45310", + "issue:42175|issue:42222", + "issue:43408|issue:43742", + "issue:43937|issue:44496", + "issue:44483|issue:45464", + "issue:44075|issue:45656", + "issue:44964|issue:45278", + "issue:43012|issue:43577", + "issue:43066|issue:43122", + "issue:42371|issue:44261", + "issue:43874|issue:44261", + "issue:38617|issue:44220", + "issue:44410|issue:45478", + "issue:44484|issue:45478", + "issue:42222|issue:45459", + "issue:43097|issue:44493", + "issue:44263|issue:44485", + "issue:43441|issue:44829", + "issue:43012|issue:43408", + "issue:41628|issue:45071", + "issue:45071|issue:45542", + "issue:42673|issue:44977", + "issue:42371|issue:42831", + "issue:42673|issue:43906", + "issue:43931|issue:44038", + "issue:43986|issue:44484", + "issue:43335|issue:45071", + "issue:44117|issue:44987", + "issue:43097|issue:43452", + "issue:43976|issue:44945" + ], + "prepared_review_unit_hash": "a82fc3732cd1b0501e7d653ad3f1838a48ca67adde492c99bd3a567d0b734d33", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36711, + "estimated_input_tokens": 9178, + "estimated_eval_tokens": 18612 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is broad and mostly noisy: most pairs are only loosely related Transformers v5 regressions or model-loading failures, not exact duplicates. I would keep them split; issue 45278 is the broadest representative of the import/regression subset.", + "confidence": 0.61, + "canonical_issue_reason": "Issue 45278 is the broadest umbrella in this set for version-upgrade import/regression breakage, whereas the others are mostly narrower model-specific failures.", + "canonical_pr_reason": null, + "best_issue_reason": "45278 is the most representative single issue to anchor the cluster because it captures the widest release-regression surface.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42222", + "right": "issue:45542", + "accept": false, + "reason": "Different failures: vitpose model breakage vs missing TensorFlow backend." + }, + { + "left": "issue:44484", + "right": "issue:45310", + "accept": false, + "reason": "Unrelated topics: save_pretrained shard size question vs Qwen3.5 loading error." + }, + { + "left": "issue:42175", + "right": "issue:42222", + "accept": false, + "reason": "TF installation/backend packaging issue vs vitpose model-specific breakage." + }, + { + "left": "issue:43408", + "right": "issue:43742", + "accept": false, + "reason": "Different model/config warnings; one is SAM type mismatch, the other a MobileLLM key error." + }, + { + "left": "issue:43937", + "right": "issue:44496", + "accept": false, + "reason": "Both are load-time ValueErrors, but for different model/config problems." + }, + { + "left": "issue:44483", + "right": "issue:45464", + "accept": false, + "reason": "Chat/completions API request handling is unrelated to streaming inference on Qwen3.5." + }, + { + "left": "issue:44075", + "right": "issue:45656", + "accept": false, + "reason": "Optimizer SGD args issue is not the same as deepspeed calling step twice." + }, + { + "left": "issue:44964", + "right": "issue:45278", + "accept": false, + "reason": "Different breakages: multimodal model loading vs broad import errors after upgrade." + }, + { + "left": "issue:43012", + "right": "issue:43577", + "accept": false, + "reason": "Precision warning on compile is unrelated to Blip2 dtype propagation." + }, + { + "left": "issue:43066", + "right": "issue:43122", + "accept": false, + "reason": "Related tokenizer regressions, but not clearly the same concrete defect." + }, + { + "left": "issue:42371", + "right": "issue:44261", + "accept": false, + "reason": "TF32 control warning is unrelated to MLA q_a_layernorm epsilon precision mismatch." + }, + { + "left": "issue:43874", + "right": "issue:44261", + "accept": false, + "reason": "Image-patch API missing method is unrelated to MLA layernorm epsilon handling." + }, + { + "left": "issue:38617", + "right": "issue:44220", + "accept": false, + "reason": "Different import/helper failures: configuration_utils symbol missing vs fbank feature extraction." + }, + { + "left": "issue:44410", + "right": "issue:45478", + "accept": false, + "reason": "Missing qkv/gate projections in qwen3next is not the same as Qwen3.5 MoE from_pretrained failure." + }, + { + "left": "issue:44484", + "right": "issue:45478", + "accept": false, + "reason": "save_pretrained shard-size question is unrelated to Qwen3.5 MoE loading errors." + }, + { + "left": "issue:42222", + "right": "issue:45459", + "accept": false, + "reason": "vitpose model breakage is unrelated to protobuf-hidden tokenizer errors." + }, + { + "left": "issue:43097", + "right": "issue:44493", + "accept": false, + "reason": "Removed config flag vs unexpected key/position-id warnings are different issues." + }, + { + "left": "issue:44263", + "right": "issue:44485", + "accept": false, + "reason": "torch.split return-value issue is unrelated to GLM-5 RoPE implementation." + }, + { + "left": "issue:43441", + "right": "issue:44829", + "accept": false, + "reason": "Ministral FlashAttention failure and FA3 degenerate training are different code-path problems." + }, + { + "left": "issue:43012", + "right": "issue:43408", + "accept": false, + "reason": "Precision-warning compile issue is unrelated to SAM model-type warning." + }, + { + "left": "issue:41628", + "right": "issue:45071", + "accept": false, + "reason": "AutoImageProcessor import failure is not the same as PretrainedConfig type-checking breakage." + }, + { + "left": "issue:45071", + "right": "issue:45542", + "accept": false, + "reason": "Config type-checking regression and missing TF backend are unrelated." + }, + { + "left": "issue:42673", + "right": "issue:44977", + "accept": false, + "reason": "VRAM leak in dataloader threads is unrelated to flash-attention generation issues." + }, + { + "left": "issue:42371", + "right": "issue:42831", + "accept": false, + "reason": "TF32 behavior settings and FineGrainedFP8 accuracy are different precision concerns." + }, + { + "left": "issue:42673", + "right": "issue:43906", + "accept": false, + "reason": "VRAM leak report is unrelated to an isolated reproduction of another issue." + }, + { + "left": "issue:43931", + "right": "issue:44038", + "accept": false, + "reason": "Weight-shape mismatch for Qwen3-VL differs from Qwen3.5/VL-Moe bug report." + }, + { + "left": "issue:43986", + "right": "issue:44484", + "accept": false, + "reason": "AutoProcessor torchvision crash is unrelated to save_pretrained shard sizing." + }, + { + "left": "issue:43335", + "right": "issue:45071", + "accept": false, + "reason": "SwitchTransformers sparse-layer config bug is unrelated to PretrainedConfig type checking." + }, + { + "left": "issue:44117", + "right": "issue:44987", + "accept": false, + "reason": "Tokenizer mapping None bug is unrelated to fast model loading failure." + }, + { + "left": "issue:43097", + "right": "issue:43452", + "accept": false, + "reason": "Removed encoder-decoder tie flag is unrelated to gguf_file loading failures." + }, + { + "left": "issue:43976", + "right": "issue:44945", + "accept": false, + "reason": "Python version support issue is unrelated to pipeline-parallelism output corruption." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 40, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:38617", + "issue:42617", + "issue:42673", + "issue:42757", + "issue:42886", + "issue:43012", + "issue:43064", + "issue:43066", + "issue:43097", + "issue:43208", + "issue:43381", + "issue:43408", + "issue:43502", + "issue:43550", + "issue:43577", + "issue:43825", + "issue:43873", + "issue:43874", + "issue:43901", + "issue:43906", + "issue:43931", + "issue:43986", + "issue:43992", + "issue:44038", + "issue:44062", + "issue:44117", + "issue:44261", + "issue:44263", + "issue:44315", + "issue:44351", + "issue:44368", + "issue:44410", + "issue:44484", + "issue:44485", + "issue:44655", + "issue:44704", + "issue:44829", + "issue:44964", + "issue:45071", + "issue:45103", + "issue:45245", + "issue:45290", + "issue:45341", + "issue:45372", + "issue:45375", + "issue:45561", + "issue:45588" + ], + "soft_pairs": [ + "issue:43408|issue:44368", + "issue:43874|issue:44263", + "issue:44829|issue:45245", + "issue:38617|issue:42757", + "issue:43064|issue:44315", + "issue:44410|issue:45375", + "issue:38617|issue:44351", + "issue:44062|issue:44117", + "issue:42673|issue:43577", + "issue:43097|issue:45588", + "issue:44038|issue:44410", + "issue:44704|issue:45103", + "issue:44964|issue:45071", + "issue:43931|issue:44410", + "issue:44964|issue:45341", + "issue:44261|issue:44485", + "issue:43502|issue:43992", + "issue:43986|issue:44117", + "issue:43097|issue:43873", + "issue:43066|issue:43906", + "issue:43986|issue:45290", + "issue:45341|issue:45561", + "issue:43986|issue:45372", + "issue:43097|issue:43901", + "issue:43986|issue:45341", + "issue:42617|issue:45341", + "issue:43825|issue:44655", + "issue:43992|issue:44484", + "issue:45341|issue:45588", + "issue:43012|issue:43550", + "issue:43012|issue:44368", + "issue:42886|issue:43381", + "issue:43208|issue:43550" + ], + "prepared_review_unit_hash": "209d8ab379a1e7607f46e7921cf0b7cf2f6eac99a2d75575c84baf22132515ff", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 33, + "serialized_chars": 37026, + "estimated_input_tokens": 9257, + "estimated_eval_tokens": 18770 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items do not look like a duplicate cluster; they span many unrelated transformer bugs across imports, tokenizer loading, model config, training, and processor paths. I rejected all soft-edge pairs because none appear to be the same underlying bug or change.", + "confidence": 0.94, + "canonical_issue_reason": "issue:43873 is the best issue anchor here: it is open, has the most discussion/inbound attention, and describes a concrete user-facing regression with clear impact.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43873 is the strongest standalone issue to keep as the cluster representative because it is active, substantive, and broadly scoped compared with the other narrowly targeted reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43408", + "right": "issue:44368", + "accept": false, + "reason": "Both are warnings, but they concern different models and different causes: sam3 tracker type mismatch vs tie_word_embeddings config advice." + }, + { + "left": "issue:43874", + "right": "issue:44263", + "accept": false, + "reason": "Different GLM bugs: missing image-patch method in a processor vs unexpected torch.split return handling." + }, + { + "left": "issue:44829", + "right": "issue:45245", + "accept": false, + "reason": "Unrelated failures: flash_attention_3 training degeneration vs a category-count limit error." + }, + { + "left": "issue:38617", + "right": "issue:42757", + "accept": false, + "reason": "Both are ImportErrors, but they are for different missing symbols from different modules." + }, + { + "left": "issue:43064", + "right": "issue:44315", + "accept": false, + "reason": "Different training-path problems: optimizer state corruption on nonzero ranks vs Liger Kernel not being applied with model_init." + }, + { + "left": "issue:44410", + "right": "issue:45375", + "accept": false, + "reason": "Both are Qwen-related, but one is missing attention projections and the other is a missing config field silently dropped." + }, + { + "left": "issue:38617", + "right": "issue:44351", + "accept": false, + "reason": "Different missing exports: layer_type_validation vs HybridCache." + }, + { + "left": "issue:44062", + "right": "issue:44117", + "accept": false, + "reason": "Tokenizer-related, but one is an AddedToken constructor conflict and the other is TOKENIZER_MAPPING_NAMES returning None." + }, + { + "left": "issue:42673", + "right": "issue:43577", + "accept": false, + "reason": "Unrelated model issues: VRAM leak across dataloader threads vs dtype not propagating in BLIP-2 loading." + }, + { + "left": "issue:43097", + "right": "issue:45588", + "accept": false, + "reason": "Different code paths: removed config behavior in v5 vs a flash_attention crash on sink-less models." + }, + { + "left": "issue:44038", + "right": "issue:44410", + "accept": false, + "reason": "Both mention Qwen, but one is a broader v5/Qwen3-VL-Moe issue and the other is a specific Qwen3Next layer-projection bug." + }, + { + "left": "issue:44704", + "right": "issue:45103", + "accept": false, + "reason": "Different subsystems: AutoProcessor kwargs forwarding vs auto_docstring parsing with future annotations." + }, + { + "left": "issue:44964", + "right": "issue:45071", + "accept": false, + "reason": "A model loading failure is not the same as a generic PretrainedConfig type-checking regression." + }, + { + "left": "issue:43931", + "right": "issue:44410", + "accept": false, + "reason": "Different Qwen model failures: weight-shape mismatch vs missing projections in a different architecture." + }, + { + "left": "issue:44964", + "right": "issue:45341", + "accept": false, + "reason": "A model load regression is unrelated to a testing_utils bug." + }, + { + "left": "issue:44261", + "right": "issue:44485", + "accept": false, + "reason": "Different numerical/model issues: missing rms_norm_eps precision error vs RoPE implementation discussion." + }, + { + "left": "issue:43502", + "right": "issue:43992", + "accept": false, + "reason": "Offline/local_files_only request leakage is unrelated to a missing embed_tokens.weight load issue." + }, + { + "left": "issue:43986", + "right": "issue:44117", + "accept": false, + "reason": "Different failures: video AutoProcessor needing torchvision vs tokenizer mapping assumptions." + }, + { + "left": "issue:43097", + "right": "issue:43873", + "accept": false, + "reason": "No shared bug: one is a v5 API/config removal warning, the other is a quantization offloading bug." + }, + { + "left": "issue:43066", + "right": "issue:43906", + "accept": false, + "reason": "The titles point to different tokenizer problems; the reproduction issue is not enough to equate them." + }, + { + "left": "issue:43986", + "right": "issue:45290", + "accept": false, + "reason": "Video processor import/loading failure is unrelated to chat-template tool-call crashes." + }, + { + "left": "issue:45341", + "right": "issue:45561", + "accept": false, + "reason": "A generic testing_utils bug is not the same as the xdist race on captured_info.txt." + }, + { + "left": "issue:43986", + "right": "issue:45372", + "accept": false, + "reason": "Different dependency/import failures: missing torchvision vs missing ReasoningEffort from mistral_common." + }, + { + "left": "issue:43097", + "right": "issue:43901", + "accept": false, + "reason": "Config removal and docstring warning changes are unrelated to a docs-behavior mismatch in TextClassificationPipeline." + }, + { + "left": "issue:42617", + "right": "issue:45341", + "accept": false, + "reason": "A 3d_parallel.py execution failure is unrelated to a testing_utils bug." + }, + { + "left": "issue:43825", + "right": "issue:44655", + "accept": false, + "reason": "Different pipeline issues: incorrect translation-task messaging vs save_pretrained serialization of Pipeline objects." + }, + { + "left": "issue:43992", + "right": "issue:44484", + "accept": false, + "reason": "Missing encoder weights during load is unrelated to the max_shard_size default question." + }, + { + "left": "issue:45341", + "right": "issue:45588", + "accept": false, + "reason": "Testing utilities and flash_attention are different code paths with different failures." + }, + { + "left": "issue:43012", + "right": "issue:43550", + "accept": false, + "reason": "A precision-warning regression is not the same as a torch.compile SDPA training failure." + }, + { + "left": "issue:43012", + "right": "issue:44368", + "accept": false, + "reason": "These are different warnings with different root causes and model contexts." + }, + { + "left": "issue:42886", + "right": "issue:43381", + "accept": false, + "reason": "Offline tokenizer cache loading is unrelated to gradient checkpointing in eval mode." + }, + { + "left": "issue:43208", + "right": "issue:43550", + "accept": false, + "reason": "xLSTM small-model training bugs and Bamba SDPA compile failure are different model-specific problems." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 41, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:36010", + "issue:36683", + "issue:38617", + "issue:42757", + "issue:42907", + "issue:42994", + "issue:43012", + "issue:43064", + "issue:43066", + "issue:43208", + "issue:43299", + "issue:43352", + "issue:43441", + "issue:43475", + "issue:43502", + "issue:43525", + "issue:43526", + "issue:43531", + "issue:43618", + "issue:43756", + "issue:43761", + "issue:43824", + "issue:43867", + "issue:43881", + "issue:43901", + "issue:43906", + "issue:43937", + "issue:43976", + "issue:43992", + "issue:44038", + "issue:44220", + "issue:44230", + "issue:44242", + "issue:44263", + "issue:44380", + "issue:44483", + "issue:44485", + "issue:44514", + "issue:44655", + "issue:44683", + "issue:45216", + "issue:45290", + "issue:45310", + "issue:45341", + "issue:45381", + "issue:45440", + "issue:45479", + "issue:45753" + ], + "soft_pairs": [ + "issue:42907|issue:45753", + "issue:42907|issue:44655", + "issue:43531|issue:45341", + "issue:43208|issue:43526", + "issue:44483|issue:44514", + "issue:43012|issue:44683", + "issue:42757|issue:43824", + "issue:43618|issue:43761", + "issue:38617|issue:43502", + "issue:44038|issue:44230", + "issue:44483|issue:45290", + "issue:43299|issue:43867", + "issue:44483|issue:45381", + "issue:43064|issue:44380", + "issue:43901|issue:44655", + "issue:36683|issue:43475", + "issue:43867|issue:45216", + "issue:42994|issue:44655", + "issue:43352|issue:43937", + "issue:43066|issue:45381", + "issue:36010|issue:42757", + "issue:44220|issue:44655", + "issue:43756|issue:44485", + "issue:44263|issue:45440", + "issue:36683|issue:43525", + "issue:43618|issue:45216", + "issue:43906|issue:45753", + "issue:36683|issue:44242", + "issue:36683|issue:43881", + "issue:43299|issue:45753", + "issue:43352|issue:43976", + "issue:43992|issue:45310", + "issue:43441|issue:44380", + "issue:43352|issue:44380", + "issue:44380|issue:45479" + ], + "prepared_review_unit_hash": "a936051c6890f59a08921674ffe62bff5fb1f1aa01521141659656d1386d7240", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 35, + "serialized_chars": 37731, + "estimated_input_tokens": 9433, + "estimated_eval_tokens": 19122 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: import errors, model config/weight-loading regressions, save_pretrained issues, attention/backend bugs, and chat/pipeline behavior changes. None of the soft pairs look like the same underlying bug or change, so they should stay separate.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "If a single issue had to represent the cluster, issue 42907 is the clearest self-contained bug report, but it is not a duplicate center for the rest of the items.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42907", + "right": "issue:45753", + "accept": false, + "reason": "Different bugs: quantized/dequantized model saving vs an image-specific Qwen3.5 generation loop." + }, + { + "left": "issue:42907", + "right": "issue:44655", + "accept": false, + "reason": "Both involve saving, but one is about dequantized model saving and the other about Pipeline.save_pretrained; different code paths." + }, + { + "left": "issue:43531", + "right": "issue:45341", + "accept": false, + "reason": "Unrelated: Qwen3-MoE sliding_window bug vs a testing_utils.py issue." + }, + { + "left": "issue:43208", + "right": "issue:43526", + "accept": false, + "reason": "Different models and failures: xLSTM training bugs vs BeitImageProcessorFast reduce_labels behavior." + }, + { + "left": "issue:44483", + "right": "issue:44514", + "accept": false, + "reason": "Different layers and symptoms: OpenAI-style /v1/chat/completions rejection vs Qwen2_5_VLProcessor chat template crash." + }, + { + "left": "issue:43012", + "right": "issue:44683", + "accept": false, + "reason": "Both mention compilation/precision, but one is a PyTorch warning on bfloat16 compile and the other is a torch>=2.9 flex_attention failure." + }, + { + "left": "issue:42757", + "right": "issue:43824", + "accept": false, + "reason": "Both are import errors, but for different symbols from different packages/modules." + }, + { + "left": "issue:43618", + "right": "issue:43761", + "accept": false, + "reason": "Same broad CLIP area, but different regressions: attentions missing vs hidden_states=None." + }, + { + "left": "issue:38617", + "right": "issue:43502", + "accept": false, + "reason": "Different problems: import failure for layer_type_validation vs network requests despite local_files_only=True." + }, + { + "left": "issue:44038", + "right": "issue:44230", + "accept": false, + "reason": "Different bug classes: Qwen3-VL-Moe loading breakage vs fp8 inference support request/feature." + }, + { + "left": "issue:44483", + "right": "issue:45290", + "accept": false, + "reason": "Different APIs: /v1/chat/completions request handling vs tokenizer chat-template crash with tool calls." + }, + { + "left": "issue:43299", + "right": "issue:43867", + "accept": false, + "reason": "Both are loading failures, but one is Qwen3.5-VL-MoE-specific and the other is a generic state_dict sorting issue." + }, + { + "left": "issue:44483", + "right": "issue:45381", + "accept": false, + "reason": "Unrelated: chat/completions request acceptance vs Qwen2.5-VL video position_ids bug." + }, + { + "left": "issue:43064", + "right": "issue:44380", + "accept": false, + "reason": "Different subsystems: distributed training optimizer state bug vs GPT2 attention scaling ignored under SDPA/FlashAttention." + }, + { + "left": "issue:43901", + "right": "issue:44655", + "accept": false, + "reason": "Docs mismatch for return_all_scores vs inability to save Pipeline objects; not the same bug." + }, + { + "left": "issue:36683", + "right": "issue:43475", + "accept": false, + "reason": "Both are missing-attribute errors, but they affect different model configs/outputs and different fields." + }, + { + "left": "issue:43867", + "right": "issue:45216", + "accept": false, + "reason": "Related to saving/loading, but one is a load failure with sorted state_dict and the other is a save_pretrained regression for Qwen3.5." + }, + { + "left": "issue:42994", + "right": "issue:44655", + "accept": false, + "reason": "Both involve saving, but quantized model saving failure and pipeline save_pretrained are distinct code paths." + }, + { + "left": "issue:43352", + "right": "issue:43937", + "accept": false, + "reason": "Different failures: FlashAttention unsupported for Nemotron vs invalid GenerationConfig for GLM-5." + }, + { + "left": "issue:43066", + "right": "issue:45381", + "accept": false, + "reason": "Unrelated tokenizer-decoder typing issue vs Qwen2.5-VL video input position_ids bug." + }, + { + "left": "issue:36010", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but for unrelated symbols from different packages." + }, + { + "left": "issue:44220", + "right": "issue:44655", + "accept": false, + "reason": "Audio feature extraction bug vs saving Pipeline objects; no shared underlying defect." + }, + { + "left": "issue:43756", + "right": "issue:44485", + "accept": false, + "reason": "Different model-specific RoPE/implementation problems; not the same bug." + }, + { + "left": "issue:44263", + "right": "issue:45440", + "accept": false, + "reason": "Different model families and code paths: GlmMoeDsaIndexer split handling vs DeepseekV3MoE divergence." + }, + { + "left": "issue:36683", + "right": "issue:43525", + "accept": false, + "reason": "Both are missing config attributes, but they are different models and different missing fields." + }, + { + "left": "issue:43618", + "right": "issue:45216", + "accept": false, + "reason": "CLIP attentions regression and Qwen3.5 checkpoint corruption are unrelated." + }, + { + "left": "issue:43906", + "right": "issue:45753", + "accept": false, + "reason": "A reproduction of a prior issue is not the same bug as a Qwen3.5 image-specific infinite loop." + }, + { + "left": "issue:36683", + "right": "issue:44242", + "accept": false, + "reason": "Gemma3Config attribute error vs MoE load-balancing loss omission; different defects." + }, + { + "left": "issue:36683", + "right": "issue:43881", + "accept": false, + "reason": "Both are model-loading/config issues, but for different models and failures." + }, + { + "left": "issue:43299", + "right": "issue:45753", + "accept": false, + "reason": "Different Qwen3-related problems: MoE loading breakage vs generation infinite loop on a specific image." + }, + { + "left": "issue:43352", + "right": "issue:43976", + "accept": false, + "reason": "FlashAttention support issue vs Python version compatibility problem; unrelated." + }, + { + "left": "issue:43992", + "right": "issue:45310", + "accept": false, + "reason": "Different from_pretrained failures on different models and versions." + }, + { + "left": "issue:43441", + "right": "issue:44380", + "accept": false, + "reason": "Both involve attention backends, but one is a Ministral FlashAttention failure and the other is GPT2 attention scaling being ignored." + }, + { + "left": "issue:43352", + "right": "issue:44380", + "accept": false, + "reason": "Unrelated backend/attention bugs affecting different models and failure modes." + }, + { + "left": "issue:44380", + "right": "issue:45479", + "accept": false, + "reason": "GPT2 attention scaling bug and zero-loss sequence-classification bug are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 42, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:28282", + "issue:33453", + "issue:36296", + "issue:36683", + "issue:41669", + "issue:42548", + "issue:42890", + "issue:43010", + "issue:43064", + "issue:43097", + "issue:43352", + "issue:43502", + "issue:43575", + "issue:43618", + "issue:43867", + "issue:43901", + "issue:43976", + "issue:43992", + "issue:44062", + "issue:44075", + "issue:44077", + "issue:44112", + "issue:44117", + "issue:44222", + "issue:44246", + "issue:44351", + "issue:44355", + "issue:44360", + "issue:44380", + "issue:44484", + "issue:44485", + "issue:44492", + "issue:44655", + "issue:44749", + "issue:44855", + "issue:44857", + "issue:44938", + "issue:44964", + "issue:44977", + "issue:45125", + "issue:45341", + "issue:45357", + "issue:45375", + "issue:45440", + "issue:45478", + "issue:45561", + "issue:45588", + "issue:45600" + ], + "soft_pairs": [ + "issue:43867|issue:45375", + "issue:41669|issue:44246", + "issue:43618|issue:44380", + "issue:43064|issue:44492", + "issue:44355|issue:44855", + "issue:43352|issue:45478", + "issue:36683|issue:44117", + "issue:42890|issue:45561", + "issue:43097|issue:43352", + "issue:43867|issue:45357", + "issue:43976|issue:44938", + "issue:43992|issue:45478", + "issue:44360|issue:45440", + "issue:43064|issue:44655", + "issue:36296|issue:43575", + "issue:44077|issue:44380", + "issue:43867|issue:44484", + "issue:28282|issue:33453", + "issue:43618|issue:44857", + "issue:43618|issue:45588", + "issue:43618|issue:44977", + "issue:44655|issue:44938", + "issue:43901|issue:44938", + "issue:42890|issue:44964", + "issue:42890|issue:44112", + "issue:42890|issue:45600", + "issue:43502|issue:44062", + "issue:43010|issue:44075", + "issue:42890|issue:45341", + "issue:44222|issue:45125", + "issue:42548|issue:44351", + "issue:43502|issue:44485", + "issue:44355|issue:44749", + "issue:45125|issue:45478" + ], + "prepared_review_unit_hash": "3200ac9c6afe46eda2e2016bdb0a71a0c0738dfb946f0503f36025378c13beeb", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37423, + "estimated_input_tokens": 9356, + "estimated_eval_tokens": 18968 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a loose grab bag of unrelated issues across loading, training, testing, and model-specific regressions. None of the soft pairs look safe to merge as true duplicates.", + "confidence": 0.95, + "canonical_issue_reason": "issue:43867 is a clear, concrete core loading failure and the most broadly representative user-facing bug among this set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43867 is a strong standalone issue to anchor the cluster because it describes a specific model-loading error with likely broad impact.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43867", + "right": "issue:45375", + "accept": false, + "reason": "Sorted state_dict loading error is unrelated to missing Qwen3.5 vision config fields." + }, + { + "left": "issue:41669", + "right": "issue:44246", + "accept": false, + "reason": "Both mention import performance, but one is about removing import * and the other is an intermittent slowdown with different root cause." + }, + { + "left": "issue:43618", + "right": "issue:44380", + "accept": false, + "reason": "Different models and different bugs: missing CLIPOutput attentions vs GPT2 attention scaling ignored in backend paths." + }, + { + "left": "issue:43064", + "right": "issue:44492", + "accept": false, + "reason": "FSDP2/PEFT optimizer-state corruption is unrelated to a cache-strategy typo." + }, + { + "left": "issue:44355", + "right": "issue:44855", + "accept": false, + "reason": "Both are import-time failures, but one concerns compiled Python files generally and the other is a Python 3.13 torch.jit.script parsing issue." + }, + { + "left": "issue:43352", + "right": "issue:45478", + "accept": false, + "reason": "Nemotron Flash Attention 2 support and Qwen3.5 MoE from_pretrained errors are different model-specific problems." + }, + { + "left": "issue:36683", + "right": "issue:44117", + "accept": false, + "reason": "A missing config attribute is not the same as TOKENIZER_MAPPING_NAMES returning None during from_pretrained." + }, + { + "left": "issue:42890", + "right": "issue:45561", + "accept": false, + "reason": "SamHQ seeding flakiness and xdist race on captured_info.txt are different test failures." + }, + { + "left": "issue:43097", + "right": "issue:43352", + "accept": false, + "reason": "Removed tie_embeddings behavior is unrelated to Flash Attention support errors." + }, + { + "left": "issue:43867", + "right": "issue:45357", + "accept": false, + "reason": "Loading a sorted state_dict and saving incorrect visual encoder keys are different serialization bugs." + }, + { + "left": "issue:43976", + "right": "issue:44938", + "accept": false, + "reason": "These are separate Python-version compatibility failures with no shared code-path evidence." + }, + { + "left": "issue:43992", + "right": "issue:45478", + "accept": false, + "reason": "UMT5Encoder missing embed_tokens.weight and Qwen3.5 MoE from_pretrained failure are unrelated model-loading bugs." + }, + { + "left": "issue:44360", + "right": "issue:45440", + "accept": false, + "reason": "A missing ReLU in the DSA indexer is unrelated to DeepseekV3MoE diverging from remote implementation." + }, + { + "left": "issue:43064", + "right": "issue:44655", + "accept": false, + "reason": "Optimizer-state corruption during training is not the same as Pipeline.save_pretrained failing." + }, + { + "left": "issue:36296", + "right": "issue:43575", + "accept": false, + "reason": "Tensor-parallel training bug and TP OOM while loading a large model are different problems." + }, + { + "left": "issue:44077", + "right": "issue:44380", + "accept": false, + "reason": "A patchtsmixer post_init policy change is unrelated to GPT2 attention scaling under SDPA/FlashAttention." + }, + { + "left": "issue:43867", + "right": "issue:44484", + "accept": false, + "reason": "Sorted state_dict loading failure is not the same as a question about the default max_shard_size in save_pretrained." + }, + { + "left": "issue:28282", + "right": "issue:33453", + "accept": false, + "reason": "PyTorch-missing ImportError and tokenizer-loading regression are different failure modes." + }, + { + "left": "issue:43618", + "right": "issue:44857", + "accept": false, + "reason": "Missing CLIPOutput attentions is unrelated to LwDetrImageLoss crashing under float16 AMP." + }, + { + "left": "issue:43618", + "right": "issue:45588", + "accept": false, + "reason": "CLIPOutput attentions regression is unrelated to flash_attention.py crashing on s_aux=None." + }, + { + "left": "issue:43618", + "right": "issue:44977", + "accept": false, + "reason": "These concern different models and different flash-attention-related bugs." + }, + { + "left": "issue:44655", + "right": "issue:44938", + "accept": false, + "reason": "Pipeline save_pretrained failure is unrelated to Python 3.14 import/load breakage." + }, + { + "left": "issue:43901", + "right": "issue:44938", + "accept": false, + "reason": "A documentation mismatch in TextClassificationPipeline is not the same as Python 3.14 loading failure." + }, + { + "left": "issue:42890", + "right": "issue:44964", + "accept": false, + "reason": "SamHQ test seeding flakiness is unrelated to Phi-4 multimodal model loading failure." + }, + { + "left": "issue:42890", + "right": "issue:44112", + "accept": false, + "reason": "Both are test-related, but one is missing seeding and the other is a stale CI device-override test." + }, + { + "left": "issue:42890", + "right": "issue:45600", + "accept": false, + "reason": "SamHQ test seeding and auto_mappings references to removed configs are different issues." + }, + { + "left": "issue:43502", + "right": "issue:44062", + "accept": false, + "reason": "Local_files_only still making API requests and AddedToken duplicate special arg are unrelated." + }, + { + "left": "issue:43010", + "right": "issue:44075", + "accept": false, + "reason": "Cache update no_grad decoration and SGD args not used are unrelated training/runtime issues." + }, + { + "left": "issue:42890", + "right": "issue:45341", + "accept": false, + "reason": "SamHQ seeding flakiness is not the same as a generic bug in testing_utils.py." + }, + { + "left": "issue:44222", + "right": "issue:45125", + "accept": false, + "reason": "FP8 save_pretrained for MoE and missing _tp_plan for Qwen3_5Moe are different code paths." + }, + { + "left": "issue:42548", + "right": "issue:44351", + "accept": false, + "reason": "Cannot import PreTrainedModel and cannot import HybridCache are different missing-export problems." + }, + { + "left": "issue:43502", + "right": "issue:44485", + "accept": false, + "reason": "Local_files_only network requests and GLM-5 RoPE implementation are unrelated." + }, + { + "left": "issue:44355", + "right": "issue:44749", + "accept": false, + "reason": "Compiled Python import errors and a data-filtering slowdown after upgrade are not the same bug." + }, + { + "left": "issue:45125", + "right": "issue:45478", + "accept": false, + "reason": "Both involve Qwen3.5 MoE, but one is missing tensor-parallel plan support and the other is a from_pretrained regression." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 43, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:30333", + "issue:30990", + "issue:31795", + "issue:33453", + "issue:34689", + "issue:36296", + "issue:38617", + "issue:41628", + "issue:42548", + "issue:42757", + "issue:42831", + "issue:43010", + "issue:43232", + "issue:43299", + "issue:43502", + "issue:43526", + "issue:43576", + "issue:43723", + "issue:43824", + "issue:43827", + "issue:43874", + "issue:43901", + "issue:43976", + "issue:44222", + "issue:44230", + "issue:44261", + "issue:44273", + "issue:44315", + "issue:44351", + "issue:44355", + "issue:44360", + "issue:44368", + "issue:44387", + "issue:44556", + "issue:44623", + "issue:44655", + "issue:44908", + "issue:44961", + "issue:45003", + "issue:45071", + "issue:45125", + "issue:45230", + "issue:45278", + "issue:45375", + "issue:45468", + "issue:45542", + "issue:45656" + ], + "soft_pairs": [ + "issue:30990|issue:31795", + "issue:45125|issue:45375", + "issue:44387|issue:44556", + "issue:43010|issue:45278", + "issue:30333|issue:33453", + "issue:43723|issue:44556", + "issue:43010|issue:44368", + "issue:43502|issue:44222", + "issue:44315|issue:44360", + "issue:43502|issue:44961", + "issue:42831|issue:43874", + "issue:30333|issue:36296", + "issue:44355|issue:45071", + "issue:44355|issue:44655", + "issue:44222|issue:44230", + "issue:43827|issue:44961", + "issue:33453|issue:34689", + "issue:43010|issue:45656", + "issue:43299|issue:44556", + "issue:42757|issue:43576", + "issue:33453|issue:36296", + "issue:43576|issue:45071", + "issue:43576|issue:43824", + "issue:44961|issue:45468", + "issue:31795|issue:38617", + "issue:38617|issue:43576", + "issue:43010|issue:43976", + "issue:41628|issue:42548", + "issue:43576|issue:44351", + "issue:44908|issue:44961", + "issue:36296|issue:43901", + "issue:43010|issue:43232", + "issue:41628|issue:44355", + "issue:36296|issue:43526", + "issue:44261|issue:44360", + "issue:44273|issue:45003", + "issue:44273|issue:45542", + "issue:44623|issue:45230" + ], + "prepared_review_unit_hash": "83117f6a01803c198e801d79f1f56d1e58f0e7ca4c27932488d4df3555f67695", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 38, + "serialized_chars": 37903, + "estimated_input_tokens": 9476, + "estimated_eval_tokens": 19208 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These issues are mostly related by broad Transformers v5 regression themes, but they describe different concrete failures: import/export breakages, tokenizer/model loading, quantization, training, docs, and CLI behavior. I do not see any soft pair that is clearly the same underlying bug/change.", + "confidence": 0.84, + "canonical_issue_reason": "issue:45278 is the broadest and most representative open report of the upgrade/import-regression class, covering multiple failures after moving from 4.57.0 to 5.5.0.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the best single issue to anchor this cluster because it is explicit, broad, and closest to the repeated v5 import/loading regressions seen across the set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:30990", + "right": "issue:31795", + "accept": false, + "reason": "Different problems: a loading hang in Sentence Transformers vs docs confusion about forward args." + }, + { + "left": "issue:45125", + "right": "issue:45375", + "accept": false, + "reason": "Both touch Qwen3.5 MoE, but one is tensor-parallel plan support and the other is a config field being dropped by strict parsing." + }, + { + "left": "issue:44387", + "right": "issue:44556", + "accept": false, + "reason": "Int4 quantization OOM is a runtime memory regression; checkpoint reload after upgrade is a separate loading failure." + }, + { + "left": "issue:43010", + "right": "issue:45278", + "accept": false, + "reason": "Cache/layer no_grad behavior is unrelated to the broad import-error regression report." + }, + { + "left": "issue:30333", + "right": "issue:33453", + "accept": false, + "reason": "MLFlow reporting after failed training is unrelated to tokenizer loading regression." + }, + { + "left": "issue:43723", + "right": "issue:44556", + "accept": false, + "reason": "Tokenizer loading in v5 and checkpoint reload after upgrade are different loading paths and likely different bugs." + }, + { + "left": "issue:43010", + "right": "issue:44368", + "accept": false, + "reason": "No-grad cache updates and a tie_word_embeddings warning are unrelated." + }, + { + "left": "issue:43502", + "right": "issue:44222", + "accept": false, + "reason": "Local_files_only network leakage and FP8 save_pretrained moE are different code paths." + }, + { + "left": "issue:44315", + "right": "issue:44360", + "accept": false, + "reason": "Applying Liger Kernel via model_init is unrelated to a DSA indexer ReLU omission." + }, + { + "left": "issue:43502", + "right": "issue:44961", + "accept": false, + "reason": "API calls despite local_files_only and an unrelated placeholder issue are not the same bug." + }, + { + "left": "issue:42831", + "right": "issue:43874", + "accept": false, + "reason": "FineGrainedFP8 accuracy drift and a missing image-patch-count method are different issues." + }, + { + "left": "issue:30333", + "right": "issue:36296", + "accept": false, + "reason": "MLFlow failure reporting and tensor-parallel training are unrelated." + }, + { + "left": "issue:44355", + "right": "issue:45071", + "accept": false, + "reason": "Compiled Python file errors and PretrainedConfig type checking are different regressions." + }, + { + "left": "issue:44355", + "right": "issue:44655", + "accept": false, + "reason": "Compiled-file execution errors are unrelated to saving Pipeline objects." + }, + { + "left": "issue:44222", + "right": "issue:44230", + "accept": false, + "reason": "Save_pretrained on FP8 MoE and FP8 inference support are different change requests." + }, + { + "left": "issue:43827", + "right": "issue:44961", + "accept": false, + "reason": "Docs still referencing pipeline() and a placeholder issue are unrelated." + }, + { + "left": "issue:33453", + "right": "issue:34689", + "accept": false, + "reason": "Tokenizer-loading regression and Llama 3.2 model-loading breakage are different failures." + }, + { + "left": "issue:43010", + "right": "issue:45656", + "accept": false, + "reason": "Cache update no_grad behavior is unrelated to double optimizer-step calls under deepspeed." + }, + { + "left": "issue:43299", + "right": "issue:44556", + "accept": false, + "reason": "Qwen3VL MoE model loading and checkpoint reload-after-upgrade are not the same concrete bug." + }, + { + "left": "issue:42757", + "right": "issue:43576", + "accept": false, + "reason": "Missing huggingface_hub symbol import and the transformers env CLI are different surfaces." + }, + { + "left": "issue:33453", + "right": "issue:36296", + "accept": false, + "reason": "Tokenizer loading regression and tensor-parallel training bug are unrelated." + }, + { + "left": "issue:43576", + "right": "issue:45071", + "accept": false, + "reason": "CLI env command breakage and PretrainedConfig type-checking are separate regressions." + }, + { + "left": "issue:43576", + "right": "issue:43824", + "accept": false, + "reason": "CLI env command breakage and missing Qwen2_5_VL export are different import surfaces." + }, + { + "left": "issue:44961", + "right": "issue:45468", + "accept": false, + "reason": "Placeholder racoon issue is unrelated to Gemma4 audio positional encoding." + }, + { + "left": "issue:31795", + "right": "issue:38617", + "accept": false, + "reason": "Docs confusion in model.forward is unrelated to an ImportError for layer_type_validation." + }, + { + "left": "issue:38617", + "right": "issue:43576", + "accept": false, + "reason": "ImportError for a missing utility symbol is not the same as the env CLI breakage." + }, + { + "left": "issue:43010", + "right": "issue:43976", + "accept": false, + "reason": "No-grad cache update behavior is unrelated to Python version compatibility failure." + }, + { + "left": "issue:41628", + "right": "issue:42548", + "accept": false, + "reason": "Both are import errors, but for different exported symbols and likely different breakages." + }, + { + "left": "issue:43576", + "right": "issue:44351", + "accept": false, + "reason": "CLI env command and HybridCache import failure are different issues." + }, + { + "left": "issue:44908", + "right": "issue:44961", + "accept": false, + "reason": "Inverse_sqrt scheduler kwargs handling is unrelated to the placeholder issue." + }, + { + "left": "issue:36296", + "right": "issue:43901", + "accept": false, + "reason": "Tensor-parallel training bug and documentation of text-classification outputs are unrelated." + }, + { + "left": "issue:43010", + "right": "issue:43232", + "accept": false, + "reason": "Cache/layer update no_grad and generation sync_gpus model-kwargs handling are different code paths." + }, + { + "left": "issue:41628", + "right": "issue:44355", + "accept": false, + "reason": "AutoImageProcessor import failure and compiled Python file errors are unrelated." + }, + { + "left": "issue:36296", + "right": "issue:43526", + "accept": false, + "reason": "Tensor-parallel training and BeitImageProcessorFast label reduction are different bugs." + }, + { + "left": "issue:44261", + "right": "issue:44360", + "accept": false, + "reason": "MLA q_a_layernorm precision/config issue is unrelated to the DSA indexer ReLU bug." + }, + { + "left": "issue:44273", + "right": "issue:45003", + "accept": false, + "reason": "Lazy loading failure and unsafe sys.modules access are related in theme but not clearly the same concrete bug." + }, + { + "left": "issue:44273", + "right": "issue:45542", + "accept": false, + "reason": "Lazy loading behavior and TensorBoard-without-TF backend handling are separate problems." + }, + { + "left": "issue:44623", + "right": "issue:45230", + "accept": false, + "reason": "Missing processor save_pretrained files is too specific to merge with a generic bug report." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 44, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:31795", + "issue:33453", + "issue:34689", + "issue:37428", + "issue:41669", + "issue:42371", + "issue:42890", + "issue:43352", + "issue:43408", + "issue:43502", + "issue:43519", + "issue:43576", + "issue:43606", + "issue:43673", + "issue:43704", + "issue:43827", + "issue:43976", + "issue:44038", + "issue:44077", + "issue:44246", + "issue:44263", + "issue:44273", + "issue:44295", + "issue:44297", + "issue:44315", + "issue:44351", + "issue:44360", + "issue:44373", + "issue:44393", + "issue:44485", + "issue:44492", + "issue:44556", + "issue:44623", + "issue:44655", + "issue:44704", + "issue:44829", + "issue:44861", + "issue:44908", + "issue:44961", + "issue:45071", + "issue:45092", + "issue:45125", + "issue:45230", + "issue:45310", + "issue:45341", + "issue:45468", + "issue:45478", + "issue:45753" + ], + "soft_pairs": [ + "issue:44393|issue:45753", + "issue:43576|issue:44556", + "issue:44038|issue:45125", + "issue:44393|issue:45071", + "issue:41669|issue:43673", + "issue:44556|issue:45092", + "issue:44373|issue:44961", + "issue:44704|issue:44908", + "issue:42890|issue:44908", + "issue:44246|issue:44273", + "issue:43408|issue:44315", + "issue:43976|issue:44393", + "issue:43352|issue:44393", + "issue:43576|issue:44908", + "issue:44908|issue:45071", + "issue:44297|issue:45230", + "issue:41669|issue:44351", + "issue:44295|issue:45230", + "issue:43673|issue:44492", + "issue:41669|issue:45341", + "issue:44393|issue:45478", + "issue:41669|issue:44492", + "issue:44315|issue:44829", + "issue:44077|issue:44861", + "issue:43827|issue:44908", + "issue:31795|issue:33453", + "issue:41669|issue:44908", + "issue:42371|issue:44492", + "issue:44655|issue:44861", + "issue:43576|issue:44273", + "issue:44360|issue:45468", + "issue:44273|issue:44908", + "issue:43827|issue:44492", + "issue:45230|issue:45310", + "issue:43519|issue:44485", + "issue:41669|issue:43704", + "issue:43519|issue:44908", + "issue:31795|issue:34689", + "issue:31795|issue:37428", + "issue:44315|issue:45092", + "issue:43704|issue:44485", + "issue:44485|issue:45468", + "issue:42371|issue:43704", + "issue:43502|issue:43519", + "issue:43519|issue:44623", + "issue:43519|issue:43704", + "issue:44263|issue:45468", + "issue:43606|issue:45468" + ], + "prepared_review_unit_hash": "109b2890f00cfd2d3e96c25ec4c1965b5eb03a53ba37ea062b2122f300bd2685", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 48, + "serialized_chars": 41368, + "estimated_input_tokens": 10342, + "estimated_eval_tokens": 20940 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is highly heterogeneous: the soft links are mostly title similarity across unrelated docs, loading regressions, model-specific bugs, and perf issues. I would not merge any of the soft pairs as duplicates.", + "confidence": 0.92, + "canonical_issue_reason": "No clear canonical issue emerges because the items do not share one underlying bug or change; they span distinct subsystems and symptoms.", + "canonical_pr_reason": null, + "best_issue_reason": "No single issue is a good global representative here; the set is too broad and inconsistent to center on one bug report.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44393", + "right": "issue:45753", + "accept": false, + "reason": "Both are Qwen3 vision-model problems, but one is a 2D bbox hallucination/error and the other is an infinite-loop case on a specific image; different bugs." + }, + { + "left": "issue:43576", + "right": "issue:44556", + "accept": false, + "reason": "One is a broken `transformers env` command and the other is a checkpoint reload regression after upgrading to v5; separate code paths." + }, + { + "left": "issue:44038", + "right": "issue:45125", + "accept": false, + "reason": "These are both Qwen3-MoE related, but one is a from_pretrained error and the other is a missing tensor-parallel plan; not the same defect." + }, + { + "left": "issue:44393", + "right": "issue:45071", + "accept": false, + "reason": "A vision-model bbox output bug is unrelated to a `PretrainedConfig` type-checking regression." + }, + { + "left": "issue:41669", + "right": "issue:43673", + "accept": false, + "reason": "Import-star cleanup/perf concerns do not match the chunked_prefill cache regression." + }, + { + "left": "issue:44556", + "right": "issue:45092", + "accept": false, + "reason": "Both involve v5 loading regressions, but one is generic checkpoint reload and the other is remote-code meta-initialization incompatibility for InternVL2." + }, + { + "left": "issue:44373", + "right": "issue:44961", + "accept": false, + "reason": "A wrong docstring for `position_ids` is unrelated to a placeholder `racoon` issue." + }, + { + "left": "issue:44704", + "right": "issue:44908", + "accept": false, + "reason": "Forwarding kwargs to `cached_file` and scheduler `lr_scheduler_kwargs` are unrelated API bugs." + }, + { + "left": "issue:42890", + "right": "issue:44908", + "accept": false, + "reason": "A flaky integration test due to missing seeds is unrelated to an inverse-sqrt scheduler kwargs regression." + }, + { + "left": "issue:44246", + "right": "issue:44273", + "accept": false, + "reason": "Import-time slowness and lazy-loading failure are different symptoms without a shared concrete bug." + }, + { + "left": "issue:43408", + "right": "issue:44315", + "accept": false, + "reason": "A sam3_video/sam3_tracker type mismatch is unrelated to `patchtsmixer` and `model_init`/`post_init` handling." + }, + { + "left": "issue:43976", + "right": "issue:44393", + "accept": false, + "reason": "Python version support regression and Qwen3-VL bbox output issues are unrelated." + }, + { + "left": "issue:43352", + "right": "issue:44393", + "accept": false, + "reason": "Flash Attention 2 support for Nemotron and a Qwen3-VL output bug are different problems." + }, + { + "left": "issue:43576", + "right": "issue:44908", + "accept": false, + "reason": "A broken CLI env command and scheduler keyword handling are unrelated." + }, + { + "left": "issue:44908", + "right": "issue:45071", + "accept": false, + "reason": "Scheduler kwargs handling and `PretrainedConfig` type checking do not share the same root cause." + }, + { + "left": "issue:44297", + "right": "issue:45230", + "accept": false, + "reason": "Tokenizer save metadata mismatch and a vague generic bug report are not enough to establish a duplicate." + }, + { + "left": "issue:41669", + "right": "issue:44351", + "accept": false, + "reason": "Import-star cleanup/perf work is unrelated to the missing `HybridCache` import failure." + }, + { + "left": "issue:44295", + "right": "issue:45230", + "accept": false, + "reason": "Position-ids buffer handling and a generic bug report are unrelated." + }, + { + "left": "issue:43673", + "right": "issue:44492", + "accept": false, + "reason": "Missing cache in chunked_prefill and a typo in cache strategy docs are not the same issue." + }, + { + "left": "issue:41669", + "right": "issue:45341", + "accept": false, + "reason": "Import performance work is unrelated to a small `testing_utils.py` bug." + }, + { + "left": "issue:44393", + "right": "issue:45478", + "accept": false, + "reason": "A Qwen3-VL bbox output bug and a Qwen3.5 MoE from_pretrained regression are different model failures." + }, + { + "left": "issue:41669", + "right": "issue:44492", + "accept": false, + "reason": "Import-star cleanup/perf and a cache-strategy typo are unrelated." + }, + { + "left": "issue:44315", + "right": "issue:44829", + "accept": false, + "reason": "`model_init`/`post_init` behavior with Liger Kernel is unrelated to Flash Attention 3 degenerate training." + }, + { + "left": "issue:44077", + "right": "issue:44861", + "accept": false, + "reason": "A `post_init` restriction and `_get_tied_weight_keys` crashing on a list are different issues." + }, + { + "left": "issue:43827", + "right": "issue:44908", + "accept": false, + "reason": "Docs still mentioning `pipeline()` and scheduler kwargs are unrelated." + }, + { + "left": "issue:31795", + "right": "issue:33453", + "accept": false, + "reason": "Confusing forward-docs for `input_ids`/`past_key_values` is unrelated to a tokenizer loading regression." + }, + { + "left": "issue:41669", + "right": "issue:44908", + "accept": false, + "reason": "Import performance and scheduler kwargs handling are unrelated." + }, + { + "left": "issue:42371", + "right": "issue:44492", + "accept": false, + "reason": "TF32 API guidance and cache-strategy typos do not describe the same bug." + }, + { + "left": "issue:44655", + "right": "issue:44861", + "accept": false, + "reason": "Saving Pipeline objects and `_get_tied_weight_keys` AttributeError are unrelated." + }, + { + "left": "issue:43576", + "right": "issue:44273", + "accept": false, + "reason": "A broken env command and lazy loading not working are different bugs." + }, + { + "left": "issue:44360", + "right": "issue:45468", + "accept": false, + "reason": "A DSA indexer discussion about ReLU is unrelated to Gemma-4 audio positional encoding." + }, + { + "left": "issue:44273", + "right": "issue:44908", + "accept": false, + "reason": "Lazy loading behavior and inverse-sqrt scheduler kwargs are unrelated." + }, + { + "left": "issue:43827", + "right": "issue:44492", + "accept": false, + "reason": "Pipeline-removal docs and cache-strategy typos are unrelated." + }, + { + "left": "issue:45230", + "right": "issue:45310", + "accept": false, + "reason": "The generic bug report is too vague to match the Qwen3.5 MoE from_pretrained regression." + }, + { + "left": "issue:43519", + "right": "issue:44485", + "accept": false, + "reason": "Qwen3-VL timestamp calculation and GLM-5 RoPE implementation are different model-specific bugs." + }, + { + "left": "issue:41669", + "right": "issue:43704", + "accept": false, + "reason": "Import-star cleanup/perf and a VRAM leak in Qwen3ForCausalLM are unrelated." + }, + { + "left": "issue:43519", + "right": "issue:44908", + "accept": false, + "reason": "Qwen3VL timestamp math and scheduler kwargs handling are unrelated." + }, + { + "left": "issue:31795", + "right": "issue:34689", + "accept": false, + "reason": "Forward-doc confusion for `input_ids`/`past_key_values` is unrelated to the Llama 3.2 Vision model-loading regression." + }, + { + "left": "issue:31795", + "right": "issue:37428", + "accept": false, + "reason": "A documentation issue and a flash-attention import error are unrelated." + }, + { + "left": "issue:44315", + "right": "issue:45092", + "accept": false, + "reason": "`model_init`/Liger Kernel behavior and InternVL2 meta-init incompatibility are different problems." + }, + { + "left": "issue:43704", + "right": "issue:44485", + "accept": false, + "reason": "A VRAM leak in Qwen3ForCausalLM is unrelated to GLM-5 RoPE implementation." + }, + { + "left": "issue:44485", + "right": "issue:45468", + "accept": false, + "reason": "GLM-5 RoPE implementation and Gemma-4 audio positional encoding are unrelated." + }, + { + "left": "issue:42371", + "right": "issue:43704", + "accept": false, + "reason": "TF32 API guidance and a Qwen3ForCausalLM VRAM leak are unrelated." + }, + { + "left": "issue:43502", + "right": "issue:43519", + "accept": false, + "reason": "Unexpected API requests with `local_files_only=True` and Qwen3VL timestamp calculation are different bugs." + }, + { + "left": "issue:43519", + "right": "issue:44623", + "accept": false, + "reason": "Qwen3VL timestamp computation and missing files in `processor.save_pretrained` are unrelated." + }, + { + "left": "issue:43519", + "right": "issue:43704", + "accept": false, + "reason": "Timestamp calculation in Qwen3VL and a VRAM leak in Qwen3ForCausalLM are different defects." + }, + { + "left": "issue:44263", + "right": "issue:45468", + "accept": false, + "reason": "A `torch.split()` return-value issue in GlmMoeDsaIndexer is unrelated to Gemma-4 audio positional encoding." + }, + { + "left": "issue:43606", + "right": "issue:45468", + "accept": false, + "reason": "CPU offload device mismatch in Bark is unrelated to Gemma-4 audio positional encoding." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 45, + "review_unit_count": 45, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-390", + "nodes": [ + "issue:30333", + "issue:31515", + "issue:31795", + "issue:33453", + "issue:36296", + "issue:38617", + "issue:41669", + "issue:42913", + "issue:43066", + "issue:43298", + "issue:43525", + "issue:43572", + "issue:43704", + "issue:44230", + "issue:44261", + "issue:44360", + "issue:44623", + "issue:44861", + "issue:44908", + "issue:44998", + "issue:45290", + "issue:45310", + "issue:45341", + "issue:45468" + ], + "soft_pairs": [ + "issue:44261|issue:45468", + "issue:43704|issue:45341", + "issue:42913|issue:43066", + "issue:44908|issue:44998", + "issue:44861|issue:45290", + "issue:43525|issue:44861", + "issue:43704|issue:44998", + "issue:41669|issue:44998", + "issue:43572|issue:44861", + "issue:43066|issue:44998", + "issue:31515|issue:38617", + "issue:44360|issue:44998", + "issue:44230|issue:44623", + "issue:30333|issue:31515", + "issue:31515|issue:36296", + "issue:31515|issue:31795", + "issue:44230|issue:45310", + "issue:31515|issue:33453", + "issue:43298|issue:44230" + ], + "prepared_review_unit_hash": "0402f14e9110bbbc279ca0ced579c476daaa9a2350bc85290cd379d132406361", + "component_budget": { + "node_count": 390, + "item_count": 390, + "soft_pair_count": 1471, + "serialized_chars": 757027, + "estimated_input_tokens": 189257, + "estimated_eval_tokens": 378770 + }, + "budget": { + "node_count": 24, + "item_count": 24, + "soft_pair_count": 19, + "serialized_chars": 19156, + "estimated_input_tokens": 4789, + "estimated_eval_tokens": 9834 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: the soft-similarity links mostly connect unrelated bugs that only share broad subsystem vocabulary (loading, tokenizer, configs, training). No pair looks like the same underlying issue, so I would not merge any of them as duplicates.", + "confidence": 0.9, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44261", + "right": "issue:45468", + "accept": false, + "reason": "Both are model/config-related, but they concern different components and failure modes: MLA RMS norm epsilon precision vs Gemma4 audio positional encoding." + }, + { + "left": "issue:43704", + "right": "issue:45341", + "accept": false, + "reason": "A VRAM leak in Qwen3ForCausalLM is unrelated to a testing_utils bug; no shared code-path or concrete fix target." + }, + { + "left": "issue:42913", + "right": "issue:43066", + "accept": false, + "reason": "Both mention tokenizer changes in v5, but one is about behavioral differences across versions and the other about the wrong decoder type; too different to be the same bug." + }, + { + "left": "issue:44908", + "right": "issue:44998", + "accept": false, + "reason": "Scheduler kwargs handling and an unrelated placeholder issue are not the same underlying change." + }, + { + "left": "issue:44861", + "right": "issue:45290", + "accept": false, + "reason": "Tied-weight key handling and chat template tool-call crashes affect different code paths and error surfaces." + }, + { + "left": "issue:43525", + "right": "issue:44861", + "accept": false, + "reason": "Missing pad_token_id on Llama4Config is unrelated to _get_tied_weight_keys crashing on list-typed _tied_weights_keys." + }, + { + "left": "issue:43704", + "right": "issue:44998", + "accept": false, + "reason": "No substantive overlap; a memory leak bug is not related to the placeholder issue." + }, + { + "left": "issue:41669", + "right": "issue:44998", + "accept": false, + "reason": "Import-star performance regression and the placeholder issue are clearly unrelated." + }, + { + "left": "issue:43572", + "right": "issue:44861", + "accept": false, + "reason": "StableLmConfig missing pad_token_idx is a config-field regression, not a tied-weights attribute error." + }, + { + "left": "issue:43066", + "right": "issue:44998", + "accept": false, + "reason": "Wrong tokenizer decoder type is unrelated to the placeholder issue." + }, + { + "left": "issue:31515", + "right": "issue:38617", + "accept": false, + "reason": "Slow checkpoint loading and an ImportError for layer_type_validation are different failure modes with no shared fix." + }, + { + "left": "issue:44360", + "right": "issue:44998", + "accept": false, + "reason": "A DSA indexer activation-function discussion is unrelated to the placeholder issue." + }, + { + "left": "issue:44230", + "right": "issue:44623", + "accept": false, + "reason": "FP8 Qwen3-VL/MoE inference support and processor.save_pretrained missing files are distinct feature/bug areas." + }, + { + "left": "issue:30333", + "right": "issue:31515", + "accept": false, + "reason": "MLflow job status reporting on training failure is unrelated to slow from_pretrained checkpoint loading." + }, + { + "left": "issue:31515", + "right": "issue:36296", + "accept": false, + "reason": "Slow checkpoint loading and a tensor-parallel training bug are different problems and would not be fixed by one PR." + }, + { + "left": "issue:31515", + "right": "issue:31795", + "accept": false, + "reason": "Checkpoint loading performance and documentation confusion about input_ids/past_key_values are not the same underlying issue." + }, + { + "left": "issue:44230", + "right": "issue:45310", + "accept": false, + "reason": "Both involve Qwen3/MoE model loading/inference, but one is fp8 support and the other is a from_pretrained regression; too different to merge as duplicates." + }, + { + "left": "issue:31515", + "right": "issue:33453", + "accept": false, + "reason": "Slow checkpoint loading and a tokenizer-loading regression are superficially related but not the same concrete bug." + }, + { + "left": "issue:43298", + "right": "issue:44230", + "accept": false, + "reason": "Continuous batching support for audio models and fp8 Qwen3-VL/Qwen3.5 MoE inference 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": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-26350-2", + "nodes": [ + "issue:26350", + "issue:33260" + ], + "soft_pairs": [ + "issue:26350|issue:33260" + ], + "prepared_review_unit_hash": "9e2a8079ad7609ae8131c254c0c41bdaf0de2012b6182768b2366f97caa9ad84", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1589, + "estimated_input_tokens": 398, + "estimated_eval_tokens": 1052 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1589, + "estimated_input_tokens": 398, + "estimated_eval_tokens": 1052 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are not duplicates: one requests Flash Attention 2 support for more architectures, the other requests GGUF support for more architectures. They share a phrasing pattern but describe different feature areas and different underlying changes.", + "confidence": 0.98, + "canonical_issue_reason": "No canonical issue: the requests target different features (Flash Attention 2 vs GGUF) and are not the same bug or change.", + "canonical_pr_reason": null, + "best_issue_reason": "Neither issue is a duplicate of the other; if a representative is needed, issue 26350 is slightly more established by discussion activity, but the cluster should really be kept separate.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:26350", + "right": "issue:33260", + "accept": false, + "reason": "Different requested capabilities and code paths: Flash Attention 2 support vs GGUF support. Similar wording, 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": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-27088-4", + "nodes": [ + "issue:27088", + "issue:43834", + "issue:44365", + "issue:44370" + ], + "soft_pairs": [ + "issue:27088|issue:44370", + "issue:27088|issue:44365", + "issue:27088|issue:43834", + "issue:43834|issue:44370", + "issue:43834|issue:44365", + "issue:44365|issue:44370" + ], + "prepared_review_unit_hash": "0724cc51aed38e8269fa5b11920a43d7a35de3cb2dd0e2ddba4f3ab849f2564e", + "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": "Three of the issues are near-verbatim duplicates of the same i18n translation template, while the Turkish-specific issue is similar but not clearly the same request. No PRs are present.", + "confidence": 0.73, + "canonical_issue_reason": "issue:43834 is the cleanest representative of the clearly duplicate template trio: it matches the other placeholder issues almost exactly and is the earliest of that set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43834 is the best canonical representative because its title/body are essentially identical to the other duplicate template issues and it is the earliest instance.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:27088", + "right": "issue:44370", + "accept": false, + "reason": "The Turkish-specific title differs from the placeholder template issues; similarity alone is not enough to prove the same underlying request." + }, + { + "left": "issue:27088", + "right": "issue:44365", + "accept": false, + "reason": "Same reason: this is a language-specific issue versus a generic template variant, so the match is too weak to merge confidently." + }, + { + "left": "issue:27088", + "right": "issue:43834", + "accept": false, + "reason": "The content is highly similar, but the concrete Turkish issue is not clearly the same underlying request as the generic placeholder issue." + }, + { + "left": "issue:43834", + "right": "issue:44370", + "accept": true, + "reason": "These two are near-verbatim duplicates with the same generic i18n translation template wording and almost identical body size." + }, + { + "left": "issue:43834", + "right": "issue:44365", + "accept": true, + "reason": "Near-identical placeholder issue text; they look like the same underlying template issue." + }, + { + "left": "issue:44365", + "right": "issue:44370", + "accept": true, + "reason": "These are effectively the same issue text/body and clearly duplicate each other." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet: 43834 is the earliest of the three near-identical template issues, the template trio is supported by the identical titles and very high similarity scores, and the Turkish issue is conservatively kept separate. No PRs are present, and the soft-edge verdicts do not overstate the evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 5, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-36817-15", + "nodes": [ + "issue:36817", + "issue:36879", + "issue:37015", + "issue:41115", + "issue:41211", + "issue:42503", + "issue:42738", + "issue:43671", + "issue:43837", + "issue:43909", + "issue:44121", + "issue:44205", + "issue:45027", + "issue:45177", + "issue:45322" + ], + "soft_pairs": [ + "issue:36817|issue:41211", + "issue:36817|issue:43671", + "issue:36817|issue:36879", + "issue:36879|issue:41211", + "issue:36879|issue:43909", + "issue:36879|issue:44121", + "issue:36879|issue:43837", + "issue:36879|issue:43671", + "issue:37015|issue:43837", + "issue:37015|issue:44121", + "issue:37015|issue:43909", + "issue:37015|issue:42503", + "issue:36879|issue:37015", + "issue:41115|issue:43837", + "issue:41115|issue:44121", + "issue:41115|issue:42503", + "issue:41115|issue:45027", + "issue:41211|issue:43671", + "issue:42503|issue:43837", + "issue:42503|issue:43671", + "issue:42503|issue:42738", + "issue:42738|issue:45027", + "issue:43671|issue:43837", + "issue:43671|issue:45027", + "issue:43671|issue:45177", + "issue:43671|issue:44121", + "issue:43837|issue:45322", + "issue:43837|issue:43909", + "issue:43909|issue:44205", + "issue:43671|issue:43909", + "issue:44121|issue:45322", + "issue:43837|issue:44121", + "issue:43837|issue:45027", + "issue:37015|issue:45027", + "issue:43837|issue:45177" + ], + "prepared_review_unit_hash": "e66e00a9b79eb67d78a35a0d698423c3baecf01753195ccb91c5958b9c760912", + "component_budget": { + "node_count": 15, + "item_count": 15, + "soft_pair_count": 35, + "serialized_chars": 20708, + "estimated_input_tokens": 5177, + "estimated_eval_tokens": 10610 + }, + "budget": { + "node_count": 15, + "item_count": 15, + "soft_pair_count": 35, + "serialized_chars": 20708, + "estimated_input_tokens": 5177, + "estimated_eval_tokens": 10610 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This is a loose cluster of model-support requests that share topical wording ('add/support model') but not the same underlying change. None of the soft edges look like true duplicates, so all are rejected. If a single representative issue is needed, the broadest umbrella-style request is the BERT-family/RoPE item.", + "confidence": 0.42, + "canonical_issue_reason": "issue:42738 is the broadest, most umbrella-like request in the set ('BERT-like models with RoPE'), so it best represents the BERT-family subset without being tied to one narrow model name.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:42738 is the most general and reusable representative among the issues; the others are mostly model-specific requests spanning unrelated modalities and architectures.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36817", + "right": "issue:41211", + "accept": false, + "reason": "Different model families; only the generic 'add model' wording overlaps." + }, + { + "left": "issue:36817", + "right": "issue:43671", + "accept": false, + "reason": "EuroBert and Qwen3-TTS are unrelated model requests and code paths." + }, + { + "left": "issue:36817", + "right": "issue:36879", + "accept": false, + "reason": "Both are model-add requests, but for different concrete models and domains." + }, + { + "left": "issue:36879", + "right": "issue:41211", + "accept": false, + "reason": "RF-DETR and DEIMv2 are distinct detection models, not the same change." + }, + { + "left": "issue:36879", + "right": "issue:43909", + "accept": false, + "reason": "Object detection vs audio model support; unrelated implementations." + }, + { + "left": "issue:36879", + "right": "issue:44121", + "accept": false, + "reason": "Different architectures and product goals; not the same concrete fix." + }, + { + "left": "issue:36879", + "right": "issue:43837", + "accept": false, + "reason": "Different tasks (detection vs ASR) and different model families." + }, + { + "left": "issue:36879", + "right": "issue:43671", + "accept": false, + "reason": "Detection model request vs TTS request; no shared code path." + }, + { + "left": "issue:37015", + "right": "issue:43837", + "accept": false, + "reason": "NeoBERT and Qwen3-ASR are unrelated models and modalities." + }, + { + "left": "issue:37015", + "right": "issue:44121", + "accept": false, + "reason": "Different model families; only broad transformer overlap." + }, + { + "left": "issue:37015", + "right": "issue:43909", + "accept": false, + "reason": "BERT-style encoder request vs audio model support." + }, + { + "left": "issue:37015", + "right": "issue:42503", + "accept": false, + "reason": "Related naming pattern, but these are separate model additions, not one bug/change." + }, + { + "left": "issue:36879", + "right": "issue:37015", + "accept": false, + "reason": "Different specific model requests; no evidence of the same underlying change." + }, + { + "left": "issue:41115", + "right": "issue:43837", + "accept": false, + "reason": "MiniCPM3 and Qwen3-ASR address different model support paths." + }, + { + "left": "issue:41115", + "right": "issue:44121", + "accept": false, + "reason": "Different model architectures; not mergeable as one PR-style fix." + }, + { + "left": "issue:41115", + "right": "issue:42503", + "accept": false, + "reason": "Both are model requests, but for distinct models with separate integration work." + }, + { + "left": "issue:41115", + "right": "issue:45027", + "accept": false, + "reason": "MiniCPM3 vs Voxtral TTS are different model families and tasks." + }, + { + "left": "issue:41211", + "right": "issue:43671", + "accept": false, + "reason": "DEIMv2 and Qwen3-TTS are unrelated requests." + }, + { + "left": "issue:42503", + "right": "issue:43837", + "accept": false, + "reason": "ModernVBERT and Qwen3-ASR are distinct model additions." + }, + { + "left": "issue:42503", + "right": "issue:43671", + "accept": false, + "reason": "Different families and tasks; no shared concrete implementation." + }, + { + "left": "issue:42503", + "right": "issue:42738", + "accept": false, + "reason": "ModernVBERT is a specific model request, while 42738 is a broader family-level request." + }, + { + "left": "issue:42738", + "right": "issue:45027", + "accept": false, + "reason": "BERT-like RoPE models and Voxtral TTS are different domains." + }, + { + "left": "issue:43671", + "right": "issue:43837", + "accept": false, + "reason": "Same base family name (Qwen3) but different modalities/tasks: TTS vs ASR." + }, + { + "left": "issue:43671", + "right": "issue:45027", + "accept": false, + "reason": "Both are TTS-related, but they target different model families and integration paths." + }, + { + "left": "issue:43671", + "right": "issue:45177", + "accept": false, + "reason": "Speech synthesis vs OCR are unrelated changes." + }, + { + "left": "issue:43671", + "right": "issue:44121", + "accept": false, + "reason": "Different model families and code paths; not the same change." + }, + { + "left": "issue:43837", + "right": "issue:45322", + "accept": false, + "reason": "ASR support and EUPE are unrelated model requests." + }, + { + "left": "issue:43837", + "right": "issue:43909", + "accept": false, + "reason": "Both are audio-related, but they request different models and tasks." + }, + { + "left": "issue:43909", + "right": "issue:44205", + "accept": false, + "reason": "Audio model request vs segmentation/text model request; unrelated." + }, + { + "left": "issue:43671", + "right": "issue:43909", + "accept": false, + "reason": "Different audio model families and different concrete support work." + }, + { + "left": "issue:44121", + "right": "issue:45322", + "accept": false, + "reason": "OpenAI sparse transformer and EUPE are different architectures with no shared fix." + }, + { + "left": "issue:43837", + "right": "issue:44121", + "accept": false, + "reason": "ASR model support and sparse transformer support are unrelated." + }, + { + "left": "issue:43837", + "right": "issue:45027", + "accept": false, + "reason": "Qwen3-ASR and Voxtral TTS are different speech tasks and model integrations." + }, + { + "left": "issue:37015", + "right": "issue:45027", + "accept": false, + "reason": "NeoBERT and Voxtral TTS are unrelated model families/tasks." + }, + { + "left": "issue:43837", + "right": "issue:45177", + "accept": false, + "reason": "Speech recognition vs OCR; not the same underlying request." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 6, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-37934-6", + "nodes": [ + "issue:37934", + "issue:42936", + "issue:43240", + "issue:43668", + "issue:43813", + "issue:44031" + ], + "soft_pairs": [ + "issue:37934|issue:43668", + "issue:42936|issue:43240", + "issue:42936|issue:44031", + "issue:42936|issue:43813", + "issue:42936|issue:43668", + "issue:43240|issue:43668", + "issue:43668|issue:44031", + "issue:43668|issue:43813" + ], + "prepared_review_unit_hash": "ce14def5214907f448c730130aa08696445b4647727e2c946cc1cc0b1a7fd98b", + "component_budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 8, + "serialized_chars": 6292, + "estimated_input_tokens": 1573, + "estimated_eval_tokens": 3402 + }, + "budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 8, + "serialized_chars": 6292, + "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 thematically similar only at a very broad level (model/config/runtime bugs), but they describe distinct bugs in different components and code paths. I do not see any true duplicates in this cluster.", + "confidence": 0.96, + "canonical_issue_reason": "No single duplicate stands out; issue 43668 is the most self-contained and concrete report, so it is the best anchor if one must be chosen.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43668 is the clearest standalone bug report in the set (a specific ModernBERT config typing problem), but the cluster is too heterogeneous for a real canonical duplicate.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:37934", + "right": "issue:43668", + "accept": false, + "reason": "Different models and different defects: Llama4TextL2Norm/RMS-norm semantics vs ModernBERTConfig type-hint mismatch." + }, + { + "left": "issue:42936", + "right": "issue:43240", + "accept": false, + "reason": "Mask2Former ignore_value not being used is unrelated to kwargs not being forwarded into a loss function." + }, + { + "left": "issue:42936", + "right": "issue:44031", + "accept": false, + "reason": "Mask2Former loss handling and tokenizer regex warnings are unrelated subsystems and bugs." + }, + { + "left": "issue:42936", + "right": "issue:43813", + "accept": false, + "reason": "Unused ignore_value in Mask2Former is not the same as a typo in a quantization-operation attribute name." + }, + { + "left": "issue:42936", + "right": "issue:43668", + "accept": false, + "reason": "Different component and failure mode: Mask2Former target handling vs ModernBERT config typing." + }, + { + "left": "issue:43240", + "right": "issue:43668", + "accept": false, + "reason": "Forwarding kwargs to a loss function is a runtime wiring bug; the other is a config type annotation issue." + }, + { + "left": "issue:43668", + "right": "issue:44031", + "accept": false, + "reason": "A config type hint bug is unrelated to tokenizer regex pattern warnings." + }, + { + "left": "issue:43668", + "right": "issue:43813", + "accept": false, + "reason": "ModernBERTConfig norm_eps typing and a quantization-operation typo are distinct, non-overlapping issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 7, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-41084-2", + "nodes": [ + "issue:41084", + "issue:43037" + ], + "soft_pairs": [ + "issue:41084|issue:43037" + ], + "prepared_review_unit_hash": "5c48b6205293bc4587f63b433d2fab725ed4f1ce19b00dfcdbe2c3be6247370e", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1479, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1479, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two issues are not duplicates: one asks for a general \"Set Block Decoding\" capability, while the other requests support for a specific model version (DeepSeek v3.2). They describe different features and likely different implementation work.", + "confidence": 0.95, + "canonical_issue_reason": "No canonical duplicate issue: the titles and likely scopes are too different to treat as the same underlying request.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43037 is the better standalone issue because it is more specific and actionable (a concrete model-support request).", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41084", + "right": "issue:43037", + "accept": false, + "reason": "Different feature requests with no clear shared code-path or identical bug/change; one is about block decoding generally, the other about DeepSeek v3.2 support." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 8, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43598-2", + "nodes": [ + "issue:43598", + "issue:43600" + ], + "soft_pairs": [ + "issue:43598|issue:43600" + ], + "prepared_review_unit_hash": "10b2486a99e5b29bafe09c4fa0ae9485521586c7b0bd7f8629a172db6ee7cbcd", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1583, + "estimated_input_tokens": 396, + "estimated_eval_tokens": 1048 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1583, + "estimated_input_tokens": 396, + "estimated_eval_tokens": 1048 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two issues are only loosely related by Trainer customization, but they describe different problems: one is about `remove_unused_column` behavior, the other about FLOPS estimation for custom trainers.", + "confidence": 0.88, + "canonical_issue_reason": "#43598 is the better anchor if one must be chosen because it is the more direct Trainer customization request; #43600 is a separate accounting/metrics concern rather than the same bug.", + "canonical_pr_reason": null, + "best_issue_reason": "#43598 is the strongest representative issue in this cluster due to its clearer, broader customization focus; #43600 appears orthogonal and should not be treated as a duplicate.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43598", + "right": "issue:43600", + "accept": false, + "reason": "They share a general Trainer/custom trainer theme, but the underlying changes differ: unused-column removal customization vs FLOPS estimation logic. They would not plausibly be merged as one duplicate fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 9, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43684-2", + "nodes": [ + "issue:43684", + "issue:44405" + ], + "soft_pairs": [ + "issue:43684|issue:44405" + ], + "prepared_review_unit_hash": "308762975b97f4f6e474a961da303294953cddc3225a45a725b0802d627a5579", + "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 related only at a very broad level (Qwen model AutoModel support), but they target different model families and different heads/tasks, so they do not look like the same bug/change.", + "confidence": 0.93, + "canonical_issue_reason": "Issue 43684 is the broader and more central request: registering Qwen3-Omni with AutoModel/AutoModelForConditionalGeneration. It reads like the more general model-registration gap.", + "canonical_pr_reason": null, + "best_issue_reason": "43684 is the best representative issue for the cluster because it covers the general AutoModel registration problem rather than a narrower task-specific variant.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43684", + "right": "issue:44405", + "accept": false, + "reason": "Different underlying requests: Qwen3-Omni registration for AutoModel/AutoModelForConditionalGeneration vs. Qwen3.5 sequence-classification support. They touch different configs and different auto classes, so they are not duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 10, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43835-4", + "nodes": [ + "issue:43835", + "issue:43845", + "issue:43846", + "issue:43859" + ], + "soft_pairs": [ + "issue:43835|issue:43845", + "issue:43835|issue:43846", + "issue:43835|issue:43859", + "issue:43845|issue:43846", + "issue:43845|issue:43859", + "issue:43846|issue:43859" + ], + "prepared_review_unit_hash": "5bd6c832b9dd168e0ae24ca6643a782b2f7cf41e7e424271eeb0ce6561e98aad", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4265, + "estimated_input_tokens": 1067, + "estimated_eval_tokens": 2390 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4265, + "estimated_input_tokens": 1067, + "estimated_eval_tokens": 2390 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is dominated by low-information, likely unrelated issues with generic titles; there is no strong evidence of a shared underlying bug. The two identical \"huggingface\" issues are the closest pair, but still too underspecified to confidently treat as duplicates.", + "confidence": 0.41, + "canonical_issue_reason": "Issue 43845 is the best available issue representative because it is one of the repeated \"huggingface\" reports, is earlier than 43846/43859, and is more on-theme than the outlier titled \"Fett\".", + "canonical_pr_reason": null, + "best_issue_reason": "43845 is the strongest cluster representative by title similarity and recency among the repeated reports, though the evidence is weak due to the lack of substantive body text.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43835", + "right": "issue:43845", + "accept": false, + "reason": "Titles are different and there is no body/detail evidence showing the same bug." + }, + { + "left": "issue:43835", + "right": "issue:43846", + "accept": false, + "reason": "Titles are different and there is no body/detail evidence showing the same bug." + }, + { + "left": "issue:43835", + "right": "issue:43859", + "accept": false, + "reason": "Titles are different and there is no body/detail evidence showing the same bug." + }, + { + "left": "issue:43845", + "right": "issue:43846", + "accept": false, + "reason": "Identical generic titles are not enough; there is no description or issue-target evidence that they report the same underlying problem." + }, + { + "left": "issue:43845", + "right": "issue:43859", + "accept": false, + "reason": "Similar generic titles, but insufficient substantive evidence to confirm the same bug." + }, + { + "left": "issue:43846", + "right": "issue:43859", + "accept": false, + "reason": "Similar generic titles, but insufficient substantive evidence to confirm the same bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 11, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-44371-5", + "nodes": [ + "issue:44371", + "issue:44418", + "issue:44572", + "issue:44573", + "issue:44937" + ], + "soft_pairs": [ + "issue:44371|issue:44572", + "issue:44371|issue:44573", + "issue:44371|issue:44418", + "issue:44371|issue:44937", + "issue:44418|issue:44572", + "issue:44418|issue:44573", + "issue:44572|issue:44573", + "issue:44572|issue:44937", + "issue:44573|issue:44937" + ], + "prepared_review_unit_hash": "c87f2ba32eda7b2a8280a48ef5c544f3771007c9918166364d59f43e8d9521f2", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 9, + "serialized_chars": 5785, + "estimated_input_tokens": 1447, + "estimated_eval_tokens": 3150 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 9, + "serialized_chars": 5785, + "estimated_input_tokens": 1447, + "estimated_eval_tokens": 3150 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is mostly spammy or placeholder issues with no shared concrete bug or change, so there is no real duplicate set here.", + "confidence": 0.97, + "canonical_issue_reason": "Issue 44418 is the only semi-descriptive title, but the cluster is still too vague and unrelated to treat it as a true canonical duplicate.", + "canonical_pr_reason": null, + "best_issue_reason": "No issue in this cluster is a good global representative; the items are spam or unrelated prompts, not the same underlying problem.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44371", + "right": "issue:44572", + "accept": false, + "reason": "Both are spam placeholders; no shared concrete bug or topic." + }, + { + "left": "issue:44371", + "right": "issue:44573", + "accept": false, + "reason": "Both are spam placeholders, but not the same underlying issue." + }, + { + "left": "issue:44371", + "right": "issue:44418", + "accept": false, + "reason": "Spam placeholder vs generic documentation suggestion; unrelated." + }, + { + "left": "issue:44371", + "right": "issue:44937", + "accept": false, + "reason": "Spam placeholder vs unrelated \"Google LLC\" prompt; not a duplicate." + }, + { + "left": "issue:44418", + "right": "issue:44572", + "accept": false, + "reason": "Generic documentation suggestion vs spam placeholder; no common concrete problem." + }, + { + "left": "issue:44418", + "right": "issue:44573", + "accept": false, + "reason": "Generic documentation suggestion vs spam placeholder; unrelated." + }, + { + "left": "issue:44572", + "right": "issue:44573", + "accept": false, + "reason": "Both are spam placeholders, but there is no evidence they describe the same bug or change." + }, + { + "left": "issue:44572", + "right": "issue:44937", + "accept": false, + "reason": "Spam placeholder vs unrelated named prompt; not the same issue." + }, + { + "left": "issue:44573", + "right": "issue:44937", + "accept": false, + "reason": "Spam placeholder vs unrelated named prompt; not a duplicate." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 12, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45145-2", + "nodes": [ + "issue:45145", + "issue:45151" + ], + "soft_pairs": [ + "issue:45145|issue:45151" + ], + "prepared_review_unit_hash": "e6187a3e629fb37e31d3894ec45bde7f84369a3b27ae4f484936f3f088e8578e", + "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 issues are highly similar and likely related, but the packet does not prove they are exact duplicates. #45145 remains the best canonical issue because it was created first and already has an inbound reference, while #45151 can be treated as a near-match rather than a confirmed duplicate.", + "confidence": 0.78, + "canonical_issue_reason": "#45145 is the better canonical issue because it was created earlier and already has one inbound reference, so it is the more established thread for this topic.", + "canonical_pr_reason": null, + "best_issue_reason": "#45145 is the best issue representative for the cluster because it is the earliest instance and has the only inbound reference, but the evidence only supports near-duplication, not indistinguishability.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45145", + "right": "issue:45151", + "accept": false, + "reason": "The available evidence is limited to identical titles, similar body lengths, and a soft_similarity signal. That supports a likely related/near-duplicate relationship, but not a confident conclusion that they are the same underlying issue." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The canonical-choice rationale is grounded (earlier creation time and one inbound reference for #45145), but the cluster summary and soft-edge verdict overstate the evidence. The packet only shows identical titles, similar body lengths, and a soft_similarity signal; it does not establish that these issues are exact duplicates or that their substance is indistinguishable. A more conservative verdict would be that they are highly similar and likely related, not definitively the same issue." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 13, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45295-2", + "nodes": [ + "issue:45295", + "issue:45373" + ], + "soft_pairs": [], + "prepared_review_unit_hash": "f5fd95fada2f530ab0999e343c17c16266cde0c7182bb22509972ca44827cd49", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 0, + "serialized_chars": 1286, + "estimated_input_tokens": 322, + "estimated_eval_tokens": 900 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 0, + "serialized_chars": 1286, + "estimated_input_tokens": 322, + "estimated_eval_tokens": 900 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two issues describe the same missing Gemma 4 sequence-classification support; the later, more specific open issue is the better cluster representative.", + "confidence": 0.94, + "canonical_issue_reason": "issue #45373 is the clearest canonical tracker: it is open, explicitly names the missing class `Gemma4ForSequenceClassification`, and states the module-level gap relative to Gemma 2/3.", + "canonical_pr_reason": null, + "best_issue_reason": "issue #45373 best captures the concrete request and likely remaining work, while #45295 is a shorter earlier duplicate with less detail and is already closed.", + "best_pr_reason": null, + "soft_edge_verdicts": [] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 14, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45672-2", + "nodes": [ + "issue:45672", + "issue:45674" + ], + "soft_pairs": [ + "issue:45672|issue:45674" + ], + "prepared_review_unit_hash": "e6c636be2f7ba7a249c6ac36d82d99ade01b30da5e285e0f7bdcc16057073db3", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1668, + "estimated_input_tokens": 417, + "estimated_eval_tokens": 1090 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1668, + "estimated_input_tokens": 417, + "estimated_eval_tokens": 1090 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two open issues both concern 4-bit inference, but they describe different bugs with different failure points: one is a Gemma4 audio-module `torch.finfo()` TypeError on `uint8` weights, the other is a BitsAndBytesConfig regression where `llm_int8_skip_modules` drops the default `lm_head` exclusion and triggers an AssertionError. They should not be merged as duplicates.", + "confidence": 0.93, + "canonical_issue_reason": "No clear canonical duplicate: the reports describe separate root causes and distinct code paths. If one must be kept as the cluster representative, issue #45674 is slightly better as the more general configuration regression report.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue #45674 is the better representative because it states the configuration regression and expected-vs-actual behavior more directly, making it easier to route and triage.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45672", + "right": "issue:45674", + "accept": false, + "reason": "Reject: both are 4-bit inference problems, but one is a Gemma4 audio-module `torch.finfo()` type issue on `uint8` weights while the other is an `llm_int8_skip_modules`/`lm_head` exclusion regression causing AssertionError. Different bugs, not one fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 15, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45762-2", + "nodes": [ + "issue:45762", + "issue:45763" + ], + "soft_pairs": [ + "issue:45762|issue:45763" + ], + "prepared_review_unit_hash": "979e58bbff4e03746f2a84f09d1ec77430969d2ad00383a1e10461f512df9c77", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1477, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1477, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two closed issues do not look like duplicates; they are unrelated name/date entries and appear to be spam or placeholder posts rather than the same bug report.", + "confidence": 0.96, + "canonical_issue_reason": "No single canonical issue is appropriate here because the two issues are not about the same underlying problem.", + "canonical_pr_reason": null, + "best_issue_reason": "Neither issue is a good global representative: both are unrelated, content-free entries with no shared technical problem.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45762", + "right": "issue:45763", + "accept": false, + "reason": "Different personal-name/date titles with no body, links, or technical context; they do not appear to describe the same bug or change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 16, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45764-2", + "nodes": [ + "issue:45764", + "issue:45765" + ], + "soft_pairs": [ + "issue:45764|issue:45765" + ], + "prepared_review_unit_hash": "cd93425d808271a24112ee43f8b412cba57e5b8ce9016dbbca69d7eb1d1b7724", + "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 closed issues are unrelated name/date placeholders with no body or shared technical context, so they should not be clustered as duplicates.", + "confidence": 0.99, + "canonical_issue_reason": "Neither issue contains substantive content, and the titles are distinct personal-name/date strings with no evidence of the same problem.", + "canonical_pr_reason": null, + "best_issue_reason": "No issue here is meaningfully better as a canonical duplicate target; both are empty and unrelated.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45764", + "right": "issue:45765", + "accept": false, + "reason": "The titles do not describe the same bug or request, and there is no body, linkage, or shared technical context connecting them." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 1, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-39895-13", + "nodes": [ + "pull_request:39895", + "pull_request:41855", + "pull_request:42668", + "pull_request:43251", + "pull_request:43254", + "pull_request:43424", + "pull_request:43823", + "pull_request:43995", + "pull_request:44827", + "pull_request:45170", + "pull_request:45213", + "pull_request:45655", + "pull_request:45795" + ], + "soft_pairs": [ + "pull_request:39895|pull_request:43424", + "pull_request:41855|pull_request:43823", + "pull_request:41855|pull_request:43424", + "pull_request:42668|pull_request:43823", + "pull_request:43251|pull_request:43823", + "pull_request:43251|pull_request:44827", + "pull_request:43424|pull_request:44827", + "pull_request:43424|pull_request:43823", + "pull_request:43823|pull_request:45655", + "pull_request:43823|pull_request:43995", + "pull_request:43995|pull_request:44827", + "pull_request:43995|pull_request:45213", + "pull_request:44827|pull_request:45170", + "pull_request:44827|pull_request:45795", + "pull_request:44827|pull_request:45655", + "pull_request:44827|pull_request:45213", + "pull_request:43823|pull_request:45213", + "pull_request:43823|pull_request:45795", + "pull_request:43251|pull_request:43254" + ], + "prepared_review_unit_hash": "fd665eb0087351da1f1690706793c539736fa805e7890d8621e6035e839fec27", + "component_budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 19, + "serialized_chars": 35206, + "estimated_input_tokens": 8802, + "estimated_eval_tokens": 17860 + }, + "budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 19, + "serialized_chars": 35206, + "estimated_input_tokens": 8802, + "estimated_eval_tokens": 17860 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The cluster is mostly unrelated PRs grouped by broad subsystem similarity. The only true duplicate is the pair of `fixed_cross_entropy` patches for issue 43240; all other soft links are too coarse and should remain separate.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "`pull_request:43251` is a valid canonical anchor for the only real duplicate pair because it is explicitly tied to issue 43240 and makes the same `fixed_cross_entropy` kwargs-forwarding change in `src/transformers/loss/loss_utils.py` as `pull_request:43254`.", + "best_issue_reason": null, + "best_pr_reason": "`pull_request:43251` is the best cluster PR candidate because it belongs to the only accepted duplicate pair, is issue-linked to 43240, and clearly expresses the cross-entropy kwargs fix in the same file as the matching PR.", + "soft_edge_verdicts": [ + { + "left": "pull_request:39895", + "right": "pull_request:43424", + "accept": false, + "reason": "VideoPrism model addition and ExecuTorch dynamic-shape test are unrelated changes." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43823", + "accept": false, + "reason": "Mistral tokenizer helper methods and a new MobileLLM model are different code paths and fixes." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43424", + "accept": false, + "reason": "Tokenizer API additions and exportability tests are not the same underlying change." + }, + { + "left": "pull_request:42668", + "right": "pull_request:43823", + "accept": false, + "reason": "Processor robustness work and a new model implementation are unrelated." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43823", + "accept": false, + "reason": "Cross-entropy kwargs forwarding and MobileLLM model creation are unrelated." + }, + { + "left": "pull_request:43251", + "right": "pull_request:44827", + "accept": false, + "reason": "Loss utility kwargs fix and Mistral4 test/model work address different bugs." + }, + { + "left": "pull_request:43424", + "right": "pull_request:44827", + "accept": false, + "reason": "ExecuTorch export tests and Mistral4 fixes are separate changes." + }, + { + "left": "pull_request:43424", + "right": "pull_request:43823", + "accept": false, + "reason": "Dynamic-shape export testing and MobileLLM model addition are unrelated." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45655", + "accept": false, + "reason": "New MobileLLM model code and config-resolution ordering fix are different changes." + }, + { + "left": "pull_request:43823", + "right": "pull_request:43995", + "accept": false, + "reason": "MobileLLM model work and Falcon output-interface refactoring are unrelated." + }, + { + "left": "pull_request:43995", + "right": "pull_request:44827", + "accept": false, + "reason": "Falcon refactor and Mistral4 test fixes do not target the same bug or code path." + }, + { + "left": "pull_request:43995", + "right": "pull_request:45213", + "accept": false, + "reason": "Falcon refactoring and the model-creation skill/meta PR are not the same artifact." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45170", + "accept": false, + "reason": "Mistral4 test/model fixes and `layrnorm` renaming are separate changes." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45795", + "accept": false, + "reason": "Mistral4 fixes and audio/video processor docs are unrelated." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45655", + "accept": false, + "reason": "Mistral4 work and `cls.config` resolution ordering fix are different issues." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45213", + "accept": false, + "reason": "They both touch modeling-related areas, but the PRs address different problems and should not be merged as duplicates." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45213", + "accept": false, + "reason": "MobileLLM model implementation and model-creation skill/meta PR are not the same change." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45795", + "accept": false, + "reason": "MobileLLM model code and audio/video processor docs are unrelated." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43254", + "accept": true, + "reason": "Both PRs change `src/transformers/loss/loss_utils.py` to forward supported kwargs into `nn.functional.cross_entropy` for the same issue 43240, so they are the same underlying fix." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The overall cluster read is mostly grounded, but the canonical PR rationale overstates what the packet shows: there is evidence that 43251 and 43254 are the same fix on the same file/issue, but not that 43251 is the \"more complete/representative\" implementation. That comparative claim is not supported by the diff previews. The soft-edge rejections are otherwise conservative." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 2, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-40546-2", + "nodes": [ + "pull_request:40546", + "pull_request:42781" + ], + "soft_pairs": [ + "pull_request:40546|pull_request:42781" + ], + "prepared_review_unit_hash": "72e0cd2e1c1c2476e54577fc5dca0bc6e5a60b38d8cc219834f27d0842ecd387", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 7225, + "estimated_input_tokens": 1807, + "estimated_eval_tokens": 3870 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 7225, + "estimated_input_tokens": 1807, + "estimated_eval_tokens": 3870 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two related but distinct VibeVoice PRs: one for the core model integration, one for a realtime extension with acoustic-tokenizer work. They overlap heavily in shared model/auto-registration files, but they do not look like the same underlying change.", + "confidence": 0.83, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 40546 is the broader base VibeVoice implementation and reads as the foundational integration; 42781 is a later, narrower realtime follow-up that extends the stack with additional tokenizer/generation work.", + "best_issue_reason": null, + "best_pr_reason": "PR 40546 is the best representative of the cluster because it covers the primary VibeVoice model bring-up, whereas 42781 is a specialized realtime variant rather than the same change.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40546", + "right": "pull_request:42781", + "accept": false, + "reason": "Shared filenames are not enough here: 40546 implements VibeVoice itself, while 42781 adds a realtime flavor and acoustic tokenizer support. They touch related code paths but are not the same concrete change and would not plausibly merge into one PR as duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 3, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-40755-2", + "nodes": [ + "pull_request:40755", + "pull_request:41224" + ], + "soft_pairs": [ + "pull_request:40755|pull_request:41224" + ], + "prepared_review_unit_hash": "626103e09780be5f86af888af0a111e4bafc161c45a0c9d4256edd74d38a43df", + "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": "These are unrelated feature PRs in different model families: TimesFM covariate forecasting vs. DINOv3 image-classification support. The soft similarity signal is too weak to treat them as the same underlying change.", + "confidence": 0.99, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": "PR 41224 is the more focused, self-contained feature PR, but it is not a duplicate of 40755; the cluster does not have a true canonical PR.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40755", + "right": "pull_request:41224", + "accept": false, + "reason": "Different code paths and goals: 40755 adds TimesFM forecasting with covariates, while 41224 adds DINOv3 image-classification support." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 4, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-41356-2", + "nodes": [ + "pull_request:41356", + "pull_request:44339" + ], + "soft_pairs": [ + "pull_request:41356|pull_request:44339" + ], + "prepared_review_unit_hash": "aead1308c167b0bae6ff11bf9358340baa5e76f816618383418b505a10a9cd01", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6050, + "estimated_input_tokens": 1513, + "estimated_eval_tokens": 3282 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6050, + "estimated_input_tokens": 1513, + "estimated_eval_tokens": 3282 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two DEIMv2 pull requests target the same model family, but they are not the same change: PR 41356 is an early/basic model + image processor add, while PR 44339 is a much broader follow-up that adds loss code, auto-mappings, conversion tooling, modular files, and more integration work.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44339 is the more complete and representative DEIMv2 implementation; PR 41356 looks like an earlier partial version of the same model bring-up.", + "best_issue_reason": null, + "best_pr_reason": "PR 44339 is the strongest single artifact for the cluster because it subsumes the basic model work and includes the broader integration needed for a full Transformers addition.", + "soft_edge_verdicts": [ + { + "left": "pull_request:41356", + "right": "pull_request:44339", + "accept": false, + "reason": "Same model area, but not the same concrete change: 44339 expands the implementation substantially and adds new code paths beyond the basic PR 41356. They look like related iterations, not mergeable duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 5, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-41797-3", + "nodes": [ + "pull_request:41797", + "pull_request:45186", + "pull_request:45630" + ], + "soft_pairs": [ + "pull_request:41797|pull_request:45186", + "pull_request:45186|pull_request:45630" + ], + "prepared_review_unit_hash": "a513eb7bbac9c979889d9248767be3ff027b4d9aafcefe70506a68ecb8fc56bc", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 10429, + "estimated_input_tokens": 2608, + "estimated_eval_tokens": 5472 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 10429, + "estimated_input_tokens": 2608, + "estimated_eval_tokens": 5472 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "All three pull requests are separate model additions (DeepSeek OCR, Isaac, Kimi2-6) that share Hugging Face model-registration scaffolding but do not fix the same underlying bug or implement the same change.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": "None of these PRs is a duplicate of the others; they target different models and cannot be safely consolidated into one change.", + "soft_edge_verdicts": [ + { + "left": "pull_request:41797", + "right": "pull_request:45186", + "accept": false, + "reason": "Different model integrations for DeepSeek OCR vs Isaac. Shared auto-registration/docs/test plumbing is generic boilerplate, not evidence of the same concrete change." + }, + { + "left": "pull_request:45186", + "right": "pull_request:45630", + "accept": false, + "reason": "Different model integrations for Isaac vs Kimi2-6. They overlap only in broad Transformers model-support scaffolding and do not appear mergeable into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 6, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-42975-2", + "nodes": [ + "pull_request:42975", + "pull_request:42976" + ], + "soft_pairs": [ + "pull_request:42975|pull_request:42976" + ], + "prepared_review_unit_hash": "69714920e8bac28b0cc36558180747922ef785f93b2ec2fc91756ba5f138984f", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5935, + "estimated_input_tokens": 1484, + "estimated_eval_tokens": 3224 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5935, + "estimated_input_tokens": 1484, + "estimated_eval_tokens": 3224 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two unrelated GitHub Actions dependency-upgrade PRs: one for general workflow action compatibility with Node 24, and one specifically upgrading docker/build-push-action. They overlap in workflow files but do not fix the same concrete problem.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 42975 is the better canonical representative because it is the broader, more cohesive workflow-actions compatibility upgrade and touches more of the affected CI surface.", + "best_issue_reason": null, + "best_pr_reason": "PR 42975 is the strongest standalone PR in the cluster: it has the clearer overarching goal (Node 24 compatibility) and the widest workflow coverage.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42975", + "right": "pull_request:42976", + "accept": false, + "reason": "They are different dependency bumps with different targets and intents: general GitHub Actions runtime compatibility vs docker/build-push-action upgrade. Shared workflow files are 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": 7, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-42978-7", + "nodes": [ + "pull_request:42978", + "pull_request:43448", + "pull_request:43451", + "pull_request:43973", + "pull_request:44601", + "pull_request:45490", + "pull_request:45838" + ], + "soft_pairs": [ + "pull_request:42978|pull_request:43448", + "pull_request:42978|pull_request:43451", + "pull_request:42978|pull_request:45490", + "pull_request:43448|pull_request:43451", + "pull_request:43448|pull_request:45490", + "pull_request:43451|pull_request:45490", + "pull_request:43973|pull_request:45838", + "pull_request:44601|pull_request:45838", + "pull_request:45490|pull_request:45838" + ], + "prepared_review_unit_hash": "ad8c8bdae803d7d2c8eae826a7de8701331aaba6773b412a0337dc0a9ad37ab8", + "component_budget": { + "node_count": 7, + "item_count": 7, + "soft_pair_count": 9, + "serialized_chars": 23512, + "estimated_input_tokens": 5878, + "estimated_eval_tokens": 12012 + }, + "budget": { + "node_count": 7, + "item_count": 7, + "soft_pair_count": 9, + "serialized_chars": 23512, + "estimated_input_tokens": 5878, + "estimated_eval_tokens": 12012 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "No true duplicates here. The apparent overlaps are mostly shared Hugging Face boilerplate (docs/toctree, auto registries) across unrelated model-addition PRs, plus one separate distributed-loading infra PR.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single canonical PR: the shared filenames are generic model-registration/docs scaffolding, while the PRs introduce different models or an unrelated pipeline-parallel loading change.", + "best_issue_reason": null, + "best_pr_reason": "PR 43451 is the strongest standalone representative of a substantive model-addition change, with broad model-specific code and very high review activity, but it is not a duplicate anchor for the others.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42978", + "right": "pull_request:43448", + "accept": false, + "reason": "Different models (ViT NEPA vs Molmo); overlap is only docs/auto-registry boilerplate." + }, + { + "left": "pull_request:42978", + "right": "pull_request:43451", + "accept": false, + "reason": "Different models (ViT NEPA vs Molmo2); shared files reflect generic model registration, not the same bug/change." + }, + { + "left": "pull_request:42978", + "right": "pull_request:45490", + "accept": false, + "reason": "Different model additions (ViT NEPA vs CTSM); no shared concrete code-path fix." + }, + { + "left": "pull_request:43448", + "right": "pull_request:43451", + "accept": false, + "reason": "Molmo and Molmo2 are distinct model families/generations; not the same underlying change." + }, + { + "left": "pull_request:43448", + "right": "pull_request:45490", + "accept": false, + "reason": "Different models (Molmo vs CTSM); only broad subsystem overlap in registration/docs." + }, + { + "left": "pull_request:43451", + "right": "pull_request:45490", + "accept": false, + "reason": "Different models (Molmo2 vs CTSM); no evidence they fix or add the same concrete code path." + }, + { + "left": "pull_request:43973", + "right": "pull_request:45838", + "accept": false, + "reason": "Different domains: audio model support vs OCR/text-recognition model support." + }, + { + "left": "pull_request:44601", + "right": "pull_request:45838", + "accept": false, + "reason": "Infrastructure change for pipeline-parallel loading vs a specific model-support PR; not the same underlying fix." + }, + { + "left": "pull_request:45490", + "right": "pull_request:45838", + "accept": false, + "reason": "Different model additions (CTSM vs PP-OCRv6 recognition); shared registry files are insufficient for duplication." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 8, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43291-4", + "nodes": [ + "pull_request:43291", + "pull_request:43665", + "pull_request:44815", + "pull_request:45845" + ], + "soft_pairs": [ + "pull_request:43291|pull_request:45845", + "pull_request:43291|pull_request:43665", + "pull_request:43291|pull_request:44815", + "pull_request:43665|pull_request:45845", + "pull_request:43665|pull_request:44815", + "pull_request:44815|pull_request:45845" + ], + "prepared_review_unit_hash": "cf28fb45e1f90ae658ce182dccdf2b3851a509b506d3cce74dbbb5a81a03b932", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 10176, + "estimated_input_tokens": 2544, + "estimated_eval_tokens": 5344 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 10176, + "estimated_input_tokens": 2544, + "estimated_eval_tokens": 5344 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are four unrelated pull requests across different models/components; none look like true duplicates. The strongest standalone fix is the FP8 dequant/loading change in 44815.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "44815 is the most substantive and representative fix: it changes core FP8/loading code paths and includes related integration/tests, unlike the others which are model-specific or test-only.", + "best_issue_reason": null, + "best_pr_reason": "44815 is the best overall PR candidate because it addresses a concrete runtime bug in a shared code path and has the clearest production impact.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43291", + "right": "pull_request:45845", + "accept": false, + "reason": "Different model families and different bugs: Whisper tokenizer timestamp decoding vs RF-DETR proposal masking/device placement." + }, + { + "left": "pull_request:43291", + "right": "pull_request:43665", + "accept": false, + "reason": "Both touch tests, but they target different models and different issues; 43291 also changes Whisper tokenizer code, while 43665 is just test assertions." + }, + { + "left": "pull_request:43291", + "right": "pull_request:44815", + "accept": false, + "reason": "Whisper decode/timestamp handling is unrelated to FP8 dequant/loading logic in 44815." + }, + { + "left": "pull_request:43665", + "right": "pull_request:45845", + "accept": false, + "reason": "Unrelated test-only changes in CLIP/ViT versus an RF-DETR runtime fix." + }, + { + "left": "pull_request:43665", + "right": "pull_request:44815", + "accept": false, + "reason": "No shared underlying bug or code path; 43665 is test-focused, while 44815 is a core FP8 integration fix." + }, + { + "left": "pull_request:44815", + "right": "pull_request:45845", + "accept": false, + "reason": "Both are fixes, but for different subsystems and failure modes; they would not plausibly merge into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 9, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43488-2", + "nodes": [ + "pull_request:43488", + "pull_request:43532" + ], + "soft_pairs": [ + "pull_request:43488|pull_request:43532" + ], + "prepared_review_unit_hash": "37c71327ccc050fb30237eff2752e524d2d5338529d2d22e551e14defe7c8c2e", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4563, + "estimated_input_tokens": 1141, + "estimated_eval_tokens": 2538 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4563, + "estimated_input_tokens": 1141, + "estimated_eval_tokens": 2538 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two unrelated open PRs: one is a setup/version/dependency tweak, the other rewires CI/testing workflows. They share a test file path but not the same underlying change.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "pull_request:43532 is the more substantial PR and best represents the cluster, but the items are not truly duplicates of each other.", + "best_issue_reason": null, + "best_pr_reason": "No issue items are present; as a PR representative, pull_request:43532 is the strongest candidate because it contains the broader code/workflow changes.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43488", + "right": "pull_request:43532", + "accept": false, + "reason": "Reject: these PRs change different areas and solve different problems. 43488 updates setup/dependency/version metadata, while 43532 modifies GitHub workflows and test utilities; the shared Vit test file is incidental." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 10, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43612-2", + "nodes": [ + "pull_request:43612", + "pull_request:43613" + ], + "soft_pairs": [ + "pull_request:43612|pull_request:43613" + ], + "prepared_review_unit_hash": "97a2da92375c51618029bfe7fa5793fe32982cc74f824f6e427ef4972e3b5378", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6081, + "estimated_input_tokens": 1521, + "estimated_eval_tokens": 3298 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6081, + "estimated_input_tokens": 1521, + "estimated_eval_tokens": 3298 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two separate feature PRs: one adds a Promptable Concept Segmentation pipeline, the other adds a Promptable Visual Segmentation pipeline. They share scaffolding/docs work but target different tasks and model stacks, so they are not duplicates.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: these are distinct feature additions with different pipeline names, docs, and supported model families.", + "best_issue_reason": null, + "best_pr_reason": "43613 is the broader visual-segmentation feature PR and is the better representative if one must be chosen, but it still is not a duplicate of 43612.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43612", + "right": "pull_request:43613", + "accept": false, + "reason": "Different underlying features: concept segmentation vs visual segmentation. The overlapping pipeline/doc/test scaffolding is incidental and not enough to treat them as one mergeable change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 11, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43651-2", + "nodes": [ + "pull_request:43651", + "pull_request:43663" + ], + "soft_pairs": [ + "pull_request:43651|pull_request:43663" + ], + "prepared_review_unit_hash": "2e6b597885d55abd6d402cbe5185fd647506f9d14cf92dcfaf9826b78968abba", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4292, + "estimated_input_tokens": 1073, + "estimated_eval_tokens": 2402 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4292, + "estimated_input_tokens": 1073, + "estimated_eval_tokens": 2402 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are two separate trainer.py API-hook PRs: one adjusts gradient-accumulation loss scaling, the other factors out signature-column filtering for overrides. They share a file and theme but not the same underlying change or bug.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "43651 is the cleaner representative PR: it introduces a focused training-step behavior change plus an explicit hook for loss scaling. 43663 addresses a different extension point and is not a duplicate.", + "best_issue_reason": null, + "best_pr_reason": "43651 is the strongest standalone PR in this cluster because it has a single, concrete behavioral target and a narrowly scoped implementation. 43663 is related only at the subsystem level.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43651", + "right": "pull_request:43663", + "accept": false, + "reason": "Different code paths and semantics: 43651 concerns loss scaling during gradient accumulation, while 43663 concerns how Trainer derives signature columns for filtering inputs. Shared filename alone is not enough to treat them as the same change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 12, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43656-3", + "nodes": [ + "pull_request:43656", + "pull_request:43836", + "pull_request:43842" + ], + "soft_pairs": [ + "pull_request:43656|pull_request:43842", + "pull_request:43836|pull_request:43842" + ], + "prepared_review_unit_hash": "903a6848a51d905611fd58e0b05fdf22a38ea9663aa3c27061080c4e861ff0d7", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 5992, + "estimated_input_tokens": 1498, + "estimated_eval_tokens": 3252 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 5992, + "estimated_input_tokens": 1498, + "estimated_eval_tokens": 3252 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Three open PRs in transformers/cli/serve.py are all about TypeAdapter/annotation NameErrors, but only one pair looks like the same concrete fix. Two PRs are narrowly about quoting or TYPE_CHECKING-gating TypeAdapter when pydantic is optional; the earlier broad annotation cleanup appears related but not the same change.", + "confidence": 0.82, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #43842 is the most targeted and minimal fix for the TypeAdapter NameError when pydantic is absent, making it the best representative of the cluster.", + "best_issue_reason": null, + "best_pr_reason": "PR #43842 best captures the concrete bug with the smallest, most specific diff and clear issue target.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43656", + "right": "pull_request:43842", + "accept": false, + "reason": "Both touch serve.py and mention TypeAdapter, but #43656 is a broader postponed-annotations cleanup while #43842 specifically fixes the pydantic-optional TypeAdapter NameError. Related symptom, not the same underlying change." + }, + { + "left": "pull_request:43836", + "right": "pull_request:43842", + "accept": true, + "reason": "These are two variants of the same concrete fix in the same code path: both quote or defer TypeAdapter annotations in serve.py to avoid runtime NameError, and they could plausibly be merged into one PR." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: #43842 is indeed the smallest and most targeted diff, with an explicit issue target and a direct TypeAdapter/pydantic-absent fix. The soft-edge calls are conservative overall: rejecting #43656 vs #43842 is defensible given the broader annotation cleanup, while accepting #43836 vs #43842 is reasonable because both clearly address the same serve.py TypeAdapter annotation problem and share the same issue target." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 13, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43779-2", + "nodes": [ + "pull_request:43779", + "pull_request:43816" + ], + "soft_pairs": [ + "pull_request:43779|pull_request:43816" + ], + "prepared_review_unit_hash": "e7c674adcc031aa8883109a5dfc678b4407fb20b10764302092e384d031ba83a", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4362, + "estimated_input_tokens": 1091, + "estimated_eval_tokens": 2438 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4362, + "estimated_input_tokens": 1091, + "estimated_eval_tokens": 2438 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both pull requests appear to implement the same SwanLab integration change: adding run id/resume support in `integration_utils.py` for issue #43698, with one variant also expanding the docs. They are strong duplicate PR candidates.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #43816 is the cleaner representative: it carries the same SwanLab id/resume support plus the accompanying documentation updates, making it the more complete version of the shared change.", + "best_issue_reason": null, + "best_pr_reason": "PR #43816 is the best global representative because it appears to include the full feature change and docs for SwanLab run id/resume support, while #43779 is the narrower implementation-focused variant.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43779", + "right": "pull_request:43816", + "accept": true, + "reason": "Same underlying SwanLab callback enhancement for id/resume support in the same file and same issue target; the doc differences do not change the core code-path change, so these are duplicate PRs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: both PRs target issue #43698, touch the same file, and the previews indicate the same SwanLab id/resume support with #43816 adding docs. The duplicate/mergeable verdict is conservative enough given the shared target and overlapping code change." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 14, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 2, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43996-28", + "nodes": [ + "pull_request:43996", + "pull_request:43997", + "pull_request:44007", + "pull_request:44010", + "pull_request:44013", + "pull_request:44017", + "pull_request:44018", + "pull_request:44019", + "pull_request: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:44161", + "pull_request:44017|pull_request:44722", + "pull_request:44017|pull_request:44073", + "pull_request:44068|pull_request:44071", + "pull_request:44071|pull_request:44086", + "pull_request:43997|pull_request:44073", + "pull_request:44017|pull_request:44071", + "pull_request:44073|pull_request:44101", + "pull_request:44059|pull_request:44071", + "pull_request:44059|pull_request:44068", + "pull_request:44056|pull_request:44101", + "pull_request:44073|pull_request:44161", + "pull_request:44018|pull_request:44059", + "pull_request:44101|pull_request:44161", + "pull_request:43997|pull_request:44017", + "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": "19340dbf0f318e78d43b840f4a1099cc61fc60b2972e369e0044d8422db92a46", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 77, + "serialized_chars": 84508, + "estimated_input_tokens": 21127, + "estimated_eval_tokens": 42510 + }, + "budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 72, + "serialized_chars": 76943, + "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 family of model-specific output-tracing refactors, not a single duplicate change. The only strong duplicates are within the GPT-J/GPT-Neo lines; cross-model pairs are generally different code paths and should stay separate.", + "confidence": 0.89, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44722 is the most representative GPT-J-family refactor here: it is explicit about the output-tracing migration, touches the same core code path as the other GPT-J variants, and also spans the closely related CodeGen copy.", + "best_issue_reason": null, + "best_pr_reason": "PR 44722 is the best anchor for the cluster\u2019s dominant theme because it is the broadest and clearest instance of the standardized output-tracing migration in the GPT-J family.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43996", + "right": "pull_request:44085", + "accept": false, + "reason": "Different model families and different forward paths; same meta theme, not the same concrete change." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44044", + "accept": false, + "reason": "CVT/FNet output tracing is unrelated to DeBERTa\u2019s attention/output refactor." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44085", + "accept": true, + "reason": "Same GPT-J code path and same decorator-based output-tracing migration; plausibly one combined PR." + }, + { + "left": "pull_request:44007", + "right": "pull_request:44072", + "accept": false, + "reason": "RegNet and EfficientNet are separate model implementations; same pattern, not a duplicate bugfix." + }, + { + "left": "pull_request:44072", + "right": "pull_request:44722", + "accept": false, + "reason": "EfficientNet refactor is unrelated to the GPT-J/CodeGen change." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44072", + "accept": false, + "reason": "GPT-J/CodeGen versus EfficientNet are different code paths." + }, + { + "left": "pull_request:44013", + "right": "pull_request:44044", + "accept": false, + "reason": "MobileNetV2 and DeBERTa are unrelated implementations." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J/CodeGen refactor and MGP-STR refactor are distinct model changes." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44071", + "accept": false, + "reason": "Different models and different refactor targets." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44068", + "accept": true, + "reason": "Both target GPT-Neo output tracing in the same file/model family; this looks like the same underlying migration." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44068", + "accept": false, + "reason": "GPT-J/CodeGen and GPT-Neo are separate model code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44066", + "accept": false, + "reason": "GPT-Neo versus GPT-J/CodeGen is not the same concrete fix." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44722", + "accept": false, + "reason": "ResNet output tracing is unrelated to GPT-J/CodeGen." + }, + { + "left": "pull_request:44086", + "right": "pull_request:44722", + "accept": false, + "reason": "MGP-STR and GPT-J family changes are different model refactors." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44085", + "accept": false, + "reason": "ResNet and GPT-J are unrelated implementations." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44019", + "accept": false, + "reason": "GPT-Neo and ResNet are different code paths." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44071", + "accept": false, + "reason": "ResNet and MPT refactors are unrelated." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo and Flaubert are different model families." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT-Neo and GPT-J/CodeGen are not the same change." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44722", + "accept": false, + "reason": "MPT output tracing is unrelated to GPT-J/CodeGen." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo and Flaubert are different code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo and MGP-STR are unrelated." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44085", + "accept": false, + "reason": "GPT-Neo and GPT-J are different model implementations." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo and MGP-STR are not the same bugfix." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44086", + "accept": false, + "reason": "MPT and MGP-STR are unrelated." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT2 and MGP-STR touch different model code paths." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J and MGP-STR are unrelated model changes." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT2 output tracing is separate from the GPT-J/CodeGen refactor." + }, + { + "left": "pull_request:44098", + "right": "pull_request:44101", + "accept": false, + "reason": "ViLT and Flaubert are different implementations." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44161", + "accept": false, + "reason": "Segformer and LongT5 are unrelated model refactors." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44722", + "accept": false, + "reason": "Segformer and GPT-J/CodeGen are different code paths." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44073", + "accept": false, + "reason": "Segformer and VisualBert are separate model implementations." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44101", + "accept": false, + "reason": "VisualBert and Flaubert are unrelated." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT2 and MGP-STR are different model changes." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44161", + "accept": false, + "reason": "MPNet and LongT5 are unrelated model refactors." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44059", + "accept": false, + "reason": "GPT-Neo and GPT2 are different model code paths." + }, + { + "left": "pull_request:44101", + "right": "pull_request:44161", + "accept": false, + "reason": "Flaubert/XLM and LongT5 are unrelated." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44017", + "accept": false, + "reason": "RegNet and Segformer are separate models." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44056", + "accept": false, + "reason": "RegNet and MPNet are unrelated." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44076", + "accept": false, + "reason": "MPT and ImageGPT are different code paths." + }, + { + "left": "pull_request:44074", + "right": "pull_request:44101", + "accept": false, + "reason": "TextNet and Flaubert are unrelated model changes." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44161", + "accept": false, + "reason": "MPNet and LongT5 are different implementations." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44018", + "accept": false, + "reason": "RegNet and GPT-Neo are unrelated." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44129", + "accept": false, + "reason": "MPT and SpeechT5 are different model families." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT2 and MPT are unrelated refactors." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44074", + "accept": false, + "reason": "RegNet and TextNet are separate models." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44129", + "accept": false, + "reason": "RegNet and SpeechT5 are unrelated." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44071", + "accept": false, + "reason": "SqueezeBert and MPT are different code paths." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44073", + "accept": false, + "reason": "SqueezeBert and VisualBert are unrelated." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44129", + "accept": false, + "reason": "GPT-Neo and SpeechT5 are different model implementations." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44074", + "accept": false, + "reason": "RegNet and TextNet are unrelated." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44129", + "accept": false, + "reason": "RegNet and SpeechT5 are not the same change." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44018", + "accept": false, + "reason": "SqueezeBert and GPT-Neo are unrelated model code paths." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44129", + "accept": false, + "reason": "MPT and SpeechT5 are different implementations." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44161", + "accept": false, + "reason": "CVT/FNet and LongT5 are unrelated." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44017", + "accept": false, + "reason": "CVT/FNet and Segformer are separate model refactors." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44044", + "accept": false, + "reason": "SqueezeBert and DeBERTa are different code paths." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44074", + "accept": false, + "reason": "DeBERTa and TextNet are unrelated." + }, + { + "left": "pull_request:44024", + "right": "pull_request:44076", + "accept": false, + "reason": "FocalNet and ImageGPT are different model implementations." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: it correctly identifies the dominant GPT-J/GPT-Neo output-tracing refactor theme while treating the other model changes as separate code paths. The accepted soft-edge pairs are conservative and match the evidence that those PRs are effectively the same migration within the same model family." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 14, + "component_count": 26, + "review_unit_index": 2, + "review_unit_count": 2, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43996-28", + "nodes": [ + "pull_request:43997", + "pull_request:44010", + "pull_request: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": "2ee21b7f52e738f04d1bd9a91078d5d313cfe6d0cef648aa4234bb4af97850cb", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 77, + "serialized_chars": 84508, + "estimated_input_tokens": 21127, + "estimated_eval_tokens": 42510 + }, + "budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 5, + "serialized_chars": 13065, + "estimated_input_tokens": 3267, + "estimated_eval_tokens": 6790 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a set of model-specific refactors to standardized output tracing/capture_outputs across different architectures, not duplicate fixes of the same code-path bug.", + "confidence": 0.86, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44010 is a clean representative of the shared refactor pattern: it updates one model\u2019s forward path to the new standardized output-capture approach without extra cross-cutting scope.", + "best_issue_reason": null, + "best_pr_reason": "PR 44010 is the best cluster representative because it is a straightforward, self-contained example of the output-tracing migration pattern seen across the set.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44073", + "right": "pull_request:44074", + "accept": false, + "reason": "Both are similar output-tracing refactors, but they touch different models and different code paths; they are not the same underlying change and would not realistically merge into one PR." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44073", + "accept": false, + "reason": "Shared refactor theme only. MPNet and VisualBert have model-specific tracing implementations, so this is not a duplicate fix/change." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44074", + "accept": false, + "reason": "These are separate per-model output-capture migrations, not one concrete bug or code-path fix." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44010", + "accept": false, + "reason": "RegNet and SqueezeBert are unrelated model implementations; same high-level refactor pattern is not enough to treat them as duplicates." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44129", + "accept": false, + "reason": "Both migrate output tracing, but they are distinct model-specific changes in different files and code paths; not one mergeable 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": 15, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43998-13", + "nodes": [ + "pull_request:43998", + "pull_request:43999", + "pull_request:44000", + "pull_request:44001", + "pull_request:44002", + "pull_request:44003", + "pull_request:44004", + "pull_request:44025", + "pull_request:44026", + "pull_request:44027", + "pull_request:44028", + "pull_request:44029", + "pull_request:44030" + ], + "soft_pairs": [ + "pull_request:43998|pull_request:44002", + "pull_request:43998|pull_request:44000", + "pull_request:43998|pull_request:44001", + "pull_request:43998|pull_request:44003", + "pull_request:43998|pull_request:44029", + "pull_request:43999|pull_request:44001", + "pull_request:43999|pull_request:44002", + "pull_request:43999|pull_request:44025", + "pull_request:43999|pull_request:44026", + "pull_request:43999|pull_request:44027", + "pull_request:44000|pull_request:44001", + "pull_request:44000|pull_request:44002", + "pull_request:44000|pull_request:44003", + "pull_request:44000|pull_request:44025", + "pull_request:44001|pull_request:44002", + "pull_request:44001|pull_request:44003", + "pull_request:44001|pull_request:44025", + "pull_request:44002|pull_request:44029", + "pull_request:44002|pull_request:44003", + "pull_request:44003|pull_request:44028", + "pull_request:44003|pull_request:44004", + "pull_request:43998|pull_request:44004", + "pull_request:44001|pull_request:44004", + "pull_request:44002|pull_request:44004", + "pull_request:44000|pull_request:44004", + "pull_request:44025|pull_request:44026", + "pull_request:44025|pull_request:44027", + "pull_request:44025|pull_request:44028", + "pull_request:44025|pull_request:44029", + "pull_request:44025|pull_request:44030", + "pull_request:44026|pull_request:44029", + "pull_request:44026|pull_request:44027", + "pull_request:44026|pull_request:44028", + "pull_request:44026|pull_request:44030", + "pull_request:44027|pull_request:44028", + "pull_request:44027|pull_request:44029", + "pull_request:44027|pull_request:44030", + "pull_request:44028|pull_request:44029", + "pull_request:44028|pull_request:44030", + "pull_request:44029|pull_request:44030" + ], + "prepared_review_unit_hash": "c901facdfacf5880e8847a3f3b085e8c1b769e6a08f937b283f0c89f959567fb", + "component_budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 40, + "serialized_chars": 40168, + "estimated_input_tokens": 10042, + "estimated_eval_tokens": 20340 + }, + "budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 40, + "serialized_chars": 40168, + "estimated_input_tokens": 10042, + "estimated_eval_tokens": 20340 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs form a topical cluster around output-tracing refactors, but they are model-specific changes in different code paths, so they are not duplicates of one another.", + "confidence": 0.9, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44003 is the best representative of the cluster: it is the broadest refactor here, spans two related model files, and introduces the shared output-capturing machinery that the other PRs only apply in narrower model-specific ways.", + "best_issue_reason": null, + "best_pr_reason": "PR 44003 is the strongest single example of the output-tracing refactor theme, with the largest and most structural change set among the PRs shown.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43998", + "right": "pull_request:44002", + "accept": false, + "reason": "Both are output-tracing refactors, but they affect different models and different forward paths; not the same concrete fix." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44000", + "accept": false, + "reason": "Different model families and files; same pattern of refactor, but not one mergeable duplicate change." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44001", + "accept": false, + "reason": "Unrelated model code paths; only the refactor style matches." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44003", + "accept": false, + "reason": "Different architectures and files; not the same underlying bug/change." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44029", + "accept": false, + "reason": "Same tracing theme, but timm_backbone and rwkv are separate implementations with distinct fixes." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44001", + "accept": false, + "reason": "Different models and forward signatures; not a duplicate change." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44002", + "accept": false, + "reason": "Both refactor outputs, but for unrelated models and code paths." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44025", + "accept": false, + "reason": "MobileNetV1 and DepthAnything are unrelated model implementations; same general theme only." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44026", + "accept": false, + "reason": "No shared bug or code path; only a common decorator/refactor pattern." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44027", + "accept": false, + "reason": "Different encoder-decoder models; not the same concrete change." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44001", + "accept": false, + "reason": "Same refactor wording, but vision_text_dual_encoder and univnet are separate code paths." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44002", + "accept": false, + "reason": "Different model families; not the same fix." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44003", + "accept": false, + "reason": "These touch unrelated model implementations, so they are not mergeable duplicates." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44025", + "accept": false, + "reason": "Shared output-tracing theme only; different models and different forward logic." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44002", + "accept": false, + "reason": "Different model code paths; no indication of the same underlying bug." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44003", + "accept": false, + "reason": "Unrelated model implementations; same refactor class, not the same change." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44025", + "accept": false, + "reason": "Different models and outputs; not a duplicate fix." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44029", + "accept": false, + "reason": "Different model families and forward paths; only the tracing refactor pattern is shared." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44003", + "accept": false, + "reason": "No shared concrete code-path problem; the similarity is only thematic." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44028", + "accept": false, + "reason": "Falcon/Mamba refactor versus SuperPoint refactor; separate implementations and fixes." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44004", + "accept": false, + "reason": "Different model internals and outputs; not the same underlying change." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44004", + "accept": false, + "reason": "Timm backbone and CodeGen are unrelated code paths; same refactor family only." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44004", + "accept": false, + "reason": "Unrelated model implementations; not a duplicate PR." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44004", + "accept": false, + "reason": "Different models and forward behaviors; not the same fix." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44004", + "accept": false, + "reason": "Only the output-tracing theme matches; the code paths do not." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44026", + "accept": false, + "reason": "Different model families and files; same broad refactor pattern, but not the same concrete bug/change." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44027", + "accept": false, + "reason": "DepthAnything/PromptDepthAnything versus VisionEncoderDecoder are unrelated implementations." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44028", + "accept": false, + "reason": "Different model code paths; no evidence they fix the same problem." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44029", + "accept": false, + "reason": "Separate model families with distinct output mechanics; not mergeable as one PR." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44030", + "accept": false, + "reason": "DepthAnything refactor and DPR refactor are unrelated changes." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44029", + "accept": false, + "reason": "VisionEncoderDecoder and RWKV are different systems; not the same code-path issue." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44027", + "accept": false, + "reason": "Different model families and forward paths; no duplicate evidence." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44028", + "accept": false, + "reason": "Same refactor style only; unrelated model implementations." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44030", + "accept": false, + "reason": "VisionEncoderDecoder and DPR are distinct model code paths." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44028", + "accept": false, + "reason": "SpeechEncoderDecoder and SuperPoint are unrelated model implementations." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44029", + "accept": false, + "reason": "Different model families and output shapes; not the same underlying change." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44030", + "accept": false, + "reason": "Different code paths and behaviors; only the refactor pattern overlaps." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44029", + "accept": false, + "reason": "SuperPoint and RWKV are unrelated implementations; not a duplicate." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44030", + "accept": false, + "reason": "Different model families; no shared concrete bug or fix." + }, + { + "left": "pull_request:44029", + "right": "pull_request:44030", + "accept": false, + "reason": "RWKV and DPR are separate model code paths, so these are not duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 16, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-44662-3", + "nodes": [ + "pull_request:44662", + "pull_request:45075", + "pull_request:45401" + ], + "soft_pairs": [ + "pull_request:44662|pull_request:45401", + "pull_request:44662|pull_request:45075", + "pull_request:45075|pull_request:45401" + ], + "prepared_review_unit_hash": "e23d3d3f2fa42a80e59ede1e3f4b13b5f28d1d8133b765f0aa21757d508f46c5", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 10912, + "estimated_input_tokens": 2728, + "estimated_eval_tokens": 5712 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 10912, + "estimated_input_tokens": 2728, + "estimated_eval_tokens": 5712 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "All three items are separate model-addition pull requests for different models (PenguinVL, DeepSeek-OCR-2, Voxtral TTS). They share framework-wide registry/docs files, but not the same underlying code change or bug.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single canonical PR: each PR implements a different model integration, so they are not duplicates of one another.", + "best_issue_reason": null, + "best_pr_reason": "Voxtral TTS is the most self-contained/traceable of the three because it has an explicit issue target, but it still represents a distinct model addition rather than a duplicate of the others.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44662", + "right": "pull_request:45401", + "accept": false, + "reason": "Different model implementations (PenguinVL vs Voxtral TTS). Shared auto-registry/docs files are generic integration boilerplate, not the same concrete change." + }, + { + "left": "pull_request:44662", + "right": "pull_request:45075", + "accept": false, + "reason": "PenguinVL and DeepSeek-OCR-2 are unrelated model additions. Overlap is limited to common model-registration files and does not indicate the same fix/change." + }, + { + "left": "pull_request:45075", + "right": "pull_request:45401", + "accept": false, + "reason": "DeepSeek-OCR-2 and Voxtral TTS target different models and codepaths. Similar filenames reflect standard model onboarding, not duplicate work." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 17, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-44979-2", + "nodes": [ + "pull_request:44979", + "pull_request:45363" + ], + "soft_pairs": [ + "pull_request:44979|pull_request:45363" + ], + "prepared_review_unit_hash": "31a0e84d7dbdcc13dcd35f9ea6bc3bb8d5f6d5dfdd051cd271be32d7d7fb76c6", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4407, + "estimated_input_tokens": 1102, + "estimated_eval_tokens": 2460 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4407, + "estimated_input_tokens": 1102, + "estimated_eval_tokens": 2460 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two related PRs around fusion, but they address different levels of the stack: one introduces a generic Module Fusion API, the other adds n-to-1 kernel fusion integration via KernelConfig. They are connected, but not the same concrete change and would not be merged as a single PR.", + "confidence": 0.87, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #44979 is the more foundational change: it introduces the generic Module Fusion API and test coverage. It is the broader reusable base that the later KernelConfig work builds on.", + "best_issue_reason": null, + "best_pr_reason": "PR #45363 is the more user-facing and complete feature proposal for kernel fusion via KernelConfig, with integration across multiple files and an example demonstrating the workflow.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44979", + "right": "pull_request:45363", + "accept": false, + "reason": "Related fusion work, but not the same concrete bug/change. #44979 adds a generic module-fusion API, while #45363 wires n-to-1 kernel fusion through KernelConfig and integration code. They could coexist as separate PRs and are not strict duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 18, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45086-2", + "nodes": [ + "pull_request:45086", + "pull_request:45317" + ], + "soft_pairs": [ + "pull_request:45086|pull_request:45317" + ], + "prepared_review_unit_hash": "62ae4d570e382e1d5e49f120c105839d792dce9b3714430ee876f98f96a53da4", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4414, + "estimated_input_tokens": 1104, + "estimated_eval_tokens": 2464 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4414, + "estimated_input_tokens": 1104, + "estimated_eval_tokens": 2464 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both pull requests target the same Mistral regex patch in the same file, with the same fix for the AttributeError and the same issue link. PR 45317 is the more complete duplicate because it adds test coverage while implementing the same code-path fix.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45317 is the best canonical PR: it fixes the same AttributeError in `_patch_mistral_regex` as PR 45086, but adds accompanying tests and has the more complete implementation.", + "best_issue_reason": null, + "best_pr_reason": "PR 45317 is the best overall representative because it addresses the same concrete bug as 45086 and includes tests, making it the stronger final patch.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45086", + "right": "pull_request:45317", + "accept": true, + "reason": "Same explicit issue target, same file, same AttributeError fix in `_patch_mistral_regex`; 45317 is a superset with tests, so these are duplicate PRs for 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": 19, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45115-2", + "nodes": [ + "pull_request:45115", + "pull_request:45569" + ], + "soft_pairs": [ + "pull_request:45115|pull_request:45569" + ], + "prepared_review_unit_hash": "bc8918f70e8285c7a2befd9b0990a9e7e480479b73ed352967ddca94396eeba9", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6066, + "estimated_input_tokens": 1517, + "estimated_eval_tokens": 3290 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6066, + "estimated_input_tokens": 1517, + "estimated_eval_tokens": 3290 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two NemotronH pull requests that overlap in model files but target different changes: one refactors NemotronH to inherit GraniteMoeHybrid behavior, the other splits NemotronH into dense/sparse variants with docs and tests. They are related but not duplicates.", + "confidence": 0.89, + "canonical_issue_reason": null, + "canonical_pr_reason": "45569 is the more complete, user-facing model change: it adds the dense/sparse architecture split plus docs/tests, whereas 45115 is a narrower inheritance/conversion refactor.", + "best_issue_reason": null, + "best_pr_reason": "45569 is the strongest representative PR for this cluster because it covers the main architectural and documentation update rather than just an internal refactor.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45115", + "right": "pull_request:45569", + "accept": false, + "reason": "They share NemotronH implementation files, but 45115 focuses on GraniteMoeHybrid-style refactoring/conversion mapping while 45569 introduces a broader NemotronH dense/sparse model split with docs and tests. Different concrete changes, so not the same PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 20, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45332-2", + "nodes": [ + "pull_request:45332", + "pull_request:45333" + ], + "soft_pairs": [ + "pull_request:45332|pull_request:45333" + ], + "prepared_review_unit_hash": "34146f9b604c6318807b619275f90816a46f2bf466f1e66c10177b3eef9e3d85", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5398, + "estimated_input_tokens": 1350, + "estimated_eval_tokens": 2956 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5398, + "estimated_input_tokens": 1350, + "estimated_eval_tokens": 2956 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are related feature work, not duplicates: one adds heterogeneous per-layer config plumbing, the other adds heterogeneous model/runtime support that consumes it. They share some foundational files, but they address different layers of the implementation and would not be merged as one duplicate change.", + "confidence": 0.84, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45332 is the broader umbrella change: it includes the runtime/modeling integration and also references the heterogeneous config plumbing needed to make the feature usable end-to-end.", + "best_issue_reason": null, + "best_pr_reason": "PR #45332 is the best representative because it covers the user-facing heterogeneous model support and the concrete code-path changes beyond the config scaffolding.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45332", + "right": "pull_request:45333", + "accept": false, + "reason": "Related but distinct scopes: #45333 is config-only per-layer support, while #45332 adds modeling/cache/masking integration that uses that config. They share groundwork, but they are not the same underlying change and should not be merged as duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 21, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45415-2", + "nodes": [ + "pull_request:45415", + "pull_request:45425" + ], + "soft_pairs": [ + "pull_request:45415|pull_request:45425" + ], + "prepared_review_unit_hash": "6a484169d52d658c4d988a673c2c1aa39fc03f2299eb860797ef8d14ff0fa954", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5513, + "estimated_input_tokens": 1379, + "estimated_eval_tokens": 3014 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5513, + "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 two separate typing-related PRs, but they address different changes: one is a broad repo-wide type-checking cleanup, the other adds specific typing protocols and targeted integration updates. They are not duplicates.", + "confidence": 0.89, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45425 is the more focused, self-contained typing change; it introduces concrete protocol/type aliases and targeted code updates rather than a broad sweep.", + "best_issue_reason": null, + "best_pr_reason": "PR 45425 is the better representative of the cluster because it has a narrower, more coherent purpose and clearer code-path intent.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45415", + "right": "pull_request:45425", + "accept": false, + "reason": "Overlap is only at the level of general typing cleanup and a few shared files. 45415 is a broad type-checking pass with ignore-rule adjustments, while 45425 adds specific typing protocols and targeted fixes; they are not the same underlying change and 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": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45487-6", + "nodes": [ + "pull_request:45487", + "pull_request:45817", + "pull_request:45836", + "pull_request:45842", + "pull_request:45843", + "pull_request:45844" + ], + "soft_pairs": [ + "pull_request:45487|pull_request:45843", + "pull_request:45487|pull_request:45842", + "pull_request:45487|pull_request:45836", + "pull_request:45817|pull_request:45843", + "pull_request:45817|pull_request:45842", + "pull_request:45836|pull_request:45842", + "pull_request:45836|pull_request:45843", + "pull_request:45836|pull_request:45844", + "pull_request:45842|pull_request:45843", + "pull_request:45843|pull_request:45844" + ], + "prepared_review_unit_hash": "5163687df060a9a391d9261d3f0216f5aed010755e73254c12de968be9629f6d", + "component_budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 10, + "serialized_chars": 15296, + "estimated_input_tokens": 3824, + "estimated_eval_tokens": 7904 + }, + "budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 10, + "serialized_chars": 15296, + "estimated_input_tokens": 3824, + "estimated_eval_tokens": 7904 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This is a loose topical cluster, not a duplicate set: most PRs are unrelated model-parallel fixes for different architectures, and a couple are test-only adjustments. They share a broad theme of \u201cfixing failures,\u201d but not the same underlying bug or change.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "45487 is the best representative because it makes a concrete code-path device-placement fix in model forward logic and includes targeted tests; the other substantive PRs fix different models, while the remaining ones are test-only changes.", + "best_issue_reason": null, + "best_pr_reason": "45487 is the strongest PR candidate in this cluster for the same reason: it is the clearest real bug fix rather than a test tweak, but it is not duplicate with the others.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45487", + "right": "pull_request:45843", + "accept": false, + "reason": "Same broad model-parallel theme, but different models and different code paths; not the same underlying bug or change." + }, + { + "left": "pull_request:45487", + "right": "pull_request:45842", + "accept": false, + "reason": "45487 fixes a model-parallel device-placement bug; 45842 only adjusts Laguna test setup. Different problems." + }, + { + "left": "pull_request:45487", + "right": "pull_request:45836", + "accept": false, + "reason": "45487 is a code fix; 45836 skips an invalid test. These are unrelated changes." + }, + { + "left": "pull_request:45817", + "right": "pull_request:45843", + "accept": false, + "reason": "Both are model-parallel fixes, but for different models and different failing paths; too broad to be a duplicate." + }, + { + "left": "pull_request:45817", + "right": "pull_request:45842", + "accept": false, + "reason": "Gemma4 model-parallel code fix versus Laguna test parameter change; not the same bug." + }, + { + "left": "pull_request:45836", + "right": "pull_request:45842", + "accept": false, + "reason": "Both are test-only changes, but they address different models and different failures." + }, + { + "left": "pull_request:45836", + "right": "pull_request:45843", + "accept": false, + "reason": "Test skip for MiniCPM-V versus Deimv2 model-parallel code fix; unrelated." + }, + { + "left": "pull_request:45836", + "right": "pull_request:45844", + "accept": false, + "reason": "MiniCPM-V test skip and Granite4-Vision test/model-parallel change are not the same underlying issue." + }, + { + "left": "pull_request:45842", + "right": "pull_request:45843", + "accept": false, + "reason": "Laguna test fix and Deimv2 model-parallel code fix target different failures." + }, + { + "left": "pull_request:45843", + "right": "pull_request:45844", + "accept": false, + "reason": "Deimv2 model-parallel fix versus Granite4-Vision test/model-splitting tweak; same general area, not the same change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 23, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45548-2", + "nodes": [ + "pull_request:45548", + "pull_request:45662" + ], + "soft_pairs": [ + "pull_request:45548|pull_request:45662" + ], + "prepared_review_unit_hash": "80f456fff708dc0e9843c9bf21f6b0fd7a5509206865cea698629eb7ba32792a", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4505, + "estimated_input_tokens": 1127, + "estimated_eval_tokens": 2510 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4505, + "estimated_input_tokens": 1127, + "estimated_eval_tokens": 2510 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are thematically related around expert-parallel loading, but they fix different concrete bugs and should not be merged as duplicates. PR 45548 is about EP + DeepSpeed ZeRO-3 loading via accelerate launch and config serialization; PR 45662 is about experts being overwritten by rank-0 broadcast in EP + FSDP2 loading.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "45662 is the stronger canonical PR for the cluster because it addresses a specific data-corruption bug in expert-parallel loading with a clearer multi-file fix; 45548 is a separate, narrower accelerate/DeepSpeed serialization/loading issue.", + "best_issue_reason": null, + "best_pr_reason": "45662 is the best overall PR candidate here because it targets a concrete code-path corruption problem and includes the more substantial fix across loading/integration paths.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45548", + "right": "pull_request:45662", + "accept": false, + "reason": "Both involve expert-parallel model loading, but the bugs differ: 45548 fixes EP + DeepSpeed ZeRO-3/accelerate serialization and initialization, while 45662 fixes expert parameters being overwritten by rank-0 broadcast under EP + FSDP2. Shared 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": 24, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45639-2", + "nodes": [ + "pull_request:45639", + "pull_request:45645" + ], + "soft_pairs": [ + "pull_request:45639|pull_request:45645" + ], + "prepared_review_unit_hash": "39276d985a6250d297d5f633c665fe4ea5dcf697962aa5ac782ffba0dece6f09", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4590, + "estimated_input_tokens": 1148, + "estimated_eval_tokens": 2552 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4590, + "estimated_input_tokens": 1148, + "estimated_eval_tokens": 2552 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs target the same xdist collision in patched testing debug log capture; one is a narrower implementation, the other includes the broader CI/log handling around the same artifact path.", + "confidence": 0.84, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45645 is the more complete fix: it addresses the xdist-safe capture file naming and also updates CI to collect multiple captured_info files, matching the broader artifact-handling problem.", + "best_issue_reason": null, + "best_pr_reason": "PR 45645 is the best standalone candidate because it covers the core bug plus the downstream log collection change needed to preserve debug output in CI.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45639", + "right": "pull_request:45645", + "accept": true, + "reason": "Both PRs fix the same underlying captured_info/xdist collision path in testing_utils; 45645 extends the same fix with CI log aggregation, and they could plausibly be merged into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 25, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45683-2", + "nodes": [ + "pull_request:45683", + "pull_request:45734" + ], + "soft_pairs": [ + "pull_request:45683|pull_request:45734" + ], + "prepared_review_unit_hash": "eba4ca0f26b2d3be0c00e316270a9341d31af2208b44dbab31b1d3a8e81e7538", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4469, + "estimated_input_tokens": 1118, + "estimated_eval_tokens": 2492 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4469, + "estimated_input_tokens": 1118, + "estimated_eval_tokens": 2492 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two open PRs touch the same quantization helper, but they fix different bugs: one special-cases audio submodules, the other changes how default skip lists are combined with user-supplied skips. They should not be clustered as duplicates.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "45734 is the better representative PR because it fixes the core skip-module composition logic in `get_modules_to_not_convert`, which is broader and more central than the narrow audio-module special case in 45683.", + "best_issue_reason": null, + "best_pr_reason": "45734 is the strongest standalone PR in the set: it addresses a concrete quantization failure mode in the main code path and its fix is directly about the helper\u2019s behavior rather than a model-specific workaround.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45683", + "right": "pull_request:45734", + "accept": false, + "reason": "Both touch quantization skip logic, but 45683 adds audio-tower/embed_audio exclusions while 45734 changes additive handling of `skip_modules`; these are different underlying bugs and would not naturally merge into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 26, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45737-2", + "nodes": [ + "pull_request:45737", + "pull_request:45738" + ], + "soft_pairs": [ + "pull_request:45737|pull_request:45738" + ], + "prepared_review_unit_hash": "cc2ade73a49ec6a8883a7a24c433988645588bcd049e8aad2bce56b1b24daa1c", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4131, + "estimated_input_tokens": 1033, + "estimated_eval_tokens": 2322 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4131, + "estimated_input_tokens": 1033, + "estimated_eval_tokens": 2322 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs address the same MusicgenMelody cache initialization bug in `forward()`: replacing `EncoderDecoderCache(DynamicCache, DynamicCache)` with a single `DynamicCache`. PR #45737 is the more complete duplicate because it bundles the fix with a regression test, while #45738 is the fix-only variant.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45737 is the best canonical PR because it contains the same code fix as #45738 plus a regression test, making it the most complete representation of the bug fix.", + "best_issue_reason": null, + "best_pr_reason": "PR #45737 is the strongest overall candidate: it fixes the concrete cache bug and adds a targeted regression test, whereas #45738 only changes the implementation.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45737", + "right": "pull_request:45738", + "accept": true, + "reason": "Same underlying code-path bug in `musicgen_melody` cache setup; the diffs match on the core fix and the test-only addition in #45737 could plausibly live in the same PR as #45738." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The assessment is grounded in the packet: both PRs make the same `musicgen_melody` cache initialization change, and #45737 only adds a regression test on top of that fix. The soft-edge accept is conservative enough because the diffs are mergeable into one PR for the same bugfix." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + } + ] +} diff --git a/snapshots/20260508T120022Z/analysis-runs/hybrid-model-20260508t120022z/manifest.json b/snapshots/20260508T120022Z/analysis-runs/hybrid-model-20260508t120022z/manifest.json new file mode 100644 index 0000000000000000000000000000000000000000..76afb36dfc9c1b43214bbdc4188d5fac87b948f7 --- /dev/null +++ b/snapshots/20260508T120022Z/analysis-runs/hybrid-model-20260508t120022z/manifest.json @@ -0,0 +1,14 @@ +{ + "analysis_id": "hybrid-model-20260508t120022z", + "artifacts": { + "hybrid": "snapshots/20260508T120022Z/analysis-runs/hybrid-model-20260508t120022z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260508T120022Z/analysis-runs/hybrid-model-20260508t120022z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "model": null, + "published_at": "2026-05-08T12:10:15Z", + "repo": "huggingface/transformers", + "schema_version": 1, + "snapshot_id": "20260508T120022Z", + "variant": "hybrid" +} diff --git a/snapshots/20260508T120022Z/manifest.json b/snapshots/20260508T120022Z/manifest.json index b83bb8716405593136f2ef8507d4ce1fe7616bf6..2e7209b90f58ef985e57e158d2703b47fd8b3ce2 100644 --- a/snapshots/20260508T120022Z/manifest.json +++ b/snapshots/20260508T120022Z/manifest.json @@ -32,6 +32,24 @@ "timeline_events": 693 }, "extracted_at": "2026-05-08T12:00:22Z", + "published_analysis": { + "canonical_analysis_id": "hybrid-model-20260508t120022z", + "runs": { + "hybrid-model-20260508t120022z": { + "analysis_id": "hybrid-model-20260508t120022z", + "artifacts": { + "hybrid": "snapshots/20260508T120022Z/analysis-runs/hybrid-model-20260508t120022z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260508T120022Z/analysis-runs/hybrid-model-20260508t120022z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "manifest_path": "snapshots/20260508T120022Z/analysis-runs/hybrid-model-20260508t120022z/manifest.json", + "model": null, + "published_at": "2026-05-08T12:10:15Z", + "variant": "hybrid" + } + }, + "schema_version": 1 + }, "repo": "huggingface/transformers", "snapshot_id": "20260508T120022Z", "watermark": {